diff --git "a/profile_trace/iteration_12288/rank0_trace.json" "b/profile_trace/iteration_12288/rank0_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_12288/rank0_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": 0, "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": "35027E4699E1403CA7C809B66F6D2869", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 4183436, "tid": 31338, + "ts": 667115508784.594, "dur": 130.700, + "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": 4183436, "tid": 31338, + "ts": 667115508822.726, "dur": 83.581, + "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": 4183436, "tid": 31338, "ts": 667115508822.726, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 4183436, "tid": 31338, + "ts": 667115508830.100, "dur": 74.276, + "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": 4183436, "tid": 31338, + "ts": 667115508929.676, "dur": 202.242, + "args": { + "External id": 229892,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 4183436, "tid": 31338, + "ts": 667115508981.262, "dur": 82.852, + "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": 4183436, "tid": 31338, + "ts": 667115509011.159, "dur": 41.682, + "args": { + "External id": 229894,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183436, "tid": 31338, + "ts": 667115509068.775, "dur": 1.651, + "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": 4183436, "tid": 31338, "ts": 667115509068.775, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183436, "tid": 31338, + "ts": 667115509074.121, "dur": 52.499, + "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": 4183436, "tid": 31338, + "ts": 667115509081.014, "dur": 45.071, + "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": 4183436, "tid": 31338, + "ts": 667115509090.398, "dur": 3.295, + "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": 4183436, "tid": 31338, + "ts": 667115509140.394, "dur": 16843.960, + "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": 4183436, "tid": 31338, + "ts": 667115509142.214, "dur": 16832.594, + "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": 4183436, "tid": 31338, "ts": 667115509142.214, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115509180.388, "dur": 3.534, + "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": 4183436, "tid": 31338, + "ts": 667115509188.588, "dur": 16682.529, + "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": 4183436, "tid": 31338, + "ts": 667115509190.521, "dur": 16680.324, + "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": 4183436, "tid": 31338, + "ts": 667115509195.299, "dur": 6.528, + "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": 4183436, "tid": 31338, + "ts": 667115509203.456, "dur": 16665.939, + "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": 4183436, "tid": 31338, + "ts": 667115525875.723, "dur": 0.469, + "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": 4183436, "tid": 31338, + "ts": 667115525878.168, "dur": 2.601, + "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": 4183436, "tid": 31338, + "ts": 667115525879.546, "dur": 1.095, + "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": 4183436, "tid": 31338, + "ts": 667115525886.393, "dur": 27.582, + "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": 4183436, "tid": 31338, + "ts": 667115525921.467, "dur": 44.624, + "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": 4183436, "tid": 31338, + "ts": 667115525923.298, "dur": 42.573, + "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": 4183436, "tid": 31338, + "ts": 667115525924.509, "dur": 41.006, + "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": 4183436, "tid": 31338, + "ts": 667115525994.920, "dur": 17.147, + "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": 4183436, "tid": 31338, + "ts": 667115525996.550, "dur": 13.038, + "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": 4183436, "tid": 31338, "ts": 667115525996.550, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115526000.018, "dur": 9.344, + "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": 4183436, "tid": 31338, + "ts": 667115526003.648, "dur": 5.529, + "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": 4183436, "tid": 31338, + "ts": 667115526015.861, "dur": 82.946, + "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": 4183436, "tid": 31338, + "ts": 667115526017.184, "dur": 73.234, + "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": 4183436, "tid": 31338, "ts": 667115526017.184, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115526020.661, "dur": 69.299, + "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": 4183436, "tid": 31338, + "ts": 667115526024.780, "dur": 29.539, + "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": 4183436, "tid": 31338, + "ts": 667115526028.665, "dur": 5.256, + "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": 4183436, "tid": 31338, + "ts": 667115526035.264, "dur": 18.771, + "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": 4183436, "tid": 31338, + "ts": 667115526037.819, "dur": 15.817, + "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": 4183436, "tid": 31338, + "ts": 667115526058.901, "dur": 4.480, + "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": 4183436, "tid": 31338, + "ts": 667115526061.448, "dur": 1.643, + "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": 4183436, "tid": 31338, + "ts": 667115526064.563, "dur": 24.604, + "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": 4183436, "tid": 31338, + "ts": 667115526103.449, "dur": 59.291, + "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": 4183436, "tid": 31338, + "ts": 667115526104.412, "dur": 54.565, + "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": 4183436, "tid": 31338, "ts": 667115526104.412, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183436, "tid": 31338, + "ts": 667115526107.579, "dur": 51.075, + "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": 4183436, "tid": 31338, + "ts": 667115526111.673, "dur": 19.919, + "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": 4183436, "tid": 31338, + "ts": 667115526112.670, "dur": 2.930, + "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": 4183436, "tid": 31338, + "ts": 667115526116.295, "dur": 15.015, + "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": 4183436, "tid": 31338, + "ts": 667115526119.556, "dur": 11.344, + "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": 4183436, "tid": 31338, + "ts": 667115526135.056, "dur": 5.187, + "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": 4183436, "tid": 31338, + "ts": 667115526138.405, "dur": 1.193, + "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": 4183436, "tid": 31338, + "ts": 667115526140.908, "dur": 17.076, + "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": 4183436, "tid": 31338, + "ts": 667115526166.909, "dur": 101.539, + "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": 4183436, "tid": 31338, + "ts": 667115526167.857, "dur": 96.658, + "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": 4183436, "tid": 31338, "ts": 667115526167.857, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115526170.597, "dur": 93.592, + "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": 4183436, "tid": 31338, + "ts": 667115526173.780, "dur": 17.722, + "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": 4183436, "tid": 31338, + "ts": 667115526174.558, "dur": 2.014, + "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": 4183436, "tid": 31338, + "ts": 667115526177.313, "dur": 13.909, + "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": 4183436, "tid": 31338, + "ts": 667115526178.238, "dur": 12.660, + "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": 4183436, "tid": 31338, + "ts": 667115526194.413, "dur": 4.298, + "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": 4183436, "tid": 31338, + "ts": 667115526195.518, "dur": 3.045, + "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": 4183436, "tid": 31338, + "ts": 667115526199.291, "dur": 64.199, + "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": 4183436, "tid": 31338, + "ts": 667115526274.338, "dur": 67.075, + "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": 4183436, "tid": 31338, + "ts": 667115526275.338, "dur": 63.475, + "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": 4183436, "tid": 31338, "ts": 667115526275.338, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115526276.779, "dur": 61.764, + "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": 4183436, "tid": 31338, + "ts": 667115526279.096, "dur": 15.198, + "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": 4183436, "tid": 31338, + "ts": 667115526279.858, "dur": 1.986, + "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": 4183436, "tid": 31338, + "ts": 667115526282.453, "dur": 11.585, + "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": 4183436, "tid": 31338, + "ts": 667115526283.261, "dur": 10.443, + "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": 4183436, "tid": 31338, + "ts": 667115526295.029, "dur": 4.037, + "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": 4183436, "tid": 31338, + "ts": 667115526298.364, "dur": 0.567, + "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": 4183436, "tid": 31338, + "ts": 667115526301.884, "dur": 35.966, + "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": 4183436, "tid": 31338, + "ts": 667115526345.477, "dur": 36.340, + "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": 4183436, "tid": 31338, + "ts": 667115526346.466, "dur": 0.789, + "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": 4183436, "tid": 31338, "ts": 667115526346.466, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183436, "tid": 31338, + "ts": 667115526349.099, "dur": 29.377, + "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": 4183436, "tid": 31338, + "ts": 667115526350.913, "dur": 27.122, + "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": 4183436, "tid": 31338, + "ts": 667115526358.661, "dur": 0.503, + "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": 4183436, "tid": 31338, + "ts": 667115526386.451, "dur": 1094.614, + "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": 4183436, "tid": 31338, + "ts": 667115526387.705, "dur": 1062.179, + "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": 4183436, "tid": 31338, "ts": 667115526387.705, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115526420.659, "dur": 2.431, + "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": 4183436, "tid": 31338, + "ts": 667115526425.473, "dur": 939.110, + "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": 4183436, "tid": 31338, + "ts": 667115526427.188, "dur": 937.097, + "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": 4183436, "tid": 31338, + "ts": 667115526429.674, "dur": 5.479, + "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": 4183436, "tid": 31338, + "ts": 667115526435.987, "dur": 927.151, + "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": 4183436, "tid": 31338, + "ts": 667115527367.750, "dur": 0.359, + "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": 4183436, "tid": 31338, + "ts": 667115527369.578, "dur": 4.268, + "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": 4183436, "tid": 31338, + "ts": 667115527372.794, "dur": 0.921, + "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": 4183436, "tid": 31338, + "ts": 667115527377.738, "dur": 21.915, + "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": 4183436, "tid": 31338, + "ts": 667115527404.871, "dur": 38.113, + "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": 4183436, "tid": 31338, + "ts": 667115527405.985, "dur": 36.792, + "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": 4183436, "tid": 31338, + "ts": 667115527406.772, "dur": 35.430, + "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": 4183436, "tid": 31338, + "ts": 667115527458.654, "dur": 18.917, + "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": 4183436, "tid": 31338, + "ts": 667115527488.156, "dur": 28.547, + "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": 4183436, "tid": 31338, + "ts": 667115527489.434, "dur": 24.156, + "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": 4183436, "tid": 31338, "ts": 667115527489.434, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115527506.033, "dur": 7.346, + "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": 4183436, "tid": 31338, + "ts": 667115527509.305, "dur": 3.792, + "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": 4183436, "tid": 31338, + "ts": 667115527521.742, "dur": 62.269, + "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": 4183436, "tid": 31338, + "ts": 667115527522.723, "dur": 56.598, + "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": 4183436, "tid": 31338, "ts": 667115527522.723, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115527524.231, "dur": 54.654, + "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": 4183436, "tid": 31338, + "ts": 667115527527.427, "dur": 24.813, + "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": 4183436, "tid": 31338, + "ts": 667115527528.626, "dur": 5.517, + "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": 4183436, "tid": 31338, + "ts": 667115527535.019, "dur": 16.953, + "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": 4183436, "tid": 31338, + "ts": 667115527536.000, "dur": 15.507, + "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": 4183436, "tid": 31338, + "ts": 667115527553.646, "dur": 3.229, + "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": 4183436, "tid": 31338, + "ts": 667115527555.483, "dur": 1.143, + "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": 4183436, "tid": 31338, + "ts": 667115527557.962, "dur": 20.097, + "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": 4183436, "tid": 31338, + "ts": 667115527590.029, "dur": 51.946, + "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": 4183436, "tid": 31338, + "ts": 667115527591.030, "dur": 47.987, + "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": 4183436, "tid": 31338, "ts": 667115527591.030, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183436, "tid": 31338, + "ts": 667115527594.009, "dur": 44.788, + "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": 4183436, "tid": 31338, + "ts": 667115527595.417, "dur": 18.083, + "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": 4183436, "tid": 31338, + "ts": 667115527596.043, "dur": 2.334, + "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": 4183436, "tid": 31338, + "ts": 667115527598.970, "dur": 14.265, + "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": 4183436, "tid": 31338, + "ts": 667115527599.663, "dur": 13.118, + "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": 4183436, "tid": 31338, + "ts": 667115527614.605, "dur": 6.711, + "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": 4183436, "tid": 31338, + "ts": 667115527620.050, "dur": 0.715, + "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": 4183436, "tid": 31338, + "ts": 667115527622.132, "dur": 16.169, + "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": 4183436, "tid": 31338, + "ts": 667115527645.780, "dur": 125.377, + "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": 4183436, "tid": 31338, + "ts": 667115527646.830, "dur": 120.789, + "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": 4183436, "tid": 31338, "ts": 667115527646.830, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115527647.785, "dur": 119.491, + "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": 4183436, "tid": 31338, + "ts": 667115527648.808, "dur": 50.450, + "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": 4183436, "tid": 31338, + "ts": 667115527649.455, "dur": 29.852, + "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": 4183436, "tid": 31338, + "ts": 667115527681.240, "dur": 17.746, + "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": 4183436, "tid": 31338, + "ts": 667115527682.470, "dur": 16.132, + "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": 4183436, "tid": 31338, + "ts": 667115527700.291, "dur": 4.332, + "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": 4183436, "tid": 31338, + "ts": 667115527703.706, "dur": 0.700, + "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": 4183436, "tid": 31338, + "ts": 667115527705.395, "dur": 61.195, + "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": 4183436, "tid": 31338, + "ts": 667115527778.372, "dur": 78.681, + "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": 4183436, "tid": 31338, + "ts": 667115527779.443, "dur": 58.883, + "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": 4183436, "tid": 31338, "ts": 667115527779.443, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115527781.555, "dur": 56.542, + "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": 4183436, "tid": 31338, + "ts": 667115527782.617, "dur": 15.932, + "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": 4183436, "tid": 31338, + "ts": 667115527783.403, "dur": 1.999, + "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": 4183436, "tid": 31338, + "ts": 667115527786.100, "dur": 12.189, + "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": 4183436, "tid": 31338, + "ts": 667115527787.017, "dur": 10.929, + "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": 4183436, "tid": 31338, + "ts": 667115527799.231, "dur": 1.590, + "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": 4183436, "tid": 31338, + "ts": 667115527800.276, "dur": 0.419, + "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": 4183436, "tid": 31338, + "ts": 667115527801.374, "dur": 36.114, + "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": 4183436, "tid": 31338, + "ts": 667115527841.817, "dur": 13.857, + "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": 4183436, "tid": 31338, + "ts": 667115527861.119, "dur": 33.645, + "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": 4183436, "tid": 31338, + "ts": 667115527863.514, "dur": 0.840, + "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": 4183436, "tid": 31338, "ts": 667115527863.514, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183436, "tid": 31338, + "ts": 667115527866.131, "dur": 25.886, + "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": 4183436, "tid": 31338, + "ts": 667115527867.727, "dur": 23.928, + "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": 4183436, "tid": 31338, + "ts": 667115527875.010, "dur": 0.614, + "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": 4183436, "tid": 31338, + "ts": 667115527899.154, "dur": 1441.140, + "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": 4183436, "tid": 31338, + "ts": 667115527902.952, "dur": 1412.064, + "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": 4183436, "tid": 31338, "ts": 667115527902.952, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115527930.883, "dur": 2.016, + "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": 4183436, "tid": 31338, + "ts": 667115527934.980, "dur": 1300.531, + "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": 4183436, "tid": 31338, + "ts": 667115527936.254, "dur": 1299.022, + "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": 4183436, "tid": 31338, + "ts": 667115527938.343, "dur": 4.394, + "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": 4183436, "tid": 31338, + "ts": 667115527943.586, "dur": 1290.592, + "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": 4183436, "tid": 31338, + "ts": 667115529239.136, "dur": 0.312, + "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": 4183436, "tid": 31338, + "ts": 667115529240.387, "dur": 2.306, + "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": 4183436, "tid": 31338, + "ts": 667115529241.748, "dur": 0.824, + "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": 4183436, "tid": 31338, + "ts": 667115529245.901, "dur": 19.706, + "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": 4183436, "tid": 31338, + "ts": 667115529272.444, "dur": 36.322, + "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": 4183436, "tid": 31338, + "ts": 667115529273.343, "dur": 35.260, + "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": 4183436, "tid": 31338, + "ts": 667115529274.566, "dur": 33.715, + "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": 4183436, "tid": 31338, + "ts": 667115529321.932, "dur": 15.189, + "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": 4183436, "tid": 31338, + "ts": 667115529349.077, "dur": 9.398, + "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": 4183436, "tid": 31338, + "ts": 667115529350.432, "dur": 6.071, + "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": 4183436, "tid": 31338, "ts": 667115529350.432, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115529352.630, "dur": 3.687, + "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": 4183436, "tid": 31338, + "ts": 667115529353.453, "dur": 2.704, + "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": 4183436, "tid": 31338, + "ts": 667115529361.864, "dur": 60.003, + "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": 4183436, "tid": 31338, + "ts": 667115529362.809, "dur": 55.173, + "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": 4183436, "tid": 31338, "ts": 667115529362.809, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115529365.577, "dur": 51.988, + "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": 4183436, "tid": 31338, + "ts": 667115529369.745, "dur": 20.132, + "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": 4183436, "tid": 31338, + "ts": 667115529370.766, "dur": 2.489, + "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": 4183436, "tid": 31338, + "ts": 667115529373.997, "dur": 15.611, + "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": 4183436, "tid": 31338, + "ts": 667115529374.977, "dur": 14.218, + "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": 4183436, "tid": 31338, + "ts": 667115529391.114, "dur": 3.614, + "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": 4183436, "tid": 31338, + "ts": 667115529393.754, "dur": 0.810, + "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": 4183436, "tid": 31338, + "ts": 667115529395.527, "dur": 21.144, + "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": 4183436, "tid": 31338, + "ts": 667115529425.852, "dur": 52.625, + "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": 4183436, "tid": 31338, + "ts": 667115529426.767, "dur": 48.964, + "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": 4183436, "tid": 31338, "ts": 667115529426.767, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183436, "tid": 31338, + "ts": 667115529428.232, "dur": 47.245, + "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": 4183436, "tid": 31338, + "ts": 667115529429.431, "dur": 18.261, + "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": 4183436, "tid": 31338, + "ts": 667115529431.831, "dur": 2.051, + "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": 4183436, "tid": 31338, + "ts": 667115529434.444, "dur": 13.009, + "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": 4183436, "tid": 31338, + "ts": 667115529435.185, "dur": 11.855, + "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": 4183436, "tid": 31338, + "ts": 667115529448.665, "dur": 6.889, + "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": 4183436, "tid": 31338, + "ts": 667115529452.320, "dur": 2.847, + "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": 4183436, "tid": 31338, + "ts": 667115529456.142, "dur": 18.934, + "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": 4183436, "tid": 31338, + "ts": 667115529482.058, "dur": 89.402, + "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": 4183436, "tid": 31338, + "ts": 667115529482.978, "dur": 84.890, + "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": 4183436, "tid": 31338, "ts": 667115529482.978, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115529484.156, "dur": 83.387, + "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": 4183436, "tid": 31338, + "ts": 667115529485.090, "dur": 33.625, + "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": 4183436, "tid": 31338, + "ts": 667115529487.701, "dur": 1.755, + "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": 4183436, "tid": 31338, + "ts": 667115529490.040, "dur": 28.385, + "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": 4183436, "tid": 31338, + "ts": 667115529501.681, "dur": 16.121, + "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": 4183436, "tid": 31338, + "ts": 667115529520.053, "dur": 3.156, + "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": 4183436, "tid": 31338, + "ts": 667115529522.188, "dur": 0.814, + "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": 4183436, "tid": 31338, + "ts": 667115529523.774, "dur": 42.906, + "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": 4183436, "tid": 31338, + "ts": 667115529576.550, "dur": 113.396, + "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": 4183436, "tid": 31338, + "ts": 667115529577.564, "dur": 65.149, + "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": 4183436, "tid": 31338, "ts": 667115529577.564, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115529580.796, "dur": 61.658, + "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": 4183436, "tid": 31338, + "ts": 667115529581.751, "dur": 18.598, + "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": 4183436, "tid": 31338, + "ts": 667115529584.344, "dur": 2.169, + "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": 4183436, "tid": 31338, + "ts": 667115529587.146, "dur": 12.943, + "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": 4183436, "tid": 31338, + "ts": 667115529587.919, "dur": 11.774, + "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": 4183436, "tid": 31338, + "ts": 667115529601.084, "dur": 2.762, + "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": 4183436, "tid": 31338, + "ts": 667115529603.138, "dur": 0.573, + "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": 4183436, "tid": 31338, + "ts": 667115529604.371, "dur": 37.432, + "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": 4183436, "tid": 31338, + "ts": 667115529645.699, "dur": 42.095, + "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": 4183436, "tid": 31338, + "ts": 667115529696.201, "dur": 32.991, + "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": 4183436, "tid": 31338, + "ts": 667115529697.623, "dur": 0.734, + "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": 4183436, "tid": 31338, "ts": 667115529697.623, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183436, "tid": 31338, + "ts": 667115529699.907, "dur": 23.898, + "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": 4183436, "tid": 31338, + "ts": 667115529701.488, "dur": 21.935, + "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": 4183436, "tid": 31338, + "ts": 667115529705.569, "dur": 0.460, + "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": 4183436, "tid": 31338, + "ts": 667115529733.341, "dur": 1448.588, + "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": 4183436, "tid": 31338, + "ts": 667115529744.886, "dur": 1411.230, + "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": 4183436, "tid": 31338, "ts": 667115529744.886, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115529770.081, "dur": 2.931, + "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": 4183436, "tid": 31338, + "ts": 667115529774.957, "dur": 1300.064, + "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": 4183436, "tid": 31338, + "ts": 667115529776.041, "dur": 1298.667, + "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": 4183436, "tid": 31338, + "ts": 667115529779.304, "dur": 2.841, + "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": 4183436, "tid": 31338, + "ts": 667115529782.984, "dur": 1290.651, + "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": 4183436, "tid": 31338, + "ts": 667115531078.290, "dur": 0.400, + "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": 4183436, "tid": 31338, + "ts": 667115531079.485, "dur": 2.076, + "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": 4183436, "tid": 31338, + "ts": 667115531080.670, "dur": 0.758, + "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": 4183436, "tid": 31338, + "ts": 667115531084.873, "dur": 21.868, + "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": 4183436, "tid": 31338, + "ts": 667115531110.889, "dur": 39.392, + "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": 4183436, "tid": 31338, + "ts": 667115531111.676, "dur": 38.386, + "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": 4183436, "tid": 31338, + "ts": 667115531112.675, "dur": 37.091, + "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": 4183436, "tid": 31338, + "ts": 667115531165.774, "dur": 12.729, + "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": 4183436, "tid": 31338, + "ts": 667115531192.218, "dur": 10.670, + "args": { + "External id": 230107,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115531194.270, "dur": 7.140, + "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": 4183436, "tid": 31338, + "ts": 667115531196.810, "dur": 3.714, + "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": 4183436, "tid": 31338, + "ts": 667115531197.600, "dur": 2.797, + "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": 4183436, "tid": 31338, + "ts": 667115531206.235, "dur": 10.269, + "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": 4183436, "tid": 31338, + "ts": 667115531207.520, "dur": 6.637, + "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": 4183436, "tid": 31338, "ts": 667115531207.520, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115531209.612, "dur": 4.345, + "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": 4183436, "tid": 31338, + "ts": 667115531211.406, "dur": 2.415, + "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": 4183436, "tid": 31338, + "ts": 667115531219.864, "dur": 58.168, + "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": 4183436, "tid": 31338, + "ts": 667115531220.590, "dur": 53.824, + "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": 4183436, "tid": 31338, "ts": 667115531220.590, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115531221.979, "dur": 52.155, + "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": 4183436, "tid": 31338, + "ts": 667115531226.041, "dur": 21.818, + "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": 4183436, "tid": 31338, + "ts": 667115531227.343, "dur": 2.826, + "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": 4183436, "tid": 31338, + "ts": 667115531230.985, "dur": 16.590, + "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": 4183436, "tid": 31338, + "ts": 667115531232.377, "dur": 14.683, + "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": 4183436, "tid": 31338, + "ts": 667115531249.116, "dur": 3.873, + "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": 4183436, "tid": 31338, + "ts": 667115531252.118, "dur": 0.653, + "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": 4183436, "tid": 31338, + "ts": 667115531253.917, "dur": 19.476, + "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": 4183436, "tid": 31338, + "ts": 667115531283.074, "dur": 54.990, + "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": 4183436, "tid": 31338, + "ts": 667115531284.093, "dur": 51.931, + "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": 4183436, "tid": 31338, "ts": 667115531284.093, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183436, "tid": 31338, + "ts": 667115531285.713, "dur": 50.085, + "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": 4183436, "tid": 31338, + "ts": 667115531286.987, "dur": 21.252, + "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": 4183436, "tid": 31338, + "ts": 667115531292.743, "dur": 2.662, + "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": 4183436, "tid": 31338, + "ts": 667115531296.099, "dur": 11.897, + "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": 4183436, "tid": 31338, + "ts": 667115531296.940, "dur": 10.669, + "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": 4183436, "tid": 31338, + "ts": 667115531309.190, "dur": 3.746, + "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": 4183436, "tid": 31338, + "ts": 667115531311.946, "dur": 0.613, + "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": 4183436, "tid": 31338, + "ts": 667115531313.600, "dur": 21.660, + "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": 4183436, "tid": 31338, + "ts": 667115531341.983, "dur": 72.370, + "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": 4183436, "tid": 31338, + "ts": 667115531343.084, "dur": 68.447, + "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": 4183436, "tid": 31338, "ts": 667115531343.084, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115531344.167, "dur": 67.109, + "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": 4183436, "tid": 31338, + "ts": 667115531345.438, "dur": 17.334, + "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": 4183436, "tid": 31338, + "ts": 667115531347.986, "dur": 1.737, + "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": 4183436, "tid": 31338, + "ts": 667115531350.327, "dur": 12.192, + "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": 4183436, "tid": 31338, + "ts": 667115531351.304, "dur": 10.836, + "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": 4183436, "tid": 31338, + "ts": 667115531363.415, "dur": 4.930, + "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": 4183436, "tid": 31338, + "ts": 667115531365.470, "dur": 2.693, + "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": 4183436, "tid": 31338, + "ts": 667115531368.887, "dur": 41.689, + "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": 4183436, "tid": 31338, + "ts": 667115531418.327, "dur": 114.288, + "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": 4183436, "tid": 31338, + "ts": 667115531419.069, "dur": 92.726, + "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": 4183436, "tid": 31338, "ts": 667115531419.069, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 667115531420.553, "dur": 90.944, + "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": 4183436, "tid": 31338, + "ts": 667115531422.034, "dur": 37.973, + "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": 4183436, "tid": 31338, + "ts": 667115531426.664, "dur": 1.716, + "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": 4183436, "tid": 31338, + "ts": 667115531444.899, "dur": 14.839, + "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": 4183436, "tid": 31338, + "ts": 667115531447.157, "dur": 12.167, + "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": 4183436, "tid": 31338, + "ts": 667115531460.759, "dur": 2.533, + "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": 4183436, "tid": 31338, + "ts": 667115531462.556, "dur": 0.515, + "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": 4183436, "tid": 31338, + "ts": 667115531463.855, "dur": 46.667, + "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": 4183436, "tid": 31338, + "ts": 667115531516.689, "dur": 14.151, + "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": 4183436, "tid": 31338, + "ts": 667115531539.532, "dur": 354.186, + "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": 4183436, "tid": 31338, + "ts": 667115531541.665, "dur": 342.877, + "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": 4183436, "tid": 31338, "ts": 667115531541.665, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183436, "tid": 31338, + "ts": 667115531727.949, "dur": 42.983, + "args": { + "External id": 230158,"kernel_hash": "ck7evvvu6eivc2josrcpvirfrftjlskqpvua2pu6vmp5a7rpdlri", "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/k7/ck7evvvu6eivc2josrcpvirfrftjlskqpvua2pu6vmp5a7rpdlri.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": 4183436, "tid": 31338, + "ts": 667115531800.164, "dur": 25.592, + "args": { + "External id": 230159,"kernel_hash": "cxaizktrqq7lw6othle3qymtuybh5kdnw4xphe6opexgfakz3ovw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/xa/cxaizktrqq7lw6othle3qymtuybh5kdnw4xphe6opexgfakz3ovw.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": 4183436, "tid": 31338, + "ts": 667115531845.023, "dur": 17.594, + "args": { + "External id": 230160,"kernel_hash": "c73bfck6gmh76a5uvdmaias3jflktyvas5f2fbubp4xjz372vuot", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/73/c73bfck6gmh76a5uvdmaias3jflktyvas5f2fbubp4xjz372vuot.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": 4183436, "tid": 31338, + "ts": 667115531904.312, "dur": 12.912, + "args": { + "External id": 230161,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115531906.604, "dur": 9.774, + "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": 4183436, "tid": 31338, + "ts": 667115531909.638, "dur": 5.802, + "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": 4183436, "tid": 31338, + "ts": 667115531912.221, "dur": 3.118, + "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": 4183436, "tid": 31338, + "ts": 667115531922.934, "dur": 29.489, + "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": 4183436, "tid": 31338, + "ts": 667115531923.809, "dur": 21.736, + "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": 4183436, "tid": 31338, "ts": 667115531923.809, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183436, "tid": 31338, + "ts": 667115531926.272, "dur": 8.571, + "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": 4183436, "tid": 31338, + "ts": 667115531931.788, "dur": 1.281, + "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": 4183436, "tid": 31338, + "ts": 667115531935.545, "dur": 2.899, + "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": 4183436, "tid": 31338, + "ts": 667115531937.277, "dur": 0.615, + "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": 4183436, "tid": 31338, + "ts": 667115531938.822, "dur": 2.786, + "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": 4183436, "tid": 31338, + "ts": 667115531940.691, "dur": 0.350, + "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": 4183436, "tid": 31338, + "ts": 667115531941.971, "dur": 2.999, + "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": 4183436, "tid": 31338, + "ts": 667115531943.886, "dur": 0.576, + "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": 4183436, "tid": 31338, + "ts": 667115531956.255, "dur": 5.317, + "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": 4183436, "tid": 31338, + "ts": 667115531957.222, "dur": 0.965, + "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": 4183436, "tid": 31338, "ts": 667115531957.222, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115531965.528, "dur": 441.696, + "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": 4183436, "tid": 31338, + "ts": 667115531966.919, "dur": 428.923, + "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": 4183436, "tid": 31338, "ts": 667115531966.919, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115532000.561, "dur": 9.164, + "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": 4183436, "tid": 31338, + "ts": 667115532006.173, "dur": 3.185, + "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": 4183436, "tid": 31338, + "ts": 667115532013.973, "dur": 10.026, + "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": 4183436, "tid": 31338, + "ts": 667115532016.405, "dur": 6.746, + "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": 4183436, "tid": 31338, + "ts": 667115532020.180, "dur": 2.732, + "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": 4183436, "tid": 31338, + "ts": 667115532027.862, "dur": 113.210, + "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": 4183436, "tid": 31338, + "ts": 667115532028.760, "dur": 2.940, + "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": 4183436, "tid": 31338, + "ts": 667115532029.269, "dur": 1.827, + "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": 4183436, "tid": 31338, + "ts": 667115532030.685, "dur": 0.333, + "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": 4183436, "tid": 31338, + "ts": 667115532032.945, "dur": 107.381, + "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": 4183436, "tid": 31338, + "ts": 667115532034.847, "dur": 104.288, + "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": 4183436, "tid": 31338, + "ts": 667115532147.094, "dur": 4.670, + "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": 4183436, "tid": 31338, + "ts": 667115532149.052, "dur": 2.603, + "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": 4183436, "tid": 31338, + "ts": 667115532182.871, "dur": 5.228, + "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": 4183436, "tid": 31338, + "ts": 667115532189.416, "dur": 1.825, + "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": 4183436, "tid": 31338, + "ts": 667115532192.384, "dur": 1.731, + "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": 4183436, "tid": 31338, + "ts": 667115532230.002, "dur": 2.866, + "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": 4183436, "tid": 31338, + "ts": 667115532231.110, "dur": 1.594, + "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": 4183436, "tid": 31338, + "ts": 667115532254.929, "dur": 121.700, + "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": 4183436, "tid": 31338, + "ts": 667115532260.315, "dur": 8.846, + "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": 4183436, "tid": 31338, + "ts": 667115532264.460, "dur": 2.966, + "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": 4183436, "tid": 31338, + "ts": 667115532271.857, "dur": 6.170, + "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": 4183436, "tid": 31338, + "ts": 667115532276.817, "dur": 0.584, + "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": 4183436, "tid": 31338, + "ts": 667115532279.323, "dur": 2.478, + "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": 4183436, "tid": 31338, + "ts": 667115532280.927, "dur": 0.522, + "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": 4183436, "tid": 31338, + "ts": 667115532283.274, "dur": 3.052, + "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": 4183436, "tid": 31338, + "ts": 667115532285.166, "dur": 0.635, + "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": 4183436, "tid": 31338, + "ts": 667115532292.535, "dur": 3.047, + "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": 4183436, "tid": 31338, + "ts": 667115532294.654, "dur": 0.601, + "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": 4183436, "tid": 31338, + "ts": 667115532296.752, "dur": 6.313, + "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": 4183436, "tid": 31338, + "ts": 667115532301.145, "dur": 1.733, + "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": 4183436, "tid": 31338, + "ts": 667115532304.353, "dur": 2.640, + "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": 4183436, "tid": 31338, + "ts": 667115532306.185, "dur": 0.534, + "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": 4183436, "tid": 31338, + "ts": 667115532307.928, "dur": 2.451, + "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": 4183436, "tid": 31338, + "ts": 667115532308.994, "dur": 1.278, + "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": 4183436, "tid": 31338, + "ts": 667115532312.038, "dur": 53.435, + "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": 4183436, "tid": 31338, + "ts": 667115532367.374, "dur": 1.153, + "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": 4183436, "tid": 31338, + "ts": 667115532369.496, "dur": 3.027, + "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": 4183436, "tid": 31338, + "ts": 667115532371.625, "dur": 0.409, + "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": 4183436, "tid": 31338, + "ts": 667115532374.808, "dur": 0.826, + "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": 4183436, "tid": 31338, + "ts": 667115532417.383, "dur": 8.771, + "args": { + "External id": 230219,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115532419.891, "dur": 5.548, + "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": 4183436, "tid": 31338, + "ts": 667115532421.638, "dur": 3.073, + "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": 4183436, "tid": 31338, + "ts": 667115532422.608, "dur": 2.004, + "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": 4183436, "tid": 31338, + "ts": 667115532430.775, "dur": 7.194, + "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": 4183436, "tid": 31338, + "ts": 667115532432.007, "dur": 3.815, + "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": 4183436, "tid": 31338, "ts": 667115532432.007, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115532433.793, "dur": 1.853, + "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": 4183436, "tid": 31338, + "ts": 667115532434.560, "dur": 0.939, + "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": 4183436, "tid": 31338, + "ts": 667115532441.581, "dur": 145.603, + "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": 4183436, "tid": 31338, + "ts": 667115532443.907, "dur": 134.536, + "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": 4183436, "tid": 31338, "ts": 667115532443.907, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115532446.943, "dur": 4.234, + "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": 4183436, "tid": 31338, + "ts": 667115532448.346, "dur": 2.276, + "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": 4183436, "tid": 31338, + "ts": 667115532449.908, "dur": 0.550, + "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": 4183436, "tid": 31338, + "ts": 667115532452.174, "dur": 35.495, + "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": 4183436, "tid": 31338, + "ts": 667115532488.900, "dur": 26.813, + "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": 4183436, "tid": 31338, + "ts": 667115532489.693, "dur": 25.020, + "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": 4183436, "tid": 31338, + "ts": 667115532512.769, "dur": 1.506, + "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": 4183436, "tid": 31338, + "ts": 667115532517.537, "dur": 5.871, + "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": 4183436, "tid": 31338, + "ts": 667115532518.643, "dur": 4.228, + "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": 4183436, "tid": 31338, + "ts": 667115532520.220, "dur": 2.552, + "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": 4183436, "tid": 31338, + "ts": 667115532524.264, "dur": 53.139, + "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": 4183436, "tid": 31338, + "ts": 667115532593.713, "dur": 8.468, + "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": 4183436, "tid": 31338, + "ts": 667115532594.758, "dur": 5.922, + "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": 4183436, "tid": 31338, "ts": 667115532594.758, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115532596.532, "dur": 3.996, + "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": 4183436, "tid": 31338, + "ts": 667115532599.153, "dur": 1.238, + "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": 4183436, "tid": 31338, + "ts": 667115532606.132, "dur": 8.194, + "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": 4183436, "tid": 31338, + "ts": 667115532607.079, "dur": 5.032, + "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": 4183436, "tid": 31338, "ts": 667115532607.079, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115532608.251, "dur": 3.666, + "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": 4183436, "tid": 31338, + "ts": 667115532609.043, "dur": 2.436, + "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": 4183436, "tid": 31338, + "ts": 667115532610.765, "dur": 0.627, + "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": 4183436, "tid": 31338, + "ts": 667115532618.530, "dur": 6.557, + "args": { + "External id": 230249,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115532620.092, "dur": 4.441, + "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": 4183436, "tid": 31338, + "ts": 667115532621.505, "dur": 2.688, + "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": 4183436, "tid": 31338, + "ts": 667115532622.515, "dur": 1.581, + "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": 4183436, "tid": 31338, + "ts": 667115532628.569, "dur": 8.615, + "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": 4183436, "tid": 31338, + "ts": 667115532629.649, "dur": 5.523, + "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": 4183436, "tid": 31338, "ts": 667115532629.649, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115532632.841, "dur": 2.161, + "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": 4183436, "tid": 31338, + "ts": 667115532634.119, "dur": 0.730, + "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": 4183436, "tid": 31338, + "ts": 667115532640.381, "dur": 144.722, + "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": 4183436, "tid": 31338, + "ts": 667115532641.186, "dur": 134.678, + "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": 4183436, "tid": 31338, "ts": 667115532641.186, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115532643.112, "dur": 4.526, + "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": 4183436, "tid": 31338, + "ts": 667115532643.591, "dur": 3.620, + "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": 4183436, "tid": 31338, + "ts": 667115532646.758, "dur": 0.353, + "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": 4183436, "tid": 31338, + "ts": 667115532648.197, "dur": 71.203, + "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": 4183436, "tid": 31338, + "ts": 667115532721.554, "dur": 6.778, + "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": 4183436, "tid": 31338, + "ts": 667115532722.714, "dur": 4.950, + "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": 4183436, "tid": 31338, + "ts": 667115532724.927, "dur": 2.629, + "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": 4183436, "tid": 31338, + "ts": 667115532729.459, "dur": 4.948, + "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": 4183436, "tid": 31338, + "ts": 667115532729.994, "dur": 3.939, + "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": 4183436, "tid": 31338, + "ts": 667115532733.232, "dur": 0.605, + "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": 4183436, "tid": 31338, + "ts": 667115532735.054, "dur": 40.037, + "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": 4183436, "tid": 31338, + "ts": 667115532793.081, "dur": 35.944, + "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": 4183436, "tid": 31338, + "ts": 667115532794.191, "dur": 4.152, + "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": 4183436, "tid": 31338, "ts": 667115532794.191, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115532795.922, "dur": 2.281, + "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": 4183436, "tid": 31338, + "ts": 667115532796.903, "dur": 1.150, + "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": 4183436, "tid": 31338, + "ts": 667115532801.602, "dur": 24.584, + "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": 4183436, "tid": 31338, + "ts": 667115532833.322, "dur": 10.726, + "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": 4183436, "tid": 31338, + "ts": 667115532834.509, "dur": 7.093, + "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": 4183436, "tid": 31338, "ts": 667115532834.509, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115532837.578, "dur": 3.812, + "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": 4183436, "tid": 31338, + "ts": 667115532838.528, "dur": 2.303, + "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": 4183436, "tid": 31338, + "ts": 667115532840.155, "dur": 0.579, + "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": 4183436, "tid": 31338, + "ts": 667115532848.058, "dur": 5.844, + "args": { + "External id": 230280,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115532849.854, "dur": 3.518, + "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": 4183436, "tid": 31338, + "ts": 667115532850.976, "dur": 2.073, + "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": 4183436, "tid": 31338, + "ts": 667115532851.707, "dur": 1.258, + "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": 4183436, "tid": 31338, + "ts": 667115532858.618, "dur": 412.228, + "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": 4183436, "tid": 31338, + "ts": 667115532860.799, "dur": 397.775, + "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": 4183436, "tid": 31338, "ts": 667115532860.799, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 31338, + "ts": 667115532888.219, "dur": 33.998, + "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": 4183436, "tid": 31338, + "ts": 667115532889.648, "dur": 32.370, + "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": 4183436, "tid": 31338, + "ts": 667115532892.566, "dur": 6.070, + "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": 4183436, "tid": 31338, + "ts": 667115532895.124, "dur": 2.951, + "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": 4183436, "tid": 31338, + "ts": 667115532899.915, "dur": 21.700, + "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": 4183436, "tid": 31338, + "ts": 667115532935.282, "dur": 4.426, + "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": 4183436, "tid": 31338, + "ts": 667115532936.436, "dur": 3.128, + "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": 4183436, "tid": 31338, + "ts": 667115532943.898, "dur": 2.077, + "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": 4183436, "tid": 31338, + "ts": 667115532944.966, "dur": 0.919, + "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": 4183436, "tid": 31338, + "ts": 667115532960.300, "dur": 1.998, + "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": 4183436, "tid": 31338, + "ts": 667115532975.004, "dur": 2.714, + "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": 4183436, "tid": 31338, + "ts": 667115533150.301, "dur": 2.339, + "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": 4183436, "tid": 31338, + "ts": 667115533157.086, "dur": 32.335, + "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": 4183436, "tid": 31338, + "ts": 667115533166.396, "dur": 0.737, + "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": 4183436, "tid": 31338, + "ts": 667115533195.432, "dur": 30.198, + "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": 4183436, "tid": 31338, + "ts": 667115533197.313, "dur": 28.106, + "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": 4183436, "tid": 31338, + "ts": 667115533201.683, "dur": 3.678, + "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": 4183436, "tid": 31338, + "ts": 667115533208.251, "dur": 16.689, + "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": 4183436, "tid": 31338, + "ts": 667115533230.331, "dur": 2.302, + "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": 4183436, "tid": 31338, + "ts": 667115533231.547, "dur": 0.949, + "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": 4183436, "tid": 31338, + "ts": 667115533239.415, "dur": 4.380, + "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": 4183436, "tid": 31338, + "ts": 667115533240.480, "dur": 3.219, + "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": 4183436, "tid": 31338, + "ts": 667115533246.099, "dur": 1.824, + "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": 4183436, "tid": 31338, + "ts": 667115533247.020, "dur": 0.814, + "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": 4183436, "tid": 31338, + "ts": 667115533281.158, "dur": 7.713, + "args": { + "External id": 230310,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115533283.421, "dur": 4.787, + "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": 4183436, "tid": 31338, + "ts": 667115533284.930, "dur": 2.291, + "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": 4183436, "tid": 31338, + "ts": 667115533285.751, "dur": 1.329, + "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": 4183436, "tid": 31338, + "ts": 667115533292.821, "dur": 7.247, + "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": 4183436, "tid": 31338, + "ts": 667115533294.251, "dur": 3.550, + "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": 4183436, "tid": 31338, "ts": 667115533294.251, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115533295.640, "dur": 1.927, + "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": 4183436, "tid": 31338, + "ts": 667115533296.320, "dur": 1.131, + "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": 4183436, "tid": 31338, + "ts": 667115533305.711, "dur": 127.689, + "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": 4183436, "tid": 31338, + "ts": 667115533306.660, "dur": 122.273, + "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": 4183436, "tid": 31338, "ts": 667115533306.660, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115533309.469, "dur": 4.997, + "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": 4183436, "tid": 31338, + "ts": 667115533310.820, "dur": 3.000, + "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": 4183436, "tid": 31338, + "ts": 667115533312.861, "dur": 0.759, + "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": 4183436, "tid": 31338, + "ts": 667115533315.577, "dur": 63.930, + "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": 4183436, "tid": 31338, + "ts": 667115533380.875, "dur": 7.941, + "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": 4183436, "tid": 31338, + "ts": 667115533383.850, "dur": 4.425, + "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": 4183436, "tid": 31338, + "ts": 667115533385.708, "dur": 2.413, + "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": 4183436, "tid": 31338, + "ts": 667115533390.054, "dur": 3.219, + "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": 4183436, "tid": 31338, + "ts": 667115533390.851, "dur": 1.953, + "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": 4183436, "tid": 31338, + "ts": 667115533392.270, "dur": 0.449, + "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": 4183436, "tid": 31338, + "ts": 667115533393.886, "dur": 34.129, + "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": 4183436, "tid": 31338, + "ts": 667115533437.847, "dur": 11.352, + "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": 4183436, "tid": 31338, + "ts": 667115533438.961, "dur": 8.435, + "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": 4183436, "tid": 31338, "ts": 667115533438.961, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115533442.524, "dur": 4.736, + "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": 4183436, "tid": 31338, + "ts": 667115533443.830, "dur": 3.279, + "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": 4183436, "tid": 31338, + "ts": 667115533452.491, "dur": 7.930, + "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": 4183436, "tid": 31338, + "ts": 667115533453.533, "dur": 4.661, + "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": 4183436, "tid": 31338, "ts": 667115533453.533, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115533454.364, "dur": 3.620, + "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": 4183436, "tid": 31338, + "ts": 667115533454.945, "dur": 2.511, + "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": 4183436, "tid": 31338, + "ts": 667115533456.983, "dur": 0.328, + "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": 4183436, "tid": 31338, + "ts": 667115533464.529, "dur": 7.681, + "args": { + "External id": 230340,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115533466.455, "dur": 5.269, + "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": 4183436, "tid": 31338, + "ts": 667115533467.591, "dur": 3.860, + "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": 4183436, "tid": 31338, + "ts": 667115533470.180, "dur": 1.154, + "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": 4183436, "tid": 31338, + "ts": 667115533475.310, "dur": 6.200, + "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": 4183436, "tid": 31338, + "ts": 667115533476.162, "dur": 3.370, + "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": 4183436, "tid": 31338, "ts": 667115533476.162, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115533477.369, "dur": 2.018, + "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": 4183436, "tid": 31338, + "ts": 667115533478.131, "dur": 1.129, + "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": 4183436, "tid": 31338, + "ts": 667115533485.849, "dur": 377.939, + "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": 4183436, "tid": 31338, + "ts": 667115533487.150, "dur": 359.057, + "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": 4183436, "tid": 31338, "ts": 667115533487.150, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 31338, + "ts": 667115533524.696, "dur": 8.650, + "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": 4183436, "tid": 31338, + "ts": 667115533527.935, "dur": 4.627, + "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": 4183436, "tid": 31338, + "ts": 667115533535.600, "dur": 3.749, + "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": 4183436, "tid": 31338, + "ts": 667115533536.967, "dur": 2.182, + "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": 4183436, "tid": 31338, + "ts": 667115533540.992, "dur": 5.243, + "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": 4183436, "tid": 31338, + "ts": 667115533542.809, "dur": 3.229, + "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": 4183436, "tid": 31338, + "ts": 667115533590.660, "dur": 228.121, + "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": 4183436, "tid": 31338, + "ts": 667115533715.744, "dur": 5.297, + "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": 4183436, "tid": 31338, + "ts": 667115533723.092, "dur": 4.086, + "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": 4183436, "tid": 31338, + "ts": 667115533832.225, "dur": 4.328, + "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": 4183436, "tid": 31338, + "ts": 667115533839.718, "dur": 0.697, + "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": 4183436, "tid": 31338, + "ts": 667115533842.506, "dur": 0.559, + "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": 4183436, "tid": 31338, + "ts": 667115533875.774, "dur": 227.816, + "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": 4183436, "tid": 31338, + "ts": 667115533877.649, "dur": 219.247, + "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": 4183436, "tid": 31338, "ts": 667115533877.649, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 667115533899.609, "dur": 43.601, + "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": 4183436, "tid": 31338, + "ts": 667115533902.960, "dur": 3.357, + "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": 4183436, "tid": 31338, + "ts": 667115533908.178, "dur": 34.449, + "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": 4183436, "tid": 31338, + "ts": 667115533952.857, "dur": 4.440, + "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": 4183436, "tid": 31338, + "ts": 667115533954.863, "dur": 2.134, + "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": 4183436, "tid": 31338, + "ts": 667115534110.397, "dur": 148.170, + "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": 4183436, "tid": 31338, + "ts": 667115534112.593, "dur": 140.008, + "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": 4183436, "tid": 31338, "ts": 667115534112.593, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 667115534123.873, "dur": 29.417, + "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": 4183436, "tid": 31338, + "ts": 667115534126.446, "dur": 2.247, + "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": 4183436, "tid": 31338, + "ts": 667115534129.662, "dur": 23.106, + "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": 4183436, "tid": 31338, + "ts": 667115534160.055, "dur": 5.924, + "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": 4183436, "tid": 31338, + "ts": 667115534162.026, "dur": 3.665, + "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": 4183436, "tid": 31338, + "ts": 667115534264.649, "dur": 14.481, + "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": 4183436, "tid": 31338, + "ts": 667115534266.017, "dur": 10.848, + "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": 4183436, "tid": 31338, "ts": 667115534266.017, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115534268.306, "dur": 8.236, + "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": 4183436, "tid": 31338, + "ts": 667115534270.206, "dur": 6.083, + "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": 4183436, "tid": 31338, + "ts": 667115534282.895, "dur": 7.406, + "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": 4183436, "tid": 31338, + "ts": 667115534283.829, "dur": 4.614, + "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": 4183436, "tid": 31338, "ts": 667115534283.829, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115534285.932, "dur": 2.363, + "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": 4183436, "tid": 31338, + "ts": 667115534287.223, "dur": 0.871, + "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": 4183436, "tid": 31338, + "ts": 667115534293.376, "dur": 8.350, + "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": 4183436, "tid": 31338, + "ts": 667115534296.086, "dur": 3.743, + "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": 4183436, "tid": 31338, "ts": 667115534296.086, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115534297.634, "dur": 2.051, + "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": 4183436, "tid": 31338, + "ts": 667115534298.752, "dur": 0.851, + "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": 4183436, "tid": 31338, + "ts": 667115534305.381, "dur": 6.633, + "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": 4183436, "tid": 31338, + "ts": 667115534306.957, "dur": 2.973, + "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": 4183436, "tid": 31338, "ts": 667115534306.957, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115534307.912, "dur": 1.876, + "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": 4183436, "tid": 31338, + "ts": 667115534308.698, "dur": 1.000, + "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": 4183436, "tid": 31338, + "ts": 667115534315.253, "dur": 264.622, + "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": 4183436, "tid": 31338, + "ts": 667115534316.092, "dur": 253.912, + "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": 4183436, "tid": 31338, "ts": 667115534316.092, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115534321.358, "dur": 6.987, + "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": 4183436, "tid": 31338, + "ts": 667115534323.220, "dur": 4.482, + "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": 4183436, "tid": 31338, + "ts": 667115534325.896, "dur": 1.540, + "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": 4183436, "tid": 31338, + "ts": 667115534329.698, "dur": 81.395, + "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": 4183436, "tid": 31338, + "ts": 667115534412.428, "dur": 7.072, + "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": 4183436, "tid": 31338, + "ts": 667115534413.217, "dur": 5.584, + "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": 4183436, "tid": 31338, + "ts": 667115534417.670, "dur": 0.944, + "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": 4183436, "tid": 31338, + "ts": 667115534489.847, "dur": 26.967, + "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": 4183436, "tid": 31338, + "ts": 667115534512.614, "dur": 3.397, + "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": 4183436, "tid": 31338, + "ts": 667115534515.170, "dur": 0.568, + "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": 4183436, "tid": 31338, + "ts": 667115534517.604, "dur": 51.383, + "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": 4183436, "tid": 31338, + "ts": 667115534588.274, "dur": 8.004, + "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": 4183436, "tid": 31338, + "ts": 667115534589.365, "dur": 5.102, + "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": 4183436, "tid": 31338, "ts": 667115534589.365, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115534591.225, "dur": 3.068, + "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": 4183436, "tid": 31338, + "ts": 667115534592.464, "dur": 1.692, + "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": 4183436, "tid": 31338, + "ts": 667115534599.605, "dur": 8.799, + "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": 4183436, "tid": 31338, + "ts": 667115534601.786, "dur": 4.402, + "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": 4183436, "tid": 31338, "ts": 667115534601.786, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115534602.583, "dur": 3.395, + "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": 4183436, "tid": 31338, + "ts": 667115534603.327, "dur": 2.111, + "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": 4183436, "tid": 31338, + "ts": 667115534604.822, "dur": 0.521, + "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": 4183436, "tid": 31338, + "ts": 667115534614.268, "dur": 9.644, + "args": { + "External id": 230414,"Record function id": 0, "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115534616.324, "dur": 6.951, + "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": 4183436, "tid": 31338, + "ts": 667115534618.986, "dur": 3.884, + "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": 4183436, "tid": 31338, + "ts": 667115534620.053, "dur": 2.718, + "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": 4183436, "tid": 31338, + "ts": 667115534629.080, "dur": 8.412, + "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": 4183436, "tid": 31338, + "ts": 667115534630.891, "dur": 4.585, + "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": 4183436, "tid": 31338, "ts": 667115534630.891, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115534631.997, "dur": 3.322, + "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": 4183436, "tid": 31338, + "ts": 667115534634.449, "dur": 0.747, + "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": 4183436, "tid": 31338, + "ts": 667115534640.894, "dur": 141.138, + "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": 4183436, "tid": 31338, + "ts": 667115534641.656, "dur": 132.635, + "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": 4183436, "tid": 31338, "ts": 667115534641.656, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115534643.542, "dur": 3.260, + "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": 4183436, "tid": 31338, + "ts": 667115534643.976, "dur": 2.400, + "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": 4183436, "tid": 31338, + "ts": 667115534645.751, "dur": 0.491, + "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": 4183436, "tid": 31338, + "ts": 667115534649.165, "dur": 75.736, + "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": 4183436, "tid": 31338, + "ts": 667115534726.878, "dur": 4.476, + "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": 4183436, "tid": 31338, + "ts": 667115534727.700, "dur": 2.848, + "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": 4183436, "tid": 31338, + "ts": 667115534729.660, "dur": 0.776, + "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": 4183436, "tid": 31338, + "ts": 667115534732.674, "dur": 4.689, + "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": 4183436, "tid": 31338, + "ts": 667115534733.346, "dur": 3.522, + "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": 4183436, "tid": 31338, + "ts": 667115534734.871, "dur": 1.933, + "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": 4183436, "tid": 31338, + "ts": 667115534739.502, "dur": 34.177, + "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": 4183436, "tid": 31338, + "ts": 667115534788.133, "dur": 33.050, + "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": 4183436, "tid": 31338, + "ts": 667115534788.984, "dur": 4.254, + "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": 4183436, "tid": 31338, "ts": 667115534788.984, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115534790.578, "dur": 2.500, + "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": 4183436, "tid": 31338, + "ts": 667115534791.647, "dur": 1.315, + "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": 4183436, "tid": 31338, + "ts": 667115534796.571, "dur": 22.833, + "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": 4183436, "tid": 31338, + "ts": 667115534825.278, "dur": 9.799, + "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": 4183436, "tid": 31338, + "ts": 667115534826.235, "dur": 6.724, + "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": 4183436, "tid": 31338, "ts": 667115534826.235, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115534826.856, "dur": 5.914, + "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": 4183436, "tid": 31338, + "ts": 667115534829.531, "dur": 2.745, + "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": 4183436, "tid": 31338, + "ts": 667115534831.580, "dur": 0.606, + "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": 4183436, "tid": 31338, + "ts": 667115534839.462, "dur": 5.778, + "args": { + "External id": 230445,"Record function id": 0, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115534841.097, "dur": 3.592, + "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": 4183436, "tid": 31338, + "ts": 667115534842.295, "dur": 1.997, + "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": 4183436, "tid": 31338, + "ts": 667115534842.864, "dur": 1.312, + "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": 4183436, "tid": 31338, + "ts": 667115534848.529, "dur": 6.094, + "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": 4183436, "tid": 31338, + "ts": 667115534850.272, "dur": 2.839, + "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": 4183436, "tid": 31338, "ts": 667115534850.272, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115534851.230, "dur": 1.734, + "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": 4183436, "tid": 31338, + "ts": 667115534851.914, "dur": 0.959, + "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": 4183436, "tid": 31338, + "ts": 667115534859.717, "dur": 89.567, + "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": 4183436, "tid": 31338, + "ts": 667115534860.587, "dur": 80.947, + "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": 4183436, "tid": 31338, "ts": 667115534860.587, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115534862.581, "dur": 2.746, + "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": 4183436, "tid": 31338, + "ts": 667115534862.981, "dur": 1.860, + "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": 4183436, "tid": 31338, + "ts": 667115534864.297, "dur": 0.429, + "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": 4183436, "tid": 31338, + "ts": 667115534865.868, "dur": 35.573, + "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": 4183436, "tid": 31338, + "ts": 667115534902.613, "dur": 5.044, + "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": 4183436, "tid": 31338, + "ts": 667115534904.740, "dur": 2.343, + "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": 4183436, "tid": 31338, + "ts": 667115534906.525, "dur": 0.448, + "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": 4183436, "tid": 31338, + "ts": 667115534908.698, "dur": 2.549, + "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": 4183436, "tid": 31338, + "ts": 667115534909.205, "dur": 1.619, + "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": 4183436, "tid": 31338, + "ts": 667115534910.421, "dur": 0.337, + "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": 4183436, "tid": 31338, + "ts": 667115534911.639, "dur": 29.352, + "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": 4183436, "tid": 31338, + "ts": 667115534953.671, "dur": 25.253, + "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": 4183436, "tid": 31338, + "ts": 667115534956.417, "dur": 4.106, + "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": 4183436, "tid": 31338, "ts": 667115534956.417, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115534958.014, "dur": 2.357, + "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": 4183436, "tid": 31338, + "ts": 667115534959.277, "dur": 1.000, + "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": 4183436, "tid": 31338, + "ts": 667115534962.798, "dur": 14.187, + "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": 4183436, "tid": 31338, + "ts": 667115534982.672, "dur": 10.296, + "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": 4183436, "tid": 31338, + "ts": 667115534983.622, "dur": 7.306, + "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": 4183436, "tid": 31338, "ts": 667115534983.622, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115534984.352, "dur": 6.375, + "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": 4183436, "tid": 31338, + "ts": 667115534986.241, "dur": 3.914, + "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": 4183436, "tid": 31338, + "ts": 667115534989.616, "dur": 0.448, + "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": 4183436, "tid": 31338, + "ts": 667115534997.145, "dur": 5.071, + "args": { + "External id": 230476,"Record function id": 0, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115534999.055, "dur": 2.717, + "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": 4183436, "tid": 31338, + "ts": 667115534999.948, "dur": 1.534, + "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": 4183436, "tid": 31338, + "ts": 667115535000.436, "dur": 0.955, + "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": 4183436, "tid": 31338, + "ts": 667115535006.680, "dur": 362.996, + "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": 4183436, "tid": 31338, + "ts": 667115535008.175, "dur": 330.842, + "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": 4183436, "tid": 31338, "ts": 667115535008.175, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115535043.696, "dur": 2.182, + "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": 4183436, "tid": 31338, + "ts": 667115535044.542, "dur": 1.168, + "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": 4183436, "tid": 31338, + "ts": 667115535060.568, "dur": 5.472, + "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": 4183436, "tid": 31338, + "ts": 667115535077.991, "dur": 4.090, + "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": 4183436, "tid": 31338, + "ts": 667115535237.361, "dur": 1.876, + "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": 4183436, "tid": 31338, + "ts": 667115535243.904, "dur": 33.574, + "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": 4183436, "tid": 31338, + "ts": 667115535253.352, "dur": 0.977, + "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": 4183436, "tid": 31338, + "ts": 667115535282.931, "dur": 31.182, + "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": 4183436, "tid": 31338, + "ts": 667115535284.757, "dur": 29.149, + "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": 4183436, "tid": 31338, + "ts": 667115535289.403, "dur": 3.976, + "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": 4183436, "tid": 31338, + "ts": 667115535294.856, "dur": 18.523, + "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": 4183436, "tid": 31338, + "ts": 667115535318.412, "dur": 4.789, + "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": 4183436, "tid": 31338, + "ts": 667115535322.027, "dur": 1.065, + "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": 4183436, "tid": 31338, + "ts": 667115535329.823, "dur": 2.364, + "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": 4183436, "tid": 31338, + "ts": 667115535331.083, "dur": 0.957, + "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": 4183436, "tid": 31338, + "ts": 667115535348.727, "dur": 15.671, + "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": 4183436, "tid": 31338, + "ts": 667115535379.969, "dur": 7.555, + "args": { + "External id": 230498,"Record function id": 0, "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115535381.804, "dur": 5.056, + "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": 4183436, "tid": 31338, + "ts": 667115535383.581, "dur": 2.475, + "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": 4183436, "tid": 31338, + "ts": 667115535384.464, "dur": 1.475, + "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": 4183436, "tid": 31338, + "ts": 667115535393.202, "dur": 5.270, + "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": 4183436, "tid": 31338, + "ts": 667115535394.436, "dur": 1.111, + "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": 4183436, "tid": 31338, "ts": 667115535394.436, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115535402.653, "dur": 488.440, + "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": 4183436, "tid": 31338, + "ts": 667115535404.370, "dur": 475.113, + "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": 4183436, "tid": 31338, "ts": 667115535404.370, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115535434.460, "dur": 8.625, + "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": 4183436, "tid": 31338, + "ts": 667115535439.721, "dur": 3.127, + "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": 4183436, "tid": 31338, + "ts": 667115535446.040, "dur": 7.239, + "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": 4183436, "tid": 31338, + "ts": 667115535447.479, "dur": 5.121, + "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": 4183436, "tid": 31338, + "ts": 667115535449.706, "dur": 2.738, + "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": 4183436, "tid": 31338, + "ts": 667115535458.524, "dur": 119.584, + "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": 4183436, "tid": 31338, + "ts": 667115535459.367, "dur": 3.420, + "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": 4183436, "tid": 31338, + "ts": 667115535460.242, "dur": 2.064, + "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": 4183436, "tid": 31338, + "ts": 667115535461.663, "dur": 0.566, + "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": 4183436, "tid": 31338, + "ts": 667115535463.878, "dur": 113.633, + "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": 4183436, "tid": 31338, + "ts": 667115535465.287, "dur": 111.092, + "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": 4183436, "tid": 31338, + "ts": 667115535583.280, "dur": 5.874, + "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": 4183436, "tid": 31338, + "ts": 667115535587.062, "dur": 1.953, + "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": 4183436, "tid": 31338, + "ts": 667115535622.743, "dur": 5.100, + "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": 4183436, "tid": 31338, + "ts": 667115535629.247, "dur": 1.967, + "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": 4183436, "tid": 31338, + "ts": 667115535632.457, "dur": 1.531, + "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": 4183436, "tid": 31338, + "ts": 667115535707.410, "dur": 3.281, + "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": 4183436, "tid": 31338, + "ts": 667115535708.468, "dur": 1.967, + "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": 4183436, "tid": 31338, + "ts": 667115535733.669, "dur": 124.492, + "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": 4183436, "tid": 31338, + "ts": 667115535739.381, "dur": 8.363, + "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": 4183436, "tid": 31338, + "ts": 667115535743.742, "dur": 3.076, + "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": 4183436, "tid": 31338, + "ts": 667115535749.678, "dur": 6.175, + "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": 4183436, "tid": 31338, + "ts": 667115535754.614, "dur": 0.541, + "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": 4183436, "tid": 31338, + "ts": 667115535757.316, "dur": 2.881, + "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": 4183436, "tid": 31338, + "ts": 667115535759.418, "dur": 0.375, + "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": 4183436, "tid": 31338, + "ts": 667115535761.184, "dur": 3.105, + "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": 4183436, "tid": 31338, + "ts": 667115535763.159, "dur": 0.684, + "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": 4183436, "tid": 31338, + "ts": 667115535768.082, "dur": 2.423, + "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": 4183436, "tid": 31338, + "ts": 667115535769.628, "dur": 0.576, + "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": 4183436, "tid": 31338, + "ts": 667115535773.978, "dur": 6.774, + "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": 4183436, "tid": 31338, + "ts": 667115535778.595, "dur": 1.951, + "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": 4183436, "tid": 31338, + "ts": 667115535782.028, "dur": 2.770, + "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": 4183436, "tid": 31338, + "ts": 667115535783.934, "dur": 0.595, + "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": 4183436, "tid": 31338, + "ts": 667115535785.765, "dur": 2.940, + "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": 4183436, "tid": 31338, + "ts": 667115535786.536, "dur": 2.066, + "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": 4183436, "tid": 31338, + "ts": 667115535790.366, "dur": 55.858, + "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": 4183436, "tid": 31338, + "ts": 667115535848.349, "dur": 1.058, + "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": 4183436, "tid": 31338, + "ts": 667115535850.389, "dur": 3.587, + "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": 4183436, "tid": 31338, + "ts": 667115535853.076, "dur": 0.501, + "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": 4183436, "tid": 31338, + "ts": 667115535856.185, "dur": 0.976, + "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": 4183436, "tid": 31338, + "ts": 667115535903.900, "dur": 9.105, + "args": { + "External id": 230546,"Record function id": 0, "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115535906.307, "dur": 5.979, + "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": 4183436, "tid": 31338, + "ts": 667115535908.335, "dur": 3.151, + "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": 4183436, "tid": 31338, + "ts": 667115535909.293, "dur": 2.076, + "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": 4183436, "tid": 31338, + "ts": 667115535917.108, "dur": 6.811, + "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": 4183436, "tid": 31338, + "ts": 667115535918.341, "dur": 3.759, + "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": 4183436, "tid": 31338, "ts": 667115535918.341, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115535919.873, "dur": 2.007, + "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": 4183436, "tid": 31338, + "ts": 667115535920.812, "dur": 0.923, + "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": 4183436, "tid": 31338, + "ts": 667115535927.734, "dur": 104.224, + "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": 4183436, "tid": 31338, + "ts": 667115535928.469, "dur": 96.793, + "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": 4183436, "tid": 31338, "ts": 667115535928.469, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115535934.127, "dur": 4.610, + "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": 4183436, "tid": 31338, + "ts": 667115535935.677, "dur": 2.486, + "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": 4183436, "tid": 31338, + "ts": 667115535937.228, "dur": 0.787, + "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": 4183436, "tid": 31338, + "ts": 667115535939.815, "dur": 34.510, + "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": 4183436, "tid": 31338, + "ts": 667115535975.510, "dur": 5.732, + "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": 4183436, "tid": 31338, + "ts": 667115535976.277, "dur": 4.282, + "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": 4183436, "tid": 31338, + "ts": 667115535979.624, "dur": 0.789, + "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": 4183436, "tid": 31338, + "ts": 667115535982.752, "dur": 4.679, + "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": 4183436, "tid": 31338, + "ts": 667115535983.537, "dur": 3.453, + "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": 4183436, "tid": 31338, + "ts": 667115535984.774, "dur": 2.153, + "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": 4183436, "tid": 31338, + "ts": 667115535987.975, "dur": 36.555, + "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": 4183436, "tid": 31338, + "ts": 667115536036.750, "dur": 6.644, + "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": 4183436, "tid": 31338, + "ts": 667115536037.874, "dur": 4.320, + "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": 4183436, "tid": 31338, "ts": 667115536037.874, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115536039.891, "dur": 2.141, + "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": 4183436, "tid": 31338, + "ts": 667115536040.675, "dur": 1.212, + "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": 4183436, "tid": 31338, + "ts": 667115536047.205, "dur": 9.039, + "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": 4183436, "tid": 31338, + "ts": 667115536049.931, "dur": 4.377, + "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": 4183436, "tid": 31338, "ts": 667115536049.931, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115536050.950, "dur": 3.146, + "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": 4183436, "tid": 31338, + "ts": 667115536051.687, "dur": 1.945, + "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": 4183436, "tid": 31338, + "ts": 667115536053.090, "dur": 0.442, + "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": 4183436, "tid": 31338, + "ts": 667115536060.390, "dur": 5.067, + "args": { + "External id": 230576,"Record function id": 0, "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115536062.027, "dur": 2.863, + "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": 4183436, "tid": 31338, + "ts": 667115536062.916, "dur": 1.723, + "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": 4183436, "tid": 31338, + "ts": 667115536063.542, "dur": 0.998, + "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": 4183436, "tid": 31338, + "ts": 667115536068.704, "dur": 7.655, + "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": 4183436, "tid": 31338, + "ts": 667115536069.964, "dur": 4.402, + "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": 4183436, "tid": 31338, "ts": 667115536069.964, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115536070.983, "dur": 3.216, + "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": 4183436, "tid": 31338, + "ts": 667115536073.440, "dur": 0.625, + "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": 4183436, "tid": 31338, + "ts": 667115536079.558, "dur": 105.636, + "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": 4183436, "tid": 31338, + "ts": 667115536080.266, "dur": 97.311, + "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": 4183436, "tid": 31338, "ts": 667115536080.266, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115536082.073, "dur": 19.105, + "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": 4183436, "tid": 31338, + "ts": 667115536082.767, "dur": 17.835, + "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": 4183436, "tid": 31338, + "ts": 667115536099.745, "dur": 0.589, + "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": 4183436, "tid": 31338, + "ts": 667115536103.777, "dur": 27.190, + "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": 4183436, "tid": 31338, + "ts": 667115536131.938, "dur": 7.448, + "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": 4183436, "tid": 31338, + "ts": 667115536132.780, "dur": 6.055, + "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": 4183436, "tid": 31338, + "ts": 667115536134.345, "dur": 4.344, + "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": 4183436, "tid": 31338, + "ts": 667115536140.482, "dur": 4.717, + "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": 4183436, "tid": 31338, + "ts": 667115536141.184, "dur": 3.576, + "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": 4183436, "tid": 31338, + "ts": 667115536144.282, "dur": 0.400, + "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": 4183436, "tid": 31338, + "ts": 667115536145.641, "dur": 31.181, + "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": 4183436, "tid": 31338, + "ts": 667115536189.783, "dur": 29.286, + "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": 4183436, "tid": 31338, + "ts": 667115536190.707, "dur": 3.708, + "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": 4183436, "tid": 31338, "ts": 667115536190.707, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115536192.073, "dur": 2.185, + "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": 4183436, "tid": 31338, + "ts": 667115536193.138, "dur": 1.015, + "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": 4183436, "tid": 31338, + "ts": 667115536197.162, "dur": 19.443, + "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": 4183436, "tid": 31338, + "ts": 667115536223.095, "dur": 8.970, + "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": 4183436, "tid": 31338, + "ts": 667115536224.032, "dur": 5.833, + "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": 4183436, "tid": 31338, "ts": 667115536224.032, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115536224.766, "dur": 4.893, + "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": 4183436, "tid": 31338, + "ts": 667115536225.649, "dur": 3.515, + "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": 4183436, "tid": 31338, + "ts": 667115536228.652, "dur": 0.399, + "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": 4183436, "tid": 31338, + "ts": 667115536236.262, "dur": 5.557, + "args": { + "External id": 230607,"Record function id": 0, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115536238.254, "dur": 3.067, + "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": 4183436, "tid": 31338, + "ts": 667115536239.226, "dur": 1.825, + "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": 4183436, "tid": 31338, + "ts": 667115536239.953, "dur": 1.011, + "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": 4183436, "tid": 31338, + "ts": 667115536248.813, "dur": 471.825, + "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": 4183436, "tid": 31338, + "ts": 667115536250.492, "dur": 392.267, + "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": 4183436, "tid": 31338, "ts": 667115536250.492, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 31338, + "ts": 667115536273.133, "dur": 31.926, + "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": 4183436, "tid": 31338, + "ts": 667115536274.610, "dur": 30.259, + "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": 4183436, "tid": 31338, + "ts": 667115536277.419, "dur": 5.604, + "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": 4183436, "tid": 31338, + "ts": 667115536280.016, "dur": 2.431, + "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": 4183436, "tid": 31338, + "ts": 667115536284.329, "dur": 20.085, + "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": 4183436, "tid": 31338, + "ts": 667115536314.721, "dur": 6.146, + "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": 4183436, "tid": 31338, + "ts": 667115536317.486, "dur": 3.241, + "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": 4183436, "tid": 31338, + "ts": 667115536324.660, "dur": 1.973, + "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": 4183436, "tid": 31338, + "ts": 667115536325.737, "dur": 0.807, + "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": 4183436, "tid": 31338, + "ts": 667115536338.326, "dur": 1.876, + "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": 4183436, "tid": 31338, + "ts": 667115536350.818, "dur": 2.909, + "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": 4183436, "tid": 31338, + "ts": 667115536531.578, "dur": 3.535, + "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": 4183436, "tid": 31338, + "ts": 667115536540.050, "dur": 36.038, + "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": 4183436, "tid": 31338, + "ts": 667115536549.370, "dur": 1.032, + "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": 4183436, "tid": 31338, + "ts": 667115536581.797, "dur": 28.344, + "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": 4183436, "tid": 31338, + "ts": 667115536583.324, "dur": 26.595, + "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": 4183436, "tid": 31338, + "ts": 667115536587.582, "dur": 4.349, + "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": 4183436, "tid": 31338, + "ts": 667115536593.224, "dur": 16.140, + "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": 4183436, "tid": 31338, + "ts": 667115536614.807, "dur": 4.393, + "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": 4183436, "tid": 31338, + "ts": 667115536617.873, "dur": 1.174, + "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": 4183436, "tid": 31338, + "ts": 667115536625.920, "dur": 4.299, + "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": 4183436, "tid": 31338, + "ts": 667115536626.865, "dur": 3.246, + "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": 4183436, "tid": 31338, + "ts": 667115536632.503, "dur": 1.878, + "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": 4183436, "tid": 31338, + "ts": 667115536633.334, "dur": 0.955, + "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": 4183436, "tid": 31338, + "ts": 667115536697.832, "dur": 20.669, + "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": 4183436, "tid": 31338, + "ts": 667115536735.430, "dur": 11.746, + "args": { + "External id": 230638,"Record function id": 0, "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115536737.768, "dur": 8.674, + "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": 4183436, "tid": 31338, + "ts": 667115536739.933, "dur": 5.609, + "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": 4183436, "tid": 31338, + "ts": 667115536743.250, "dur": 2.218, + "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": 4183436, "tid": 31338, + "ts": 667115536751.482, "dur": 8.815, + "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": 4183436, "tid": 31338, + "ts": 667115536752.885, "dur": 4.696, + "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": 4183436, "tid": 31338, "ts": 667115536752.885, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115536754.741, "dur": 2.591, + "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": 4183436, "tid": 31338, + "ts": 667115536755.526, "dur": 1.661, + "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": 4183436, "tid": 31338, + "ts": 667115536763.860, "dur": 138.665, + "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": 4183436, "tid": 31338, + "ts": 667115536764.696, "dur": 131.478, + "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": 4183436, "tid": 31338, "ts": 667115536764.696, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115536767.954, "dur": 7.747, + "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": 4183436, "tid": 31338, + "ts": 667115536771.613, "dur": 3.440, + "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": 4183436, "tid": 31338, + "ts": 667115536773.612, "dur": 1.202, + "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": 4183436, "tid": 31338, + "ts": 667115536777.040, "dur": 69.583, + "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": 4183436, "tid": 31338, + "ts": 667115536847.871, "dur": 6.141, + "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": 4183436, "tid": 31338, + "ts": 667115536848.752, "dur": 4.723, + "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": 4183436, "tid": 31338, + "ts": 667115536850.536, "dur": 2.781, + "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": 4183436, "tid": 31338, + "ts": 667115536857.336, "dur": 3.678, + "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": 4183436, "tid": 31338, + "ts": 667115536858.316, "dur": 2.193, + "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": 4183436, "tid": 31338, + "ts": 667115536859.971, "dur": 0.476, + "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": 4183436, "tid": 31338, + "ts": 667115536861.675, "dur": 33.653, + "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": 4183436, "tid": 31338, + "ts": 667115536907.364, "dur": 9.874, + "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": 4183436, "tid": 31338, + "ts": 667115536908.429, "dur": 6.777, + "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": 4183436, "tid": 31338, "ts": 667115536908.429, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115536910.251, "dur": 4.787, + "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": 4183436, "tid": 31338, + "ts": 667115536911.449, "dur": 3.443, + "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": 4183436, "tid": 31338, + "ts": 667115536920.593, "dur": 8.146, + "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": 4183436, "tid": 31338, + "ts": 667115536922.889, "dur": 4.289, + "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": 4183436, "tid": 31338, "ts": 667115536922.889, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115536923.617, "dur": 3.404, + "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": 4183436, "tid": 31338, + "ts": 667115536924.198, "dur": 2.331, + "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": 4183436, "tid": 31338, + "ts": 667115536925.823, "dur": 0.634, + "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": 4183436, "tid": 31338, + "ts": 667115536932.734, "dur": 5.728, + "args": { + "External id": 230668,"Record function id": 0, "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115536934.615, "dur": 3.310, + "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": 4183436, "tid": 31338, + "ts": 667115536935.627, "dur": 1.988, + "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": 4183436, "tid": 31338, + "ts": 667115536936.215, "dur": 1.326, + "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": 4183436, "tid": 31338, + "ts": 667115536941.391, "dur": 8.239, + "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": 4183436, "tid": 31338, + "ts": 667115536942.087, "dur": 5.867, + "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": 4183436, "tid": 31338, "ts": 667115536942.087, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115536945.698, "dur": 2.107, + "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": 4183436, "tid": 31338, + "ts": 667115536946.549, "dur": 1.112, + "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": 4183436, "tid": 31338, + "ts": 667115536953.778, "dur": 268.789, + "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": 4183436, "tid": 31338, + "ts": 667115536955.281, "dur": 250.481, + "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": 4183436, "tid": 31338, "ts": 667115536955.281, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 31338, + "ts": 667115536970.817, "dur": 6.687, + "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": 4183436, "tid": 31338, + "ts": 667115536973.627, "dur": 3.385, + "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": 4183436, "tid": 31338, + "ts": 667115536979.712, "dur": 4.034, + "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": 4183436, "tid": 31338, + "ts": 667115536981.692, "dur": 1.884, + "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": 4183436, "tid": 31338, + "ts": 667115536985.080, "dur": 4.329, + "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": 4183436, "tid": 31338, + "ts": 667115536986.610, "dur": 2.614, + "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": 4183436, "tid": 31338, + "ts": 667115537014.100, "dur": 167.512, + "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": 4183436, "tid": 31338, + "ts": 667115537092.558, "dur": 3.110, + "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": 4183436, "tid": 31338, + "ts": 667115537097.385, "dur": 3.446, + "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": 4183436, "tid": 31338, + "ts": 667115537193.718, "dur": 3.196, + "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": 4183436, "tid": 31338, + "ts": 667115537199.772, "dur": 0.717, + "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": 4183436, "tid": 31338, + "ts": 667115537202.521, "dur": 0.661, + "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": 4183436, "tid": 31338, + "ts": 667115537229.766, "dur": 216.820, + "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": 4183436, "tid": 31338, + "ts": 667115537232.089, "dur": 207.643, + "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": 4183436, "tid": 31338, "ts": 667115537232.089, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 667115537250.617, "dur": 45.297, + "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": 4183436, "tid": 31338, + "ts": 667115537253.336, "dur": 2.506, + "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": 4183436, "tid": 31338, + "ts": 667115537257.050, "dur": 38.192, + "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": 4183436, "tid": 31338, + "ts": 667115537303.973, "dur": 4.524, + "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": 4183436, "tid": 31338, + "ts": 667115537305.857, "dur": 2.381, + "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": 4183436, "tid": 31338, + "ts": 667115537453.212, "dur": 175.088, + "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": 4183436, "tid": 31338, + "ts": 667115537455.139, "dur": 166.254, + "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": 4183436, "tid": 31338, "ts": 667115537455.139, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 667115537467.025, "dur": 51.326, + "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": 4183436, "tid": 31338, + "ts": 667115537469.317, "dur": 2.430, + "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": 4183436, "tid": 31338, + "ts": 667115537473.056, "dur": 44.557, + "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": 4183436, "tid": 31338, + "ts": 667115537526.818, "dur": 5.975, + "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": 4183436, "tid": 31338, + "ts": 667115537529.013, "dur": 3.506, + "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": 4183436, "tid": 31338, + "ts": 667115537636.498, "dur": 54.175, + "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": 4183436, "tid": 31338, + "ts": 667115537638.036, "dur": 48.110, + "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": 4183436, "tid": 31338, "ts": 667115537638.036, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115537640.863, "dur": 44.234, + "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": 4183436, "tid": 31338, + "ts": 667115537644.351, "dur": 5.653, + "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": 4183436, "tid": 31338, + "ts": 667115537697.122, "dur": 8.002, + "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": 4183436, "tid": 31338, + "ts": 667115537698.310, "dur": 4.817, + "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": 4183436, "tid": 31338, "ts": 667115537698.310, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115537700.163, "dur": 2.794, + "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": 4183436, "tid": 31338, + "ts": 667115537701.144, "dur": 1.666, + "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": 4183436, "tid": 31338, + "ts": 667115537710.423, "dur": 6.149, + "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": 4183436, "tid": 31338, + "ts": 667115537711.318, "dur": 3.404, + "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": 4183436, "tid": 31338, "ts": 667115537711.318, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115537712.516, "dur": 2.054, + "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": 4183436, "tid": 31338, + "ts": 667115537713.522, "dur": 0.914, + "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": 4183436, "tid": 31338, + "ts": 667115537720.425, "dur": 8.265, + "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": 4183436, "tid": 31338, + "ts": 667115537721.647, "dur": 5.155, + "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": 4183436, "tid": 31338, "ts": 667115537721.647, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115537722.706, "dur": 3.954, + "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": 4183436, "tid": 31338, + "ts": 667115537725.620, "dur": 0.935, + "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": 4183436, "tid": 31338, + "ts": 667115537732.318, "dur": 160.018, + "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": 4183436, "tid": 31338, + "ts": 667115537733.369, "dur": 151.605, + "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": 4183436, "tid": 31338, "ts": 667115537733.369, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115537736.874, "dur": 7.301, + "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": 4183436, "tid": 31338, + "ts": 667115537738.796, "dur": 4.703, + "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": 4183436, "tid": 31338, + "ts": 667115537741.390, "dur": 1.835, + "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": 4183436, "tid": 31338, + "ts": 667115537747.966, "dur": 83.982, + "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": 4183436, "tid": 31338, + "ts": 667115537833.187, "dur": 4.530, + "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": 4183436, "tid": 31338, + "ts": 667115537833.900, "dur": 3.173, + "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": 4183436, "tid": 31338, + "ts": 667115537835.774, "dur": 1.110, + "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": 4183436, "tid": 31338, + "ts": 667115537839.109, "dur": 5.637, + "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": 4183436, "tid": 31338, + "ts": 667115537840.204, "dur": 4.011, + "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": 4183436, "tid": 31338, + "ts": 667115537843.690, "dur": 0.444, + "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": 4183436, "tid": 31338, + "ts": 667115537845.671, "dur": 38.497, + "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": 4183436, "tid": 31338, + "ts": 667115537896.987, "dur": 7.431, + "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": 4183436, "tid": 31338, + "ts": 667115537897.824, "dur": 4.445, + "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": 4183436, "tid": 31338, "ts": 667115537897.824, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115537899.643, "dur": 2.480, + "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": 4183436, "tid": 31338, + "ts": 667115537900.602, "dur": 1.415, + "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": 4183436, "tid": 31338, + "ts": 667115537907.655, "dur": 9.463, + "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": 4183436, "tid": 31338, + "ts": 667115537908.518, "dur": 6.422, + "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": 4183436, "tid": 31338, "ts": 667115537908.518, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115537909.484, "dur": 5.256, + "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": 4183436, "tid": 31338, + "ts": 667115537910.190, "dur": 3.989, + "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": 4183436, "tid": 31338, + "ts": 667115537913.537, "dur": 0.525, + "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": 4183436, "tid": 31338, + "ts": 667115537922.799, "dur": 9.433, + "args": { + "External id": 230742,"Record function id": 0, "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115537924.820, "dur": 6.665, + "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": 4183436, "tid": 31338, + "ts": 667115537927.248, "dur": 3.846, + "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": 4183436, "tid": 31338, + "ts": 667115537928.433, "dur": 2.554, + "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": 4183436, "tid": 31338, + "ts": 667115537935.600, "dur": 6.320, + "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": 4183436, "tid": 31338, + "ts": 667115537936.792, "dur": 2.901, + "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": 4183436, "tid": 31338, "ts": 667115537936.792, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115537937.804, "dur": 1.743, + "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": 4183436, "tid": 31338, + "ts": 667115537938.653, "dur": 0.760, + "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": 4183436, "tid": 31338, + "ts": 667115537945.316, "dur": 92.068, + "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": 4183436, "tid": 31338, + "ts": 667115537946.181, "dur": 85.947, + "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": 4183436, "tid": 31338, "ts": 667115537946.181, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115537950.128, "dur": 2.816, + "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": 4183436, "tid": 31338, + "ts": 667115537950.631, "dur": 1.880, + "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": 4183436, "tid": 31338, + "ts": 667115537951.919, "dur": 0.486, + "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": 4183436, "tid": 31338, + "ts": 667115537953.605, "dur": 33.796, + "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": 4183436, "tid": 31338, + "ts": 667115537988.381, "dur": 4.494, + "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": 4183436, "tid": 31338, + "ts": 667115537989.047, "dur": 3.251, + "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": 4183436, "tid": 31338, + "ts": 667115537991.039, "dur": 1.154, + "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": 4183436, "tid": 31338, + "ts": 667115537996.044, "dur": 4.983, + "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": 4183436, "tid": 31338, + "ts": 667115537997.066, "dur": 3.437, + "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": 4183436, "tid": 31338, + "ts": 667115537998.520, "dur": 1.905, + "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": 4183436, "tid": 31338, + "ts": 667115538001.476, "dur": 30.069, + "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": 4183436, "tid": 31338, + "ts": 667115538041.637, "dur": 34.466, + "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": 4183436, "tid": 31338, + "ts": 667115538042.747, "dur": 4.097, + "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": 4183436, "tid": 31338, "ts": 667115538042.747, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115538044.385, "dur": 2.310, + "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": 4183436, "tid": 31338, + "ts": 667115538045.427, "dur": 1.133, + "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": 4183436, "tid": 31338, + "ts": 667115538049.616, "dur": 22.702, + "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": 4183436, "tid": 31338, + "ts": 667115538080.083, "dur": 7.291, + "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": 4183436, "tid": 31338, + "ts": 667115538081.194, "dur": 4.723, + "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": 4183436, "tid": 31338, "ts": 667115538081.194, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115538081.930, "dur": 3.809, + "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": 4183436, "tid": 31338, + "ts": 667115538082.679, "dur": 2.552, + "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": 4183436, "tid": 31338, + "ts": 667115538084.520, "dur": 0.566, + "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": 4183436, "tid": 31338, + "ts": 667115538091.339, "dur": 7.054, + "args": { + "External id": 230773,"Record function id": 0, "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115538093.385, "dur": 4.484, + "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": 4183436, "tid": 31338, + "ts": 667115538094.428, "dur": 3.087, + "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": 4183436, "tid": 31338, + "ts": 667115538096.355, "dur": 1.004, + "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": 4183436, "tid": 31338, + "ts": 667115538101.952, "dur": 6.940, + "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": 4183436, "tid": 31338, + "ts": 667115538102.948, "dur": 3.397, + "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": 4183436, "tid": 31338, "ts": 667115538102.948, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115538104.335, "dur": 1.852, + "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": 4183436, "tid": 31338, + "ts": 667115538105.230, "dur": 0.863, + "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": 4183436, "tid": 31338, + "ts": 667115538113.948, "dur": 96.104, + "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": 4183436, "tid": 31338, + "ts": 667115538114.753, "dur": 88.278, + "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": 4183436, "tid": 31338, "ts": 667115538114.753, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115538116.692, "dur": 4.477, + "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": 4183436, "tid": 31338, + "ts": 667115538117.283, "dur": 3.429, + "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": 4183436, "tid": 31338, + "ts": 667115538120.171, "dur": 0.435, + "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": 4183436, "tid": 31338, + "ts": 667115538121.665, "dur": 36.272, + "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": 4183436, "tid": 31338, + "ts": 667115538159.147, "dur": 3.848, + "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": 4183436, "tid": 31338, + "ts": 667115538159.805, "dur": 2.645, + "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": 4183436, "tid": 31338, + "ts": 667115538161.389, "dur": 0.953, + "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": 4183436, "tid": 31338, + "ts": 667115538164.198, "dur": 7.320, + "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": 4183436, "tid": 31338, + "ts": 667115538169.218, "dur": 1.794, + "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": 4183436, "tid": 31338, + "ts": 667115538170.436, "dur": 0.463, + "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": 4183436, "tid": 31338, + "ts": 667115538172.153, "dur": 30.177, + "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": 4183436, "tid": 31338, + "ts": 667115538214.480, "dur": 25.492, + "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": 4183436, "tid": 31338, + "ts": 667115538215.521, "dur": 3.916, + "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": 4183436, "tid": 31338, "ts": 667115538215.521, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115538216.915, "dur": 2.379, + "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": 4183436, "tid": 31338, + "ts": 667115538218.089, "dur": 1.065, + "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": 4183436, "tid": 31338, + "ts": 667115538221.893, "dur": 16.069, + "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": 4183436, "tid": 31338, + "ts": 667115538243.564, "dur": 9.016, + "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": 4183436, "tid": 31338, + "ts": 667115538246.336, "dur": 4.552, + "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": 4183436, "tid": 31338, "ts": 667115538246.336, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115538247.317, "dur": 3.400, + "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": 4183436, "tid": 31338, + "ts": 667115538247.936, "dur": 2.261, + "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": 4183436, "tid": 31338, + "ts": 667115538249.450, "dur": 0.608, + "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": 4183436, "tid": 31338, + "ts": 667115538256.571, "dur": 5.237, + "args": { + "External id": 230804,"Record function id": 0, "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115538258.471, "dur": 2.895, + "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": 4183436, "tid": 31338, + "ts": 667115538259.238, "dur": 1.825, + "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": 4183436, "tid": 31338, + "ts": 667115538260.029, "dur": 0.954, + "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": 4183436, "tid": 31338, + "ts": 667115538266.316, "dur": 460.129, + "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": 4183436, "tid": 31338, + "ts": 667115538267.740, "dur": 417.676, + "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": 4183436, "tid": 31338, "ts": 667115538267.740, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115538317.862, "dur": 4.163, + "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": 4183436, "tid": 31338, + "ts": 667115538320.581, "dur": 1.303, + "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": 4183436, "tid": 31338, + "ts": 667115538335.705, "dur": 5.699, + "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": 4183436, "tid": 31338, + "ts": 667115538351.089, "dur": 2.692, + "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": 4183436, "tid": 31338, + "ts": 667115538528.350, "dur": 3.178, + "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": 4183436, "tid": 31338, + "ts": 667115538536.259, "dur": 38.564, + "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": 4183436, "tid": 31338, + "ts": 667115538547.481, "dur": 1.011, + "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": 4183436, "tid": 31338, + "ts": 667115538594.915, "dur": 34.502, + "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": 4183436, "tid": 31338, + "ts": 667115538596.987, "dur": 32.219, + "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": 4183436, "tid": 31338, + "ts": 667115538603.450, "dur": 5.916, + "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": 4183436, "tid": 31338, + "ts": 667115538610.981, "dur": 17.672, + "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": 4183436, "tid": 31338, + "ts": 667115538634.504, "dur": 2.676, + "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": 4183436, "tid": 31338, + "ts": 667115538635.830, "dur": 1.253, + "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": 4183436, "tid": 31338, + "ts": 667115538643.505, "dur": 2.337, + "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": 4183436, "tid": 31338, + "ts": 667115538644.840, "dur": 0.893, + "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": 4183436, "tid": 31338, + "ts": 667115538700.846, "dur": 20.897, + "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": 4183436, "tid": 31338, + "ts": 667115538741.867, "dur": 10.728, + "args": { + "External id": 230826,"Record function id": 0, "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115538744.649, "dur": 7.086, + "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": 4183436, "tid": 31338, + "ts": 667115538747.310, "dur": 3.342, + "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": 4183436, "tid": 31338, + "ts": 667115538748.295, "dur": 2.233, + "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": 4183436, "tid": 31338, + "ts": 667115538756.708, "dur": 6.820, + "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": 4183436, "tid": 31338, + "ts": 667115538758.207, "dur": 1.720, + "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": 4183436, "tid": 31338, "ts": 667115538758.207, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115538767.552, "dur": 402.805, + "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": 4183436, "tid": 31338, + "ts": 667115538769.066, "dur": 390.676, + "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": 4183436, "tid": 31338, "ts": 667115538769.066, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115538801.710, "dur": 8.946, + "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": 4183436, "tid": 31338, + "ts": 667115538807.131, "dur": 3.240, + "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": 4183436, "tid": 31338, + "ts": 667115538813.713, "dur": 5.719, + "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": 4183436, "tid": 31338, + "ts": 667115538815.588, "dur": 3.185, + "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": 4183436, "tid": 31338, + "ts": 667115538817.577, "dur": 0.994, + "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": 4183436, "tid": 31338, + "ts": 667115538823.093, "dur": 95.513, + "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": 4183436, "tid": 31338, + "ts": 667115538824.122, "dur": 6.706, + "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": 4183436, "tid": 31338, + "ts": 667115538826.451, "dur": 3.855, + "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": 4183436, "tid": 31338, + "ts": 667115538827.768, "dur": 2.472, + "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": 4183436, "tid": 31338, + "ts": 667115538832.020, "dur": 85.988, + "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": 4183436, "tid": 31338, + "ts": 667115538833.402, "dur": 83.899, + "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": 4183436, "tid": 31338, + "ts": 667115538922.315, "dur": 3.151, + "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": 4183436, "tid": 31338, + "ts": 667115538923.718, "dur": 1.600, + "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": 4183436, "tid": 31338, + "ts": 667115538958.846, "dur": 4.938, + "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": 4183436, "tid": 31338, + "ts": 667115538965.051, "dur": 1.747, + "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": 4183436, "tid": 31338, + "ts": 667115538968.152, "dur": 1.503, + "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": 4183436, "tid": 31338, + "ts": 667115538999.830, "dur": 2.334, + "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": 4183436, "tid": 31338, + "ts": 667115539000.797, "dur": 1.220, + "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": 4183436, "tid": 31338, + "ts": 667115539025.122, "dur": 115.641, + "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": 4183436, "tid": 31338, + "ts": 667115539030.366, "dur": 5.423, + "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": 4183436, "tid": 31338, + "ts": 667115539034.078, "dur": 1.023, + "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": 4183436, "tid": 31338, + "ts": 667115539037.442, "dur": 7.561, + "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": 4183436, "tid": 31338, + "ts": 667115539041.731, "dur": 2.651, + "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": 4183436, "tid": 31338, + "ts": 667115539046.439, "dur": 2.955, + "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": 4183436, "tid": 31338, + "ts": 667115539048.579, "dur": 0.464, + "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": 4183436, "tid": 31338, + "ts": 667115539050.696, "dur": 3.211, + "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": 4183436, "tid": 31338, + "ts": 667115539052.664, "dur": 0.741, + "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": 4183436, "tid": 31338, + "ts": 667115539057.728, "dur": 3.261, + "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": 4183436, "tid": 31338, + "ts": 667115539060.038, "dur": 0.658, + "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": 4183436, "tid": 31338, + "ts": 667115539061.954, "dur": 5.743, + "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": 4183436, "tid": 31338, + "ts": 667115539065.847, "dur": 1.624, + "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": 4183436, "tid": 31338, + "ts": 667115539068.820, "dur": 2.905, + "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": 4183436, "tid": 31338, + "ts": 667115539070.827, "dur": 0.591, + "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": 4183436, "tid": 31338, + "ts": 667115539074.613, "dur": 3.129, + "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": 4183436, "tid": 31338, + "ts": 667115539075.699, "dur": 1.943, + "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": 4183436, "tid": 31338, + "ts": 667115539079.273, "dur": 48.670, + "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": 4183436, "tid": 31338, + "ts": 667115539129.847, "dur": 2.619, + "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": 4183436, "tid": 31338, + "ts": 667115539133.631, "dur": 3.253, + "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": 4183436, "tid": 31338, + "ts": 667115539135.889, "dur": 0.531, + "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": 4183436, "tid": 31338, + "ts": 667115539138.924, "dur": 0.822, + "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": 4183436, "tid": 31338, + "ts": 667115539179.296, "dur": 8.657, + "args": { + "External id": 230874,"Record function id": 0, "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115539181.608, "dur": 5.488, + "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": 4183436, "tid": 31338, + "ts": 667115539183.131, "dur": 3.100, + "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": 4183436, "tid": 31338, + "ts": 667115539184.148, "dur": 1.867, + "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": 4183436, "tid": 31338, + "ts": 667115539191.914, "dur": 6.790, + "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": 4183436, "tid": 31338, + "ts": 667115539193.220, "dur": 3.624, + "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": 4183436, "tid": 31338, "ts": 667115539193.220, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115539194.781, "dur": 1.900, + "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": 4183436, "tid": 31338, + "ts": 667115539195.857, "dur": 0.689, + "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": 4183436, "tid": 31338, + "ts": 667115539202.381, "dur": 104.934, + "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": 4183436, "tid": 31338, + "ts": 667115539203.144, "dur": 98.035, + "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": 4183436, "tid": 31338, "ts": 667115539203.144, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115539206.837, "dur": 6.032, + "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": 4183436, "tid": 31338, + "ts": 667115539207.867, "dur": 4.446, + "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": 4183436, "tid": 31338, + "ts": 667115539211.638, "dur": 0.450, + "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": 4183436, "tid": 31338, + "ts": 667115539213.727, "dur": 33.744, + "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": 4183436, "tid": 31338, + "ts": 667115539248.699, "dur": 4.340, + "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": 4183436, "tid": 31338, + "ts": 667115539249.339, "dur": 3.124, + "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": 4183436, "tid": 31338, + "ts": 667115539251.172, "dur": 1.125, + "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": 4183436, "tid": 31338, + "ts": 667115539254.521, "dur": 5.612, + "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": 4183436, "tid": 31338, + "ts": 667115539257.579, "dur": 2.083, + "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": 4183436, "tid": 31338, + "ts": 667115539259.088, "dur": 0.493, + "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": 4183436, "tid": 31338, + "ts": 667115539260.835, "dur": 39.581, + "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": 4183436, "tid": 31338, + "ts": 667115539312.330, "dur": 6.105, + "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": 4183436, "tid": 31338, + "ts": 667115539313.236, "dur": 3.793, + "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": 4183436, "tid": 31338, "ts": 667115539313.236, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115539314.715, "dur": 2.164, + "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": 4183436, "tid": 31338, + "ts": 667115539315.719, "dur": 1.031, + "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": 4183436, "tid": 31338, + "ts": 667115539322.024, "dur": 8.624, + "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": 4183436, "tid": 31338, + "ts": 667115539322.946, "dur": 5.872, + "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": 4183436, "tid": 31338, "ts": 667115539322.946, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115539323.513, "dur": 5.084, + "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": 4183436, "tid": 31338, + "ts": 667115539325.772, "dur": 2.311, + "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": 4183436, "tid": 31338, + "ts": 667115539327.333, "dur": 0.652, + "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": 4183436, "tid": 31338, + "ts": 667115539334.537, "dur": 4.931, + "args": { + "External id": 230904,"Record function id": 0, "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115539336.216, "dur": 2.696, + "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": 4183436, "tid": 31338, + "ts": 667115539337.116, "dur": 1.553, + "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": 4183436, "tid": 31338, + "ts": 667115539337.742, "dur": 0.831, + "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": 4183436, "tid": 31338, + "ts": 667115539344.585, "dur": 5.369, + "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": 4183436, "tid": 31338, + "ts": 667115539345.754, "dur": 2.599, + "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": 4183436, "tid": 31338, "ts": 667115539345.754, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115539346.718, "dur": 1.488, + "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": 4183436, "tid": 31338, + "ts": 667115539347.320, "dur": 0.750, + "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": 4183436, "tid": 31338, + "ts": 667115539354.520, "dur": 184.402, + "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": 4183436, "tid": 31338, + "ts": 667115539425.650, "dur": 104.134, + "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": 4183436, "tid": 31338, "ts": 667115539425.650, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115539427.860, "dur": 3.829, + "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": 4183436, "tid": 31338, + "ts": 667115539428.557, "dur": 2.531, + "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": 4183436, "tid": 31338, + "ts": 667115539430.255, "dur": 0.697, + "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": 4183436, "tid": 31338, + "ts": 667115539432.168, "dur": 28.680, + "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": 4183436, "tid": 31338, + "ts": 667115539463.978, "dur": 4.049, + "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": 4183436, "tid": 31338, + "ts": 667115539464.476, "dur": 3.046, + "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": 4183436, "tid": 31338, + "ts": 667115539466.116, "dur": 1.266, + "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": 4183436, "tid": 31338, + "ts": 667115539469.018, "dur": 5.145, + "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": 4183436, "tid": 31338, + "ts": 667115539469.938, "dur": 3.726, + "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": 4183436, "tid": 31338, + "ts": 667115539471.281, "dur": 2.296, + "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": 4183436, "tid": 31338, + "ts": 667115539475.957, "dur": 52.579, + "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": 4183436, "tid": 31338, + "ts": 667115539546.129, "dur": 35.010, + "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": 4183436, "tid": 31338, + "ts": 667115539547.462, "dur": 4.782, + "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": 4183436, "tid": 31338, "ts": 667115539547.462, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115539549.185, "dur": 2.906, + "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": 4183436, "tid": 31338, + "ts": 667115539550.218, "dur": 1.737, + "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": 4183436, "tid": 31338, + "ts": 667115539555.496, "dur": 22.727, + "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": 4183436, "tid": 31338, + "ts": 667115539585.391, "dur": 9.272, + "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": 4183436, "tid": 31338, + "ts": 667115539586.424, "dur": 6.251, + "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": 4183436, "tid": 31338, "ts": 667115539586.424, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115539587.231, "dur": 5.224, + "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": 4183436, "tid": 31338, + "ts": 667115539587.917, "dur": 3.995, + "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": 4183436, "tid": 31338, + "ts": 667115539591.303, "dur": 0.506, + "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": 4183436, "tid": 31338, + "ts": 667115539598.733, "dur": 5.183, + "args": { + "External id": 230935,"Record function id": 0, "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115539600.227, "dur": 3.156, + "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": 4183436, "tid": 31338, + "ts": 667115539601.147, "dur": 1.926, + "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": 4183436, "tid": 31338, + "ts": 667115539601.609, "dur": 1.374, + "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": 4183436, "tid": 31338, + "ts": 667115539608.016, "dur": 455.407, + "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": 4183436, "tid": 31338, + "ts": 667115539609.819, "dur": 420.920, + "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": 4183436, "tid": 31338, "ts": 667115539609.819, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 31338, + "ts": 667115539635.077, "dur": 73.087, + "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": 4183436, "tid": 31338, + "ts": 667115539636.498, "dur": 71.403, + "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": 4183436, "tid": 31338, + "ts": 667115539639.590, "dur": 6.124, + "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": 4183436, "tid": 31338, + "ts": 667115539642.303, "dur": 2.774, + "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": 4183436, "tid": 31338, + "ts": 667115539646.974, "dur": 60.013, + "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": 4183436, "tid": 31338, + "ts": 667115539721.523, "dur": 2.834, + "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": 4183436, "tid": 31338, + "ts": 667115539722.433, "dur": 1.784, + "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": 4183436, "tid": 31338, + "ts": 667115539730.390, "dur": 3.720, + "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": 4183436, "tid": 31338, + "ts": 667115539731.192, "dur": 2.824, + "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": 4183436, "tid": 31338, + "ts": 667115539746.173, "dur": 2.808, + "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": 4183436, "tid": 31338, + "ts": 667115539759.632, "dur": 2.866, + "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": 4183436, "tid": 31338, + "ts": 667115539918.080, "dur": 2.627, + "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": 4183436, "tid": 31338, + "ts": 667115539925.261, "dur": 39.365, + "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": 4183436, "tid": 31338, + "ts": 667115539933.715, "dur": 0.988, + "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": 4183436, "tid": 31338, + "ts": 667115539970.400, "dur": 28.811, + "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": 4183436, "tid": 31338, + "ts": 667115539972.088, "dur": 26.911, + "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": 4183436, "tid": 31338, + "ts": 667115539976.445, "dur": 4.127, + "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": 4183436, "tid": 31338, + "ts": 667115539981.772, "dur": 16.678, + "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": 4183436, "tid": 31338, + "ts": 667115540003.525, "dur": 2.801, + "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": 4183436, "tid": 31338, + "ts": 667115540004.832, "dur": 1.383, + "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": 4183436, "tid": 31338, + "ts": 667115540014.399, "dur": 2.513, + "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": 4183436, "tid": 31338, + "ts": 667115540015.720, "dur": 1.061, + "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": 4183436, "tid": 31338, + "ts": 667115540019.105, "dur": 3.342, + "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": 4183436, "tid": 31338, + "ts": 667115540019.910, "dur": 2.446, + "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": 4183436, "tid": 31338, + "ts": 667115540045.102, "dur": 16.492, + "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": 4183436, "tid": 31338, + "ts": 667115540076.294, "dur": 10.016, + "args": { + "External id": 230966,"Record function id": 0, "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115540078.546, "dur": 7.074, + "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": 4183436, "tid": 31338, + "ts": 667115540080.427, "dur": 4.253, + "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": 4183436, "tid": 31338, + "ts": 667115540082.829, "dur": 1.728, + "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": 4183436, "tid": 31338, + "ts": 667115540090.260, "dur": 7.490, + "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": 4183436, "tid": 31338, + "ts": 667115540091.566, "dur": 3.698, + "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": 4183436, "tid": 31338, "ts": 667115540091.566, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115540092.960, "dur": 2.081, + "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": 4183436, "tid": 31338, + "ts": 667115540093.697, "dur": 1.179, + "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": 4183436, "tid": 31338, + "ts": 667115540101.328, "dur": 138.754, + "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": 4183436, "tid": 31338, + "ts": 667115540102.063, "dur": 130.996, + "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": 4183436, "tid": 31338, "ts": 667115540102.063, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115540104.881, "dur": 6.590, + "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": 4183436, "tid": 31338, + "ts": 667115540106.340, "dur": 4.527, + "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": 4183436, "tid": 31338, + "ts": 667115540109.785, "dur": 0.867, + "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": 4183436, "tid": 31338, + "ts": 667115540112.516, "dur": 72.084, + "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": 4183436, "tid": 31338, + "ts": 667115540185.760, "dur": 4.871, + "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": 4183436, "tid": 31338, + "ts": 667115540186.391, "dur": 3.625, + "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": 4183436, "tid": 31338, + "ts": 667115540188.121, "dur": 1.757, + "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": 4183436, "tid": 31338, + "ts": 667115540192.160, "dur": 5.311, + "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": 4183436, "tid": 31338, + "ts": 667115540195.169, "dur": 1.861, + "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": 4183436, "tid": 31338, + "ts": 667115540196.671, "dur": 0.291, + "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": 4183436, "tid": 31338, + "ts": 667115540198.268, "dur": 34.033, + "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": 4183436, "tid": 31338, + "ts": 667115540245.061, "dur": 8.701, + "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": 4183436, "tid": 31338, + "ts": 667115540245.971, "dur": 5.938, + "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": 4183436, "tid": 31338, "ts": 667115540245.971, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115540247.681, "dur": 4.077, + "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": 4183436, "tid": 31338, + "ts": 667115540248.839, "dur": 2.789, + "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": 4183436, "tid": 31338, + "ts": 667115540257.054, "dur": 8.918, + "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": 4183436, "tid": 31338, + "ts": 667115540258.161, "dur": 6.164, + "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": 4183436, "tid": 31338, "ts": 667115540258.161, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115540259.102, "dur": 5.033, + "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": 4183436, "tid": 31338, + "ts": 667115540261.759, "dur": 1.903, + "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": 4183436, "tid": 31338, + "ts": 667115540263.020, "dur": 0.510, + "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": 4183436, "tid": 31338, + "ts": 667115540269.993, "dur": 5.550, + "args": { + "External id": 230996,"Record function id": 0, "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115540271.781, "dur": 3.237, + "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": 4183436, "tid": 31338, + "ts": 667115540272.865, "dur": 1.890, + "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": 4183436, "tid": 31338, + "ts": 667115540273.566, "dur": 1.090, + "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": 4183436, "tid": 31338, + "ts": 667115540280.716, "dur": 6.147, + "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": 4183436, "tid": 31338, + "ts": 667115540281.494, "dur": 3.574, + "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": 4183436, "tid": 31338, "ts": 667115540281.494, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115540282.698, "dur": 2.234, + "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": 4183436, "tid": 31338, + "ts": 667115540283.636, "dur": 1.143, + "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": 4183436, "tid": 31338, + "ts": 667115540290.993, "dur": 318.751, + "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": 4183436, "tid": 31338, + "ts": 667115540292.464, "dur": 300.615, + "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": 4183436, "tid": 31338, "ts": 667115540292.464, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 31338, + "ts": 667115540306.651, "dur": 7.672, + "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": 4183436, "tid": 31338, + "ts": 667115540310.239, "dur": 3.704, + "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": 4183436, "tid": 31338, + "ts": 667115540316.210, "dur": 4.277, + "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": 4183436, "tid": 31338, + "ts": 667115540317.704, "dur": 2.590, + "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": 4183436, "tid": 31338, + "ts": 667115540328.983, "dur": 5.019, + "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": 4183436, "tid": 31338, + "ts": 667115540332.281, "dur": 1.527, + "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": 4183436, "tid": 31338, + "ts": 667115540360.314, "dur": 205.922, + "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": 4183436, "tid": 31338, + "ts": 667115540433.745, "dur": 4.211, + "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": 4183436, "tid": 31338, + "ts": 667115540439.767, "dur": 4.160, + "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": 4183436, "tid": 31338, + "ts": 667115540579.726, "dur": 4.294, + "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": 4183436, "tid": 31338, + "ts": 667115540586.866, "dur": 0.757, + "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": 4183436, "tid": 31338, + "ts": 667115540589.617, "dur": 0.689, + "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": 4183436, "tid": 31338, + "ts": 667115540619.460, "dur": 270.648, + "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": 4183436, "tid": 31338, + "ts": 667115540621.315, "dur": 260.861, + "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": 4183436, "tid": 31338, "ts": 667115540621.315, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 667115540641.582, "dur": 84.762, + "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": 4183436, "tid": 31338, + "ts": 667115540645.000, "dur": 3.300, + "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": 4183436, "tid": 31338, + "ts": 667115540649.652, "dur": 75.327, + "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": 4183436, "tid": 31338, + "ts": 667115540738.451, "dur": 7.472, + "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": 4183436, "tid": 31338, + "ts": 667115540741.323, "dur": 4.268, + "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": 4183436, "tid": 31338, + "ts": 667115540899.162, "dur": 169.335, + "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": 4183436, "tid": 31338, + "ts": 667115540901.251, "dur": 160.328, + "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": 4183436, "tid": 31338, "ts": 667115540901.251, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 667115540913.177, "dur": 53.075, + "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": 4183436, "tid": 31338, + "ts": 667115540916.035, "dur": 2.819, + "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": 4183436, "tid": 31338, + "ts": 667115540936.437, "dur": 29.160, + "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": 4183436, "tid": 31338, + "ts": 667115540974.365, "dur": 4.301, + "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": 4183436, "tid": 31338, + "ts": 667115540976.412, "dur": 1.977, + "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": 4183436, "tid": 31338, + "ts": 667115541074.828, "dur": 15.180, + "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": 4183436, "tid": 31338, + "ts": 667115541076.213, "dur": 11.607, + "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": 4183436, "tid": 31338, "ts": 667115541076.213, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115541078.855, "dur": 8.615, + "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": 4183436, "tid": 31338, + "ts": 667115541080.630, "dur": 6.595, + "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": 4183436, "tid": 31338, + "ts": 667115541093.380, "dur": 8.175, + "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": 4183436, "tid": 31338, + "ts": 667115541096.126, "dur": 3.429, + "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": 4183436, "tid": 31338, "ts": 667115541096.126, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115541097.540, "dur": 1.853, + "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": 4183436, "tid": 31338, + "ts": 667115541098.400, "dur": 0.842, + "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": 4183436, "tid": 31338, + "ts": 667115541104.765, "dur": 6.931, + "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": 4183436, "tid": 31338, + "ts": 667115541105.793, "dur": 3.905, + "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": 4183436, "tid": 31338, "ts": 667115541105.793, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115541107.422, "dur": 2.125, + "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": 4183436, "tid": 31338, + "ts": 667115541108.480, "dur": 0.972, + "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": 4183436, "tid": 31338, + "ts": 667115541115.241, "dur": 8.818, + "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": 4183436, "tid": 31338, + "ts": 667115541116.652, "dur": 5.586, + "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": 4183436, "tid": 31338, "ts": 667115541116.652, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115541117.826, "dur": 4.257, + "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": 4183436, "tid": 31338, + "ts": 667115541121.065, "dur": 0.926, + "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": 4183436, "tid": 31338, + "ts": 667115541127.458, "dur": 155.998, + "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": 4183436, "tid": 31338, + "ts": 667115541128.698, "dur": 146.852, + "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": 4183436, "tid": 31338, "ts": 667115541128.698, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115541132.101, "dur": 7.038, + "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": 4183436, "tid": 31338, + "ts": 667115541134.276, "dur": 4.230, + "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": 4183436, "tid": 31338, + "ts": 667115541136.948, "dur": 1.286, + "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": 4183436, "tid": 31338, + "ts": 667115541140.812, "dur": 80.375, + "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": 4183436, "tid": 31338, + "ts": 667115541223.841, "dur": 4.793, + "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": 4183436, "tid": 31338, + "ts": 667115541224.482, "dur": 3.530, + "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": 4183436, "tid": 31338, + "ts": 667115541226.647, "dur": 1.187, + "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": 4183436, "tid": 31338, + "ts": 667115541230.236, "dur": 3.478, + "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": 4183436, "tid": 31338, + "ts": 667115541231.283, "dur": 1.948, + "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": 4183436, "tid": 31338, + "ts": 667115541232.766, "dur": 0.354, + "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": 4183436, "tid": 31338, + "ts": 667115541236.707, "dur": 38.130, + "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": 4183436, "tid": 31338, + "ts": 667115541290.072, "dur": 6.739, + "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": 4183436, "tid": 31338, + "ts": 667115541291.019, "dur": 4.368, + "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": 4183436, "tid": 31338, "ts": 667115541291.019, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115541292.560, "dur": 2.678, + "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": 4183436, "tid": 31338, + "ts": 667115541294.079, "dur": 1.045, + "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": 4183436, "tid": 31338, + "ts": 667115541300.187, "dur": 8.873, + "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": 4183436, "tid": 31338, + "ts": 667115541301.026, "dur": 6.298, + "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": 4183436, "tid": 31338, "ts": 667115541301.026, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115541301.913, "dur": 5.214, + "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": 4183436, "tid": 31338, + "ts": 667115541302.341, "dur": 4.236, + "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": 4183436, "tid": 31338, + "ts": 667115541306.019, "dur": 0.442, + "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": 4183436, "tid": 31338, + "ts": 667115541314.814, "dur": 9.736, + "args": { + "External id": 231070,"Record function id": 0, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115541316.791, "dur": 6.981, + "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": 4183436, "tid": 31338, + "ts": 667115541319.370, "dur": 3.990, + "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": 4183436, "tid": 31338, + "ts": 667115541320.600, "dur": 2.643, + "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": 4183436, "tid": 31338, + "ts": 667115541327.901, "dur": 6.625, + "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": 4183436, "tid": 31338, + "ts": 667115541329.253, "dur": 2.976, + "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": 4183436, "tid": 31338, "ts": 667115541329.253, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115541330.365, "dur": 1.693, + "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": 4183436, "tid": 31338, + "ts": 667115541331.157, "dur": 0.810, + "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": 4183436, "tid": 31338, + "ts": 667115541337.835, "dur": 94.136, + "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": 4183436, "tid": 31338, + "ts": 667115541338.629, "dur": 87.542, + "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": 4183436, "tid": 31338, "ts": 667115541338.629, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115541342.838, "dur": 3.041, + "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": 4183436, "tid": 31338, + "ts": 667115541343.280, "dur": 2.142, + "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": 4183436, "tid": 31338, + "ts": 667115541344.688, "dur": 0.573, + "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": 4183436, "tid": 31338, + "ts": 667115541346.485, "dur": 33.550, + "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": 4183436, "tid": 31338, + "ts": 667115541381.054, "dur": 3.834, + "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": 4183436, "tid": 31338, + "ts": 667115541381.802, "dur": 2.573, + "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": 4183436, "tid": 31338, + "ts": 667115541383.660, "dur": 0.619, + "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": 4183436, "tid": 31338, + "ts": 667115541387.845, "dur": 6.027, + "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": 4183436, "tid": 31338, + "ts": 667115541389.351, "dur": 4.014, + "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": 4183436, "tid": 31338, + "ts": 667115541391.106, "dur": 2.194, + "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": 4183436, "tid": 31338, + "ts": 667115541394.316, "dur": 31.127, + "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": 4183436, "tid": 31338, + "ts": 667115541436.424, "dur": 33.522, + "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": 4183436, "tid": 31338, + "ts": 667115541437.544, "dur": 5.261, + "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": 4183436, "tid": 31338, "ts": 667115541437.544, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115541438.951, "dur": 3.713, + "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": 4183436, "tid": 31338, + "ts": 667115541441.564, "dur": 1.000, + "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": 4183436, "tid": 31338, + "ts": 667115541445.729, "dur": 21.842, + "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": 4183436, "tid": 31338, + "ts": 667115541473.793, "dur": 7.555, + "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": 4183436, "tid": 31338, + "ts": 667115541474.752, "dur": 4.687, + "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": 4183436, "tid": 31338, "ts": 667115541474.752, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115541475.429, "dur": 3.833, + "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": 4183436, "tid": 31338, + "ts": 667115541476.309, "dur": 2.446, + "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": 4183436, "tid": 31338, + "ts": 667115541478.142, "dur": 0.486, + "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": 4183436, "tid": 31338, + "ts": 667115541485.311, "dur": 29.490, + "args": { + "External id": 231101,"Record function id": 0, "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115541486.722, "dur": 26.885, + "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": 4183436, "tid": 31338, + "ts": 667115541487.948, "dur": 25.093, + "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": 4183436, "tid": 31338, + "ts": 667115541490.198, "dur": 22.388, + "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": 4183436, "tid": 31338, + "ts": 667115541520.121, "dur": 18.666, + "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": 4183436, "tid": 31338, + "ts": 667115541521.633, "dur": 14.897, + "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": 4183436, "tid": 31338, "ts": 667115541521.633, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115541522.934, "dur": 13.395, + "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": 4183436, "tid": 31338, + "ts": 667115541534.526, "dur": 1.631, + "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": 4183436, "tid": 31338, + "ts": 667115541542.192, "dur": 105.709, + "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": 4183436, "tid": 31338, + "ts": 667115541543.021, "dur": 96.278, + "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": 4183436, "tid": 31338, "ts": 667115541543.021, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115541546.873, "dur": 3.899, + "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": 4183436, "tid": 31338, + "ts": 667115541547.750, "dur": 2.513, + "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": 4183436, "tid": 31338, + "ts": 667115541549.576, "dur": 0.571, + "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": 4183436, "tid": 31338, + "ts": 667115541551.398, "dur": 41.998, + "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": 4183436, "tid": 31338, + "ts": 667115541594.636, "dur": 6.801, + "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": 4183436, "tid": 31338, + "ts": 667115541595.108, "dur": 5.740, + "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": 4183436, "tid": 31338, + "ts": 667115541599.059, "dur": 1.662, + "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": 4183436, "tid": 31338, + "ts": 667115541602.511, "dur": 3.539, + "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": 4183436, "tid": 31338, + "ts": 667115541603.586, "dur": 2.105, + "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": 4183436, "tid": 31338, + "ts": 667115541605.041, "dur": 0.569, + "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": 4183436, "tid": 31338, + "ts": 667115541606.571, "dur": 32.050, + "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": 4183436, "tid": 31338, + "ts": 667115541652.751, "dur": 67.206, + "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": 4183436, "tid": 31338, + "ts": 667115541653.681, "dur": 40.309, + "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": 4183436, "tid": 31338, "ts": 667115541653.681, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115541688.113, "dur": 5.693, + "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": 4183436, "tid": 31338, + "ts": 667115541691.440, "dur": 2.106, + "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": 4183436, "tid": 31338, + "ts": 667115541697.630, "dur": 19.406, + "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": 4183436, "tid": 31338, + "ts": 667115541725.356, "dur": 8.341, + "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": 4183436, "tid": 31338, + "ts": 667115541726.366, "dur": 5.320, + "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": 4183436, "tid": 31338, "ts": 667115541726.366, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115541727.390, "dur": 4.098, + "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": 4183436, "tid": 31338, + "ts": 667115541728.338, "dur": 2.543, + "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": 4183436, "tid": 31338, + "ts": 667115541730.144, "dur": 0.638, + "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": 4183436, "tid": 31338, + "ts": 667115541738.111, "dur": 6.476, + "args": { + "External id": 231132,"Record function id": 0, "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115541740.013, "dur": 4.006, + "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": 4183436, "tid": 31338, + "ts": 667115541741.177, "dur": 2.548, + "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": 4183436, "tid": 31338, + "ts": 667115541742.057, "dur": 1.578, + "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": 4183436, "tid": 31338, + "ts": 667115541750.793, "dur": 354.650, + "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": 4183436, "tid": 31338, + "ts": 667115541752.352, "dur": 323.046, + "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": 4183436, "tid": 31338, "ts": 667115541752.352, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115541789.250, "dur": 2.035, + "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": 4183436, "tid": 31338, + "ts": 667115541790.195, "dur": 0.980, + "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": 4183436, "tid": 31338, + "ts": 667115541805.960, "dur": 5.567, + "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": 4183436, "tid": 31338, + "ts": 667115541820.759, "dur": 3.381, + "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": 4183436, "tid": 31338, + "ts": 667115541974.788, "dur": 1.838, + "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": 4183436, "tid": 31338, + "ts": 667115541981.343, "dur": 34.152, + "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": 4183436, "tid": 31338, + "ts": 667115541990.616, "dur": 0.827, + "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": 4183436, "tid": 31338, + "ts": 667115542020.969, "dur": 31.262, + "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": 4183436, "tid": 31338, + "ts": 667115542024.606, "dur": 27.416, + "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": 4183436, "tid": 31338, + "ts": 667115542028.902, "dur": 4.236, + "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": 4183436, "tid": 31338, + "ts": 667115542034.463, "dur": 17.115, + "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": 4183436, "tid": 31338, + "ts": 667115542056.646, "dur": 2.471, + "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": 4183436, "tid": 31338, + "ts": 667115542057.895, "dur": 1.107, + "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": 4183436, "tid": 31338, + "ts": 667115542065.259, "dur": 3.770, + "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": 4183436, "tid": 31338, + "ts": 667115542068.162, "dur": 0.776, + "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": 4183436, "tid": 31338, + "ts": 667115542084.708, "dur": 16.764, + "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": 4183436, "tid": 31338, + "ts": 667115542114.275, "dur": 7.078, + "args": { + "External id": 231154,"Record function id": 0, "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115542116.306, "dur": 4.386, + "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": 4183436, "tid": 31338, + "ts": 667115542117.633, "dur": 2.100, + "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": 4183436, "tid": 31338, + "ts": 667115542118.278, "dur": 1.315, + "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": 4183436, "tid": 31338, + "ts": 667115542125.498, "dur": 5.432, + "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": 4183436, "tid": 31338, + "ts": 667115542126.769, "dur": 1.230, + "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": 4183436, "tid": 31338, "ts": 667115542126.769, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115542134.939, "dur": 394.785, + "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": 4183436, "tid": 31338, + "ts": 667115542136.233, "dur": 381.508, + "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": 4183436, "tid": 31338, "ts": 667115542136.233, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115542164.851, "dur": 8.052, + "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": 4183436, "tid": 31338, + "ts": 667115542170.004, "dur": 2.668, + "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": 4183436, "tid": 31338, + "ts": 667115542175.824, "dur": 4.671, + "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": 4183436, "tid": 31338, + "ts": 667115542177.286, "dur": 2.584, + "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": 4183436, "tid": 31338, + "ts": 667115542178.923, "dur": 0.767, + "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": 4183436, "tid": 31338, + "ts": 667115542184.111, "dur": 83.825, + "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": 4183436, "tid": 31338, + "ts": 667115542186.699, "dur": 5.464, + "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": 4183436, "tid": 31338, + "ts": 667115542187.262, "dur": 4.441, + "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": 4183436, "tid": 31338, + "ts": 667115542188.780, "dur": 2.815, + "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": 4183436, "tid": 31338, + "ts": 667115542193.315, "dur": 74.199, + "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": 4183436, "tid": 31338, + "ts": 667115542194.601, "dur": 72.176, + "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": 4183436, "tid": 31338, + "ts": 667115542271.203, "dur": 2.840, + "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": 4183436, "tid": 31338, + "ts": 667115542272.732, "dur": 1.178, + "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": 4183436, "tid": 31338, + "ts": 667115542306.015, "dur": 4.486, + "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": 4183436, "tid": 31338, + "ts": 667115542312.070, "dur": 2.194, + "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": 4183436, "tid": 31338, + "ts": 667115542315.480, "dur": 1.378, + "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": 4183436, "tid": 31338, + "ts": 667115542347.065, "dur": 2.280, + "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": 4183436, "tid": 31338, + "ts": 667115542347.986, "dur": 1.223, + "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": 4183436, "tid": 31338, + "ts": 667115542370.659, "dur": 107.068, + "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": 4183436, "tid": 31338, + "ts": 667115542375.714, "dur": 6.606, + "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": 4183436, "tid": 31338, + "ts": 667115542379.516, "dur": 2.055, + "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": 4183436, "tid": 31338, + "ts": 667115542384.162, "dur": 6.075, + "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": 4183436, "tid": 31338, + "ts": 667115542387.483, "dur": 1.870, + "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": 4183436, "tid": 31338, + "ts": 667115542391.571, "dur": 2.627, + "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": 4183436, "tid": 31338, + "ts": 667115542393.439, "dur": 0.376, + "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": 4183436, "tid": 31338, + "ts": 667115542395.127, "dur": 2.959, + "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": 4183436, "tid": 31338, + "ts": 667115542397.206, "dur": 0.474, + "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": 4183436, "tid": 31338, + "ts": 667115542402.078, "dur": 2.861, + "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": 4183436, "tid": 31338, + "ts": 667115542404.020, "dur": 0.600, + "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": 4183436, "tid": 31338, + "ts": 667115542406.096, "dur": 5.124, + "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": 4183436, "tid": 31338, + "ts": 667115542409.758, "dur": 1.302, + "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": 4183436, "tid": 31338, + "ts": 667115542413.907, "dur": 3.056, + "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": 4183436, "tid": 31338, + "ts": 667115542416.292, "dur": 0.342, + "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": 4183436, "tid": 31338, + "ts": 667115542418.182, "dur": 2.887, + "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": 4183436, "tid": 31338, + "ts": 667115542418.956, "dur": 2.011, + "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": 4183436, "tid": 31338, + "ts": 667115542422.233, "dur": 42.579, + "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": 4183436, "tid": 31338, + "ts": 667115542466.597, "dur": 2.995, + "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": 4183436, "tid": 31338, + "ts": 667115542470.687, "dur": 2.777, + "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": 4183436, "tid": 31338, + "ts": 667115542472.500, "dur": 0.551, + "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": 4183436, "tid": 31338, + "ts": 667115542475.880, "dur": 0.818, + "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": 4183436, "tid": 31338, + "ts": 667115542541.727, "dur": 9.472, + "args": { + "External id": 231202,"Record function id": 0, "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115542544.294, "dur": 6.149, + "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": 4183436, "tid": 31338, + "ts": 667115542546.386, "dur": 3.151, + "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": 4183436, "tid": 31338, + "ts": 667115542547.263, "dur": 2.182, + "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": 4183436, "tid": 31338, + "ts": 667115542555.401, "dur": 7.545, + "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": 4183436, "tid": 31338, + "ts": 667115542557.012, "dur": 4.112, + "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": 4183436, "tid": 31338, "ts": 667115542557.012, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115542558.809, "dur": 2.067, + "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": 4183436, "tid": 31338, + "ts": 667115542559.667, "dur": 1.061, + "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": 4183436, "tid": 31338, + "ts": 667115542566.338, "dur": 150.032, + "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": 4183436, "tid": 31338, + "ts": 667115542567.085, "dur": 141.107, + "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": 4183436, "tid": 31338, "ts": 667115542567.085, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115542571.909, "dur": 4.657, + "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": 4183436, "tid": 31338, + "ts": 667115542573.190, "dur": 2.800, + "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": 4183436, "tid": 31338, + "ts": 667115542575.285, "dur": 0.547, + "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": 4183436, "tid": 31338, + "ts": 667115542577.612, "dur": 39.415, + "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": 4183436, "tid": 31338, + "ts": 667115542617.936, "dur": 6.046, + "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": 4183436, "tid": 31338, + "ts": 667115542618.632, "dur": 4.743, + "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": 4183436, "tid": 31338, + "ts": 667115542621.945, "dur": 1.291, + "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": 4183436, "tid": 31338, + "ts": 667115542625.339, "dur": 3.775, + "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": 4183436, "tid": 31338, + "ts": 667115542626.343, "dur": 2.221, + "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": 4183436, "tid": 31338, + "ts": 667115542627.988, "dur": 0.507, + "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": 4183436, "tid": 31338, + "ts": 667115542629.561, "dur": 77.211, + "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": 4183436, "tid": 31338, + "ts": 667115542723.458, "dur": 9.526, + "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": 4183436, "tid": 31338, + "ts": 667115542724.616, "dur": 6.812, + "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": 4183436, "tid": 31338, "ts": 667115542724.616, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115542726.569, "dur": 4.680, + "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": 4183436, "tid": 31338, + "ts": 667115542729.234, "dur": 1.904, + "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": 4183436, "tid": 31338, + "ts": 667115542736.691, "dur": 7.446, + "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": 4183436, "tid": 31338, + "ts": 667115542737.387, "dur": 4.885, + "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": 4183436, "tid": 31338, "ts": 667115542737.387, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115542738.103, "dur": 3.979, + "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": 4183436, "tid": 31338, + "ts": 667115542739.150, "dur": 2.396, + "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": 4183436, "tid": 31338, + "ts": 667115542740.922, "dur": 0.502, + "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": 4183436, "tid": 31338, + "ts": 667115542748.552, "dur": 5.466, + "args": { + "External id": 231232,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115542749.949, "dur": 3.514, + "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": 4183436, "tid": 31338, + "ts": 667115542751.104, "dur": 2.103, + "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": 4183436, "tid": 31338, + "ts": 667115542751.821, "dur": 1.290, + "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": 4183436, "tid": 31338, + "ts": 667115542757.237, "dur": 7.130, + "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": 4183436, "tid": 31338, + "ts": 667115542758.652, "dur": 4.073, + "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": 4183436, "tid": 31338, "ts": 667115542758.652, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115542761.127, "dur": 1.458, + "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": 4183436, "tid": 31338, + "ts": 667115542761.820, "dur": 0.637, + "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": 4183436, "tid": 31338, + "ts": 667115542767.474, "dur": 89.268, + "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": 4183436, "tid": 31338, + "ts": 667115542768.174, "dur": 82.050, + "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": 4183436, "tid": 31338, "ts": 667115542768.174, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115542770.045, "dur": 3.961, + "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": 4183436, "tid": 31338, + "ts": 667115542770.483, "dur": 3.068, + "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": 4183436, "tid": 31338, + "ts": 667115542773.055, "dur": 0.366, + "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": 4183436, "tid": 31338, + "ts": 667115542774.635, "dur": 31.299, + "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": 4183436, "tid": 31338, + "ts": 667115542806.861, "dur": 3.656, + "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": 4183436, "tid": 31338, + "ts": 667115542807.449, "dur": 2.499, + "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": 4183436, "tid": 31338, + "ts": 667115542808.975, "dur": 0.820, + "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": 4183436, "tid": 31338, + "ts": 667115542811.522, "dur": 6.153, + "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": 4183436, "tid": 31338, + "ts": 667115542812.405, "dur": 4.845, + "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": 4183436, "tid": 31338, + "ts": 667115542815.247, "dur": 1.893, + "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": 4183436, "tid": 31338, + "ts": 667115542818.260, "dur": 31.382, + "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": 4183436, "tid": 31338, + "ts": 667115542862.828, "dur": 30.841, + "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": 4183436, "tid": 31338, + "ts": 667115542863.809, "dur": 3.872, + "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": 4183436, "tid": 31338, "ts": 667115542863.809, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115542865.331, "dur": 2.199, + "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": 4183436, "tid": 31338, + "ts": 667115542866.278, "dur": 1.146, + "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": 4183436, "tid": 31338, + "ts": 667115542870.702, "dur": 20.295, + "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": 4183436, "tid": 31338, + "ts": 667115542897.558, "dur": 8.111, + "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": 4183436, "tid": 31338, + "ts": 667115542898.403, "dur": 5.564, + "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": 4183436, "tid": 31338, "ts": 667115542898.403, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115542899.042, "dur": 4.713, + "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": 4183436, "tid": 31338, + "ts": 667115542899.919, "dur": 3.295, + "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": 4183436, "tid": 31338, + "ts": 667115542902.566, "dur": 0.508, + "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": 4183436, "tid": 31338, + "ts": 667115542909.554, "dur": 5.043, + "args": { + "External id": 231263,"Record function id": 0, "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115542911.319, "dur": 2.747, + "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": 4183436, "tid": 31338, + "ts": 667115542912.229, "dur": 1.549, + "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": 4183436, "tid": 31338, + "ts": 667115542912.695, "dur": 1.001, + "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": 4183436, "tid": 31338, + "ts": 667115542918.771, "dur": 409.307, + "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": 4183436, "tid": 31338, + "ts": 667115542935.288, "dur": 359.794, + "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": 4183436, "tid": 31338, "ts": 667115542935.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 31338, + "ts": 667115542960.636, "dur": 33.426, + "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": 4183436, "tid": 31338, + "ts": 667115542962.028, "dur": 31.804, + "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": 4183436, "tid": 31338, + "ts": 667115542964.970, "dur": 6.589, + "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": 4183436, "tid": 31338, + "ts": 667115542968.066, "dur": 3.019, + "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": 4183436, "tid": 31338, + "ts": 667115542972.836, "dur": 20.494, + "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": 4183436, "tid": 31338, + "ts": 667115543006.321, "dur": 2.268, + "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": 4183436, "tid": 31338, + "ts": 667115543007.147, "dur": 1.325, + "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": 4183436, "tid": 31338, + "ts": 667115543012.215, "dur": 3.660, + "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": 4183436, "tid": 31338, + "ts": 667115543013.215, "dur": 2.513, + "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": 4183436, "tid": 31338, + "ts": 667115543028.792, "dur": 2.678, + "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": 4183436, "tid": 31338, + "ts": 667115543042.030, "dur": 3.623, + "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": 4183436, "tid": 31338, + "ts": 667115543197.700, "dur": 2.588, + "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": 4183436, "tid": 31338, + "ts": 667115543205.008, "dur": 28.792, + "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": 4183436, "tid": 31338, + "ts": 667115543212.868, "dur": 0.725, + "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": 4183436, "tid": 31338, + "ts": 667115543238.991, "dur": 27.255, + "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": 4183436, "tid": 31338, + "ts": 667115543240.417, "dur": 25.566, + "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": 4183436, "tid": 31338, + "ts": 667115543244.649, "dur": 3.672, + "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": 4183436, "tid": 31338, + "ts": 667115543251.685, "dur": 13.730, + "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": 4183436, "tid": 31338, + "ts": 667115543270.289, "dur": 2.400, + "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": 4183436, "tid": 31338, + "ts": 667115543271.435, "dur": 1.149, + "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": 4183436, "tid": 31338, + "ts": 667115543278.635, "dur": 2.435, + "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": 4183436, "tid": 31338, + "ts": 667115543279.680, "dur": 1.261, + "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": 4183436, "tid": 31338, + "ts": 667115543283.466, "dur": 3.362, + "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": 4183436, "tid": 31338, + "ts": 667115543284.205, "dur": 2.528, + "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": 4183436, "tid": 31338, + "ts": 667115543309.506, "dur": 16.984, + "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": 4183436, "tid": 31338, + "ts": 667115543337.543, "dur": 8.022, + "args": { + "External id": 231294,"Record function id": 0, "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115543339.868, "dur": 5.044, + "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": 4183436, "tid": 31338, + "ts": 667115543341.464, "dur": 2.401, + "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": 4183436, "tid": 31338, + "ts": 667115543342.283, "dur": 1.483, + "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": 4183436, "tid": 31338, + "ts": 667115543349.259, "dur": 7.207, + "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": 4183436, "tid": 31338, + "ts": 667115543350.376, "dur": 3.790, + "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": 4183436, "tid": 31338, "ts": 667115543350.376, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115543351.827, "dur": 2.115, + "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": 4183436, "tid": 31338, + "ts": 667115543352.696, "dur": 1.054, + "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": 4183436, "tid": 31338, + "ts": 667115543361.893, "dur": 120.681, + "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": 4183436, "tid": 31338, + "ts": 667115543362.882, "dur": 113.960, + "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": 4183436, "tid": 31338, "ts": 667115543362.882, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115543365.252, "dur": 4.904, + "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": 4183436, "tid": 31338, + "ts": 667115543366.516, "dur": 3.065, + "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": 4183436, "tid": 31338, + "ts": 667115543368.725, "dur": 0.658, + "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": 4183436, "tid": 31338, + "ts": 667115543371.078, "dur": 58.686, + "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": 4183436, "tid": 31338, + "ts": 667115543431.019, "dur": 6.468, + "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": 4183436, "tid": 31338, + "ts": 667115543433.185, "dur": 3.697, + "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": 4183436, "tid": 31338, + "ts": 667115543434.880, "dur": 1.837, + "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": 4183436, "tid": 31338, + "ts": 667115543438.732, "dur": 3.971, + "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": 4183436, "tid": 31338, + "ts": 667115543440.031, "dur": 2.164, + "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": 4183436, "tid": 31338, + "ts": 667115543441.712, "dur": 0.364, + "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": 4183436, "tid": 31338, + "ts": 667115543443.334, "dur": 32.777, + "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": 4183436, "tid": 31338, + "ts": 667115543487.397, "dur": 33.617, + "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": 4183436, "tid": 31338, + "ts": 667115543488.215, "dur": 29.981, + "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": 4183436, "tid": 31338, "ts": 667115543488.215, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115543512.198, "dur": 5.797, + "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": 4183436, "tid": 31338, + "ts": 667115543513.815, "dur": 3.924, + "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": 4183436, "tid": 31338, + "ts": 667115543526.314, "dur": 7.845, + "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": 4183436, "tid": 31338, + "ts": 667115543527.181, "dur": 4.825, + "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": 4183436, "tid": 31338, "ts": 667115543527.181, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115543528.094, "dur": 3.693, + "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": 4183436, "tid": 31338, + "ts": 667115543528.944, "dur": 2.284, + "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": 4183436, "tid": 31338, + "ts": 667115543530.535, "dur": 0.560, + "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": 4183436, "tid": 31338, + "ts": 667115543538.299, "dur": 8.934, + "args": { + "External id": 231324,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115543540.273, "dur": 6.399, + "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": 4183436, "tid": 31338, + "ts": 667115543541.618, "dur": 4.718, + "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": 4183436, "tid": 31338, + "ts": 667115543544.871, "dur": 1.351, + "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": 4183436, "tid": 31338, + "ts": 667115543550.306, "dur": 5.720, + "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": 4183436, "tid": 31338, + "ts": 667115543551.102, "dur": 3.444, + "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": 4183436, "tid": 31338, "ts": 667115543551.102, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115543552.367, "dur": 2.033, + "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": 4183436, "tid": 31338, + "ts": 667115543553.163, "dur": 1.111, + "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": 4183436, "tid": 31338, + "ts": 667115543560.162, "dur": 317.283, + "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": 4183436, "tid": 31338, + "ts": 667115543561.802, "dur": 300.078, + "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": 4183436, "tid": 31338, "ts": 667115543561.802, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 31338, + "ts": 667115543576.078, "dur": 7.647, + "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": 4183436, "tid": 31338, + "ts": 667115543579.118, "dur": 4.133, + "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": 4183436, "tid": 31338, + "ts": 667115543585.679, "dur": 3.262, + "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": 4183436, "tid": 31338, + "ts": 667115543587.225, "dur": 1.526, + "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": 4183436, "tid": 31338, + "ts": 667115543590.301, "dur": 3.377, + "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": 4183436, "tid": 31338, + "ts": 667115543592.263, "dur": 1.235, + "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": 4183436, "tid": 31338, + "ts": 667115543616.609, "dur": 219.001, + "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": 4183436, "tid": 31338, + "ts": 667115543738.129, "dur": 5.910, + "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": 4183436, "tid": 31338, + "ts": 667115543746.148, "dur": 3.393, + "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": 4183436, "tid": 31338, + "ts": 667115543848.400, "dur": 4.070, + "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": 4183436, "tid": 31338, + "ts": 667115543855.393, "dur": 0.907, + "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": 4183436, "tid": 31338, + "ts": 667115543858.609, "dur": 0.488, + "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": 4183436, "tid": 31338, + "ts": 667115543887.290, "dur": 222.221, + "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": 4183436, "tid": 31338, + "ts": 667115543889.383, "dur": 213.716, + "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": 4183436, "tid": 31338, "ts": 667115543889.383, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 667115543908.424, "dur": 48.873, + "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": 4183436, "tid": 31338, + "ts": 667115543911.806, "dur": 3.648, + "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": 4183436, "tid": 31338, + "ts": 667115543916.984, "dur": 39.642, + "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": 4183436, "tid": 31338, + "ts": 667115543966.296, "dur": 4.620, + "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": 4183436, "tid": 31338, + "ts": 667115543968.487, "dur": 2.140, + "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": 4183436, "tid": 31338, + "ts": 667115544116.846, "dur": 142.949, + "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": 4183436, "tid": 31338, + "ts": 667115544118.928, "dur": 135.550, + "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": 4183436, "tid": 31338, "ts": 667115544118.928, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 667115544130.513, "dur": 32.017, + "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": 4183436, "tid": 31338, + "ts": 667115544132.939, "dur": 2.945, + "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": 4183436, "tid": 31338, + "ts": 667115544136.881, "dur": 25.140, + "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": 4183436, "tid": 31338, + "ts": 667115544169.186, "dur": 4.386, + "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": 4183436, "tid": 31338, + "ts": 667115544171.269, "dur": 2.002, + "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": 4183436, "tid": 31338, + "ts": 667115544265.753, "dur": 16.257, + "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": 4183436, "tid": 31338, + "ts": 667115544267.278, "dur": 12.617, + "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": 4183436, "tid": 31338, "ts": 667115544267.278, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115544271.925, "dur": 7.645, + "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": 4183436, "tid": 31338, + "ts": 667115544273.638, "dur": 5.703, + "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": 4183436, "tid": 31338, + "ts": 667115544285.560, "dur": 6.825, + "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": 4183436, "tid": 31338, + "ts": 667115544286.506, "dur": 4.199, + "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": 4183436, "tid": 31338, "ts": 667115544286.506, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115544288.176, "dur": 2.372, + "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": 4183436, "tid": 31338, + "ts": 667115544289.397, "dur": 1.009, + "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": 4183436, "tid": 31338, + "ts": 667115544295.417, "dur": 5.877, + "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": 4183436, "tid": 31338, + "ts": 667115544296.375, "dur": 3.043, + "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": 4183436, "tid": 31338, "ts": 667115544296.375, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115544297.399, "dur": 1.867, + "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": 4183436, "tid": 31338, + "ts": 667115544298.529, "dur": 0.617, + "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": 4183436, "tid": 31338, + "ts": 667115544304.771, "dur": 9.000, + "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": 4183436, "tid": 31338, + "ts": 667115544306.138, "dur": 5.434, + "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": 4183436, "tid": 31338, "ts": 667115544306.138, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115544309.374, "dur": 2.037, + "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": 4183436, "tid": 31338, + "ts": 667115544310.338, "dur": 0.982, + "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": 4183436, "tid": 31338, + "ts": 667115544317.140, "dur": 152.330, + "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": 4183436, "tid": 31338, + "ts": 667115544318.103, "dur": 145.118, + "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": 4183436, "tid": 31338, "ts": 667115544318.103, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115544321.246, "dur": 8.958, + "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": 4183436, "tid": 31338, + "ts": 667115544323.639, "dur": 5.838, + "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": 4183436, "tid": 31338, + "ts": 667115544327.674, "dur": 1.536, + "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": 4183436, "tid": 31338, + "ts": 667115544331.817, "dur": 79.013, + "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": 4183436, "tid": 31338, + "ts": 667115544412.547, "dur": 4.728, + "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": 4183436, "tid": 31338, + "ts": 667115544413.333, "dur": 3.367, + "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": 4183436, "tid": 31338, + "ts": 667115544415.273, "dur": 1.281, + "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": 4183436, "tid": 31338, + "ts": 667115544418.880, "dur": 4.890, + "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": 4183436, "tid": 31338, + "ts": 667115544419.910, "dur": 3.377, + "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": 4183436, "tid": 31338, + "ts": 667115544422.904, "dur": 0.297, + "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": 4183436, "tid": 31338, + "ts": 667115544424.503, "dur": 37.814, + "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": 4183436, "tid": 31338, + "ts": 667115544474.509, "dur": 6.845, + "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": 4183436, "tid": 31338, + "ts": 667115544475.459, "dur": 4.311, + "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": 4183436, "tid": 31338, "ts": 667115544475.459, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115544477.236, "dur": 2.378, + "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": 4183436, "tid": 31338, + "ts": 667115544478.370, "dur": 1.134, + "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": 4183436, "tid": 31338, + "ts": 667115544484.675, "dur": 32.731, + "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": 4183436, "tid": 31338, + "ts": 667115544485.548, "dur": 29.051, + "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": 4183436, "tid": 31338, "ts": 667115544485.548, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115544486.390, "dur": 27.956, + "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": 4183436, "tid": 31338, + "ts": 667115544488.704, "dur": 24.736, + "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": 4183436, "tid": 31338, + "ts": 667115544490.401, "dur": 22.546, + "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": 4183436, "tid": 31338, + "ts": 667115544525.450, "dur": 10.585, + "args": { + "External id": 231398,"Record function id": 0, "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115544527.807, "dur": 7.437, + "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": 4183436, "tid": 31338, + "ts": 667115544530.417, "dur": 4.387, + "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": 4183436, "tid": 31338, + "ts": 667115544531.860, "dur": 2.802, + "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": 4183436, "tid": 31338, + "ts": 667115544539.545, "dur": 6.748, + "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": 4183436, "tid": 31338, + "ts": 667115544541.000, "dur": 3.743, + "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": 4183436, "tid": 31338, "ts": 667115544541.000, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115544542.642, "dur": 1.964, + "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": 4183436, "tid": 31338, + "ts": 667115544543.387, "dur": 1.088, + "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": 4183436, "tid": 31338, + "ts": 667115544551.405, "dur": 98.411, + "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": 4183436, "tid": 31338, + "ts": 667115544552.220, "dur": 91.003, + "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": 4183436, "tid": 31338, "ts": 667115544552.220, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115544554.252, "dur": 3.297, + "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": 4183436, "tid": 31338, + "ts": 667115544555.001, "dur": 2.079, + "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": 4183436, "tid": 31338, + "ts": 667115544556.439, "dur": 0.500, + "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": 4183436, "tid": 31338, + "ts": 667115544558.378, "dur": 38.271, + "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": 4183436, "tid": 31338, + "ts": 667115544597.829, "dur": 5.617, + "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": 4183436, "tid": 31338, + "ts": 667115544598.584, "dur": 4.334, + "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": 4183436, "tid": 31338, + "ts": 667115544601.757, "dur": 1.038, + "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": 4183436, "tid": 31338, + "ts": 667115544604.624, "dur": 5.844, + "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": 4183436, "tid": 31338, + "ts": 667115544605.839, "dur": 4.177, + "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": 4183436, "tid": 31338, + "ts": 667115544607.553, "dur": 2.387, + "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": 4183436, "tid": 31338, + "ts": 667115544611.088, "dur": 31.501, + "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": 4183436, "tid": 31338, + "ts": 667115544694.623, "dur": 56.301, + "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": 4183436, "tid": 31338, + "ts": 667115544696.383, "dur": 20.821, + "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": 4183436, "tid": 31338, "ts": 667115544696.383, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115544699.936, "dur": 17.077, + "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": 4183436, "tid": 31338, + "ts": 667115544714.073, "dur": 2.600, + "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": 4183436, "tid": 31338, + "ts": 667115544721.044, "dur": 26.807, + "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": 4183436, "tid": 31338, + "ts": 667115544755.503, "dur": 60.882, + "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": 4183436, "tid": 31338, + "ts": 667115544806.722, "dur": 7.667, + "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": 4183436, "tid": 31338, "ts": 667115544806.722, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115544807.865, "dur": 6.296, + "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": 4183436, "tid": 31338, + "ts": 667115544808.746, "dur": 4.769, + "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": 4183436, "tid": 31338, + "ts": 667115544812.679, "dur": 0.695, + "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": 4183436, "tid": 31338, + "ts": 667115544821.033, "dur": 6.693, + "args": { + "External id": 231429,"Record function id": 0, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115544822.916, "dur": 4.228, + "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": 4183436, "tid": 31338, + "ts": 667115544824.284, "dur": 2.488, + "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": 4183436, "tid": 31338, + "ts": 667115544824.946, "dur": 1.700, + "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": 4183436, "tid": 31338, + "ts": 667115544831.182, "dur": 6.405, + "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": 4183436, "tid": 31338, + "ts": 667115544832.734, "dur": 2.700, + "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": 4183436, "tid": 31338, "ts": 667115544832.734, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115544833.674, "dur": 1.620, + "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": 4183436, "tid": 31338, + "ts": 667115544834.274, "dur": 0.927, + "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": 4183436, "tid": 31338, + "ts": 667115544840.781, "dur": 100.561, + "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": 4183436, "tid": 31338, + "ts": 667115544841.500, "dur": 91.865, + "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": 4183436, "tid": 31338, "ts": 667115544841.500, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115544844.880, "dur": 3.359, + "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": 4183436, "tid": 31338, + "ts": 667115544845.376, "dur": 2.391, + "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": 4183436, "tid": 31338, + "ts": 667115544846.947, "dur": 0.714, + "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": 4183436, "tid": 31338, + "ts": 667115544848.787, "dur": 43.144, + "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": 4183436, "tid": 31338, + "ts": 667115544893.178, "dur": 5.313, + "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": 4183436, "tid": 31338, + "ts": 667115544893.704, "dur": 4.281, + "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": 4183436, "tid": 31338, + "ts": 667115544897.051, "dur": 0.813, + "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": 4183436, "tid": 31338, + "ts": 667115544899.648, "dur": 2.624, + "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": 4183436, "tid": 31338, + "ts": 667115544900.287, "dur": 1.488, + "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": 4183436, "tid": 31338, + "ts": 667115544901.417, "dur": 0.290, + "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": 4183436, "tid": 31338, + "ts": 667115544902.759, "dur": 29.917, + "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": 4183436, "tid": 31338, + "ts": 667115544946.102, "dur": 23.930, + "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": 4183436, "tid": 31338, + "ts": 667115544946.846, "dur": 3.869, + "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": 4183436, "tid": 31338, "ts": 667115544946.846, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115544948.392, "dur": 2.159, + "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": 4183436, "tid": 31338, + "ts": 667115544949.295, "dur": 1.110, + "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": 4183436, "tid": 31338, + "ts": 667115544953.061, "dur": 14.673, + "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": 4183436, "tid": 31338, + "ts": 667115544973.853, "dur": 8.752, + "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": 4183436, "tid": 31338, + "ts": 667115544976.421, "dur": 4.039, + "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": 4183436, "tid": 31338, "ts": 667115544976.421, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 667115544977.116, "dur": 3.143, + "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": 4183436, "tid": 31338, + "ts": 667115544977.774, "dur": 1.942, + "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": 4183436, "tid": 31338, + "ts": 667115544979.173, "dur": 0.398, + "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": 4183436, "tid": 31338, + "ts": 667115544986.467, "dur": 4.866, + "args": { + "External id": 231460,"Record function id": 0, "Ev Idx": 1571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115544987.967, "dur": 2.800, + "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": 4183436, "tid": 31338, + "ts": 667115544988.770, "dur": 1.681, + "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": 4183436, "tid": 31338, + "ts": 667115544989.158, "dur": 1.178, + "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": 4183436, "tid": 31338, + "ts": 667115544995.900, "dur": 345.516, + "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": 4183436, "tid": 31338, + "ts": 667115544997.589, "dur": 313.132, + "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": 4183436, "tid": 31338, "ts": 667115544997.589, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 667115545032.031, "dur": 3.207, + "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": 4183436, "tid": 31338, + "ts": 667115545034.049, "dur": 1.033, + "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": 4183436, "tid": 31338, + "ts": 667115545049.393, "dur": 5.124, + "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": 4183436, "tid": 31338, + "ts": 667115545064.626, "dur": 3.329, + "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": 4183436, "tid": 31338, + "ts": 667115545214.357, "dur": 2.113, + "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": 4183436, "tid": 31338, + "ts": 667115545220.801, "dur": 32.958, + "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": 4183436, "tid": 31338, + "ts": 667115545230.339, "dur": 0.626, + "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": 4183436, "tid": 31338, + "ts": 667115545259.625, "dur": 29.650, + "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": 4183436, "tid": 31338, + "ts": 667115545263.088, "dur": 25.977, + "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": 4183436, "tid": 31338, + "ts": 667115545267.466, "dur": 3.945, + "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": 4183436, "tid": 31338, + "ts": 667115545272.976, "dur": 15.463, + "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": 4183436, "tid": 31338, + "ts": 667115545293.552, "dur": 2.707, + "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": 4183436, "tid": 31338, + "ts": 667115545294.891, "dur": 1.215, + "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": 4183436, "tid": 31338, + "ts": 667115545301.849, "dur": 2.295, + "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": 4183436, "tid": 31338, + "ts": 667115545303.076, "dur": 0.969, + "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": 4183436, "tid": 31338, + "ts": 667115545323.203, "dur": 13.921, + "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": 4183436, "tid": 31338, + "ts": 667115545349.874, "dur": 7.035, + "args": { + "External id": 231482,"Record function id": 0, "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115545351.830, "dur": 4.404, + "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": 4183436, "tid": 31338, + "ts": 667115545353.116, "dur": 2.202, + "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": 4183436, "tid": 31338, + "ts": 667115545353.891, "dur": 1.340, + "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": 4183436, "tid": 31338, + "ts": 667115545361.143, "dur": 2568.595, + "args": { + "External id": 231486,"Record function id": 0, "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 4183436, "tid": 31338, + "ts": 667115545389.384, "dur": 899.222, + "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": 4183436, "tid": 31338, + "ts": 667115545413.473, "dur": 866.361, + "args": { + "External id": 231488,"Record function id": 0, "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 4183436, "tid": 31338, + "ts": 667115545426.251, "dur": 838.569, + "args": { + "External id": 231489,"Record function id": 0, "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115545519.134, "dur": 8.414, + "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": 4183436, "tid": 31338, + "ts": 667115545543.496, "dur": 31.081, + "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": 4183436, "tid": 31338, + "ts": 667115545548.021, "dur": 1.380, + "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": 4183436, "tid": 31338, + "ts": 667115545551.434, "dur": 2.398, + "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": 4183436, "tid": 31338, + "ts": 667115545556.553, "dur": 0.297, + "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": 4183436, "tid": 31338, + "ts": 667115545558.407, "dur": 0.530, + "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": 4183436, "tid": 31338, + "ts": 667115545560.544, "dur": 0.381, + "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": 4183436, "tid": 31338, + "ts": 667115545563.906, "dur": 0.408, + "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": 4183436, "tid": 31338, + "ts": 667115545565.614, "dur": 0.501, + "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": 4183436, "tid": 31338, + "ts": 667115545567.473, "dur": 1.555, + "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": 4183436, "tid": 31338, + "ts": 667115545570.200, "dur": 0.521, + "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": 4183436, "tid": 31338, + "ts": 667115545601.676, "dur": 32.696, + "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": 4183436, "tid": 31338, + "ts": 667115545709.936, "dur": 111.539, + "args": { + "External id": 231502,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115545722.217, "dur": 6.577, + "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": 4183436, "tid": 31338, + "ts": 667115545733.988, "dur": 12.334, + "args": { + "External id": 231504,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115545740.037, "dur": 5.896, + "args": { + "External id": 231505,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115545743.666, "dur": 0.716, + "args": { + "External id": 231506,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115545753.932, "dur": 24.734, + "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": 4183436, "tid": 31338, + "ts": 667115545756.002, "dur": 0.423, + "args": { + "External id": 231508,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115545757.762, "dur": 1.631, + "args": { + "External id": 231509,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115545760.492, "dur": 0.538, + "args": { + "External id": 231510,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115545762.255, "dur": 0.421, + "args": { + "External id": 231511,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115545764.569, "dur": 0.282, + "args": { + "External id": 231512,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115545766.184, "dur": 0.409, + "args": { + "External id": 231513,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115545768.047, "dur": 2.121, + "args": { + "External id": 231514,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115545772.653, "dur": 0.462, + "args": { + "External id": 231515,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115545774.680, "dur": 0.510, + "args": { + "External id": 231516,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115545789.424, "dur": 23.873, + "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": 4183436, "tid": 31338, + "ts": 667115545880.835, "dur": 292.572, + "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": 4183436, "tid": 31338, + "ts": 667115545912.064, "dur": 256.874, + "args": { + "External id": 231519,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115545922.284, "dur": 241.498, + "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": 4183436, "tid": 31338, + "ts": 667115546193.678, "dur": 2.079, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115546296.064, "dur": 1612.896, + "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": 4183436, "tid": 31338, "ts": 667115546296.064, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115546413.369, "dur": 124.653, + "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": 4183436, "tid": 31338, + "ts": 667115546583.485, "dur": 36.769, + "args": { + "External id": 231524,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115546639.634, "dur": 85.060, + "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": 4183436, "tid": 31338, + "ts": 667115546739.412, "dur": 27.912, + "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": 4183436, "tid": 31338, + "ts": 667115546773.323, "dur": 32.381, + "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": 4183436, "tid": 31338, + "ts": 667115546813.864, "dur": 19.990, + "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": 4183436, "tid": 31338, + "ts": 667115546840.415, "dur": 28.541, + "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": 4183436, "tid": 31338, + "ts": 667115546897.045, "dur": 26.227, + "args": { + "External id": 231530,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115546943.799, "dur": 26.889, + "args": { + "External id": 231531,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115546989.641, "dur": 17.252, + "args": { + "External id": 231532,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115547021.664, "dur": 15.523, + "args": { + "External id": 231533,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115547048.098, "dur": 38.221, + "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": 4183436, "tid": 31338, + "ts": 667115547089.412, "dur": 30.364, + "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": 4183436, "tid": 31338, + "ts": 667115547147.094, "dur": 166.788, + "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": 4183436, "tid": 31338, + "ts": 667115547224.603, "dur": 5.314, + "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": 4183436, "tid": 31338, + "ts": 667115547231.747, "dur": 4.513, + "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": 4183436, "tid": 31338, + "ts": 667115547345.198, "dur": 25.097, + "args": { + "External id": 231539,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115547381.849, "dur": 13.573, + "args": { + "External id": 231540,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115547403.088, "dur": 43.417, + "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": 4183436, "tid": 31338, + "ts": 667115547452.288, "dur": 32.869, + "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": 4183436, "tid": 31338, + "ts": 667115547509.771, "dur": 32.661, + "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": 4183436, "tid": 31338, + "ts": 667115547550.481, "dur": 28.332, + "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": 4183436, "tid": 31338, + "ts": 667115547584.303, "dur": 26.377, + "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": 4183436, "tid": 31338, + "ts": 667115547617.258, "dur": 27.122, + "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": 4183436, "tid": 31338, + "ts": 667115547703.573, "dur": 27.164, + "args": { + "External id": 231547,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115547751.688, "dur": 28.227, + "args": { + "External id": 231548,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115547797.515, "dur": 16.281, + "args": { + "External id": 231549,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115547833.957, "dur": 13.247, + "args": { + "External id": 231550,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115547862.309, "dur": 14.233, + "args": { + "External id": 231551,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115547955.424, "dur": 14.550, + "args": { + "External id": 231552,"Record function id": 0, "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115547958.790, "dur": 10.400, + "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": 4183436, "tid": 31338, + "ts": 667115547962.791, "dur": 5.378, + "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": 4183436, "tid": 31338, + "ts": 667115547964.235, "dur": 3.847, + "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": 4183436, "tid": 31338, + "ts": 667115547973.832, "dur": 4.456, + "args": { + "External id": 231556,"Record function id": 0, "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115547975.151, "dur": 2.645, + "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": 4183436, "tid": 31338, + "ts": 667115547975.800, "dur": 1.466, + "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": 4183436, "tid": 31338, + "ts": 667115547976.244, "dur": 0.929, + "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": 4183436, "tid": 31338, + "ts": 667115547981.562, "dur": 4.099, + "args": { + "External id": 231560,"Record function id": 0, "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115547982.828, "dur": 2.431, + "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": 4183436, "tid": 31338, + "ts": 667115547983.579, "dur": 1.240, + "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": 4183436, "tid": 31338, + "ts": 667115547983.992, "dur": 0.738, + "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": 4183436, "tid": 31338, + "ts": 667115547988.863, "dur": 5.724, + "args": { + "External id": 231564,"Record function id": 0, "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115547990.068, "dur": 4.116, + "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": 4183436, "tid": 31338, + "ts": 667115547990.624, "dur": 3.138, + "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": 4183436, "tid": 31338, + "ts": 667115547991.140, "dur": 2.560, + "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": 4183436, "tid": 31338, + "ts": 667115547997.664, "dur": 6.383, + "args": { + "External id": 231568,"Record function id": 0, "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115547999.281, "dur": 4.343, + "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": 4183436, "tid": 31338, + "ts": 667115547999.767, "dur": 3.291, + "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": 4183436, "tid": 31338, + "ts": 667115548001.949, "dur": 0.992, + "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": 4183436, "tid": 31338, + "ts": 667115548007.175, "dur": 3.628, + "args": { + "External id": 231572,"Record function id": 0, "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115548008.352, "dur": 2.065, + "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": 4183436, "tid": 31338, + "ts": 667115548008.928, "dur": 1.036, + "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": 4183436, "tid": 31338, + "ts": 667115548009.236, "dur": 0.645, + "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": 4183436, "tid": 31338, + "ts": 667115548014.041, "dur": 3.491, + "args": { + "External id": 231576,"Record function id": 0, "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115548015.046, "dur": 2.086, + "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": 4183436, "tid": 31338, + "ts": 667115548015.729, "dur": 0.971, + "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": 4183436, "tid": 31338, + "ts": 667115548016.040, "dur": 0.586, + "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": 4183436, "tid": 31338, + "ts": 667115548020.700, "dur": 3.538, + "args": { + "External id": 231580,"Record function id": 0, "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115548021.764, "dur": 2.083, + "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": 4183436, "tid": 31338, + "ts": 667115548022.346, "dur": 1.032, + "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": 4183436, "tid": 31338, + "ts": 667115548022.666, "dur": 0.646, + "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": 4183436, "tid": 31338, + "ts": 667115548028.569, "dur": 4.836, + "args": { + "External id": 231584,"Record function id": 0, "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115548029.656, "dur": 3.335, + "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": 4183436, "tid": 31338, + "ts": 667115548030.243, "dur": 2.303, + "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": 4183436, "tid": 31338, + "ts": 667115548031.901, "dur": 0.558, + "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": 4183436, "tid": 31338, + "ts": 667115548037.807, "dur": 58445.263, + "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": 4183436, "tid": 31338, + "ts": 667115548039.192, "dur": 58435.548, + "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": 4183436, "tid": 31338, "ts": 667115548039.192, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 4183436, "tid": 31338, + "ts": 667115548072.828, "dur": 39.621, + "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": 4183436, "tid": 31338, + "ts": 667115548120.426, "dur": 70.304, + "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": 4183436, "tid": 31338, + "ts": 667115548196.662, "dur": 58270.433, + "args": { + "External id": 231592,"Record function id": 0, "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115548248.536, "dur": 7.294, + "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": 4183436, "tid": 31338, + "ts": 667115548265.156, "dur": 4.443, + "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": 4183436, "tid": 31338, + "ts": 667115548286.124, "dur": 57483.191, + "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": 4183436, "tid": 31338, + "ts": 667115548299.287, "dur": 57460.481, + "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": 4183436, "tid": 31338, + "ts": 667115548362.826, "dur": 6.098, + "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": 4183436, "tid": 31338, + "ts": 667115548374.040, "dur": 57346.595, + "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": 4183436, "tid": 31338, + "ts": 667115548376.597, "dur": 57343.169, + "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": 4183436, "tid": 31338, + "ts": 667115548380.490, "dur": 5.421, + "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": 4183436, "tid": 31338, + "ts": 667115548387.446, "dur": 57328.317, + "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": 4183436, "tid": 31338, + "ts": 667115605866.045, "dur": 10.958, + "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": 4183436, "tid": 31338, + "ts": 667115605869.342, "dur": 7.299, + "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": 4183436, "tid": 31338, + "ts": 667115605911.097, "dur": 263.347, + "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": 4183436, "tid": 31338, + "ts": 667115605942.102, "dur": 228.223, + "args": { + "External id": 231605,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115605954.122, "dur": 211.063, + "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": 4183436, "tid": 31338, + "ts": 667115606194.617, "dur": 2.354, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115606248.721, "dur": 6.026, + "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": 4183436, "tid": 31338, + "ts": 667115606304.592, "dur": 1.339, + "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": 4183436, "tid": 31338, + "ts": 667115606323.294, "dur": 1.305, + "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": 4183436, "tid": 31338, + "ts": 667115606339.152, "dur": 0.936, + "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": 4183436, "tid": 31338, + "ts": 667115606353.254, "dur": 0.769, + "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": 4183436, "tid": 31338, + "ts": 667115606365.216, "dur": 0.879, + "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": 4183436, "tid": 31338, + "ts": 667115606376.741, "dur": 0.778, + "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": 4183436, "tid": 31338, + "ts": 667115606392.919, "dur": 2.022, + "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": 4183436, "tid": 31338, + "ts": 667115606406.028, "dur": 0.616, + "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": 4183436, "tid": 31338, + "ts": 667115606517.345, "dur": 2720.892, + "args": { + "External id": 231617,"Record function id": 0, "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 4183436, "tid": 31338, + "ts": 667115606540.608, "dur": 1037.741, + "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": 4183436, "tid": 31338, + "ts": 667115606560.688, "dur": 365.319, + "args": { + "External id": 231619,"Record function id": 0, "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115606641.045, "dur": 4.349, + "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": 4183436, "tid": 31338, + "ts": 667115606648.560, "dur": 0.950, + "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": 4183436, "tid": 31338, + "ts": 667115606688.896, "dur": 1.544, + "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": 4183436, "tid": 31338, + "ts": 667115606693.864, "dur": 2.846, + "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": 4183436, "tid": 31338, + "ts": 667115606700.164, "dur": 1.057, + "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": 4183436, "tid": 31338, + "ts": 667115606702.936, "dur": 0.736, + "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": 4183436, "tid": 31338, + "ts": 667115606705.318, "dur": 1.726, + "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": 4183436, "tid": 31338, + "ts": 667115606708.643, "dur": 0.618, + "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": 4183436, "tid": 31338, + "ts": 667115606712.586, "dur": 0.762, + "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": 4183436, "tid": 31338, + "ts": 667115606714.871, "dur": 0.653, + "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": 4183436, "tid": 31338, + "ts": 667115606734.494, "dur": 159.493, + "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": 4183436, "tid": 31338, + "ts": 667115606750.823, "dur": 138.715, + "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": 4183436, "tid": 31338, + "ts": 667115606779.873, "dur": 12.445, + "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": 4183436, "tid": 31338, + "ts": 667115606795.130, "dur": 65.295, + "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": 4183436, "tid": 31338, + "ts": 667115606797.571, "dur": 62.556, + "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": 4183436, "tid": 31338, + "ts": 667115606801.516, "dur": 7.330, + "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": 4183436, "tid": 31338, + "ts": 667115606812.375, "dur": 47.081, + "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": 4183436, "tid": 31338, + "ts": 667115607009.113, "dur": 561.848, + "args": { + "External id": 231637,"Record function id": 0, "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 4183436, "tid": 31338, + "ts": 667115607026.498, "dur": 531.299, + "args": { + "External id": 231638,"Record function id": 0, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115607082.369, "dur": 4.438, + "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": 4183436, "tid": 31338, + "ts": 667115607102.552, "dur": 32.783, + "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": 4183436, "tid": 31338, + "ts": 667115607107.530, "dur": 2.878, + "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": 4183436, "tid": 31338, + "ts": 667115607112.463, "dur": 0.587, + "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": 4183436, "tid": 31338, + "ts": 667115607114.435, "dur": 0.417, + "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": 4183436, "tid": 31338, + "ts": 667115607117.761, "dur": 0.351, + "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": 4183436, "tid": 31338, + "ts": 667115607119.529, "dur": 0.418, + "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": 4183436, "tid": 31338, + "ts": 667115607121.199, "dur": 0.511, + "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": 4183436, "tid": 31338, + "ts": 667115607124.262, "dur": 2.668, + "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": 4183436, "tid": 31338, + "ts": 667115607128.321, "dur": 0.489, + "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": 4183436, "tid": 31338, + "ts": 667115607130.022, "dur": 1.559, + "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": 4183436, "tid": 31338, + "ts": 667115607148.187, "dur": 31.931, + "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": 4183436, "tid": 31338, + "ts": 667115607210.869, "dur": 96.176, + "args": { + "External id": 231651,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115607223.612, "dur": 3.623, + "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": 4183436, "tid": 31338, + "ts": 667115607232.081, "dur": 9.615, + "args": { + "External id": 231653,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115607236.393, "dur": 4.863, + "args": { + "External id": 231654,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115607239.621, "dur": 0.425, + "args": { + "External id": 231655,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115607248.097, "dur": 23.610, + "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": 4183436, "tid": 31338, + "ts": 667115607249.920, "dur": 0.382, + "args": { + "External id": 231657,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115607251.925, "dur": 1.243, + "args": { + "External id": 231658,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115607254.333, "dur": 0.329, + "args": { + "External id": 231659,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115607255.951, "dur": 2.334, + "args": { + "External id": 231660,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115607260.548, "dur": 0.387, + "args": { + "External id": 231661,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115607262.007, "dur": 0.468, + "args": { + "External id": 231662,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115607263.895, "dur": 0.395, + "args": { + "External id": 231663,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115607266.356, "dur": 0.483, + "args": { + "External id": 231664,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115607268.016, "dur": 0.378, + "args": { + "External id": 231665,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115607282.312, "dur": 17.787, + "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": 4183436, "tid": 31338, + "ts": 667115607350.690, "dur": 114.543, + "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": 4183436, "tid": 31338, + "ts": 667115607379.367, "dur": 82.637, + "args": { + "External id": 231668,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115607389.523, "dur": 68.009, + "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": 4183436, "tid": 31338, + "ts": 667115607482.919, "dur": 1.977, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115607585.759, "dur": 1632.975, + "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": 4183436, "tid": 31338, "ts": 667115607585.759, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115607735.631, "dur": 105.854, + "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": 4183436, "tid": 31338, + "ts": 667115607888.017, "dur": 41.449, + "args": { + "External id": 231673,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115607944.960, "dur": 44.721, + "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": 4183436, "tid": 31338, + "ts": 667115607998.585, "dur": 26.033, + "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": 4183436, "tid": 31338, + "ts": 667115608036.432, "dur": 33.850, + "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": 4183436, "tid": 31338, + "ts": 667115608076.695, "dur": 25.875, + "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": 4183436, "tid": 31338, + "ts": 667115608108.691, "dur": 27.846, + "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": 4183436, "tid": 31338, + "ts": 667115608164.504, "dur": 21.933, + "args": { + "External id": 231679,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115608209.151, "dur": 24.772, + "args": { + "External id": 231680,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115608254.103, "dur": 21.345, + "args": { + "External id": 231681,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115608289.571, "dur": 14.676, + "args": { + "External id": 231682,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115608311.858, "dur": 34.889, + "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": 4183436, "tid": 31338, + "ts": 667115608350.020, "dur": 29.013, + "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": 4183436, "tid": 31338, + "ts": 667115608410.079, "dur": 192.355, + "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": 4183436, "tid": 31338, + "ts": 667115608487.861, "dur": 28.849, + "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": 4183436, "tid": 31338, + "ts": 667115608519.938, "dur": 2.668, + "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": 4183436, "tid": 31338, + "ts": 667115608641.085, "dur": 62.371, + "args": { + "External id": 231688,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115608721.084, "dur": 13.828, + "args": { + "External id": 231689,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115608744.828, "dur": 54.721, + "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": 4183436, "tid": 31338, + "ts": 667115608805.491, "dur": 32.027, + "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": 4183436, "tid": 31338, + "ts": 667115608846.959, "dur": 27.061, + "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": 4183436, "tid": 31338, + "ts": 667115608878.297, "dur": 27.682, + "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": 4183436, "tid": 31338, + "ts": 667115608911.928, "dur": 26.689, + "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": 4183436, "tid": 31338, + "ts": 667115608957.952, "dur": 39.875, + "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": 4183436, "tid": 31338, + "ts": 667115609020.710, "dur": 24.649, + "args": { + "External id": 231696,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115609065.883, "dur": 25.078, + "args": { + "External id": 231697,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115609105.646, "dur": 21.142, + "args": { + "External id": 231698,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115609143.413, "dur": 14.634, + "args": { + "External id": 231699,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115609173.893, "dur": 15.385, + "args": { + "External id": 231700,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115609260.149, "dur": 14.625, + "args": { + "External id": 231701,"Record function id": 0, "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115609263.454, "dur": 10.415, + "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": 4183436, "tid": 31338, + "ts": 667115609267.403, "dur": 5.532, + "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": 4183436, "tid": 31338, + "ts": 667115609268.799, "dur": 4.043, + "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": 4183436, "tid": 31338, + "ts": 667115609278.623, "dur": 4.744, + "args": { + "External id": 231705,"Record function id": 0, "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115609280.264, "dur": 2.655, + "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": 4183436, "tid": 31338, + "ts": 667115609281.074, "dur": 1.319, + "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": 4183436, "tid": 31338, + "ts": 667115609281.482, "dur": 0.794, + "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": 4183436, "tid": 31338, + "ts": 667115609286.669, "dur": 6.267, + "args": { + "External id": 231709,"Record function id": 0, "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115609288.105, "dur": 4.383, + "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": 4183436, "tid": 31338, + "ts": 667115609288.706, "dur": 3.344, + "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": 4183436, "tid": 31338, + "ts": 667115609289.534, "dur": 2.407, + "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": 4183436, "tid": 31338, + "ts": 667115609296.099, "dur": 4.156, + "args": { + "External id": 231713,"Record function id": 0, "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115609297.487, "dur": 2.375, + "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": 4183436, "tid": 31338, + "ts": 667115609298.179, "dur": 1.238, + "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": 4183436, "tid": 31338, + "ts": 667115609298.484, "dur": 0.857, + "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": 4183436, "tid": 31338, + "ts": 667115609303.330, "dur": 3.687, + "args": { + "External id": 231717,"Record function id": 0, "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115609304.381, "dur": 2.250, + "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": 4183436, "tid": 31338, + "ts": 667115609305.019, "dur": 1.175, + "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": 4183436, "tid": 31338, + "ts": 667115609305.463, "dur": 0.656, + "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": 4183436, "tid": 31338, + "ts": 667115609310.132, "dur": 3.910, + "args": { + "External id": 231721,"Record function id": 0, "Ev Idx": 1832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115609311.370, "dur": 2.313, + "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": 4183436, "tid": 31338, + "ts": 667115609311.965, "dur": 1.284, + "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": 4183436, "tid": 31338, + "ts": 667115609312.405, "dur": 0.771, + "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": 4183436, "tid": 31338, + "ts": 667115609317.349, "dur": 3.488, + "args": { + "External id": 231725,"Record function id": 0, "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115609318.482, "dur": 1.962, + "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": 4183436, "tid": 31338, + "ts": 667115609318.962, "dur": 1.073, + "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": 4183436, "tid": 31338, + "ts": 667115609319.280, "dur": 0.679, + "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": 4183436, "tid": 31338, + "ts": 667115609323.881, "dur": 3.367, + "args": { + "External id": 231729,"Record function id": 0, "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115609324.943, "dur": 1.918, + "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": 4183436, "tid": 31338, + "ts": 667115609325.392, "dur": 1.040, + "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": 4183436, "tid": 31338, + "ts": 667115609325.700, "dur": 0.654, + "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": 4183436, "tid": 31338, + "ts": 667115609330.269, "dur": 5.363, + "args": { + "External id": 231733,"Record function id": 0, "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115609331.339, "dur": 3.929, + "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": 4183436, "tid": 31338, + "ts": 667115609331.872, "dur": 2.965, + "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": 4183436, "tid": 31338, + "ts": 667115609333.983, "dur": 0.780, + "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": 4183436, "tid": 31338, + "ts": 667115609339.488, "dur": 16504.136, + "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": 4183436, "tid": 31338, + "ts": 667115609341.022, "dur": 16493.898, + "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": 4183436, "tid": 31338, "ts": 667115609341.022, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 4183436, "tid": 31338, + "ts": 667115609369.350, "dur": 36.785, + "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": 4183436, "tid": 31338, + "ts": 667115609414.176, "dur": 61.083, + "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": 4183436, "tid": 31338, + "ts": 667115609481.452, "dur": 16345.095, + "args": { + "External id": 231741,"Record function id": 0, "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115609590.557, "dur": 6.855, + "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": 4183436, "tid": 31338, + "ts": 667115609608.126, "dur": 9.675, + "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": 4183436, "tid": 31338, + "ts": 667115609635.810, "dur": 15405.842, + "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": 4183436, "tid": 31338, + "ts": 667115609649.348, "dur": 15383.537, + "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": 4183436, "tid": 31338, + "ts": 667115609736.697, "dur": 15.509, + "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": 4183436, "tid": 31338, + "ts": 667115609757.243, "dur": 15240.663, + "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": 4183436, "tid": 31338, + "ts": 667115609759.760, "dur": 15237.503, + "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": 4183436, "tid": 31338, + "ts": 667115609765.580, "dur": 5.659, + "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": 4183436, "tid": 31338, + "ts": 667115609773.097, "dur": 15220.874, + "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": 4183436, "tid": 31338, + "ts": 667115625130.695, "dur": 9.615, + "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": 4183436, "tid": 31338, + "ts": 667115625133.781, "dur": 6.210, + "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": 4183436, "tid": 31338, + "ts": 667115625168.577, "dur": 305.798, + "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": 4183436, "tid": 31338, + "ts": 667115625199.757, "dur": 270.196, + "args": { + "External id": 231754,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115625211.457, "dur": 253.569, + "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": 4183436, "tid": 31338, + "ts": 667115625513.214, "dur": 3.114, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115625574.094, "dur": 5.987, + "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": 4183436, "tid": 31338, + "ts": 667115625625.161, "dur": 1.634, + "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": 4183436, "tid": 31338, + "ts": 667115625642.936, "dur": 2.884, + "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": 4183436, "tid": 31338, + "ts": 667115625696.931, "dur": 1.585, + "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": 4183436, "tid": 31338, + "ts": 667115625712.013, "dur": 0.741, + "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": 4183436, "tid": 31338, + "ts": 667115625723.175, "dur": 0.756, + "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": 4183436, "tid": 31338, + "ts": 667115625735.142, "dur": 2.311, + "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": 4183436, "tid": 31338, + "ts": 667115625749.556, "dur": 2.148, + "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": 4183436, "tid": 31338, + "ts": 667115625763.196, "dur": 0.841, + "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": 4183436, "tid": 31338, + "ts": 667115625859.759, "dur": 2686.565, + "args": { + "External id": 231766,"Record function id": 0, "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 4183436, "tid": 31338, + "ts": 667115625879.977, "dur": 1061.635, + "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": 4183436, "tid": 31338, + "ts": 667115625895.095, "dur": 317.229, + "args": { + "External id": 231768,"Record function id": 0, "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115625975.474, "dur": 3.990, + "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": 4183436, "tid": 31338, + "ts": 667115625982.212, "dur": 4.204, + "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": 4183436, "tid": 31338, + "ts": 667115625987.876, "dur": 2.369, + "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": 4183436, "tid": 31338, + "ts": 667115625991.876, "dur": 0.705, + "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": 4183436, "tid": 31338, + "ts": 667115625994.011, "dur": 0.568, + "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": 4183436, "tid": 31338, + "ts": 667115625995.845, "dur": 0.628, + "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": 4183436, "tid": 31338, + "ts": 667115625999.606, "dur": 1.375, + "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": 4183436, "tid": 31338, + "ts": 667115626002.142, "dur": 0.873, + "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": 4183436, "tid": 31338, + "ts": 667115626004.188, "dur": 0.640, + "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": 4183436, "tid": 31338, + "ts": 667115626006.449, "dur": 0.680, + "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": 4183436, "tid": 31338, + "ts": 667115626025.418, "dur": 154.392, + "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": 4183436, "tid": 31338, + "ts": 667115626040.586, "dur": 134.898, + "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": 4183436, "tid": 31338, + "ts": 667115626067.186, "dur": 14.594, + "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": 4183436, "tid": 31338, + "ts": 667115626084.520, "dur": 64.941, + "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": 4183436, "tid": 31338, + "ts": 667115626087.185, "dur": 61.967, + "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": 4183436, "tid": 31338, + "ts": 667115626092.324, "dur": 6.240, + "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": 4183436, "tid": 31338, + "ts": 667115626099.961, "dur": 48.705, + "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": 4183436, "tid": 31338, + "ts": 667115626292.811, "dur": 640.665, + "args": { + "External id": 231786,"Record function id": 0, "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 4183436, "tid": 31338, + "ts": 667115626313.456, "dur": 606.895, + "args": { + "External id": 231787,"Record function id": 0, "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115626365.812, "dur": 7.788, + "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": 4183436, "tid": 31338, + "ts": 667115626388.664, "dur": 25.331, + "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": 4183436, "tid": 31338, + "ts": 667115626392.870, "dur": 1.326, + "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": 4183436, "tid": 31338, + "ts": 667115626395.847, "dur": 1.569, + "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": 4183436, "tid": 31338, + "ts": 667115626398.476, "dur": 0.564, + "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": 4183436, "tid": 31338, + "ts": 667115626399.884, "dur": 0.700, + "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": 4183436, "tid": 31338, + "ts": 667115626402.365, "dur": 0.505, + "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": 4183436, "tid": 31338, + "ts": 667115626403.798, "dur": 2.067, + "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": 4183436, "tid": 31338, + "ts": 667115626406.801, "dur": 0.473, + "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": 4183436, "tid": 31338, + "ts": 667115626408.946, "dur": 0.391, + "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": 4183436, "tid": 31338, + "ts": 667115626410.123, "dur": 0.480, + "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": 4183436, "tid": 31338, + "ts": 667115626422.480, "dur": 30.816, + "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": 4183436, "tid": 31338, + "ts": 667115626482.406, "dur": 147.947, + "args": { + "External id": 231800,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115626520.839, "dur": 4.690, + "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": 4183436, "tid": 31338, + "ts": 667115626530.990, "dur": 10.205, + "args": { + "External id": 231802,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115626535.111, "dur": 5.697, + "args": { + "External id": 231803,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115626538.519, "dur": 0.848, + "args": { + "External id": 231804,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115626551.006, "dur": 36.458, + "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": 4183436, "tid": 31338, + "ts": 667115626552.624, "dur": 0.426, + "args": { + "External id": 231806,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115626554.869, "dur": 0.468, + "args": { + "External id": 231807,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115626573.633, "dur": 1.549, + "args": { + "External id": 231808,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115626576.455, "dur": 1.243, + "args": { + "External id": 231809,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115626578.757, "dur": 0.351, + "args": { + "External id": 231810,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115626579.937, "dur": 0.245, + "args": { + "External id": 231811,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115626581.629, "dur": 0.342, + "args": { + "External id": 231812,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115626582.782, "dur": 0.261, + "args": { + "External id": 231813,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115626583.688, "dur": 0.148, + "args": { + "External id": 231814,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115626598.493, "dur": 24.013, + "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": 4183436, "tid": 31338, + "ts": 667115626719.921, "dur": 124.949, + "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": 4183436, "tid": 31338, + "ts": 667115626751.798, "dur": 89.385, + "args": { + "External id": 231817,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115626761.439, "dur": 75.458, + "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": 4183436, "tid": 31338, + "ts": 667115626861.917, "dur": 1.787, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115626948.831, "dur": 1572.439, + "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": 4183436, "tid": 31338, "ts": 667115626948.831, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115627063.903, "dur": 101.341, + "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": 4183436, "tid": 31338, + "ts": 667115627203.870, "dur": 36.681, + "args": { + "External id": 231822,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115627255.660, "dur": 40.768, + "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": 4183436, "tid": 31338, + "ts": 667115627306.699, "dur": 26.580, + "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": 4183436, "tid": 31338, + "ts": 667115627339.614, "dur": 31.690, + "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": 4183436, "tid": 31338, + "ts": 667115627377.150, "dur": 21.302, + "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": 4183436, "tid": 31338, + "ts": 667115627408.665, "dur": 28.644, + "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": 4183436, "tid": 31338, + "ts": 667115627462.695, "dur": 23.534, + "args": { + "External id": 231828,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115627522.717, "dur": 29.117, + "args": { + "External id": 231829,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115627575.200, "dur": 21.720, + "args": { + "External id": 231830,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115627613.487, "dur": 15.126, + "args": { + "External id": 231831,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115627637.097, "dur": 86.098, + "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": 4183436, "tid": 31338, + "ts": 667115627728.772, "dur": 32.469, + "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": 4183436, "tid": 31338, + "ts": 667115627790.144, "dur": 176.565, + "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": 4183436, "tid": 31338, + "ts": 667115627875.898, "dur": 7.393, + "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": 4183436, "tid": 31338, + "ts": 667115627885.324, "dur": 2.108, + "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": 4183436, "tid": 31338, + "ts": 667115627998.288, "dur": 25.151, + "args": { + "External id": 231837,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115628036.532, "dur": 14.591, + "args": { + "External id": 231838,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115628058.918, "dur": 42.937, + "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": 4183436, "tid": 31338, + "ts": 667115628107.404, "dur": 32.374, + "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": 4183436, "tid": 31338, + "ts": 667115628147.066, "dur": 26.462, + "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": 4183436, "tid": 31338, + "ts": 667115628177.470, "dur": 31.163, + "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": 4183436, "tid": 31338, + "ts": 667115628214.727, "dur": 25.591, + "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": 4183436, "tid": 31338, + "ts": 667115628246.203, "dur": 27.195, + "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": 4183436, "tid": 31338, + "ts": 667115628309.275, "dur": 29.102, + "args": { + "External id": 231845,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115628355.200, "dur": 28.714, + "args": { + "External id": 231846,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115628398.475, "dur": 20.456, + "args": { + "External id": 231847,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115628432.530, "dur": 13.708, + "args": { + "External id": 231848,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115628459.459, "dur": 19.242, + "args": { + "External id": 231849,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115628568.054, "dur": 15.101, + "args": { + "External id": 231850,"Record function id": 0, "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115628571.517, "dur": 10.595, + "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": 4183436, "tid": 31338, + "ts": 667115628575.557, "dur": 5.525, + "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": 4183436, "tid": 31338, + "ts": 667115628577.054, "dur": 3.918, + "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": 4183436, "tid": 31338, + "ts": 667115628587.050, "dur": 9.807, + "args": { + "External id": 231854,"Record function id": 0, "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115628588.564, "dur": 7.810, + "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": 4183436, "tid": 31338, + "ts": 667115628589.239, "dur": 6.656, + "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": 4183436, "tid": 31338, + "ts": 667115628589.927, "dur": 5.885, + "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": 4183436, "tid": 31338, + "ts": 667115628600.016, "dur": 4.524, + "args": { + "External id": 231858,"Record function id": 0, "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115628601.132, "dur": 2.992, + "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": 4183436, "tid": 31338, + "ts": 667115628601.768, "dur": 1.935, + "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": 4183436, "tid": 31338, + "ts": 667115628602.807, "dur": 0.805, + "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": 4183436, "tid": 31338, + "ts": 667115628607.753, "dur": 3.879, + "args": { + "External id": 231862,"Record function id": 0, "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115628609.047, "dur": 2.162, + "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": 4183436, "tid": 31338, + "ts": 667115628609.594, "dur": 1.198, + "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": 4183436, "tid": 31338, + "ts": 667115628610.079, "dur": 0.621, + "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": 4183436, "tid": 31338, + "ts": 667115628614.795, "dur": 3.887, + "args": { + "External id": 231866,"Record function id": 0, "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115628616.061, "dur": 2.231, + "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": 4183436, "tid": 31338, + "ts": 667115628616.682, "dur": 1.063, + "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": 4183436, "tid": 31338, + "ts": 667115628617.054, "dur": 0.625, + "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": 4183436, "tid": 31338, + "ts": 667115628621.754, "dur": 3.613, + "args": { + "External id": 231870,"Record function id": 0, "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115628622.867, "dur": 2.104, + "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": 4183436, "tid": 31338, + "ts": 667115628623.402, "dur": 1.079, + "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": 4183436, "tid": 31338, + "ts": 667115628623.873, "dur": 0.543, + "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": 4183436, "tid": 31338, + "ts": 667115628628.582, "dur": 3.376, + "args": { + "External id": 231874,"Record function id": 0, "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115628629.654, "dur": 1.866, + "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": 4183436, "tid": 31338, + "ts": 667115628630.114, "dur": 0.965, + "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": 4183436, "tid": 31338, + "ts": 667115628630.413, "dur": 0.593, + "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": 4183436, "tid": 31338, + "ts": 667115628634.989, "dur": 5.324, + "args": { + "External id": 231878,"Record function id": 0, "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115628636.118, "dur": 3.768, + "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": 4183436, "tid": 31338, + "ts": 667115628636.599, "dur": 2.734, + "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": 4183436, "tid": 31338, + "ts": 667115628638.693, "dur": 0.573, + "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": 4183436, "tid": 31338, + "ts": 667115628643.392, "dur": 4.621, + "args": { + "External id": 231882,"Record function id": 0, "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115628644.334, "dur": 3.246, + "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": 4183436, "tid": 31338, + "ts": 667115628644.819, "dur": 2.341, + "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": 4183436, "tid": 31338, + "ts": 667115628645.137, "dur": 1.958, + "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": 4183436, "tid": 31338, + "ts": 667115628687.448, "dur": 14858.422, + "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": 4183436, "tid": 31338, + "ts": 667115628689.701, "dur": 14846.799, + "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": 4183436, "tid": 31338, "ts": 667115628689.701, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 4183436, "tid": 31338, + "ts": 667115628722.495, "dur": 38.186, + "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": 4183436, "tid": 31338, + "ts": 667115628769.009, "dur": 62.636, + "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": 4183436, "tid": 31338, + "ts": 667115628839.923, "dur": 14685.029, + "args": { + "External id": 231890,"Record function id": 0, "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115628927.625, "dur": 7.116, + "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": 4183436, "tid": 31338, + "ts": 667115628944.032, "dur": 4.927, + "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": 4183436, "tid": 31338, + "ts": 667115628962.287, "dur": 13879.716, + "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": 4183436, "tid": 31338, + "ts": 667115628975.069, "dur": 13857.919, + "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": 4183436, "tid": 31338, + "ts": 667115629019.030, "dur": 13.717, + "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": 4183436, "tid": 31338, + "ts": 667115629037.248, "dur": 13758.847, + "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": 4183436, "tid": 31338, + "ts": 667115629039.535, "dur": 13755.822, + "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": 4183436, "tid": 31338, + "ts": 667115629043.175, "dur": 5.516, + "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": 4183436, "tid": 31338, + "ts": 667115629052.425, "dur": 13739.163, + "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": 4183436, "tid": 31338, + "ts": 667115642933.145, "dur": 10.045, + "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": 4183436, "tid": 31338, + "ts": 667115642936.216, "dur": 6.589, + "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": 4183436, "tid": 31338, + "ts": 667115642970.554, "dur": 266.577, + "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": 4183436, "tid": 31338, + "ts": 667115642999.956, "dur": 232.849, + "args": { + "External id": 231903,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115643010.749, "dur": 215.428, + "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": 4183436, "tid": 31338, + "ts": 667115643255.799, "dur": 1.947, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115643306.216, "dur": 6.240, + "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": 4183436, "tid": 31338, + "ts": 667115643355.083, "dur": 2.890, + "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": 4183436, "tid": 31338, + "ts": 667115643373.688, "dur": 1.244, + "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": 4183436, "tid": 31338, + "ts": 667115643385.773, "dur": 0.813, + "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": 4183436, "tid": 31338, + "ts": 667115643397.021, "dur": 0.875, + "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": 4183436, "tid": 31338, + "ts": 667115643407.374, "dur": 2.546, + "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": 4183436, "tid": 31338, + "ts": 667115643421.384, "dur": 1.071, + "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": 4183436, "tid": 31338, + "ts": 667115643434.071, "dur": 1.632, + "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": 4183436, "tid": 31338, + "ts": 667115643445.182, "dur": 0.676, + "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": 4183436, "tid": 31338, + "ts": 667115643561.208, "dur": 2732.546, + "args": { + "External id": 231915,"Record function id": 0, "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 4183436, "tid": 31338, + "ts": 667115643580.032, "dur": 1113.229, + "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": 4183436, "tid": 31338, + "ts": 667115643594.513, "dur": 348.748, + "args": { + "External id": 231917,"Record function id": 0, "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115643708.605, "dur": 6.615, + "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": 4183436, "tid": 31338, + "ts": 667115643718.723, "dur": 0.835, + "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": 4183436, "tid": 31338, + "ts": 667115643721.458, "dur": 1.167, + "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": 4183436, "tid": 31338, + "ts": 667115643726.058, "dur": 0.769, + "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": 4183436, "tid": 31338, + "ts": 667115643728.158, "dur": 0.869, + "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": 4183436, "tid": 31338, + "ts": 667115643730.405, "dur": 0.764, + "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": 4183436, "tid": 31338, + "ts": 667115643732.671, "dur": 1.663, + "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": 4183436, "tid": 31338, + "ts": 667115643738.007, "dur": 0.791, + "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": 4183436, "tid": 31338, + "ts": 667115643740.522, "dur": 2.077, + "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": 4183436, "tid": 31338, + "ts": 667115643743.941, "dur": 0.954, + "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": 4183436, "tid": 31338, + "ts": 667115643763.747, "dur": 150.861, + "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": 4183436, "tid": 31338, + "ts": 667115643779.906, "dur": 130.318, + "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": 4183436, "tid": 31338, + "ts": 667115643795.540, "dur": 12.246, + "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": 4183436, "tid": 31338, + "ts": 667115643812.622, "dur": 67.133, + "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": 4183436, "tid": 31338, + "ts": 667115643815.256, "dur": 64.172, + "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": 4183436, "tid": 31338, + "ts": 667115643819.905, "dur": 5.780, + "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": 4183436, "tid": 31338, + "ts": 667115643827.298, "dur": 51.484, + "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": 4183436, "tid": 31338, + "ts": 667115644020.966, "dur": 624.674, + "args": { + "External id": 231935,"Record function id": 0, "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 4183436, "tid": 31338, + "ts": 667115644037.701, "dur": 594.527, + "args": { + "External id": 231936,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115644148.927, "dur": 5.664, + "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": 4183436, "tid": 31338, + "ts": 667115644170.690, "dur": 26.037, + "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": 4183436, "tid": 31338, + "ts": 667115644174.718, "dur": 1.344, + "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": 4183436, "tid": 31338, + "ts": 667115644178.462, "dur": 0.331, + "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": 4183436, "tid": 31338, + "ts": 667115644179.520, "dur": 0.288, + "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": 4183436, "tid": 31338, + "ts": 667115644180.471, "dur": 2.964, + "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": 4183436, "tid": 31338, + "ts": 667115644187.486, "dur": 0.322, + "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": 4183436, "tid": 31338, + "ts": 667115644188.574, "dur": 0.260, + "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": 4183436, "tid": 31338, + "ts": 667115644190.454, "dur": 0.285, + "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": 4183436, "tid": 31338, + "ts": 667115644191.441, "dur": 0.277, + "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": 4183436, "tid": 31338, + "ts": 667115644192.281, "dur": 0.283, + "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": 4183436, "tid": 31338, + "ts": 667115644206.065, "dur": 28.810, + "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": 4183436, "tid": 31338, + "ts": 667115644268.964, "dur": 96.044, + "args": { + "External id": 231949,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115644278.636, "dur": 3.296, + "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": 4183436, "tid": 31338, + "ts": 667115644286.641, "dur": 9.496, + "args": { + "External id": 231951,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115644290.736, "dur": 4.962, + "args": { + "External id": 231952,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115644293.235, "dur": 1.314, + "args": { + "External id": 231953,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115644302.622, "dur": 26.044, + "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": 4183436, "tid": 31338, + "ts": 667115644304.517, "dur": 2.405, + "args": { + "External id": 231955,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115644308.229, "dur": 0.385, + "args": { + "External id": 231956,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115644310.403, "dur": 0.314, + "args": { + "External id": 231957,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115644312.822, "dur": 0.320, + "args": { + "External id": 231958,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115644314.342, "dur": 0.286, + "args": { + "External id": 231959,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115644316.186, "dur": 0.783, + "args": { + "External id": 231960,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115644318.309, "dur": 0.268, + "args": { + "External id": 231961,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115644320.058, "dur": 0.308, + "args": { + "External id": 231962,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115644322.415, "dur": 2.110, + "args": { + "External id": 231963,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115644338.894, "dur": 18.645, + "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": 4183436, "tid": 31338, + "ts": 667115644411.636, "dur": 144.903, + "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": 4183436, "tid": 31338, + "ts": 667115644440.536, "dur": 112.076, + "args": { + "External id": 231966,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115644449.209, "dur": 98.822, + "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": 4183436, "tid": 31338, + "ts": 667115644575.416, "dur": 1.846, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115644702.105, "dur": 1571.046, + "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": 4183436, "tid": 31338, "ts": 667115644702.105, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115644819.652, "dur": 109.028, + "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": 4183436, "tid": 31338, + "ts": 667115644971.450, "dur": 36.946, + "args": { + "External id": 231971,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115645025.270, "dur": 40.767, + "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": 4183436, "tid": 31338, + "ts": 667115645074.503, "dur": 29.808, + "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": 4183436, "tid": 31338, + "ts": 667115645110.883, "dur": 32.460, + "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": 4183436, "tid": 31338, + "ts": 667115645149.264, "dur": 24.492, + "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": 4183436, "tid": 31338, + "ts": 667115645181.191, "dur": 28.571, + "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": 4183436, "tid": 31338, + "ts": 667115645231.998, "dur": 21.080, + "args": { + "External id": 231977,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115645270.082, "dur": 26.015, + "args": { + "External id": 231978,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115645314.807, "dur": 19.326, + "args": { + "External id": 231979,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115645347.468, "dur": 14.821, + "args": { + "External id": 231980,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115645370.693, "dur": 35.535, + "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": 4183436, "tid": 31338, + "ts": 667115645409.242, "dur": 29.468, + "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": 4183436, "tid": 31338, + "ts": 667115645483.404, "dur": 232.733, + "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": 4183436, "tid": 31338, + "ts": 667115645585.601, "dur": 7.523, + "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": 4183436, "tid": 31338, + "ts": 667115645595.322, "dur": 2.276, + "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": 4183436, "tid": 31338, + "ts": 667115645753.003, "dur": 27.921, + "args": { + "External id": 231986,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115645791.875, "dur": 17.346, + "args": { + "External id": 231987,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115645817.828, "dur": 57.994, + "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": 4183436, "tid": 31338, + "ts": 667115645882.976, "dur": 30.135, + "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": 4183436, "tid": 31338, + "ts": 667115645918.931, "dur": 27.515, + "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": 4183436, "tid": 31338, + "ts": 667115645950.625, "dur": 26.687, + "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": 4183436, "tid": 31338, + "ts": 667115645982.545, "dur": 26.462, + "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": 4183436, "tid": 31338, + "ts": 667115646016.514, "dur": 44.669, + "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": 4183436, "tid": 31338, + "ts": 667115646092.908, "dur": 22.016, + "args": { + "External id": 231994,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115646133.855, "dur": 22.929, + "args": { + "External id": 231995,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115646171.892, "dur": 17.360, + "args": { + "External id": 231996,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115646204.207, "dur": 13.018, + "args": { + "External id": 231997,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115646228.152, "dur": 13.907, + "args": { + "External id": 231998,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115646318.938, "dur": 15.684, + "args": { + "External id": 231999,"Record function id": 0, "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115646322.100, "dur": 11.675, + "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": 4183436, "tid": 31338, + "ts": 667115646326.280, "dur": 6.729, + "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": 4183436, "tid": 31338, + "ts": 667115646327.706, "dur": 5.216, + "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": 4183436, "tid": 31338, + "ts": 667115646338.561, "dur": 4.437, + "args": { + "External id": 232003,"Record function id": 0, "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115646340.036, "dur": 2.495, + "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": 4183436, "tid": 31338, + "ts": 667115646340.765, "dur": 1.316, + "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": 4183436, "tid": 31338, + "ts": 667115646341.219, "dur": 0.772, + "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": 4183436, "tid": 31338, + "ts": 667115646346.310, "dur": 3.948, + "args": { + "External id": 232007,"Record function id": 0, "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115646347.434, "dur": 2.400, + "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": 4183436, "tid": 31338, + "ts": 667115646348.091, "dur": 1.310, + "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": 4183436, "tid": 31338, + "ts": 667115646348.574, "dur": 0.757, + "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": 4183436, "tid": 31338, + "ts": 667115646353.372, "dur": 3.411, + "args": { + "External id": 232011,"Record function id": 0, "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115646354.522, "dur": 1.835, + "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": 4183436, "tid": 31338, + "ts": 667115646355.032, "dur": 0.914, + "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": 4183436, "tid": 31338, + "ts": 667115646355.322, "dur": 0.556, + "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": 4183436, "tid": 31338, + "ts": 667115646362.945, "dur": 5.191, + "args": { + "External id": 232015,"Record function id": 0, "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115646363.895, "dur": 3.807, + "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": 4183436, "tid": 31338, + "ts": 667115646364.423, "dur": 2.829, + "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": 4183436, "tid": 31338, + "ts": 667115646366.477, "dur": 0.666, + "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": 4183436, "tid": 31338, + "ts": 667115646371.167, "dur": 3.866, + "args": { + "External id": 232019,"Record function id": 0, "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115646372.455, "dur": 2.165, + "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": 4183436, "tid": 31338, + "ts": 667115646372.948, "dur": 1.265, + "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": 4183436, "tid": 31338, + "ts": 667115646373.442, "dur": 0.696, + "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": 4183436, "tid": 31338, + "ts": 667115646378.300, "dur": 3.778, + "args": { + "External id": 232023,"Record function id": 0, "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115646379.710, "dur": 1.932, + "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": 4183436, "tid": 31338, + "ts": 667115646380.233, "dur": 1.018, + "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": 4183436, "tid": 31338, + "ts": 667115646380.606, "dur": 0.567, + "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": 4183436, "tid": 31338, + "ts": 667115646385.223, "dur": 5.101, + "args": { + "External id": 232027,"Record function id": 0, "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115646386.618, "dur": 3.275, + "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": 4183436, "tid": 31338, + "ts": 667115646387.123, "dur": 2.389, + "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": 4183436, "tid": 31338, + "ts": 667115646387.509, "dur": 1.932, + "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": 4183436, "tid": 31338, + "ts": 667115646393.332, "dur": 5.360, + "args": { + "External id": 232031,"Record function id": 0, "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115646394.559, "dur": 3.698, + "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": 4183436, "tid": 31338, + "ts": 667115646395.028, "dur": 2.817, + "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": 4183436, "tid": 31338, + "ts": 667115646397.063, "dur": 0.683, + "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": 4183436, "tid": 31338, + "ts": 667115646402.238, "dur": 14860.179, + "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": 4183436, "tid": 31338, + "ts": 667115646403.315, "dur": 14851.341, + "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": 4183436, "tid": 31338, "ts": 667115646403.315, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 4183436, "tid": 31338, + "ts": 667115646431.073, "dur": 40.558, + "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": 4183436, "tid": 31338, + "ts": 667115646478.926, "dur": 90.751, + "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": 4183436, "tid": 31338, + "ts": 667115646577.288, "dur": 14669.469, + "args": { + "External id": 232039,"Record function id": 0, "Ev Idx": 2150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115646707.751, "dur": 8.027, + "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": 4183436, "tid": 31338, + "ts": 667115646726.943, "dur": 5.354, + "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": 4183436, "tid": 31338, + "ts": 667115646750.556, "dur": 13799.463, + "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": 4183436, "tid": 31338, + "ts": 667115646763.880, "dur": 13777.915, + "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": 4183436, "tid": 31338, + "ts": 667115646807.267, "dur": 13.925, + "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": 4183436, "tid": 31338, + "ts": 667115646825.713, "dur": 13680.648, + "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": 4183436, "tid": 31338, + "ts": 667115646828.052, "dur": 13677.556, + "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": 4183436, "tid": 31338, + "ts": 667115646832.659, "dur": 4.948, + "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": 4183436, "tid": 31338, + "ts": 667115646839.159, "dur": 13662.649, + "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": 4183436, "tid": 31338, + "ts": 667115660638.800, "dur": 9.314, + "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": 4183436, "tid": 31338, + "ts": 667115660641.636, "dur": 6.101, + "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": 4183436, "tid": 31338, + "ts": 667115660706.713, "dur": 266.032, + "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": 4183436, "tid": 31338, + "ts": 667115660737.293, "dur": 230.834, + "args": { + "External id": 232052,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115660749.227, "dur": 213.597, + "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": 4183436, "tid": 31338, + "ts": 667115660993.532, "dur": 1.919, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115661048.445, "dur": 6.056, + "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": 4183436, "tid": 31338, + "ts": 667115661101.421, "dur": 1.448, + "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": 4183436, "tid": 31338, + "ts": 667115661117.467, "dur": 1.386, + "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": 4183436, "tid": 31338, + "ts": 667115661129.969, "dur": 1.181, + "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": 4183436, "tid": 31338, + "ts": 667115661141.861, "dur": 1.150, + "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": 4183436, "tid": 31338, + "ts": 667115661154.060, "dur": 0.661, + "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": 4183436, "tid": 31338, + "ts": 667115661163.938, "dur": 0.831, + "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": 4183436, "tid": 31338, + "ts": 667115661174.662, "dur": 1.773, + "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": 4183436, "tid": 31338, + "ts": 667115661185.786, "dur": 0.744, + "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": 4183436, "tid": 31338, + "ts": 667115661275.794, "dur": 2671.818, + "args": { + "External id": 232064,"Record function id": 0, "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 4183436, "tid": 31338, + "ts": 667115661294.818, "dur": 978.635, + "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": 4183436, "tid": 31338, + "ts": 667115661310.042, "dur": 310.325, + "args": { + "External id": 232066,"Record function id": 0, "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115661383.692, "dur": 3.942, + "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": 4183436, "tid": 31338, + "ts": 667115661390.680, "dur": 1.099, + "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": 4183436, "tid": 31338, + "ts": 667115661393.566, "dur": 0.980, + "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": 4183436, "tid": 31338, + "ts": 667115661396.101, "dur": 0.564, + "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": 4183436, "tid": 31338, + "ts": 667115661398.047, "dur": 0.749, + "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": 4183436, "tid": 31338, + "ts": 667115661401.072, "dur": 0.651, + "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": 4183436, "tid": 31338, + "ts": 667115661403.332, "dur": 1.437, + "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": 4183436, "tid": 31338, + "ts": 667115661406.114, "dur": 2.601, + "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": 4183436, "tid": 31338, + "ts": 667115661410.006, "dur": 0.732, + "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": 4183436, "tid": 31338, + "ts": 667115661413.205, "dur": 0.589, + "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": 4183436, "tid": 31338, + "ts": 667115661431.422, "dur": 158.926, + "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": 4183436, "tid": 31338, + "ts": 667115661446.770, "dur": 138.943, + "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": 4183436, "tid": 31338, + "ts": 667115661459.992, "dur": 12.750, + "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": 4183436, "tid": 31338, + "ts": 667115661475.402, "dur": 83.096, + "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": 4183436, "tid": 31338, + "ts": 667115661477.915, "dur": 80.140, + "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": 4183436, "tid": 31338, + "ts": 667115661482.618, "dur": 4.905, + "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": 4183436, "tid": 31338, + "ts": 667115661489.108, "dur": 68.036, + "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": 4183436, "tid": 31338, + "ts": 667115661739.672, "dur": 526.113, + "args": { + "External id": 232084,"Record function id": 0, "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 4183436, "tid": 31338, + "ts": 667115661757.458, "dur": 495.620, + "args": { + "External id": 232085,"Record function id": 0, "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115661815.001, "dur": 5.817, + "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": 4183436, "tid": 31338, + "ts": 667115661837.039, "dur": 31.144, + "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": 4183436, "tid": 31338, + "ts": 667115661841.970, "dur": 1.704, + "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": 4183436, "tid": 31338, + "ts": 667115661845.731, "dur": 0.462, + "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": 4183436, "tid": 31338, + "ts": 667115661848.390, "dur": 2.330, + "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": 4183436, "tid": 31338, + "ts": 667115661852.101, "dur": 0.328, + "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": 4183436, "tid": 31338, + "ts": 667115661853.697, "dur": 1.543, + "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": 4183436, "tid": 31338, + "ts": 667115661856.689, "dur": 0.447, + "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": 4183436, "tid": 31338, + "ts": 667115661858.900, "dur": 0.414, + "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": 4183436, "tid": 31338, + "ts": 667115661862.049, "dur": 0.274, + "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": 4183436, "tid": 31338, + "ts": 667115661863.651, "dur": 0.402, + "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": 4183436, "tid": 31338, + "ts": 667115661878.002, "dur": 32.283, + "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": 4183436, "tid": 31338, + "ts": 667115661941.191, "dur": 96.897, + "args": { + "External id": 232098,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115661951.285, "dur": 3.343, + "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": 4183436, "tid": 31338, + "ts": 667115661959.542, "dur": 11.014, + "args": { + "External id": 232100,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115661963.703, "dur": 6.466, + "args": { + "External id": 232101,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115661966.983, "dur": 2.056, + "args": { + "External id": 232102,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115661977.701, "dur": 23.290, + "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": 4183436, "tid": 31338, + "ts": 667115661979.705, "dur": 0.487, + "args": { + "External id": 232104,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115661983.067, "dur": 0.424, + "args": { + "External id": 232105,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115661984.928, "dur": 0.339, + "args": { + "External id": 232106,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115661986.761, "dur": 0.418, + "args": { + "External id": 232107,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115661989.137, "dur": 0.398, + "args": { + "External id": 232108,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115661990.844, "dur": 0.349, + "args": { + "External id": 232109,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115661992.324, "dur": 0.672, + "args": { + "External id": 232110,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115661994.366, "dur": 2.092, + "args": { + "External id": 232111,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115661997.741, "dur": 0.387, + "args": { + "External id": 232112,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115662011.077, "dur": 19.477, + "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": 4183436, "tid": 31338, + "ts": 667115662079.919, "dur": 110.762, + "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": 4183436, "tid": 31338, + "ts": 667115662104.800, "dur": 82.379, + "args": { + "External id": 232115,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115662113.275, "dur": 69.935, + "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": 4183436, "tid": 31338, + "ts": 667115662204.908, "dur": 1.797, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115662280.179, "dur": 1641.122, + "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": 4183436, "tid": 31338, "ts": 667115662280.179, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115662388.677, "dur": 97.978, + "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": 4183436, "tid": 31338, + "ts": 667115662548.595, "dur": 38.320, + "args": { + "External id": 232120,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115662605.427, "dur": 81.919, + "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": 4183436, "tid": 31338, + "ts": 667115662701.423, "dur": 33.334, + "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": 4183436, "tid": 31338, + "ts": 667115662740.735, "dur": 34.417, + "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": 4183436, "tid": 31338, + "ts": 667115662781.715, "dur": 21.772, + "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": 4183436, "tid": 31338, + "ts": 667115662811.981, "dur": 28.635, + "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": 4183436, "tid": 31338, + "ts": 667115662868.015, "dur": 25.688, + "args": { + "External id": 232126,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115662911.538, "dur": 26.513, + "args": { + "External id": 232127,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115662955.940, "dur": 18.426, + "args": { + "External id": 232128,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115662988.371, "dur": 15.402, + "args": { + "External id": 232129,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115663012.580, "dur": 36.995, + "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": 4183436, "tid": 31338, + "ts": 667115663052.428, "dur": 30.317, + "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": 4183436, "tid": 31338, + "ts": 667115663110.112, "dur": 175.544, + "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": 4183436, "tid": 31338, + "ts": 667115663192.740, "dur": 4.976, + "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": 4183436, "tid": 31338, + "ts": 667115663199.815, "dur": 1.904, + "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": 4183436, "tid": 31338, + "ts": 667115663314.358, "dur": 28.304, + "args": { + "External id": 232135,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115663353.016, "dur": 14.280, + "args": { + "External id": 232136,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115663375.914, "dur": 41.590, + "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": 4183436, "tid": 31338, + "ts": 667115663423.012, "dur": 29.556, + "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": 4183436, "tid": 31338, + "ts": 667115663471.765, "dur": 49.664, + "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": 4183436, "tid": 31338, + "ts": 667115663528.589, "dur": 31.022, + "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": 4183436, "tid": 31338, + "ts": 667115663567.069, "dur": 29.728, + "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": 4183436, "tid": 31338, + "ts": 667115663602.841, "dur": 31.527, + "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": 4183436, "tid": 31338, + "ts": 667115663700.233, "dur": 27.460, + "args": { + "External id": 232143,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115663748.770, "dur": 37.523, + "args": { + "External id": 232144,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115663806.694, "dur": 18.906, + "args": { + "External id": 232145,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115663843.749, "dur": 15.415, + "args": { + "External id": 232146,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115663874.863, "dur": 15.558, + "args": { + "External id": 232147,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115663969.786, "dur": 14.436, + "args": { + "External id": 232148,"Record function id": 0, "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115663973.001, "dur": 10.334, + "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": 4183436, "tid": 31338, + "ts": 667115663976.931, "dur": 5.547, + "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": 4183436, "tid": 31338, + "ts": 667115663978.533, "dur": 3.852, + "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": 4183436, "tid": 31338, + "ts": 667115663991.312, "dur": 4.901, + "args": { + "External id": 232152,"Record function id": 0, "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115663993.023, "dur": 2.766, + "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": 4183436, "tid": 31338, + "ts": 667115663993.809, "dur": 1.566, + "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": 4183436, "tid": 31338, + "ts": 667115663994.392, "dur": 0.861, + "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": 4183436, "tid": 31338, + "ts": 667115663999.433, "dur": 4.049, + "args": { + "External id": 232156,"Record function id": 0, "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115664000.997, "dur": 2.072, + "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": 4183436, "tid": 31338, + "ts": 667115664001.507, "dur": 1.151, + "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": 4183436, "tid": 31338, + "ts": 667115664001.917, "dur": 0.639, + "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": 4183436, "tid": 31338, + "ts": 667115664006.635, "dur": 3.916, + "args": { + "External id": 232160,"Record function id": 0, "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115664008.158, "dur": 1.993, + "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": 4183436, "tid": 31338, + "ts": 667115664008.657, "dur": 1.112, + "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": 4183436, "tid": 31338, + "ts": 667115664008.996, "dur": 0.698, + "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": 4183436, "tid": 31338, + "ts": 667115664013.628, "dur": 4.125, + "args": { + "External id": 232164,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115664014.925, "dur": 2.428, + "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": 4183436, "tid": 31338, + "ts": 667115664015.400, "dur": 1.411, + "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": 4183436, "tid": 31338, + "ts": 667115664016.040, "dur": 0.696, + "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": 4183436, "tid": 31338, + "ts": 667115664020.892, "dur": 3.840, + "args": { + "External id": 232168,"Record function id": 0, "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115664022.117, "dur": 2.210, + "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": 4183436, "tid": 31338, + "ts": 667115664022.602, "dur": 1.326, + "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": 4183436, "tid": 31338, + "ts": 667115664023.158, "dur": 0.704, + "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": 4183436, "tid": 31338, + "ts": 667115664027.914, "dur": 5.022, + "args": { + "External id": 232172,"Record function id": 0, "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115664029.104, "dur": 3.419, + "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": 4183436, "tid": 31338, + "ts": 667115664029.572, "dur": 2.550, + "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": 4183436, "tid": 31338, + "ts": 667115664030.039, "dur": 2.023, + "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": 4183436, "tid": 31338, + "ts": 667115664035.944, "dur": 3.896, + "args": { + "External id": 232176,"Record function id": 0, "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115664037.239, "dur": 2.192, + "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": 4183436, "tid": 31338, + "ts": 667115664037.730, "dur": 1.295, + "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": 4183436, "tid": 31338, + "ts": 667115664038.256, "dur": 0.700, + "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": 4183436, "tid": 31338, + "ts": 667115664042.893, "dur": 6.732, + "args": { + "External id": 232180,"Record function id": 0, "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115664044.096, "dur": 5.132, + "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": 4183436, "tid": 31338, + "ts": 667115664044.576, "dur": 1.281, + "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": 4183436, "tid": 31338, + "ts": 667115664045.064, "dur": 0.727, + "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": 4183436, "tid": 31338, + "ts": 667115664054.227, "dur": 15056.755, + "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": 4183436, "tid": 31338, + "ts": 667115664055.847, "dur": 15046.253, + "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": 4183436, "tid": 31338, "ts": 667115664055.847, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 4183436, "tid": 31338, + "ts": 667115664084.674, "dur": 39.571, + "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": 4183436, "tid": 31338, + "ts": 667115664132.978, "dur": 63.214, + "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": 4183436, "tid": 31338, + "ts": 667115664202.049, "dur": 14891.749, + "args": { + "External id": 232188,"Record function id": 0, "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115664294.590, "dur": 6.380, + "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": 4183436, "tid": 31338, + "ts": 667115664310.413, "dur": 4.621, + "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": 4183436, "tid": 31338, + "ts": 667115664328.721, "dur": 14003.835, + "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": 4183436, "tid": 31338, + "ts": 667115664346.042, "dur": 13977.423, + "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": 4183436, "tid": 31338, + "ts": 667115664391.040, "dur": 13.481, + "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": 4183436, "tid": 31338, + "ts": 667115664409.142, "dur": 13877.222, + "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": 4183436, "tid": 31338, + "ts": 667115664413.107, "dur": 13872.467, + "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": 4183436, "tid": 31338, + "ts": 667115664417.506, "dur": 4.518, + "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": 4183436, "tid": 31338, + "ts": 667115664423.524, "dur": 13858.790, + "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": 4183436, "tid": 31338, + "ts": 667115678421.387, "dur": 9.138, + "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": 4183436, "tid": 31338, + "ts": 667115678424.166, "dur": 6.016, + "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": 4183436, "tid": 31338, + "ts": 667115678458.355, "dur": 348.722, + "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": 4183436, "tid": 31338, + "ts": 667115678486.570, "dur": 315.338, + "args": { + "External id": 232201,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115678512.310, "dur": 283.576, + "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": 4183436, "tid": 31338, + "ts": 667115678829.292, "dur": 2.388, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115678890.954, "dur": 9.261, + "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": 4183436, "tid": 31338, + "ts": 667115678944.454, "dur": 1.252, + "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": 4183436, "tid": 31338, + "ts": 667115678959.696, "dur": 1.386, + "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": 4183436, "tid": 31338, + "ts": 667115678972.280, "dur": 0.789, + "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": 4183436, "tid": 31338, + "ts": 667115678984.751, "dur": 2.832, + "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": 4183436, "tid": 31338, + "ts": 667115678997.487, "dur": 0.854, + "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": 4183436, "tid": 31338, + "ts": 667115679008.545, "dur": 0.893, + "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": 4183436, "tid": 31338, + "ts": 667115679019.276, "dur": 1.716, + "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": 4183436, "tid": 31338, + "ts": 667115679030.294, "dur": 2.672, + "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": 4183436, "tid": 31338, + "ts": 667115679125.405, "dur": 2624.158, + "args": { + "External id": 232213,"Record function id": 0, "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 4183436, "tid": 31338, + "ts": 667115679144.778, "dur": 981.647, + "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": 4183436, "tid": 31338, + "ts": 667115679160.129, "dur": 289.629, + "args": { + "External id": 232215,"Record function id": 0, "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115679234.604, "dur": 3.867, + "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": 4183436, "tid": 31338, + "ts": 667115679241.977, "dur": 0.928, + "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": 4183436, "tid": 31338, + "ts": 667115679244.775, "dur": 0.821, + "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": 4183436, "tid": 31338, + "ts": 667115679247.168, "dur": 0.856, + "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": 4183436, "tid": 31338, + "ts": 667115679249.775, "dur": 0.875, + "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": 4183436, "tid": 31338, + "ts": 667115679252.214, "dur": 0.632, + "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": 4183436, "tid": 31338, + "ts": 667115679254.365, "dur": 3.155, + "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": 4183436, "tid": 31338, + "ts": 667115679259.146, "dur": 0.640, + "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": 4183436, "tid": 31338, + "ts": 667115679261.587, "dur": 0.661, + "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": 4183436, "tid": 31338, + "ts": 667115679263.879, "dur": 0.643, + "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": 4183436, "tid": 31338, + "ts": 667115679282.746, "dur": 140.453, + "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": 4183436, "tid": 31338, + "ts": 667115679298.817, "dur": 120.272, + "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": 4183436, "tid": 31338, + "ts": 667115679314.262, "dur": 14.088, + "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": 4183436, "tid": 31338, + "ts": 667115679331.341, "dur": 60.990, + "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": 4183436, "tid": 31338, + "ts": 667115679334.037, "dur": 57.996, + "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": 4183436, "tid": 31338, + "ts": 667115679338.299, "dur": 5.770, + "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": 4183436, "tid": 31338, + "ts": 667115679345.656, "dur": 45.630, + "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": 4183436, "tid": 31338, + "ts": 667115679550.566, "dur": 567.982, + "args": { + "External id": 232233,"Record function id": 0, "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 4183436, "tid": 31338, + "ts": 667115679569.835, "dur": 536.517, + "args": { + "External id": 232234,"Record function id": 0, "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115679626.386, "dur": 5.523, + "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": 4183436, "tid": 31338, + "ts": 667115679647.217, "dur": 69.572, + "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": 4183436, "tid": 31338, + "ts": 667115679689.036, "dur": 2.668, + "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": 4183436, "tid": 31338, + "ts": 667115679694.290, "dur": 2.446, + "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": 4183436, "tid": 31338, + "ts": 667115679698.154, "dur": 0.445, + "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": 4183436, "tid": 31338, + "ts": 667115679701.066, "dur": 0.327, + "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": 4183436, "tid": 31338, + "ts": 667115679702.864, "dur": 0.438, + "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": 4183436, "tid": 31338, + "ts": 667115679705.102, "dur": 0.298, + "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": 4183436, "tid": 31338, + "ts": 667115679707.458, "dur": 0.528, + "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": 4183436, "tid": 31338, + "ts": 667115679709.247, "dur": 0.552, + "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": 4183436, "tid": 31338, + "ts": 667115679710.832, "dur": 1.203, + "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": 4183436, "tid": 31338, + "ts": 667115679729.906, "dur": 33.493, + "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": 4183436, "tid": 31338, + "ts": 667115679795.488, "dur": 95.196, + "args": { + "External id": 232247,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115679805.968, "dur": 6.598, + "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": 4183436, "tid": 31338, + "ts": 667115679817.549, "dur": 9.765, + "args": { + "External id": 232249,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115679821.946, "dur": 4.983, + "args": { + "External id": 232250,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115679825.157, "dur": 0.609, + "args": { + "External id": 232251,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115679834.092, "dur": 21.258, + "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": 4183436, "tid": 31338, + "ts": 667115679835.753, "dur": 0.469, + "args": { + "External id": 232253,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115679837.604, "dur": 1.158, + "args": { + "External id": 232254,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115679839.855, "dur": 0.437, + "args": { + "External id": 232255,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115679841.398, "dur": 0.330, + "args": { + "External id": 232256,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115679843.580, "dur": 0.312, + "args": { + "External id": 232257,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115679845.338, "dur": 0.445, + "args": { + "External id": 232258,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115679846.767, "dur": 1.936, + "args": { + "External id": 232259,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115679850.738, "dur": 0.468, + "args": { + "External id": 232260,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115679851.977, "dur": 0.362, + "args": { + "External id": 232261,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115679865.349, "dur": 17.894, + "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": 4183436, "tid": 31338, + "ts": 667115679935.647, "dur": 107.213, + "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": 4183436, "tid": 31338, + "ts": 667115679956.785, "dur": 82.794, + "args": { + "External id": 232264,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115679965.248, "dur": 70.009, + "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": 4183436, "tid": 31338, + "ts": 667115680056.484, "dur": 2.134, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115680133.101, "dur": 1595.285, + "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": 4183436, "tid": 31338, "ts": 667115680133.101, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115680235.449, "dur": 98.947, + "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": 4183436, "tid": 31338, + "ts": 667115680372.404, "dur": 37.980, + "args": { + "External id": 232269,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115680426.244, "dur": 40.246, + "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": 4183436, "tid": 31338, + "ts": 667115680475.532, "dur": 46.947, + "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": 4183436, "tid": 31338, + "ts": 667115680531.216, "dur": 36.070, + "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": 4183436, "tid": 31338, + "ts": 667115680575.066, "dur": 21.692, + "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": 4183436, "tid": 31338, + "ts": 667115680602.989, "dur": 27.624, + "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": 4183436, "tid": 31338, + "ts": 667115680691.607, "dur": 27.120, + "args": { + "External id": 232275,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115680746.984, "dur": 27.055, + "args": { + "External id": 232276,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115680793.663, "dur": 22.893, + "args": { + "External id": 232277,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115680827.877, "dur": 14.675, + "args": { + "External id": 232278,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115680851.392, "dur": 43.279, + "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": 4183436, "tid": 31338, + "ts": 667115680897.981, "dur": 33.627, + "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": 4183436, "tid": 31338, + "ts": 667115680956.209, "dur": 175.621, + "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": 4183436, "tid": 31338, + "ts": 667115681038.384, "dur": 5.958, + "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": 4183436, "tid": 31338, + "ts": 667115681046.290, "dur": 3.780, + "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": 4183436, "tid": 31338, + "ts": 667115681161.786, "dur": 26.924, + "args": { + "External id": 232284,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115681198.875, "dur": 17.338, + "args": { + "External id": 232285,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115681223.983, "dur": 43.579, + "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": 4183436, "tid": 31338, + "ts": 667115681272.925, "dur": 31.215, + "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": 4183436, "tid": 31338, + "ts": 667115681309.943, "dur": 27.451, + "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": 4183436, "tid": 31338, + "ts": 667115681343.291, "dur": 27.456, + "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": 4183436, "tid": 31338, + "ts": 667115681375.840, "dur": 27.670, + "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": 4183436, "tid": 31338, + "ts": 667115681409.840, "dur": 30.958, + "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": 4183436, "tid": 31338, + "ts": 667115681456.919, "dur": 25.271, + "args": { + "External id": 232292,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115681515.738, "dur": 24.859, + "args": { + "External id": 232293,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115681555.680, "dur": 29.858, + "args": { + "External id": 232294,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115681609.453, "dur": 16.234, + "args": { + "External id": 232295,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115681640.244, "dur": 52.089, + "args": { + "External id": 232296,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115681774.858, "dur": 14.178, + "args": { + "External id": 232297,"Record function id": 0, "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115681777.976, "dur": 10.156, + "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": 4183436, "tid": 31338, + "ts": 667115681781.869, "dur": 5.353, + "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": 4183436, "tid": 31338, + "ts": 667115681783.223, "dur": 3.866, + "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": 4183436, "tid": 31338, + "ts": 667115681792.984, "dur": 4.349, + "args": { + "External id": 232301,"Record function id": 0, "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115681794.223, "dur": 2.692, + "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": 4183436, "tid": 31338, + "ts": 667115681795.255, "dur": 1.230, + "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": 4183436, "tid": 31338, + "ts": 667115681795.562, "dur": 0.835, + "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": 4183436, "tid": 31338, + "ts": 667115681800.562, "dur": 4.303, + "args": { + "External id": 232305,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115681802.100, "dur": 2.351, + "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": 4183436, "tid": 31338, + "ts": 667115681802.753, "dur": 1.283, + "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": 4183436, "tid": 31338, + "ts": 667115681803.251, "dur": 0.691, + "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": 4183436, "tid": 31338, + "ts": 667115681808.027, "dur": 5.995, + "args": { + "External id": 232309,"Record function id": 0, "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115681809.055, "dur": 4.560, + "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": 4183436, "tid": 31338, + "ts": 667115681809.653, "dur": 3.554, + "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": 4183436, "tid": 31338, + "ts": 667115681810.128, "dur": 3.012, + "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": 4183436, "tid": 31338, + "ts": 667115681817.572, "dur": 3.569, + "args": { + "External id": 232313,"Record function id": 0, "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115681818.538, "dur": 2.210, + "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": 4183436, "tid": 31338, + "ts": 667115681819.074, "dur": 1.262, + "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": 4183436, "tid": 31338, + "ts": 667115681819.528, "dur": 0.745, + "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": 4183436, "tid": 31338, + "ts": 667115681824.343, "dur": 7.211, + "args": { + "External id": 232317,"Record function id": 0, "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115681825.902, "dur": 2.072, + "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": 4183436, "tid": 31338, + "ts": 667115681826.435, "dur": 1.150, + "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": 4183436, "tid": 31338, + "ts": 667115681826.807, "dur": 0.702, + "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": 4183436, "tid": 31338, + "ts": 667115681834.914, "dur": 4.428, + "args": { + "External id": 232321,"Record function id": 0, "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115681836.688, "dur": 2.240, + "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": 4183436, "tid": 31338, + "ts": 667115681837.331, "dur": 1.206, + "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": 4183436, "tid": 31338, + "ts": 667115681837.809, "dur": 0.652, + "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": 4183436, "tid": 31338, + "ts": 667115681842.594, "dur": 3.907, + "args": { + "External id": 232325,"Record function id": 0, "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115681843.727, "dur": 2.382, + "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": 4183436, "tid": 31338, + "ts": 667115681844.188, "dur": 1.486, + "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": 4183436, "tid": 31338, + "ts": 667115681844.863, "dur": 0.737, + "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": 4183436, "tid": 31338, + "ts": 667115681849.619, "dur": 4.145, + "args": { + "External id": 232329,"Record function id": 0, "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115681850.710, "dur": 2.609, + "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": 4183436, "tid": 31338, + "ts": 667115681851.375, "dur": 1.539, + "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": 4183436, "tid": 31338, + "ts": 667115681851.980, "dur": 0.862, + "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": 4183436, "tid": 31338, + "ts": 667115681857.500, "dur": 14769.264, + "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": 4183436, "tid": 31338, + "ts": 667115681858.785, "dur": 14759.349, + "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": 4183436, "tid": 31338, "ts": 667115681858.785, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 4183436, "tid": 31338, + "ts": 667115681891.199, "dur": 35.869, + "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": 4183436, "tid": 31338, + "ts": 667115681935.137, "dur": 64.618, + "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": 4183436, "tid": 31338, + "ts": 667115682008.794, "dur": 14601.981, + "args": { + "External id": 232337,"Record function id": 0, "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115682095.636, "dur": 6.893, + "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": 4183436, "tid": 31338, + "ts": 667115682112.329, "dur": 4.473, + "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": 4183436, "tid": 31338, + "ts": 667115682131.224, "dur": 13816.067, + "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": 4183436, "tid": 31338, + "ts": 667115682144.011, "dur": 13794.682, + "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": 4183436, "tid": 31338, + "ts": 667115682187.354, "dur": 14.910, + "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": 4183436, "tid": 31338, + "ts": 667115682207.069, "dur": 13697.692, + "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": 4183436, "tid": 31338, + "ts": 667115682209.488, "dur": 13694.565, + "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": 4183436, "tid": 31338, + "ts": 667115682213.792, "dur": 4.327, + "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": 4183436, "tid": 31338, + "ts": 667115682219.977, "dur": 13680.338, + "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": 4183436, "tid": 31338, + "ts": 667115696037.072, "dur": 9.425, + "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": 4183436, "tid": 31338, + "ts": 667115696040.253, "dur": 5.839, + "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": 4183436, "tid": 31338, + "ts": 667115696076.193, "dur": 254.890, + "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": 4183436, "tid": 31338, + "ts": 667115696100.666, "dur": 226.343, + "args": { + "External id": 232350,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115696112.583, "dur": 209.788, + "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": 4183436, "tid": 31338, + "ts": 667115696346.078, "dur": 1.960, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115696397.488, "dur": 5.901, + "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": 4183436, "tid": 31338, + "ts": 667115696446.454, "dur": 1.366, + "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": 4183436, "tid": 31338, + "ts": 667115696462.019, "dur": 1.438, + "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": 4183436, "tid": 31338, + "ts": 667115696476.324, "dur": 0.881, + "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": 4183436, "tid": 31338, + "ts": 667115696487.369, "dur": 0.712, + "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": 4183436, "tid": 31338, + "ts": 667115696518.414, "dur": 1.336, + "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": 4183436, "tid": 31338, + "ts": 667115696529.948, "dur": 0.976, + "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": 4183436, "tid": 31338, + "ts": 667115696541.913, "dur": 1.794, + "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": 4183436, "tid": 31338, + "ts": 667115696552.107, "dur": 0.784, + "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": 4183436, "tid": 31338, + "ts": 667115696641.879, "dur": 2591.094, + "args": { + "External id": 232362,"Record function id": 0, "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 4183436, "tid": 31338, + "ts": 667115696695.815, "dur": 933.793, + "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": 4183436, "tid": 31338, + "ts": 667115696710.658, "dur": 311.070, + "args": { + "External id": 232364,"Record function id": 0, "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115696790.802, "dur": 4.529, + "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": 4183436, "tid": 31338, + "ts": 667115696798.105, "dur": 0.934, + "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": 4183436, "tid": 31338, + "ts": 667115696800.808, "dur": 0.877, + "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": 4183436, "tid": 31338, + "ts": 667115696803.289, "dur": 2.689, + "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": 4183436, "tid": 31338, + "ts": 667115696807.371, "dur": 0.794, + "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": 4183436, "tid": 31338, + "ts": 667115696809.288, "dur": 0.803, + "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": 4183436, "tid": 31338, + "ts": 667115696811.450, "dur": 1.481, + "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": 4183436, "tid": 31338, + "ts": 667115696814.405, "dur": 0.735, + "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": 4183436, "tid": 31338, + "ts": 667115696816.280, "dur": 0.540, + "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": 4183436, "tid": 31338, + "ts": 667115696818.025, "dur": 0.506, + "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": 4183436, "tid": 31338, + "ts": 667115696835.338, "dur": 156.890, + "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": 4183436, "tid": 31338, + "ts": 667115696867.953, "dur": 120.265, + "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": 4183436, "tid": 31338, + "ts": 667115696883.152, "dur": 12.603, + "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": 4183436, "tid": 31338, + "ts": 667115696898.442, "dur": 64.228, + "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": 4183436, "tid": 31338, + "ts": 667115696900.958, "dur": 61.333, + "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": 4183436, "tid": 31338, + "ts": 667115696904.986, "dur": 6.871, + "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": 4183436, "tid": 31338, + "ts": 667115696913.348, "dur": 48.349, + "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": 4183436, "tid": 31338, + "ts": 667115697097.552, "dur": 524.352, + "args": { + "External id": 232382,"Record function id": 0, "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 4183436, "tid": 31338, + "ts": 667115697113.467, "dur": 496.224, + "args": { + "External id": 232383,"Record function id": 0, "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115697166.839, "dur": 4.439, + "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": 4183436, "tid": 31338, + "ts": 667115697186.448, "dur": 26.379, + "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": 4183436, "tid": 31338, + "ts": 667115697191.224, "dur": 1.408, + "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": 4183436, "tid": 31338, + "ts": 667115697194.401, "dur": 0.279, + "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": 4183436, "tid": 31338, + "ts": 667115697195.799, "dur": 0.418, + "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": 4183436, "tid": 31338, + "ts": 667115697198.185, "dur": 0.260, + "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": 4183436, "tid": 31338, + "ts": 667115697199.851, "dur": 0.294, + "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": 4183436, "tid": 31338, + "ts": 667115697201.027, "dur": 1.078, + "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": 4183436, "tid": 31338, + "ts": 667115697203.022, "dur": 2.474, + "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": 4183436, "tid": 31338, + "ts": 667115697206.586, "dur": 0.501, + "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": 4183436, "tid": 31338, + "ts": 667115697208.611, "dur": 0.405, + "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": 4183436, "tid": 31338, + "ts": 667115697221.356, "dur": 26.808, + "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": 4183436, "tid": 31338, + "ts": 667115697278.007, "dur": 88.123, + "args": { + "External id": 232396,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115697286.825, "dur": 3.436, + "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": 4183436, "tid": 31338, + "ts": 667115697295.328, "dur": 9.304, + "args": { + "External id": 232398,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115697299.409, "dur": 4.830, + "args": { + "External id": 232399,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115697302.480, "dur": 0.579, + "args": { + "External id": 232400,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115697311.317, "dur": 19.811, + "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": 4183436, "tid": 31338, + "ts": 667115697312.726, "dur": 0.585, + "args": { + "External id": 232402,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115697314.431, "dur": 0.341, + "args": { + "External id": 232403,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115697316.417, "dur": 0.242, + "args": { + "External id": 232404,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115697317.617, "dur": 1.981, + "args": { + "External id": 232405,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115697320.520, "dur": 0.312, + "args": { + "External id": 232406,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115697322.543, "dur": 0.520, + "args": { + "External id": 232407,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115697324.082, "dur": 0.353, + "args": { + "External id": 232408,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115697325.251, "dur": 1.183, + "args": { + "External id": 232409,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115697327.404, "dur": 0.374, + "args": { + "External id": 232410,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115697340.161, "dur": 18.829, + "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": 4183436, "tid": 31338, + "ts": 667115697412.361, "dur": 129.411, + "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": 4183436, "tid": 31338, + "ts": 667115697432.614, "dur": 105.000, + "args": { + "External id": 232413,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115697440.712, "dur": 92.010, + "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": 4183436, "tid": 31338, + "ts": 667115697555.881, "dur": 2.097, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115697636.098, "dur": 1577.193, + "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": 4183436, "tid": 31338, "ts": 667115697636.098, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115697786.123, "dur": 101.897, + "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": 4183436, "tid": 31338, + "ts": 667115697929.296, "dur": 36.257, + "args": { + "External id": 232418,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115697981.088, "dur": 39.005, + "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": 4183436, "tid": 31338, + "ts": 667115698029.094, "dur": 24.321, + "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": 4183436, "tid": 31338, + "ts": 667115698060.963, "dur": 31.065, + "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": 4183436, "tid": 31338, + "ts": 667115698098.530, "dur": 19.451, + "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": 4183436, "tid": 31338, + "ts": 667115698125.028, "dur": 27.568, + "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": 4183436, "tid": 31338, + "ts": 667115698175.166, "dur": 20.914, + "args": { + "External id": 232424,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115698214.380, "dur": 25.474, + "args": { + "External id": 232425,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115698259.089, "dur": 18.754, + "args": { + "External id": 232426,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115698294.542, "dur": 13.510, + "args": { + "External id": 232427,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115698316.940, "dur": 39.408, + "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": 4183436, "tid": 31338, + "ts": 667115698359.236, "dur": 29.529, + "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": 4183436, "tid": 31338, + "ts": 667115698415.012, "dur": 192.627, + "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": 4183436, "tid": 31338, + "ts": 667115698513.018, "dur": 6.910, + "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": 4183436, "tid": 31338, + "ts": 667115698522.830, "dur": 3.274, + "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": 4183436, "tid": 31338, + "ts": 667115698643.234, "dur": 66.490, + "args": { + "External id": 232433,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115698724.901, "dur": 15.647, + "args": { + "External id": 232434,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115698753.321, "dur": 51.802, + "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": 4183436, "tid": 31338, + "ts": 667115698814.206, "dur": 31.083, + "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": 4183436, "tid": 31338, + "ts": 667115698853.673, "dur": 30.587, + "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": 4183436, "tid": 31338, + "ts": 667115698888.419, "dur": 27.445, + "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": 4183436, "tid": 31338, + "ts": 667115698921.602, "dur": 25.552, + "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": 4183436, "tid": 31338, + "ts": 667115698952.941, "dur": 27.565, + "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": 4183436, "tid": 31338, + "ts": 667115699000.099, "dur": 24.434, + "args": { + "External id": 232441,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115699043.143, "dur": 25.685, + "args": { + "External id": 232442,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115699083.710, "dur": 30.491, + "args": { + "External id": 232443,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115699141.228, "dur": 13.715, + "args": { + "External id": 232444,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115699167.378, "dur": 14.781, + "args": { + "External id": 232445,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115699254.555, "dur": 91.529, + "args": { + "External id": 232446,"Record function id": 0, "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115699257.916, "dur": 87.031, + "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": 4183436, "tid": 31338, + "ts": 667115699261.857, "dur": 82.070, + "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": 4183436, "tid": 31338, + "ts": 667115699339.507, "dur": 4.229, + "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": 4183436, "tid": 31338, + "ts": 667115699351.088, "dur": 4.221, + "args": { + "External id": 232450,"Record function id": 0, "Ev Idx": 2561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115699352.476, "dur": 2.362, + "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": 4183436, "tid": 31338, + "ts": 667115699353.170, "dur": 1.249, + "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": 4183436, "tid": 31338, + "ts": 667115699353.525, "dur": 0.822, + "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": 4183436, "tid": 31338, + "ts": 667115699358.779, "dur": 5.405, + "args": { + "External id": 232454,"Record function id": 0, "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115699360.103, "dur": 3.641, + "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": 4183436, "tid": 31338, + "ts": 667115699360.623, "dur": 2.705, + "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": 4183436, "tid": 31338, + "ts": 667115699361.121, "dur": 2.113, + "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": 4183436, "tid": 31338, + "ts": 667115699367.389, "dur": 3.969, + "args": { + "External id": 232458,"Record function id": 0, "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115699368.690, "dur": 2.245, + "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": 4183436, "tid": 31338, + "ts": 667115699369.163, "dur": 1.364, + "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": 4183436, "tid": 31338, + "ts": 667115699369.834, "dur": 0.631, + "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": 4183436, "tid": 31338, + "ts": 667115699374.460, "dur": 4.069, + "args": { + "External id": 232462,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115699375.625, "dur": 2.451, + "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": 4183436, "tid": 31338, + "ts": 667115699376.114, "dur": 1.560, + "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": 4183436, "tid": 31338, + "ts": 667115699376.881, "dur": 0.729, + "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": 4183436, "tid": 31338, + "ts": 667115699381.783, "dur": 7.235, + "args": { + "External id": 232466,"Record function id": 0, "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115699383.231, "dur": 5.365, + "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": 4183436, "tid": 31338, + "ts": 667115699383.732, "dur": 1.271, + "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": 4183436, "tid": 31338, + "ts": 667115699384.295, "dur": 0.634, + "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": 4183436, "tid": 31338, + "ts": 667115699392.516, "dur": 3.848, + "args": { + "External id": 232470,"Record function id": 0, "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115699393.649, "dur": 2.305, + "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": 4183436, "tid": 31338, + "ts": 667115699394.133, "dur": 1.452, + "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": 4183436, "tid": 31338, + "ts": 667115699394.915, "dur": 0.593, + "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": 4183436, "tid": 31338, + "ts": 667115699399.698, "dur": 3.742, + "args": { + "External id": 232474,"Record function id": 0, "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115699400.838, "dur": 2.187, + "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": 4183436, "tid": 31338, + "ts": 667115699401.398, "dur": 1.227, + "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": 4183436, "tid": 31338, + "ts": 667115699402.006, "dur": 0.545, + "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": 4183436, "tid": 31338, + "ts": 667115699406.695, "dur": 3.502, + "args": { + "External id": 232478,"Record function id": 0, "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115699407.851, "dur": 1.937, + "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": 4183436, "tid": 31338, + "ts": 667115699408.300, "dur": 1.093, + "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": 4183436, "tid": 31338, + "ts": 667115699408.862, "dur": 0.456, + "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": 4183436, "tid": 31338, + "ts": 667115699414.120, "dur": 14836.237, + "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": 4183436, "tid": 31338, + "ts": 667115699415.307, "dur": 14827.169, + "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": 4183436, "tid": 31338, "ts": 667115699415.307, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 4183436, "tid": 31338, + "ts": 667115699443.935, "dur": 39.487, + "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": 4183436, "tid": 31338, + "ts": 667115699510.243, "dur": 76.130, + "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": 4183436, "tid": 31338, + "ts": 667115699593.525, "dur": 14641.351, + "args": { + "External id": 232486,"Record function id": 0, "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115699717.181, "dur": 8.545, + "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": 4183436, "tid": 31338, + "ts": 667115699736.372, "dur": 6.806, + "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": 4183436, "tid": 31338, + "ts": 667115699764.469, "dur": 13716.236, + "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": 4183436, "tid": 31338, + "ts": 667115699778.168, "dur": 13694.205, + "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": 4183436, "tid": 31338, + "ts": 667115699816.843, "dur": 14.332, + "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": 4183436, "tid": 31338, + "ts": 667115699836.104, "dur": 13602.291, + "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": 4183436, "tid": 31338, + "ts": 667115699838.434, "dur": 13599.284, + "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": 4183436, "tid": 31338, + "ts": 667115699842.525, "dur": 6.065, + "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": 4183436, "tid": 31338, + "ts": 667115699850.164, "dur": 13584.187, + "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": 4183436, "tid": 31338, + "ts": 667115713580.279, "dur": 9.034, + "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": 4183436, "tid": 31338, + "ts": 667115713583.084, "dur": 5.755, + "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": 4183436, "tid": 31338, + "ts": 667115713618.777, "dur": 339.125, + "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": 4183436, "tid": 31338, + "ts": 667115713692.781, "dur": 260.329, + "args": { + "External id": 232499,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115713707.937, "dur": 239.536, + "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": 4183436, "tid": 31338, + "ts": 667115713978.397, "dur": 2.351, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115714036.965, "dur": 6.285, + "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": 4183436, "tid": 31338, + "ts": 667115714086.787, "dur": 1.321, + "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": 4183436, "tid": 31338, + "ts": 667115714103.585, "dur": 2.761, + "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": 4183436, "tid": 31338, + "ts": 667115714117.144, "dur": 0.960, + "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": 4183436, "tid": 31338, + "ts": 667115714127.920, "dur": 0.781, + "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": 4183436, "tid": 31338, + "ts": 667115714137.818, "dur": 0.771, + "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": 4183436, "tid": 31338, + "ts": 667115714148.980, "dur": 2.422, + "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": 4183436, "tid": 31338, + "ts": 667115714162.258, "dur": 1.707, + "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": 4183436, "tid": 31338, + "ts": 667115714173.996, "dur": 0.657, + "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": 4183436, "tid": 31338, + "ts": 667115714264.528, "dur": 2629.515, + "args": { + "External id": 232511,"Record function id": 0, "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 4183436, "tid": 31338, + "ts": 667115714284.118, "dur": 989.550, + "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": 4183436, "tid": 31338, + "ts": 667115714298.790, "dur": 323.342, + "args": { + "External id": 232513,"Record function id": 0, "Ev Idx": 2624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115714370.897, "dur": 3.706, + "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": 4183436, "tid": 31338, + "ts": 667115714377.644, "dur": 0.992, + "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": 4183436, "tid": 31338, + "ts": 667115714380.436, "dur": 2.709, + "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": 4183436, "tid": 31338, + "ts": 667115714385.216, "dur": 0.782, + "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": 4183436, "tid": 31338, + "ts": 667115714388.000, "dur": 0.724, + "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": 4183436, "tid": 31338, + "ts": 667115714390.395, "dur": 0.772, + "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": 4183436, "tid": 31338, + "ts": 667115714393.216, "dur": 1.563, + "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": 4183436, "tid": 31338, + "ts": 667115714396.362, "dur": 0.760, + "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": 4183436, "tid": 31338, + "ts": 667115714399.035, "dur": 0.552, + "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": 4183436, "tid": 31338, + "ts": 667115714400.892, "dur": 0.919, + "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": 4183436, "tid": 31338, + "ts": 667115714419.382, "dur": 170.575, + "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": 4183436, "tid": 31338, + "ts": 667115714434.732, "dur": 150.153, + "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": 4183436, "tid": 31338, + "ts": 667115714458.114, "dur": 14.982, + "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": 4183436, "tid": 31338, + "ts": 667115714475.829, "dur": 82.490, + "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": 4183436, "tid": 31338, + "ts": 667115714478.305, "dur": 79.690, + "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": 4183436, "tid": 31338, + "ts": 667115714483.338, "dur": 5.645, + "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": 4183436, "tid": 31338, + "ts": 667115714490.794, "dur": 66.299, + "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": 4183436, "tid": 31338, + "ts": 667115714742.686, "dur": 523.116, + "args": { + "External id": 232531,"Record function id": 0, "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 4183436, "tid": 31338, + "ts": 667115714762.321, "dur": 491.536, + "args": { + "External id": 232532,"Record function id": 0, "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115714818.269, "dur": 5.901, + "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": 4183436, "tid": 31338, + "ts": 667115714840.075, "dur": 28.352, + "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": 4183436, "tid": 31338, + "ts": 667115714844.965, "dur": 1.237, + "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": 4183436, "tid": 31338, + "ts": 667115714848.321, "dur": 0.380, + "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": 4183436, "tid": 31338, + "ts": 667115714850.774, "dur": 0.415, + "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": 4183436, "tid": 31338, + "ts": 667115714852.242, "dur": 0.399, + "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": 4183436, "tid": 31338, + "ts": 667115714853.582, "dur": 1.263, + "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": 4183436, "tid": 31338, + "ts": 667115714856.318, "dur": 2.456, + "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": 4183436, "tid": 31338, + "ts": 667115714859.612, "dur": 0.382, + "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": 4183436, "tid": 31338, + "ts": 667115714862.787, "dur": 0.298, + "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": 4183436, "tid": 31338, + "ts": 667115714864.047, "dur": 0.277, + "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": 4183436, "tid": 31338, + "ts": 667115714877.853, "dur": 32.126, + "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": 4183436, "tid": 31338, + "ts": 667115714942.967, "dur": 93.286, + "args": { + "External id": 232545,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115714952.377, "dur": 3.394, + "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": 4183436, "tid": 31338, + "ts": 667115714960.664, "dur": 9.273, + "args": { + "External id": 232547,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115714964.935, "dur": 4.609, + "args": { + "External id": 232548,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115714967.982, "dur": 0.456, + "args": { + "External id": 232549,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115714976.739, "dur": 22.365, + "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": 4183436, "tid": 31338, + "ts": 667115714978.371, "dur": 0.458, + "args": { + "External id": 232551,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115714981.053, "dur": 0.260, + "args": { + "External id": 232552,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115714982.603, "dur": 2.089, + "args": { + "External id": 232553,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115714985.735, "dur": 0.441, + "args": { + "External id": 232554,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115714988.115, "dur": 0.296, + "args": { + "External id": 232555,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115714989.448, "dur": 0.288, + "args": { + "External id": 232556,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115714991.164, "dur": 1.402, + "args": { + "External id": 232557,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115714993.657, "dur": 0.487, + "args": { + "External id": 232558,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115714995.442, "dur": 0.329, + "args": { + "External id": 232559,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115715009.665, "dur": 19.541, + "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": 4183436, "tid": 31338, + "ts": 667115715078.188, "dur": 111.268, + "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": 4183436, "tid": 31338, + "ts": 667115715101.819, "dur": 83.964, + "args": { + "External id": 232562,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115715110.962, "dur": 70.355, + "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": 4183436, "tid": 31338, + "ts": 667115715204.698, "dur": 1.820, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115715280.489, "dur": 1594.030, + "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": 4183436, "tid": 31338, "ts": 667115715280.489, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115715384.853, "dur": 97.628, + "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": 4183436, "tid": 31338, + "ts": 667115715544.609, "dur": 38.334, + "args": { + "External id": 232567,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115715600.227, "dur": 46.425, + "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": 4183436, "tid": 31338, + "ts": 667115715700.558, "dur": 31.480, + "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": 4183436, "tid": 31338, + "ts": 667115715739.580, "dur": 33.768, + "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": 4183436, "tid": 31338, + "ts": 667115715780.998, "dur": 20.332, + "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": 4183436, "tid": 31338, + "ts": 667115715808.550, "dur": 27.702, + "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": 4183436, "tid": 31338, + "ts": 667115715864.762, "dur": 22.240, + "args": { + "External id": 232573,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115715908.827, "dur": 25.941, + "args": { + "External id": 232574,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115715959.459, "dur": 18.337, + "args": { + "External id": 232575,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115715993.282, "dur": 16.409, + "args": { + "External id": 232576,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115716017.840, "dur": 35.950, + "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": 4183436, "tid": 31338, + "ts": 667115716057.077, "dur": 33.632, + "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": 4183436, "tid": 31338, + "ts": 667115716120.096, "dur": 173.876, + "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": 4183436, "tid": 31338, + "ts": 667115716199.666, "dur": 5.883, + "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": 4183436, "tid": 31338, + "ts": 667115716207.492, "dur": 5.848, + "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": 4183436, "tid": 31338, + "ts": 667115716324.743, "dur": 28.854, + "args": { + "External id": 232582,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115716365.687, "dur": 14.669, + "args": { + "External id": 232583,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115716388.079, "dur": 47.585, + "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": 4183436, "tid": 31338, + "ts": 667115716441.400, "dur": 30.998, + "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": 4183436, "tid": 31338, + "ts": 667115716481.575, "dur": 45.291, + "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": 4183436, "tid": 31338, + "ts": 667115716534.030, "dur": 30.676, + "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": 4183436, "tid": 31338, + "ts": 667115716571.285, "dur": 26.574, + "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": 4183436, "tid": 31338, + "ts": 667115716608.443, "dur": 27.078, + "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": 4183436, "tid": 31338, + "ts": 667115716696.169, "dur": 25.266, + "args": { + "External id": 232590,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115716739.711, "dur": 22.813, + "args": { + "External id": 232591,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115716777.256, "dur": 15.445, + "args": { + "External id": 232592,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115716807.456, "dur": 13.074, + "args": { + "External id": 232593,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115716832.882, "dur": 14.068, + "args": { + "External id": 232594,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115716920.083, "dur": 15.023, + "args": { + "External id": 232595,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115716922.978, "dur": 11.159, + "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": 4183436, "tid": 31338, + "ts": 667115716927.229, "dur": 6.076, + "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": 4183436, "tid": 31338, + "ts": 667115716928.585, "dur": 4.575, + "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": 4183436, "tid": 31338, + "ts": 667115716939.278, "dur": 6.514, + "args": { + "External id": 232599,"Record function id": 0, "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115716940.446, "dur": 4.864, + "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": 4183436, "tid": 31338, + "ts": 667115716941.131, "dur": 3.627, + "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": 4183436, "tid": 31338, + "ts": 667115716941.549, "dur": 3.120, + "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": 4183436, "tid": 31338, + "ts": 667115716949.390, "dur": 4.415, + "args": { + "External id": 232603,"Record function id": 0, "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115716950.725, "dur": 2.662, + "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": 4183436, "tid": 31338, + "ts": 667115716951.441, "dur": 1.528, + "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": 4183436, "tid": 31338, + "ts": 667115716952.090, "dur": 0.813, + "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": 4183436, "tid": 31338, + "ts": 667115716957.071, "dur": 3.313, + "args": { + "External id": 232607,"Record function id": 0, "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115716957.990, "dur": 1.950, + "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": 4183436, "tid": 31338, + "ts": 667115716958.501, "dur": 1.002, + "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": 4183436, "tid": 31338, + "ts": 667115716958.777, "dur": 0.662, + "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": 4183436, "tid": 31338, + "ts": 667115716963.881, "dur": 6.809, + "args": { + "External id": 232611,"Record function id": 0, "Ev Idx": 2722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115716967.902, "dur": 2.402, + "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": 4183436, "tid": 31338, + "ts": 667115716968.412, "dur": 1.440, + "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": 4183436, "tid": 31338, + "ts": 667115716969.143, "dur": 0.644, + "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": 4183436, "tid": 31338, + "ts": 667115716974.161, "dur": 3.723, + "args": { + "External id": 232615,"Record function id": 0, "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115716975.144, "dur": 2.365, + "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": 4183436, "tid": 31338, + "ts": 667115716975.599, "dur": 1.502, + "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": 4183436, "tid": 31338, + "ts": 667115716976.479, "dur": 0.549, + "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": 4183436, "tid": 31338, + "ts": 667115716981.345, "dur": 3.608, + "args": { + "External id": 232619,"Record function id": 0, "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115716982.576, "dur": 1.961, + "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": 4183436, "tid": 31338, + "ts": 667115716983.005, "dur": 1.124, + "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": 4183436, "tid": 31338, + "ts": 667115716983.428, "dur": 0.628, + "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": 4183436, "tid": 31338, + "ts": 667115716988.352, "dur": 4.087, + "args": { + "External id": 232623,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115716989.489, "dur": 2.561, + "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": 4183436, "tid": 31338, + "ts": 667115716990.067, "dur": 1.577, + "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": 4183436, "tid": 31338, + "ts": 667115716990.817, "dur": 0.764, + "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": 4183436, "tid": 31338, + "ts": 667115716995.893, "dur": 5.472, + "args": { + "External id": 232627,"Record function id": 0, "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115716996.969, "dur": 4.004, + "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": 4183436, "tid": 31338, + "ts": 667115716997.469, "dur": 3.091, + "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": 4183436, "tid": 31338, + "ts": 667115716998.199, "dur": 2.293, + "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": 4183436, "tid": 31338, + "ts": 667115717005.295, "dur": 16068.756, + "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": 4183436, "tid": 31338, + "ts": 667115717006.527, "dur": 16059.062, + "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": 4183436, "tid": 31338, "ts": 667115717006.527, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 4183436, "tid": 31338, + "ts": 667115717036.039, "dur": 40.497, + "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": 4183436, "tid": 31338, + "ts": 667115717084.516, "dur": 65.599, + "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": 4183436, "tid": 31338, + "ts": 667115717157.061, "dur": 15900.858, + "args": { + "External id": 232635,"Record function id": 0, "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115717243.036, "dur": 6.773, + "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": 4183436, "tid": 31338, + "ts": 667115717259.377, "dur": 4.450, + "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": 4183436, "tid": 31338, + "ts": 667115717277.334, "dur": 15037.002, + "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": 4183436, "tid": 31338, + "ts": 667115717290.588, "dur": 15015.123, + "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": 4183436, "tid": 31338, + "ts": 667115717319.587, "dur": 13.714, + "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": 4183436, "tid": 31338, + "ts": 667115717337.439, "dur": 14935.369, + "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": 4183436, "tid": 31338, + "ts": 667115717339.981, "dur": 14932.103, + "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": 4183436, "tid": 31338, + "ts": 667115717343.497, "dur": 5.052, + "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": 4183436, "tid": 31338, + "ts": 667115717350.212, "dur": 14918.284, + "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": 4183436, "tid": 31338, + "ts": 667115732401.496, "dur": 9.219, + "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": 4183436, "tid": 31338, + "ts": 667115732404.528, "dur": 5.837, + "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": 4183436, "tid": 31338, + "ts": 667115732439.701, "dur": 341.765, + "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": 4183436, "tid": 31338, + "ts": 667115732463.981, "dur": 312.657, + "args": { + "External id": 232648,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115732475.604, "dur": 295.230, + "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": 4183436, "tid": 31338, + "ts": 667115732800.755, "dur": 2.181, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115732861.280, "dur": 6.240, + "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": 4183436, "tid": 31338, + "ts": 667115732910.825, "dur": 3.121, + "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": 4183436, "tid": 31338, + "ts": 667115732929.259, "dur": 1.131, + "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": 4183436, "tid": 31338, + "ts": 667115732940.765, "dur": 1.076, + "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": 4183436, "tid": 31338, + "ts": 667115732951.060, "dur": 0.821, + "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": 4183436, "tid": 31338, + "ts": 667115732961.538, "dur": 2.671, + "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": 4183436, "tid": 31338, + "ts": 667115732974.238, "dur": 0.966, + "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": 4183436, "tid": 31338, + "ts": 667115732986.493, "dur": 2.084, + "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": 4183436, "tid": 31338, + "ts": 667115732998.387, "dur": 0.870, + "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": 4183436, "tid": 31338, + "ts": 667115733087.772, "dur": 2547.473, + "args": { + "External id": 232660,"Record function id": 0, "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 4183436, "tid": 31338, + "ts": 667115733107.309, "dur": 990.822, + "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": 4183436, "tid": 31338, + "ts": 667115733120.862, "dur": 283.288, + "args": { + "External id": 232662,"Record function id": 0, "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115733193.906, "dur": 5.693, + "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": 4183436, "tid": 31338, + "ts": 667115733203.090, "dur": 0.887, + "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": 4183436, "tid": 31338, + "ts": 667115733205.540, "dur": 0.906, + "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": 4183436, "tid": 31338, + "ts": 667115733208.212, "dur": 0.799, + "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": 4183436, "tid": 31338, + "ts": 667115733210.866, "dur": 0.578, + "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": 4183436, "tid": 31338, + "ts": 667115733214.683, "dur": 0.988, + "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": 4183436, "tid": 31338, + "ts": 667115733217.228, "dur": 1.547, + "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": 4183436, "tid": 31338, + "ts": 667115733219.951, "dur": 0.856, + "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": 4183436, "tid": 31338, + "ts": 667115733222.325, "dur": 2.245, + "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": 4183436, "tid": 31338, + "ts": 667115733225.883, "dur": 0.507, + "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": 4183436, "tid": 31338, + "ts": 667115733244.851, "dur": 134.200, + "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": 4183436, "tid": 31338, + "ts": 667115733260.709, "dur": 114.288, + "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": 4183436, "tid": 31338, + "ts": 667115733273.027, "dur": 12.245, + "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": 4183436, "tid": 31338, + "ts": 667115733288.062, "dur": 61.170, + "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": 4183436, "tid": 31338, + "ts": 667115733290.622, "dur": 58.232, + "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": 4183436, "tid": 31338, + "ts": 667115733295.649, "dur": 5.479, + "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": 4183436, "tid": 31338, + "ts": 667115733303.048, "dur": 45.375, + "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": 4183436, "tid": 31338, + "ts": 667115733472.693, "dur": 617.397, + "args": { + "External id": 232680,"Record function id": 0, "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 4183436, "tid": 31338, + "ts": 667115733487.820, "dur": 588.914, + "args": { + "External id": 232681,"Record function id": 0, "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115733563.199, "dur": 5.723, + "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": 4183436, "tid": 31338, + "ts": 667115733584.137, "dur": 29.042, + "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": 4183436, "tid": 31338, + "ts": 667115733589.105, "dur": 1.363, + "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": 4183436, "tid": 31338, + "ts": 667115733592.481, "dur": 0.333, + "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": 4183436, "tid": 31338, + "ts": 667115733595.009, "dur": 0.470, + "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": 4183436, "tid": 31338, + "ts": 667115733597.084, "dur": 1.924, + "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": 4183436, "tid": 31338, + "ts": 667115733600.013, "dur": 0.516, + "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": 4183436, "tid": 31338, + "ts": 667115733602.884, "dur": 0.480, + "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": 4183436, "tid": 31338, + "ts": 667115733604.278, "dur": 0.352, + "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": 4183436, "tid": 31338, + "ts": 667115733606.096, "dur": 1.108, + "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": 4183436, "tid": 31338, + "ts": 667115733608.729, "dur": 0.364, + "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": 4183436, "tid": 31338, + "ts": 667115733622.985, "dur": 75.838, + "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": 4183436, "tid": 31338, + "ts": 667115733733.240, "dur": 109.620, + "args": { + "External id": 232694,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115733747.815, "dur": 4.198, + "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": 4183436, "tid": 31338, + "ts": 667115733757.117, "dur": 10.110, + "args": { + "External id": 232696,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115733761.348, "dur": 5.479, + "args": { + "External id": 232697,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115733764.746, "dur": 0.693, + "args": { + "External id": 232698,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115733774.499, "dur": 29.179, + "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": 4183436, "tid": 31338, + "ts": 667115733776.660, "dur": 2.297, + "args": { + "External id": 232700,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115733780.578, "dur": 1.179, + "args": { + "External id": 232701,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115733782.862, "dur": 0.377, + "args": { + "External id": 232702,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115733784.419, "dur": 0.278, + "args": { + "External id": 232703,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115733786.818, "dur": 0.252, + "args": { + "External id": 232704,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115733788.728, "dur": 0.370, + "args": { + "External id": 232705,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115733790.046, "dur": 0.605, + "args": { + "External id": 232706,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115733793.375, "dur": 0.537, + "args": { + "External id": 232707,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115733794.768, "dur": 2.253, + "args": { + "External id": 232708,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115733814.279, "dur": 21.196, + "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": 4183436, "tid": 31338, + "ts": 667115733892.432, "dur": 115.141, + "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": 4183436, "tid": 31338, + "ts": 667115733920.300, "dur": 83.822, + "args": { + "External id": 232711,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115733929.410, "dur": 69.939, + "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": 4183436, "tid": 31338, + "ts": 667115734021.396, "dur": 1.708, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115734108.256, "dur": 1499.991, + "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": 4183436, "tid": 31338, "ts": 667115734108.256, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115734217.206, "dur": 98.304, + "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": 4183436, "tid": 31338, + "ts": 667115734352.841, "dur": 35.324, + "args": { + "External id": 232716,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115734405.931, "dur": 37.631, + "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": 4183436, "tid": 31338, + "ts": 667115734455.535, "dur": 23.559, + "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": 4183436, "tid": 31338, + "ts": 667115734484.667, "dur": 57.592, + "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": 4183436, "tid": 31338, + "ts": 667115734551.752, "dur": 23.178, + "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": 4183436, "tid": 31338, + "ts": 667115734583.741, "dur": 27.916, + "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": 4183436, "tid": 31338, + "ts": 667115734634.893, "dur": 60.917, + "args": { + "External id": 232722,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115734716.341, "dur": 27.609, + "args": { + "External id": 232723,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115734765.254, "dur": 18.426, + "args": { + "External id": 232724,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115734798.997, "dur": 17.185, + "args": { + "External id": 232725,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115734825.216, "dur": 45.133, + "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": 4183436, "tid": 31338, + "ts": 667115734873.169, "dur": 29.959, + "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": 4183436, "tid": 31338, + "ts": 667115734928.752, "dur": 164.669, + "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": 4183436, "tid": 31338, + "ts": 667115735004.644, "dur": 5.855, + "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": 4183436, "tid": 31338, + "ts": 667115735012.416, "dur": 3.578, + "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": 4183436, "tid": 31338, + "ts": 667115735121.511, "dur": 22.225, + "args": { + "External id": 232731,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115735154.881, "dur": 12.234, + "args": { + "External id": 232732,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115735174.315, "dur": 40.006, + "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": 4183436, "tid": 31338, + "ts": 667115735221.239, "dur": 31.626, + "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": 4183436, "tid": 31338, + "ts": 667115735258.613, "dur": 26.420, + "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": 4183436, "tid": 31338, + "ts": 667115735289.417, "dur": 27.513, + "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": 4183436, "tid": 31338, + "ts": 667115735322.126, "dur": 26.129, + "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": 4183436, "tid": 31338, + "ts": 667115735355.901, "dur": 30.193, + "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": 4183436, "tid": 31338, + "ts": 667115735402.703, "dur": 23.502, + "args": { + "External id": 232739,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115735442.361, "dur": 21.365, + "args": { + "External id": 232740,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115735476.673, "dur": 13.939, + "args": { + "External id": 232741,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115735525.405, "dur": 16.326, + "args": { + "External id": 232742,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115735553.379, "dur": 17.731, + "args": { + "External id": 232743,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115735698.198, "dur": 19.148, + "args": { + "External id": 232744,"Record function id": 0, "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115735702.284, "dur": 13.683, + "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": 4183436, "tid": 31338, + "ts": 667115735706.810, "dur": 7.920, + "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": 4183436, "tid": 31338, + "ts": 667115735708.275, "dur": 6.186, + "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": 4183436, "tid": 31338, + "ts": 667115735722.599, "dur": 4.209, + "args": { + "External id": 232748,"Record function id": 0, "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115735723.760, "dur": 2.574, + "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": 4183436, "tid": 31338, + "ts": 667115735724.496, "dur": 1.342, + "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": 4183436, "tid": 31338, + "ts": 667115735725.008, "dur": 0.762, + "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": 4183436, "tid": 31338, + "ts": 667115735730.229, "dur": 4.037, + "args": { + "External id": 232752,"Record function id": 0, "Ev Idx": 2863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115735731.542, "dur": 2.273, + "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": 4183436, "tid": 31338, + "ts": 667115735732.193, "dur": 1.198, + "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": 4183436, "tid": 31338, + "ts": 667115735732.719, "dur": 0.596, + "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": 4183436, "tid": 31338, + "ts": 667115735737.339, "dur": 3.855, + "args": { + "External id": 232756,"Record function id": 0, "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115735738.372, "dur": 2.377, + "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": 4183436, "tid": 31338, + "ts": 667115735738.812, "dur": 1.540, + "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": 4183436, "tid": 31338, + "ts": 667115735739.716, "dur": 0.541, + "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": 4183436, "tid": 31338, + "ts": 667115735747.272, "dur": 3.746, + "args": { + "External id": 232760,"Record function id": 0, "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115735748.286, "dur": 2.289, + "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": 4183436, "tid": 31338, + "ts": 667115735748.836, "dur": 1.126, + "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": 4183436, "tid": 31338, + "ts": 667115735749.276, "dur": 0.608, + "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": 4183436, "tid": 31338, + "ts": 667115735754.608, "dur": 3.742, + "args": { + "External id": 232764,"Record function id": 0, "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115735755.700, "dur": 2.261, + "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": 4183436, "tid": 31338, + "ts": 667115735756.169, "dur": 1.307, + "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": 4183436, "tid": 31338, + "ts": 667115735756.816, "dur": 0.594, + "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": 4183436, "tid": 31338, + "ts": 667115735761.436, "dur": 3.709, + "args": { + "External id": 232768,"Record function id": 0, "Ev Idx": 2879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115735762.519, "dur": 2.185, + "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": 4183436, "tid": 31338, + "ts": 667115735762.954, "dur": 1.362, + "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": 4183436, "tid": 31338, + "ts": 667115735763.573, "dur": 0.668, + "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": 4183436, "tid": 31338, + "ts": 667115735768.474, "dur": 5.160, + "args": { + "External id": 232772,"Record function id": 0, "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115735769.365, "dur": 3.861, + "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": 4183436, "tid": 31338, + "ts": 667115735769.798, "dur": 3.036, + "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": 4183436, "tid": 31338, + "ts": 667115735770.146, "dur": 2.600, + "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": 4183436, "tid": 31338, + "ts": 667115735776.928, "dur": 3.443, + "args": { + "External id": 232776,"Record function id": 0, "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115735777.780, "dur": 2.173, + "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": 4183436, "tid": 31338, + "ts": 667115735778.248, "dur": 1.299, + "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": 4183436, "tid": 31338, + "ts": 667115735778.816, "dur": 0.664, + "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": 4183436, "tid": 31338, + "ts": 667115735784.179, "dur": 15074.227, + "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": 4183436, "tid": 31338, + "ts": 667115735785.727, "dur": 15063.657, + "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": 4183436, "tid": 31338, "ts": 667115735785.727, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 4183436, "tid": 31338, + "ts": 667115735819.787, "dur": 37.041, + "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": 4183436, "tid": 31338, + "ts": 667115735867.210, "dur": 67.798, + "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": 4183436, "tid": 31338, + "ts": 667115735941.715, "dur": 14899.708, + "args": { + "External id": 232784,"Record function id": 0, "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115736031.439, "dur": 6.731, + "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": 4183436, "tid": 31338, + "ts": 667115736047.499, "dur": 4.854, + "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": 4183436, "tid": 31338, + "ts": 667115736066.266, "dur": 14073.889, + "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": 4183436, "tid": 31338, + "ts": 667115736079.177, "dur": 14052.383, + "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": 4183436, "tid": 31338, + "ts": 667115736114.112, "dur": 14.346, + "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": 4183436, "tid": 31338, + "ts": 667115736133.048, "dur": 13964.826, + "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": 4183436, "tid": 31338, + "ts": 667115736135.712, "dur": 13961.460, + "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": 4183436, "tid": 31338, + "ts": 667115736139.699, "dur": 5.071, + "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": 4183436, "tid": 31338, + "ts": 667115736146.383, "dur": 13946.978, + "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": 4183436, "tid": 31338, + "ts": 667115750227.327, "dur": 8.597, + "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": 4183436, "tid": 31338, + "ts": 667115750230.065, "dur": 5.517, + "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": 4183436, "tid": 31338, + "ts": 667115750264.697, "dur": 263.008, + "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": 4183436, "tid": 31338, + "ts": 667115750290.347, "dur": 232.625, + "args": { + "External id": 232797,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115750300.956, "dur": 216.241, + "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": 4183436, "tid": 31338, + "ts": 667115750546.749, "dur": 2.085, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115750601.226, "dur": 6.046, + "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": 4183436, "tid": 31338, + "ts": 667115750689.302, "dur": 2.029, + "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": 4183436, "tid": 31338, + "ts": 667115750710.378, "dur": 1.355, + "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": 4183436, "tid": 31338, + "ts": 667115750723.266, "dur": 0.917, + "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": 4183436, "tid": 31338, + "ts": 667115750734.565, "dur": 0.934, + "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": 4183436, "tid": 31338, + "ts": 667115750746.222, "dur": 0.947, + "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": 4183436, "tid": 31338, + "ts": 667115750756.842, "dur": 0.606, + "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": 4183436, "tid": 31338, + "ts": 667115750768.448, "dur": 1.540, + "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": 4183436, "tid": 31338, + "ts": 667115750779.214, "dur": 0.830, + "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": 4183436, "tid": 31338, + "ts": 667115750872.967, "dur": 2546.384, + "args": { + "External id": 232809,"Record function id": 0, "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 4183436, "tid": 31338, + "ts": 667115750892.383, "dur": 984.577, + "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": 4183436, "tid": 31338, + "ts": 667115750906.964, "dur": 282.128, + "args": { + "External id": 232811,"Record function id": 0, "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115750980.324, "dur": 3.990, + "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": 4183436, "tid": 31338, + "ts": 667115750987.458, "dur": 0.849, + "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": 4183436, "tid": 31338, + "ts": 667115750990.684, "dur": 0.961, + "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": 4183436, "tid": 31338, + "ts": 667115750993.520, "dur": 0.492, + "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": 4183436, "tid": 31338, + "ts": 667115750995.666, "dur": 0.799, + "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": 4183436, "tid": 31338, + "ts": 667115750997.945, "dur": 0.644, + "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": 4183436, "tid": 31338, + "ts": 667115751000.745, "dur": 1.678, + "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": 4183436, "tid": 31338, + "ts": 667115751004.257, "dur": 2.792, + "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": 4183436, "tid": 31338, + "ts": 667115751008.759, "dur": 0.785, + "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": 4183436, "tid": 31338, + "ts": 667115751010.984, "dur": 0.482, + "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": 4183436, "tid": 31338, + "ts": 667115751029.770, "dur": 132.437, + "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": 4183436, "tid": 31338, + "ts": 667115751045.364, "dur": 112.891, + "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": 4183436, "tid": 31338, + "ts": 667115751056.400, "dur": 12.157, + "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": 4183436, "tid": 31338, + "ts": 667115751071.428, "dur": 60.983, + "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": 4183436, "tid": 31338, + "ts": 667115751074.029, "dur": 58.053, + "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": 4183436, "tid": 31338, + "ts": 667115751077.623, "dur": 5.030, + "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": 4183436, "tid": 31338, + "ts": 667115751084.653, "dur": 46.888, + "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": 4183436, "tid": 31338, + "ts": 667115751265.012, "dur": 600.558, + "args": { + "External id": 232829,"Record function id": 0, "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 4183436, "tid": 31338, + "ts": 667115751282.247, "dur": 569.319, + "args": { + "External id": 232830,"Record function id": 0, "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115751336.697, "dur": 4.167, + "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": 4183436, "tid": 31338, + "ts": 667115751355.877, "dur": 28.504, + "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": 4183436, "tid": 31338, + "ts": 667115751360.191, "dur": 1.469, + "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": 4183436, "tid": 31338, + "ts": 667115751363.457, "dur": 0.488, + "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": 4183436, "tid": 31338, + "ts": 667115751365.380, "dur": 2.426, + "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": 4183436, "tid": 31338, + "ts": 667115751369.350, "dur": 0.735, + "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": 4183436, "tid": 31338, + "ts": 667115751372.125, "dur": 0.456, + "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": 4183436, "tid": 31338, + "ts": 667115751374.442, "dur": 0.457, + "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": 4183436, "tid": 31338, + "ts": 667115751377.265, "dur": 0.632, + "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": 4183436, "tid": 31338, + "ts": 667115751378.711, "dur": 0.578, + "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": 4183436, "tid": 31338, + "ts": 667115751380.679, "dur": 0.377, + "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": 4183436, "tid": 31338, + "ts": 667115751393.373, "dur": 28.058, + "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": 4183436, "tid": 31338, + "ts": 667115751450.844, "dur": 124.988, + "args": { + "External id": 232843,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115751459.642, "dur": 3.158, + "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": 4183436, "tid": 31338, + "ts": 667115751467.463, "dur": 14.641, + "args": { + "External id": 232845,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115751471.515, "dur": 7.040, + "args": { + "External id": 232846,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115751474.708, "dur": 2.658, + "args": { + "External id": 232847,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115751488.531, "dur": 40.980, + "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": 4183436, "tid": 31338, + "ts": 667115751490.359, "dur": 0.386, + "args": { + "External id": 232849,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115751510.758, "dur": 0.508, + "args": { + "External id": 232850,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115751512.663, "dur": 0.277, + "args": { + "External id": 232851,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115751514.286, "dur": 0.481, + "args": { + "External id": 232852,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115751516.271, "dur": 0.519, + "args": { + "External id": 232853,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115751518.117, "dur": 0.425, + "args": { + "External id": 232854,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115751519.784, "dur": 0.430, + "args": { + "External id": 232855,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115751521.573, "dur": 2.430, + "args": { + "External id": 232856,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115751525.301, "dur": 0.610, + "args": { + "External id": 232857,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115751547.291, "dur": 21.375, + "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": 4183436, "tid": 31338, + "ts": 667115751620.196, "dur": 155.082, + "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": 4183436, "tid": 31338, + "ts": 667115751644.233, "dur": 127.262, + "args": { + "External id": 232860,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115751689.256, "dur": 77.431, + "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": 4183436, "tid": 31338, + "ts": 667115751791.974, "dur": 1.817, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115751884.019, "dur": 1512.115, + "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": 4183436, "tid": 31338, "ts": 667115751884.019, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115751996.293, "dur": 98.389, + "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": 4183436, "tid": 31338, + "ts": 667115752130.828, "dur": 35.959, + "args": { + "External id": 232865,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115752184.069, "dur": 40.059, + "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": 4183436, "tid": 31338, + "ts": 667115752232.364, "dur": 24.323, + "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": 4183436, "tid": 31338, + "ts": 667115752262.520, "dur": 31.643, + "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": 4183436, "tid": 31338, + "ts": 667115752300.737, "dur": 21.767, + "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": 4183436, "tid": 31338, + "ts": 667115752330.915, "dur": 28.626, + "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": 4183436, "tid": 31338, + "ts": 667115752381.696, "dur": 23.009, + "args": { + "External id": 232871,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115752422.943, "dur": 29.415, + "args": { + "External id": 232872,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115752469.233, "dur": 18.941, + "args": { + "External id": 232873,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115752524.823, "dur": 17.599, + "args": { + "External id": 232874,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115752553.090, "dur": 39.383, + "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": 4183436, "tid": 31338, + "ts": 667115752596.183, "dur": 29.399, + "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": 4183436, "tid": 31338, + "ts": 667115752688.398, "dur": 171.706, + "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": 4183436, "tid": 31338, + "ts": 667115752766.302, "dur": 6.782, + "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": 4183436, "tid": 31338, + "ts": 667115752775.096, "dur": 4.445, + "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": 4183436, "tid": 31338, + "ts": 667115752894.556, "dur": 25.545, + "args": { + "External id": 232880,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115752931.313, "dur": 16.667, + "args": { + "External id": 232881,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115752956.720, "dur": 46.852, + "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": 4183436, "tid": 31338, + "ts": 667115753008.682, "dur": 30.388, + "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": 4183436, "tid": 31338, + "ts": 667115753045.029, "dur": 29.239, + "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": 4183436, "tid": 31338, + "ts": 667115753078.807, "dur": 27.854, + "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": 4183436, "tid": 31338, + "ts": 667115753114.003, "dur": 29.179, + "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": 4183436, "tid": 31338, + "ts": 667115753148.809, "dur": 29.879, + "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": 4183436, "tid": 31338, + "ts": 667115753196.117, "dur": 22.234, + "args": { + "External id": 232888,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115753252.320, "dur": 29.092, + "args": { + "External id": 232889,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115753295.442, "dur": 15.237, + "args": { + "External id": 232890,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115753325.083, "dur": 11.474, + "args": { + "External id": 232891,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115753352.203, "dur": 14.862, + "args": { + "External id": 232892,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115753441.388, "dur": 14.114, + "args": { + "External id": 232893,"Record function id": 0, "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115753444.554, "dur": 10.040, + "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": 4183436, "tid": 31338, + "ts": 667115753448.423, "dur": 5.440, + "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": 4183436, "tid": 31338, + "ts": 667115753449.734, "dur": 4.029, + "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": 4183436, "tid": 31338, + "ts": 667115753459.465, "dur": 7.401, + "args": { + "External id": 232897,"Record function id": 0, "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115753464.216, "dur": 2.173, + "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": 4183436, "tid": 31338, + "ts": 667115753464.803, "dur": 1.154, + "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": 4183436, "tid": 31338, + "ts": 667115753465.149, "dur": 0.707, + "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": 4183436, "tid": 31338, + "ts": 667115753470.151, "dur": 3.778, + "args": { + "External id": 232901,"Record function id": 0, "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115753471.282, "dur": 2.195, + "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": 4183436, "tid": 31338, + "ts": 667115753471.910, "dur": 1.139, + "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": 4183436, "tid": 31338, + "ts": 667115753472.301, "dur": 0.625, + "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": 4183436, "tid": 31338, + "ts": 667115753477.062, "dur": 3.551, + "args": { + "External id": 232905,"Record function id": 0, "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115753478.102, "dur": 2.067, + "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": 4183436, "tid": 31338, + "ts": 667115753478.616, "dur": 1.123, + "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": 4183436, "tid": 31338, + "ts": 667115753479.001, "dur": 0.654, + "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": 4183436, "tid": 31338, + "ts": 667115753483.690, "dur": 4.194, + "args": { + "External id": 232909,"Record function id": 0, "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115753485.000, "dur": 2.433, + "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": 4183436, "tid": 31338, + "ts": 667115753485.479, "dur": 1.517, + "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": 4183436, "tid": 31338, + "ts": 667115753486.356, "dur": 0.573, + "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": 4183436, "tid": 31338, + "ts": 667115753490.965, "dur": 24.581, + "args": { + "External id": 232913,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115753510.379, "dur": 4.488, + "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": 4183436, "tid": 31338, + "ts": 667115753511.467, "dur": 2.567, + "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": 4183436, "tid": 31338, + "ts": 667115753512.462, "dur": 1.332, + "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": 4183436, "tid": 31338, + "ts": 667115753523.320, "dur": 5.455, + "args": { + "External id": 232917,"Record function id": 0, "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115753524.659, "dur": 3.689, + "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": 4183436, "tid": 31338, + "ts": 667115753525.266, "dur": 2.664, + "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": 4183436, "tid": 31338, + "ts": 667115753525.892, "dur": 1.967, + "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": 4183436, "tid": 31338, + "ts": 667115753531.993, "dur": 4.006, + "args": { + "External id": 232921,"Record function id": 0, "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115753532.956, "dur": 2.607, + "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": 4183436, "tid": 31338, + "ts": 667115753533.447, "dur": 1.706, + "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": 4183436, "tid": 31338, + "ts": 667115753534.249, "dur": 0.831, + "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": 4183436, "tid": 31338, + "ts": 667115753539.101, "dur": 3.465, + "args": { + "External id": 232925,"Record function id": 0, "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115753540.077, "dur": 2.060, + "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": 4183436, "tid": 31338, + "ts": 667115753540.558, "dur": 1.162, + "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": 4183436, "tid": 31338, + "ts": 667115753541.031, "dur": 0.613, + "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": 4183436, "tid": 31338, + "ts": 667115753546.246, "dur": 16352.569, + "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": 4183436, "tid": 31338, + "ts": 667115753547.606, "dur": 16342.664, + "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": 4183436, "tid": 31338, "ts": 667115753547.606, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 4183436, "tid": 31338, + "ts": 667115753580.103, "dur": 39.530, + "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": 4183436, "tid": 31338, + "ts": 667115753627.206, "dur": 107.158, + "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": 4183436, "tid": 31338, + "ts": 667115753742.489, "dur": 16139.599, + "args": { + "External id": 232933,"Record function id": 0, "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115753835.621, "dur": 7.450, + "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": 4183436, "tid": 31338, + "ts": 667115753853.398, "dur": 5.056, + "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": 4183436, "tid": 31338, + "ts": 667115753873.117, "dur": 15213.123, + "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": 4183436, "tid": 31338, + "ts": 667115753905.164, "dur": 15171.551, + "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": 4183436, "tid": 31338, + "ts": 667115753946.329, "dur": 14.183, + "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": 4183436, "tid": 31338, + "ts": 667115753965.120, "dur": 15075.038, + "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": 4183436, "tid": 31338, + "ts": 667115753967.686, "dur": 15071.678, + "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": 4183436, "tid": 31338, + "ts": 667115753970.951, "dur": 4.719, + "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": 4183436, "tid": 31338, + "ts": 667115753978.202, "dur": 15057.746, + "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": 4183436, "tid": 31338, + "ts": 667115769182.462, "dur": 9.824, + "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": 4183436, "tid": 31338, + "ts": 667115769185.799, "dur": 6.080, + "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": 4183436, "tid": 31338, + "ts": 667115769220.203, "dur": 332.305, + "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": 4183436, "tid": 31338, + "ts": 667115769250.356, "dur": 297.237, + "args": { + "External id": 232946,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115769261.101, "dur": 280.845, + "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": 4183436, "tid": 31338, + "ts": 667115769572.441, "dur": 2.562, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115769631.716, "dur": 8.341, + "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": 4183436, "tid": 31338, + "ts": 667115769720.664, "dur": 2.521, + "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": 4183436, "tid": 31338, + "ts": 667115769741.452, "dur": 1.211, + "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": 4183436, "tid": 31338, + "ts": 667115769752.880, "dur": 0.935, + "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": 4183436, "tid": 31338, + "ts": 667115769765.374, "dur": 2.479, + "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": 4183436, "tid": 31338, + "ts": 667115769776.639, "dur": 0.823, + "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": 4183436, "tid": 31338, + "ts": 667115769791.342, "dur": 0.819, + "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": 4183436, "tid": 31338, + "ts": 667115769802.591, "dur": 2.080, + "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": 4183436, "tid": 31338, + "ts": 667115769813.953, "dur": 3.187, + "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": 4183436, "tid": 31338, + "ts": 667115769916.793, "dur": 2652.161, + "args": { + "External id": 232958,"Record function id": 0, "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 4183436, "tid": 31338, + "ts": 667115769936.075, "dur": 1054.008, + "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": 4183436, "tid": 31338, + "ts": 667115769951.839, "dur": 364.533, + "args": { + "External id": 232960,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115770093.404, "dur": 4.457, + "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": 4183436, "tid": 31338, + "ts": 667115770101.820, "dur": 0.868, + "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": 4183436, "tid": 31338, + "ts": 667115770104.269, "dur": 0.951, + "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": 4183436, "tid": 31338, + "ts": 667115770106.460, "dur": 0.629, + "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": 4183436, "tid": 31338, + "ts": 667115770108.318, "dur": 0.655, + "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": 4183436, "tid": 31338, + "ts": 667115770110.149, "dur": 0.687, + "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": 4183436, "tid": 31338, + "ts": 667115770112.447, "dur": 3.060, + "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": 4183436, "tid": 31338, + "ts": 667115770116.996, "dur": 0.621, + "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": 4183436, "tid": 31338, + "ts": 667115770119.026, "dur": 0.625, + "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": 4183436, "tid": 31338, + "ts": 667115770121.014, "dur": 0.663, + "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": 4183436, "tid": 31338, + "ts": 667115770140.235, "dur": 147.632, + "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": 4183436, "tid": 31338, + "ts": 667115770155.505, "dur": 128.064, + "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": 4183436, "tid": 31338, + "ts": 667115770172.715, "dur": 14.078, + "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": 4183436, "tid": 31338, + "ts": 667115770189.951, "dur": 67.009, + "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": 4183436, "tid": 31338, + "ts": 667115770192.410, "dur": 64.197, + "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": 4183436, "tid": 31338, + "ts": 667115770195.932, "dur": 6.084, + "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": 4183436, "tid": 31338, + "ts": 667115770203.793, "dur": 52.122, + "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": 4183436, "tid": 31338, + "ts": 667115770392.218, "dur": 589.920, + "args": { + "External id": 232978,"Record function id": 0, "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 4183436, "tid": 31338, + "ts": 667115770409.214, "dur": 561.046, + "args": { + "External id": 232979,"Record function id": 0, "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115770461.204, "dur": 4.341, + "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": 4183436, "tid": 31338, + "ts": 667115770480.618, "dur": 44.631, + "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": 4183436, "tid": 31338, + "ts": 667115770485.231, "dur": 1.419, + "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": 4183436, "tid": 31338, + "ts": 667115770488.313, "dur": 2.298, + "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": 4183436, "tid": 31338, + "ts": 667115770510.941, "dur": 0.513, + "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": 4183436, "tid": 31338, + "ts": 667115770513.169, "dur": 0.366, + "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": 4183436, "tid": 31338, + "ts": 667115770514.779, "dur": 0.459, + "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": 4183436, "tid": 31338, + "ts": 667115770516.673, "dur": 0.301, + "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": 4183436, "tid": 31338, + "ts": 667115770517.987, "dur": 0.589, + "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": 4183436, "tid": 31338, + "ts": 667115770519.635, "dur": 0.263, + "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": 4183436, "tid": 31338, + "ts": 667115770520.834, "dur": 0.308, + "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": 4183436, "tid": 31338, + "ts": 667115770534.922, "dur": 31.276, + "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": 4183436, "tid": 31338, + "ts": 667115770596.818, "dur": 139.034, + "args": { + "External id": 232992,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115770607.147, "dur": 6.070, + "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": 4183436, "tid": 31338, + "ts": 667115770618.274, "dur": 9.613, + "args": { + "External id": 232994,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115770622.434, "dur": 5.059, + "args": { + "External id": 232995,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115770625.623, "dur": 0.753, + "args": { + "External id": 232996,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115770634.418, "dur": 55.875, + "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": 4183436, "tid": 31338, + "ts": 667115770635.929, "dur": 0.763, + "args": { + "External id": 232998,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115770637.520, "dur": 0.396, + "args": { + "External id": 232999,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115770639.027, "dur": 0.741, + "args": { + "External id": 233000,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115770640.669, "dur": 0.768, + "args": { + "External id": 233001,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115770642.755, "dur": 0.557, + "args": { + "External id": 233002,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115770644.316, "dur": 0.743, + "args": { + "External id": 233003,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115770645.955, "dur": 2.175, + "args": { + "External id": 233004,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115770648.921, "dur": 0.409, + "args": { + "External id": 233005,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115770650.177, "dur": 0.277, + "args": { + "External id": 233006,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115770704.251, "dur": 23.958, + "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": 4183436, "tid": 31338, + "ts": 667115770786.435, "dur": 115.860, + "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": 4183436, "tid": 31338, + "ts": 667115770808.699, "dur": 89.937, + "args": { + "External id": 233009,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115770818.056, "dur": 76.575, + "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": 4183436, "tid": 31338, + "ts": 667115770915.036, "dur": 1.947, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115770997.355, "dur": 1550.924, + "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": 4183436, "tid": 31338, "ts": 667115770997.355, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115771111.787, "dur": 103.410, + "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": 4183436, "tid": 31338, + "ts": 667115771250.823, "dur": 37.337, + "args": { + "External id": 233014,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115771306.081, "dur": 40.408, + "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": 4183436, "tid": 31338, + "ts": 667115771355.525, "dur": 26.176, + "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": 4183436, "tid": 31338, + "ts": 667115771386.681, "dur": 31.865, + "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": 4183436, "tid": 31338, + "ts": 667115771426.346, "dur": 24.713, + "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": 4183436, "tid": 31338, + "ts": 667115771457.756, "dur": 28.168, + "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": 4183436, "tid": 31338, + "ts": 667115771532.915, "dur": 27.577, + "args": { + "External id": 233020,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115771577.358, "dur": 25.780, + "args": { + "External id": 233021,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115771623.196, "dur": 21.144, + "args": { + "External id": 233022,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115771695.882, "dur": 19.126, + "args": { + "External id": 233023,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115771726.165, "dur": 42.812, + "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": 4183436, "tid": 31338, + "ts": 667115771772.410, "dur": 33.319, + "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": 4183436, "tid": 31338, + "ts": 667115771831.234, "dur": 170.791, + "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": 4183436, "tid": 31338, + "ts": 667115771910.066, "dur": 5.578, + "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": 4183436, "tid": 31338, + "ts": 667115771917.586, "dur": 4.837, + "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": 4183436, "tid": 31338, + "ts": 667115772031.369, "dur": 25.072, + "args": { + "External id": 233029,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115772068.709, "dur": 14.401, + "args": { + "External id": 233030,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115772089.888, "dur": 41.972, + "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": 4183436, "tid": 31338, + "ts": 667115772137.237, "dur": 29.902, + "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": 4183436, "tid": 31338, + "ts": 667115772173.443, "dur": 27.049, + "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": 4183436, "tid": 31338, + "ts": 667115772206.076, "dur": 27.527, + "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": 4183436, "tid": 31338, + "ts": 667115772238.595, "dur": 41.032, + "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": 4183436, "tid": 31338, + "ts": 667115772292.272, "dur": 33.796, + "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": 4183436, "tid": 31338, + "ts": 667115772342.886, "dur": 25.781, + "args": { + "External id": 233037,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115772382.890, "dur": 23.606, + "args": { + "External id": 233038,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115772418.171, "dur": 19.510, + "args": { + "External id": 233039,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115772450.989, "dur": 14.565, + "args": { + "External id": 233040,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115772477.039, "dur": 38.010, + "args": { + "External id": 233041,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115772591.050, "dur": 14.778, + "args": { + "External id": 233042,"Record function id": 0, "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115772594.334, "dur": 10.508, + "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": 4183436, "tid": 31338, + "ts": 667115772598.485, "dur": 5.520, + "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": 4183436, "tid": 31338, + "ts": 667115772600.052, "dur": 3.836, + "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": 4183436, "tid": 31338, + "ts": 667115772609.724, "dur": 5.029, + "args": { + "External id": 233046,"Record function id": 0, "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115772611.326, "dur": 2.987, + "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": 4183436, "tid": 31338, + "ts": 667115772612.154, "dur": 1.717, + "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": 4183436, "tid": 31338, + "ts": 667115772612.592, "dur": 1.212, + "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": 4183436, "tid": 31338, + "ts": 667115772617.999, "dur": 3.902, + "args": { + "External id": 233050,"Record function id": 0, "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115772619.258, "dur": 2.206, + "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": 4183436, "tid": 31338, + "ts": 667115772619.737, "dur": 1.314, + "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": 4183436, "tid": 31338, + "ts": 667115772620.160, "dur": 0.814, + "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": 4183436, "tid": 31338, + "ts": 667115772625.037, "dur": 5.855, + "args": { + "External id": 233054,"Record function id": 0, "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115772626.221, "dur": 4.249, + "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": 4183436, "tid": 31338, + "ts": 667115772626.924, "dur": 3.166, + "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": 4183436, "tid": 31338, + "ts": 667115772627.362, "dur": 2.665, + "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": 4183436, "tid": 31338, + "ts": 667115772633.945, "dur": 3.443, + "args": { + "External id": 233058,"Record function id": 0, "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115772634.881, "dur": 2.074, + "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": 4183436, "tid": 31338, + "ts": 667115772635.334, "dur": 1.212, + "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": 4183436, "tid": 31338, + "ts": 667115772635.680, "dur": 0.803, + "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": 4183436, "tid": 31338, + "ts": 667115772640.496, "dur": 4.040, + "args": { + "External id": 233062,"Record function id": 0, "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115772641.765, "dur": 2.377, + "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": 4183436, "tid": 31338, + "ts": 667115772642.211, "dur": 1.515, + "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": 4183436, "tid": 31338, + "ts": 667115772642.769, "dur": 0.889, + "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": 4183436, "tid": 31338, + "ts": 667115772647.791, "dur": 40.263, + "args": { + "External id": 233066,"Record function id": 0, "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115772648.892, "dur": 37.359, + "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": 4183436, "tid": 31338, + "ts": 667115772649.438, "dur": 1.191, + "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": 4183436, "tid": 31338, + "ts": 667115772649.778, "dur": 0.788, + "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": 4183436, "tid": 31338, + "ts": 667115772693.928, "dur": 5.322, + "args": { + "External id": 233070,"Record function id": 0, "Ev Idx": 3181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115772695.429, "dur": 3.405, + "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": 4183436, "tid": 31338, + "ts": 667115772696.473, "dur": 1.910, + "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": 4183436, "tid": 31338, + "ts": 667115772697.166, "dur": 1.150, + "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": 4183436, "tid": 31338, + "ts": 667115772702.387, "dur": 3.680, + "args": { + "External id": 233074,"Record function id": 0, "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115772703.547, "dur": 2.139, + "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": 4183436, "tid": 31338, + "ts": 667115772704.029, "dur": 1.213, + "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": 4183436, "tid": 31338, + "ts": 667115772704.356, "dur": 0.823, + "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": 4183436, "tid": 31338, + "ts": 667115772709.710, "dur": 14619.625, + "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": 4183436, "tid": 31338, + "ts": 667115772710.931, "dur": 14609.913, + "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": 4183436, "tid": 31338, "ts": 667115772710.931, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 4183436, "tid": 31338, + "ts": 667115772740.572, "dur": 37.085, + "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": 4183436, "tid": 31338, + "ts": 667115772785.305, "dur": 61.838, + "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": 4183436, "tid": 31338, + "ts": 667115772853.070, "dur": 14456.360, + "args": { + "External id": 233082,"Record function id": 0, "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115772939.943, "dur": 6.886, + "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": 4183436, "tid": 31338, + "ts": 667115772956.581, "dur": 4.981, + "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": 4183436, "tid": 31338, + "ts": 667115772975.334, "dur": 13650.183, + "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": 4183436, "tid": 31338, + "ts": 667115772988.531, "dur": 13628.293, + "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": 4183436, "tid": 31338, + "ts": 667115773043.606, "dur": 15.978, + "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": 4183436, "tid": 31338, + "ts": 667115773064.338, "dur": 13517.359, + "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": 4183436, "tid": 31338, + "ts": 667115773067.289, "dur": 13513.684, + "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": 4183436, "tid": 31338, + "ts": 667115773071.132, "dur": 5.274, + "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": 4183436, "tid": 31338, + "ts": 667115773078.069, "dur": 13499.421, + "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": 4183436, "tid": 31338, + "ts": 667115786740.957, "dur": 9.094, + "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": 4183436, "tid": 31338, + "ts": 667115786743.819, "dur": 5.816, + "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": 4183436, "tid": 31338, + "ts": 667115786777.771, "dur": 262.172, + "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": 4183436, "tid": 31338, + "ts": 667115786800.842, "dur": 234.558, + "args": { + "External id": 233095,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115786811.963, "dur": 217.810, + "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": 4183436, "tid": 31338, + "ts": 667115787054.170, "dur": 2.080, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115787107.449, "dur": 5.739, + "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": 4183436, "tid": 31338, + "ts": 667115787159.371, "dur": 0.955, + "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": 4183436, "tid": 31338, + "ts": 667115787175.550, "dur": 1.439, + "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": 4183436, "tid": 31338, + "ts": 667115787189.246, "dur": 0.764, + "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": 4183436, "tid": 31338, + "ts": 667115787203.383, "dur": 0.731, + "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": 4183436, "tid": 31338, + "ts": 667115787213.603, "dur": 0.875, + "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": 4183436, "tid": 31338, + "ts": 667115787224.504, "dur": 0.754, + "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": 4183436, "tid": 31338, + "ts": 667115787237.721, "dur": 2.060, + "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": 4183436, "tid": 31338, + "ts": 667115787249.096, "dur": 0.894, + "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": 4183436, "tid": 31338, + "ts": 667115787343.185, "dur": 2587.889, + "args": { + "External id": 233107,"Record function id": 0, "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 4183436, "tid": 31338, + "ts": 667115787361.236, "dur": 956.168, + "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": 4183436, "tid": 31338, + "ts": 667115787379.203, "dur": 358.044, + "args": { + "External id": 233109,"Record function id": 0, "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115787451.931, "dur": 3.754, + "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": 4183436, "tid": 31338, + "ts": 667115787458.812, "dur": 1.046, + "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": 4183436, "tid": 31338, + "ts": 667115787461.736, "dur": 1.004, + "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": 4183436, "tid": 31338, + "ts": 667115787464.591, "dur": 2.845, + "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": 4183436, "tid": 31338, + "ts": 667115787469.019, "dur": 1.125, + "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": 4183436, "tid": 31338, + "ts": 667115787471.558, "dur": 0.646, + "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": 4183436, "tid": 31338, + "ts": 667115787473.893, "dur": 1.553, + "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": 4183436, "tid": 31338, + "ts": 667115787477.040, "dur": 0.634, + "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": 4183436, "tid": 31338, + "ts": 667115787479.420, "dur": 0.469, + "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": 4183436, "tid": 31338, + "ts": 667115787481.596, "dur": 0.795, + "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": 4183436, "tid": 31338, + "ts": 667115787522.239, "dur": 183.662, + "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": 4183436, "tid": 31338, + "ts": 667115787538.354, "dur": 162.426, + "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": 4183436, "tid": 31338, + "ts": 667115787553.604, "dur": 12.082, + "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": 4183436, "tid": 31338, + "ts": 667115787568.588, "dur": 63.855, + "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": 4183436, "tid": 31338, + "ts": 667115787570.959, "dur": 61.178, + "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": 4183436, "tid": 31338, + "ts": 667115787575.127, "dur": 6.759, + "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": 4183436, "tid": 31338, + "ts": 667115787583.526, "dur": 47.916, + "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": 4183436, "tid": 31338, + "ts": 667115787816.155, "dur": 493.460, + "args": { + "External id": 233127,"Record function id": 0, "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 4183436, "tid": 31338, + "ts": 667115787833.595, "dur": 464.598, + "args": { + "External id": 233128,"Record function id": 0, "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115787887.843, "dur": 5.168, + "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": 4183436, "tid": 31338, + "ts": 667115787908.526, "dur": 28.818, + "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": 4183436, "tid": 31338, + "ts": 667115787913.583, "dur": 1.333, + "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": 4183436, "tid": 31338, + "ts": 667115787916.728, "dur": 0.318, + "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": 4183436, "tid": 31338, + "ts": 667115787918.540, "dur": 3.611, + "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": 4183436, "tid": 31338, + "ts": 667115787923.560, "dur": 0.560, + "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": 4183436, "tid": 31338, + "ts": 667115787925.460, "dur": 0.200, + "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": 4183436, "tid": 31338, + "ts": 667115787926.983, "dur": 0.324, + "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": 4183436, "tid": 31338, + "ts": 667115787928.522, "dur": 1.283, + "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": 4183436, "tid": 31338, + "ts": 667115787930.518, "dur": 0.826, + "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": 4183436, "tid": 31338, + "ts": 667115787933.072, "dur": 0.394, + "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": 4183436, "tid": 31338, + "ts": 667115787946.222, "dur": 28.379, + "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": 4183436, "tid": 31338, + "ts": 667115788007.166, "dur": 82.678, + "args": { + "External id": 233141,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115788016.981, "dur": 2.966, + "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": 4183436, "tid": 31338, + "ts": 667115788024.817, "dur": 9.091, + "args": { + "External id": 233143,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115788028.582, "dur": 4.946, + "args": { + "External id": 233144,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115788031.875, "dur": 0.587, + "args": { + "External id": 233145,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115788039.955, "dur": 17.213, + "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": 4183436, "tid": 31338, + "ts": 667115788041.843, "dur": 0.635, + "args": { + "External id": 233147,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115788044.152, "dur": 0.516, + "args": { + "External id": 233148,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115788045.757, "dur": 0.342, + "args": { + "External id": 233149,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115788046.987, "dur": 1.132, + "args": { + "External id": 233150,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115788049.061, "dur": 0.236, + "args": { + "External id": 233151,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115788050.301, "dur": 0.183, + "args": { + "External id": 233152,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115788051.368, "dur": 0.243, + "args": { + "External id": 233153,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115788052.432, "dur": 0.347, + "args": { + "External id": 233154,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115788053.781, "dur": 0.387, + "args": { + "External id": 233155,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115788066.659, "dur": 16.606, + "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": 4183436, "tid": 31338, + "ts": 667115788131.052, "dur": 105.515, + "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": 4183436, "tid": 31338, + "ts": 667115788153.249, "dur": 79.985, + "args": { + "External id": 233158,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115788162.327, "dur": 66.875, + "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": 4183436, "tid": 31338, + "ts": 667115788249.914, "dur": 2.010, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115788324.726, "dur": 1586.049, + "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": 4183436, "tid": 31338, "ts": 667115788324.726, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115788432.830, "dur": 125.391, + "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": 4183436, "tid": 31338, + "ts": 667115788599.941, "dur": 36.831, + "args": { + "External id": 233163,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115788690.980, "dur": 50.792, + "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": 4183436, "tid": 31338, + "ts": 667115788753.256, "dur": 28.014, + "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": 4183436, "tid": 31338, + "ts": 667115788788.772, "dur": 35.696, + "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": 4183436, "tid": 31338, + "ts": 667115788834.144, "dur": 20.216, + "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": 4183436, "tid": 31338, + "ts": 667115788860.607, "dur": 30.005, + "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": 4183436, "tid": 31338, + "ts": 667115788913.471, "dur": 20.498, + "args": { + "External id": 233169,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115788952.876, "dur": 24.330, + "args": { + "External id": 233170,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115788992.486, "dur": 23.195, + "args": { + "External id": 233171,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115789026.945, "dur": 13.213, + "args": { + "External id": 233172,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115789048.698, "dur": 37.035, + "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": 4183436, "tid": 31338, + "ts": 667115789088.760, "dur": 29.442, + "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": 4183436, "tid": 31338, + "ts": 667115789147.182, "dur": 170.527, + "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": 4183436, "tid": 31338, + "ts": 667115789223.007, "dur": 6.038, + "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": 4183436, "tid": 31338, + "ts": 667115789230.918, "dur": 3.763, + "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": 4183436, "tid": 31338, + "ts": 667115789344.370, "dur": 26.670, + "args": { + "External id": 233178,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115789381.547, "dur": 14.228, + "args": { + "External id": 233179,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115789402.431, "dur": 39.893, + "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": 4183436, "tid": 31338, + "ts": 667115789447.266, "dur": 30.013, + "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": 4183436, "tid": 31338, + "ts": 667115789482.314, "dur": 50.141, + "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": 4183436, "tid": 31338, + "ts": 667115789540.749, "dur": 29.776, + "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": 4183436, "tid": 31338, + "ts": 667115789576.189, "dur": 29.403, + "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": 4183436, "tid": 31338, + "ts": 667115789611.739, "dur": 27.655, + "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": 4183436, "tid": 31338, + "ts": 667115789705.080, "dur": 24.353, + "args": { + "External id": 233186,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115789756.975, "dur": 30.842, + "args": { + "External id": 233187,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115789806.457, "dur": 15.867, + "args": { + "External id": 233188,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115789838.557, "dur": 13.506, + "args": { + "External id": 233189,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115789865.413, "dur": 14.049, + "args": { + "External id": 233190,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115789956.539, "dur": 15.020, + "args": { + "External id": 233191,"Record function id": 0, "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115789959.762, "dur": 10.866, + "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": 4183436, "tid": 31338, + "ts": 667115789963.808, "dur": 5.893, + "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": 4183436, "tid": 31338, + "ts": 667115789965.423, "dur": 4.189, + "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": 4183436, "tid": 31338, + "ts": 667115789975.412, "dur": 4.773, + "args": { + "External id": 233195,"Record function id": 0, "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115789976.728, "dur": 2.974, + "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": 4183436, "tid": 31338, + "ts": 667115789977.858, "dur": 1.387, + "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": 4183436, "tid": 31338, + "ts": 667115789978.426, "dur": 0.744, + "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": 4183436, "tid": 31338, + "ts": 667115789983.451, "dur": 4.334, + "args": { + "External id": 233199,"Record function id": 0, "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115789984.739, "dur": 2.622, + "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": 4183436, "tid": 31338, + "ts": 667115789985.256, "dur": 1.667, + "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": 4183436, "tid": 31338, + "ts": 667115789985.853, "dur": 0.980, + "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": 4183436, "tid": 31338, + "ts": 667115789990.962, "dur": 3.682, + "args": { + "External id": 233203,"Record function id": 0, "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115789992.116, "dur": 2.089, + "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": 4183436, "tid": 31338, + "ts": 667115789992.619, "dur": 1.156, + "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": 4183436, "tid": 31338, + "ts": 667115789993.239, "dur": 0.460, + "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": 4183436, "tid": 31338, + "ts": 667115789997.769, "dur": 5.327, + "args": { + "External id": 233207,"Record function id": 0, "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115789998.934, "dur": 3.713, + "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": 4183436, "tid": 31338, + "ts": 667115789999.550, "dur": 2.650, + "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": 4183436, "tid": 31338, + "ts": 667115790000.065, "dur": 2.034, + "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": 4183436, "tid": 31338, + "ts": 667115790006.231, "dur": 3.681, + "args": { + "External id": 233211,"Record function id": 0, "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115790007.493, "dur": 1.998, + "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": 4183436, "tid": 31338, + "ts": 667115790007.960, "dur": 1.127, + "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": 4183436, "tid": 31338, + "ts": 667115790008.276, "dur": 0.745, + "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": 4183436, "tid": 31338, + "ts": 667115790016.166, "dur": 3.841, + "args": { + "External id": 233215,"Record function id": 0, "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115790017.296, "dur": 2.262, + "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": 4183436, "tid": 31338, + "ts": 667115790017.845, "dur": 1.314, + "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": 4183436, "tid": 31338, + "ts": 667115790018.516, "dur": 0.577, + "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": 4183436, "tid": 31338, + "ts": 667115790023.215, "dur": 3.759, + "args": { + "External id": 233219,"Record function id": 0, "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115790024.372, "dur": 2.206, + "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": 4183436, "tid": 31338, + "ts": 667115790024.853, "dur": 1.306, + "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": 4183436, "tid": 31338, + "ts": 667115790025.273, "dur": 0.814, + "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": 4183436, "tid": 31338, + "ts": 667115790030.125, "dur": 4.199, + "args": { + "External id": 233223,"Record function id": 0, "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115790031.542, "dur": 2.331, + "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": 4183436, "tid": 31338, + "ts": 667115790032.009, "dur": 1.442, + "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": 4183436, "tid": 31338, + "ts": 667115790032.586, "dur": 0.790, + "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": 4183436, "tid": 31338, + "ts": 667115790037.859, "dur": 14736.659, + "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": 4183436, "tid": 31338, + "ts": 667115790039.007, "dur": 14726.567, + "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": 4183436, "tid": 31338, "ts": 667115790039.007, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 4183436, "tid": 31338, + "ts": 667115790066.837, "dur": 41.141, + "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": 4183436, "tid": 31338, + "ts": 667115790116.191, "dur": 63.553, + "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": 4183436, "tid": 31338, + "ts": 667115790186.282, "dur": 14570.657, + "args": { + "External id": 233231,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115790273.720, "dur": 5.976, + "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": 4183436, "tid": 31338, + "ts": 667115790288.872, "dur": 4.831, + "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": 4183436, "tid": 31338, + "ts": 667115790307.988, "dur": 13740.851, + "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": 4183436, "tid": 31338, + "ts": 667115790320.671, "dur": 13720.194, + "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": 4183436, "tid": 31338, + "ts": 667115790342.158, "dur": 13.509, + "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": 4183436, "tid": 31338, + "ts": 667115790360.377, "dur": 13647.203, + "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": 4183436, "tid": 31338, + "ts": 667115790363.159, "dur": 13643.729, + "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": 4183436, "tid": 31338, + "ts": 667115790367.178, "dur": 5.474, + "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": 4183436, "tid": 31338, + "ts": 667115790374.605, "dur": 13628.549, + "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": 4183436, "tid": 31338, + "ts": 667115804136.738, "dur": 9.103, + "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": 4183436, "tid": 31338, + "ts": 667115804139.546, "dur": 5.914, + "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": 4183436, "tid": 31338, + "ts": 667115804175.082, "dur": 258.661, + "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": 4183436, "tid": 31338, + "ts": 667115804200.222, "dur": 229.431, + "args": { + "External id": 233244,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115804211.132, "dur": 213.888, + "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": 4183436, "tid": 31338, + "ts": 667115804450.317, "dur": 2.047, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115804521.557, "dur": 6.250, + "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": 4183436, "tid": 31338, + "ts": 667115804569.826, "dur": 1.522, + "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": 4183436, "tid": 31338, + "ts": 667115804586.850, "dur": 1.175, + "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": 4183436, "tid": 31338, + "ts": 667115804599.349, "dur": 2.130, + "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": 4183436, "tid": 31338, + "ts": 667115804611.616, "dur": 0.939, + "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": 4183436, "tid": 31338, + "ts": 667115804621.891, "dur": 0.926, + "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": 4183436, "tid": 31338, + "ts": 667115804632.817, "dur": 0.705, + "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": 4183436, "tid": 31338, + "ts": 667115804643.441, "dur": 2.952, + "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": 4183436, "tid": 31338, + "ts": 667115804692.347, "dur": 1.491, + "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": 4183436, "tid": 31338, + "ts": 667115804790.186, "dur": 2506.312, + "args": { + "External id": 233256,"Record function id": 0, "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 4183436, "tid": 31338, + "ts": 667115804809.792, "dur": 936.060, + "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": 4183436, "tid": 31338, + "ts": 667115804823.837, "dur": 282.973, + "args": { + "External id": 233258,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115804899.568, "dur": 4.024, + "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": 4183436, "tid": 31338, + "ts": 667115804906.472, "dur": 1.146, + "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": 4183436, "tid": 31338, + "ts": 667115804909.225, "dur": 0.837, + "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": 4183436, "tid": 31338, + "ts": 667115804911.479, "dur": 0.686, + "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": 4183436, "tid": 31338, + "ts": 667115804913.568, "dur": 1.814, + "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": 4183436, "tid": 31338, + "ts": 667115804916.996, "dur": 0.733, + "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": 4183436, "tid": 31338, + "ts": 667115804919.060, "dur": 1.491, + "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": 4183436, "tid": 31338, + "ts": 667115804921.909, "dur": 0.713, + "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": 4183436, "tid": 31338, + "ts": 667115804924.002, "dur": 0.841, + "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": 4183436, "tid": 31338, + "ts": 667115804926.616, "dur": 0.544, + "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": 4183436, "tid": 31338, + "ts": 667115804944.806, "dur": 135.964, + "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": 4183436, "tid": 31338, + "ts": 667115804960.013, "dur": 116.297, + "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": 4183436, "tid": 31338, + "ts": 667115804971.952, "dur": 13.430, + "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": 4183436, "tid": 31338, + "ts": 667115804988.115, "dur": 62.510, + "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": 4183436, "tid": 31338, + "ts": 667115804991.151, "dur": 59.127, + "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": 4183436, "tid": 31338, + "ts": 667115804995.031, "dur": 5.686, + "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": 4183436, "tid": 31338, + "ts": 667115805002.440, "dur": 47.083, + "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": 4183436, "tid": 31338, + "ts": 667115805178.707, "dur": 559.289, + "args": { + "External id": 233276,"Record function id": 0, "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 4183436, "tid": 31338, + "ts": 667115805194.972, "dur": 529.716, + "args": { + "External id": 233277,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115805245.522, "dur": 5.818, + "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": 4183436, "tid": 31338, + "ts": 667115805266.859, "dur": 26.882, + "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": 4183436, "tid": 31338, + "ts": 667115805271.508, "dur": 1.567, + "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": 4183436, "tid": 31338, + "ts": 667115805274.492, "dur": 0.993, + "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": 4183436, "tid": 31338, + "ts": 667115805276.983, "dur": 0.829, + "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": 4183436, "tid": 31338, + "ts": 667115805279.194, "dur": 0.566, + "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": 4183436, "tid": 31338, + "ts": 667115805281.342, "dur": 0.598, + "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": 4183436, "tid": 31338, + "ts": 667115805283.587, "dur": 0.765, + "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": 4183436, "tid": 31338, + "ts": 667115805285.769, "dur": 0.164, + "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": 4183436, "tid": 31338, + "ts": 667115805287.307, "dur": 1.627, + "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": 4183436, "tid": 31338, + "ts": 667115805289.856, "dur": 0.428, + "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": 4183436, "tid": 31338, + "ts": 667115805303.191, "dur": 27.212, + "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": 4183436, "tid": 31338, + "ts": 667115805361.063, "dur": 85.412, + "args": { + "External id": 233290,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115805370.211, "dur": 2.937, + "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": 4183436, "tid": 31338, + "ts": 667115805377.755, "dur": 9.452, + "args": { + "External id": 233292,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115805381.627, "dur": 5.168, + "args": { + "External id": 233293,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115805385.099, "dur": 0.551, + "args": { + "External id": 233294,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115805393.597, "dur": 19.748, + "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": 4183436, "tid": 31338, + "ts": 667115805395.311, "dur": 0.505, + "args": { + "External id": 233296,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115805397.155, "dur": 0.497, + "args": { + "External id": 233297,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115805399.079, "dur": 0.569, + "args": { + "External id": 233298,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115805400.489, "dur": 0.397, + "args": { + "External id": 233299,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115805402.203, "dur": 1.733, + "args": { + "External id": 233300,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115805404.777, "dur": 0.420, + "args": { + "External id": 233301,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115805406.149, "dur": 0.493, + "args": { + "External id": 233302,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115805408.003, "dur": 0.503, + "args": { + "External id": 233303,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115805409.502, "dur": 0.333, + "args": { + "External id": 233304,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115805422.376, "dur": 17.049, + "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": 4183436, "tid": 31338, + "ts": 667115805487.591, "dur": 131.644, + "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": 4183436, "tid": 31338, + "ts": 667115805530.891, "dur": 84.808, + "args": { + "External id": 233307,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115805540.321, "dur": 71.136, + "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": 4183436, "tid": 31338, + "ts": 667115805632.073, "dur": 1.683, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115805753.108, "dur": 1524.017, + "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": 4183436, "tid": 31338, "ts": 667115805753.108, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115805860.619, "dur": 108.492, + "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": 4183436, "tid": 31338, + "ts": 667115806007.833, "dur": 35.818, + "args": { + "External id": 233312,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115806059.102, "dur": 41.073, + "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": 4183436, "tid": 31338, + "ts": 667115806108.903, "dur": 26.721, + "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": 4183436, "tid": 31338, + "ts": 667115806141.034, "dur": 32.937, + "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": 4183436, "tid": 31338, + "ts": 667115806181.329, "dur": 21.924, + "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": 4183436, "tid": 31338, + "ts": 667115806209.398, "dur": 27.810, + "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": 4183436, "tid": 31338, + "ts": 667115806257.322, "dur": 23.078, + "args": { + "External id": 233318,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115806296.321, "dur": 25.257, + "args": { + "External id": 233319,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115806337.387, "dur": 19.106, + "args": { + "External id": 233320,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115806367.544, "dur": 15.583, + "args": { + "External id": 233321,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115806391.366, "dur": 35.791, + "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": 4183436, "tid": 31338, + "ts": 667115806430.337, "dur": 29.616, + "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": 4183436, "tid": 31338, + "ts": 667115806485.845, "dur": 225.223, + "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": 4183436, "tid": 31338, + "ts": 667115806580.049, "dur": 6.485, + "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": 4183436, "tid": 31338, + "ts": 667115806588.420, "dur": 2.896, + "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": 4183436, "tid": 31338, + "ts": 667115806743.219, "dur": 27.816, + "args": { + "External id": 233327,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115806784.731, "dur": 14.533, + "args": { + "External id": 233328,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115806807.702, "dur": 56.281, + "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": 4183436, "tid": 31338, + "ts": 667115806871.077, "dur": 35.112, + "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": 4183436, "tid": 31338, + "ts": 667115806911.621, "dur": 27.350, + "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": 4183436, "tid": 31338, + "ts": 667115806943.604, "dur": 31.560, + "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": 4183436, "tid": 31338, + "ts": 667115806980.822, "dur": 25.967, + "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": 4183436, "tid": 31338, + "ts": 667115807017.671, "dur": 28.151, + "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": 4183436, "tid": 31338, + "ts": 667115807062.454, "dur": 26.438, + "args": { + "External id": 233335,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115807105.522, "dur": 44.051, + "args": { + "External id": 233336,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115807169.731, "dur": 20.277, + "args": { + "External id": 233337,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115807204.474, "dur": 15.515, + "args": { + "External id": 233338,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115807231.391, "dur": 19.598, + "args": { + "External id": 233339,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115807321.380, "dur": 13.659, + "args": { + "External id": 233340,"Record function id": 0, "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115807324.163, "dur": 9.863, + "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": 4183436, "tid": 31338, + "ts": 667115807328.044, "dur": 5.063, + "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": 4183436, "tid": 31338, + "ts": 667115807329.289, "dur": 3.738, + "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": 4183436, "tid": 31338, + "ts": 667115807338.989, "dur": 4.168, + "args": { + "External id": 233344,"Record function id": 0, "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115807340.132, "dur": 2.582, + "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": 4183436, "tid": 31338, + "ts": 667115807341.012, "dur": 1.227, + "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": 4183436, "tid": 31338, + "ts": 667115807341.525, "dur": 0.647, + "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": 4183436, "tid": 31338, + "ts": 667115807346.345, "dur": 5.636, + "args": { + "External id": 233348,"Record function id": 0, "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115807347.519, "dur": 4.029, + "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": 4183436, "tid": 31338, + "ts": 667115807348.069, "dur": 3.029, + "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": 4183436, "tid": 31338, + "ts": 667115807348.530, "dur": 2.487, + "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": 4183436, "tid": 31338, + "ts": 667115807355.114, "dur": 7.617, + "args": { + "External id": 233352,"Record function id": 0, "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115807356.569, "dur": 5.714, + "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": 4183436, "tid": 31338, + "ts": 667115807357.118, "dur": 4.735, + "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": 4183436, "tid": 31338, + "ts": 667115807360.931, "dur": 0.838, + "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": 4183436, "tid": 31338, + "ts": 667115807365.844, "dur": 4.280, + "args": { + "External id": 233356,"Record function id": 0, "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115807367.181, "dur": 2.502, + "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": 4183436, "tid": 31338, + "ts": 667115807367.870, "dur": 1.378, + "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": 4183436, "tid": 31338, + "ts": 667115807368.379, "dur": 0.793, + "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": 4183436, "tid": 31338, + "ts": 667115807373.165, "dur": 4.764, + "args": { + "External id": 233360,"Record function id": 0, "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115807374.522, "dur": 2.979, + "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": 4183436, "tid": 31338, + "ts": 667115807375.317, "dur": 1.681, + "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": 4183436, "tid": 31338, + "ts": 667115807376.151, "dur": 0.773, + "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": 4183436, "tid": 31338, + "ts": 667115807381.103, "dur": 3.654, + "args": { + "External id": 233364,"Record function id": 0, "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115807382.043, "dur": 2.318, + "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": 4183436, "tid": 31338, + "ts": 667115807382.521, "dur": 1.401, + "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": 4183436, "tid": 31338, + "ts": 667115807383.272, "dur": 0.575, + "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": 4183436, "tid": 31338, + "ts": 667115807387.820, "dur": 3.902, + "args": { + "External id": 233368,"Record function id": 0, "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115807389.187, "dur": 2.132, + "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": 4183436, "tid": 31338, + "ts": 667115807389.646, "dur": 1.252, + "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": 4183436, "tid": 31338, + "ts": 667115807390.303, "dur": 0.528, + "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": 4183436, "tid": 31338, + "ts": 667115807394.742, "dur": 3.454, + "args": { + "External id": 233372,"Record function id": 0, "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115807395.701, "dur": 2.095, + "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": 4183436, "tid": 31338, + "ts": 667115807396.176, "dur": 1.223, + "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": 4183436, "tid": 31338, + "ts": 667115807396.712, "dur": 0.619, + "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": 4183436, "tid": 31338, + "ts": 667115807401.652, "dur": 15111.863, + "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": 4183436, "tid": 31338, + "ts": 667115807403.089, "dur": 15081.997, + "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": 4183436, "tid": 31338, "ts": 667115807403.089, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 4183436, "tid": 31338, + "ts": 667115807432.858, "dur": 35.365, + "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": 4183436, "tid": 31338, + "ts": 667115807478.786, "dur": 85.891, + "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": 4183436, "tid": 31338, + "ts": 667115807572.160, "dur": 14906.113, + "args": { + "External id": 233380,"Record function id": 0, "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115807698.256, "dur": 8.451, + "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": 4183436, "tid": 31338, + "ts": 667115807718.215, "dur": 6.861, + "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": 4183436, "tid": 31338, + "ts": 667115807740.242, "dur": 14049.532, + "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": 4183436, "tid": 31338, + "ts": 667115807753.626, "dur": 14028.060, + "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": 4183436, "tid": 31338, + "ts": 667115807775.767, "dur": 14.233, + "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": 4183436, "tid": 31338, + "ts": 667115807794.804, "dur": 13949.569, + "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": 4183436, "tid": 31338, + "ts": 667115807797.471, "dur": 13946.119, + "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": 4183436, "tid": 31338, + "ts": 667115807801.671, "dur": 4.833, + "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": 4183436, "tid": 31338, + "ts": 667115807808.318, "dur": 13931.955, + "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": 4183436, "tid": 31338, + "ts": 667115821876.640, "dur": 9.004, + "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": 4183436, "tid": 31338, + "ts": 667115821879.530, "dur": 5.757, + "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": 4183436, "tid": 31338, + "ts": 667115821915.239, "dur": 301.775, + "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": 4183436, "tid": 31338, + "ts": 667115821940.339, "dur": 272.386, + "args": { + "External id": 233393,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115821951.028, "dur": 256.833, + "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": 4183436, "tid": 31338, + "ts": 667115822233.646, "dur": 2.269, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115822285.950, "dur": 6.127, + "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": 4183436, "tid": 31338, + "ts": 667115822335.593, "dur": 1.151, + "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": 4183436, "tid": 31338, + "ts": 667115822352.341, "dur": 1.341, + "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": 4183436, "tid": 31338, + "ts": 667115822363.625, "dur": 2.486, + "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": 4183436, "tid": 31338, + "ts": 667115822375.897, "dur": 0.934, + "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": 4183436, "tid": 31338, + "ts": 667115822385.767, "dur": 1.132, + "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": 4183436, "tid": 31338, + "ts": 667115822396.663, "dur": 0.679, + "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": 4183436, "tid": 31338, + "ts": 667115822408.436, "dur": 3.326, + "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": 4183436, "tid": 31338, + "ts": 667115822421.248, "dur": 0.607, + "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": 4183436, "tid": 31338, + "ts": 667115822529.997, "dur": 2672.660, + "args": { + "External id": 233405,"Record function id": 0, "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 4183436, "tid": 31338, + "ts": 667115822550.906, "dur": 918.847, + "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": 4183436, "tid": 31338, + "ts": 667115822564.464, "dur": 329.426, + "args": { + "External id": 233407,"Record function id": 0, "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115822638.579, "dur": 4.612, + "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": 4183436, "tid": 31338, + "ts": 667115822646.175, "dur": 0.999, + "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": 4183436, "tid": 31338, + "ts": 667115822649.075, "dur": 1.187, + "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": 4183436, "tid": 31338, + "ts": 667115822687.950, "dur": 1.330, + "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": 4183436, "tid": 31338, + "ts": 667115822692.168, "dur": 2.274, + "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": 4183436, "tid": 31338, + "ts": 667115822695.919, "dur": 0.792, + "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": 4183436, "tid": 31338, + "ts": 667115822698.461, "dur": 1.775, + "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": 4183436, "tid": 31338, + "ts": 667115822701.918, "dur": 1.075, + "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": 4183436, "tid": 31338, + "ts": 667115822705.041, "dur": 0.723, + "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": 4183436, "tid": 31338, + "ts": 667115822707.669, "dur": 0.797, + "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": 4183436, "tid": 31338, + "ts": 667115822728.166, "dur": 136.628, + "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": 4183436, "tid": 31338, + "ts": 667115822744.001, "dur": 116.554, + "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": 4183436, "tid": 31338, + "ts": 667115822756.304, "dur": 12.678, + "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": 4183436, "tid": 31338, + "ts": 667115822772.226, "dur": 61.653, + "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": 4183436, "tid": 31338, + "ts": 667115822775.056, "dur": 58.389, + "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": 4183436, "tid": 31338, + "ts": 667115822778.909, "dur": 6.009, + "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": 4183436, "tid": 31338, + "ts": 667115822786.781, "dur": 46.056, + "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": 4183436, "tid": 31338, + "ts": 667115822969.828, "dur": 492.432, + "args": { + "External id": 233425,"Record function id": 0, "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 4183436, "tid": 31338, + "ts": 667115822986.652, "dur": 464.502, + "args": { + "External id": 233426,"Record function id": 0, "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115823038.798, "dur": 6.792, + "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": 4183436, "tid": 31338, + "ts": 667115823060.674, "dur": 26.053, + "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": 4183436, "tid": 31338, + "ts": 667115823065.473, "dur": 1.604, + "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": 4183436, "tid": 31338, + "ts": 667115823069.162, "dur": 0.426, + "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": 4183436, "tid": 31338, + "ts": 667115823071.018, "dur": 0.509, + "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": 4183436, "tid": 31338, + "ts": 667115823072.998, "dur": 0.186, + "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": 4183436, "tid": 31338, + "ts": 667115823074.553, "dur": 0.478, + "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": 4183436, "tid": 31338, + "ts": 667115823076.305, "dur": 0.325, + "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": 4183436, "tid": 31338, + "ts": 667115823077.678, "dur": 0.370, + "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": 4183436, "tid": 31338, + "ts": 667115823079.084, "dur": 2.518, + "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": 4183436, "tid": 31338, + "ts": 667115823082.862, "dur": 0.410, + "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": 4183436, "tid": 31338, + "ts": 667115823096.248, "dur": 26.803, + "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": 4183436, "tid": 31338, + "ts": 667115823152.425, "dur": 91.352, + "args": { + "External id": 233439,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115823161.748, "dur": 3.271, + "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": 4183436, "tid": 31338, + "ts": 667115823170.491, "dur": 9.212, + "args": { + "External id": 233441,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115823174.627, "dur": 4.688, + "args": { + "External id": 233442,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115823177.743, "dur": 0.390, + "args": { + "External id": 233443,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115823187.520, "dur": 20.833, + "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": 4183436, "tid": 31338, + "ts": 667115823189.218, "dur": 0.438, + "args": { + "External id": 233445,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115823191.566, "dur": 0.386, + "args": { + "External id": 233446,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115823193.147, "dur": 0.485, + "args": { + "External id": 233447,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115823194.646, "dur": 0.380, + "args": { + "External id": 233448,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115823196.066, "dur": 2.560, + "args": { + "External id": 233449,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115823199.879, "dur": 0.613, + "args": { + "External id": 233450,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115823201.422, "dur": 0.535, + "args": { + "External id": 233451,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115823203.246, "dur": 0.640, + "args": { + "External id": 233452,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115823204.899, "dur": 0.280, + "args": { + "External id": 233453,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115823217.736, "dur": 19.138, + "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": 4183436, "tid": 31338, + "ts": 667115823286.156, "dur": 105.259, + "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": 4183436, "tid": 31338, + "ts": 667115823308.161, "dur": 79.903, + "args": { + "External id": 233456,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115823316.854, "dur": 66.845, + "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": 4183436, "tid": 31338, + "ts": 667115823404.990, "dur": 1.647, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115823476.489, "dur": 1706.734, + "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": 4183436, "tid": 31338, "ts": 667115823476.489, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115823604.527, "dur": 149.173, + "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": 4183436, "tid": 31338, + "ts": 667115823796.980, "dur": 35.103, + "args": { + "External id": 233461,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115823847.196, "dur": 43.889, + "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": 4183436, "tid": 31338, + "ts": 667115823899.943, "dur": 25.165, + "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": 4183436, "tid": 31338, + "ts": 667115823930.771, "dur": 33.546, + "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": 4183436, "tid": 31338, + "ts": 667115823972.005, "dur": 19.978, + "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": 4183436, "tid": 31338, + "ts": 667115823998.454, "dur": 28.544, + "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": 4183436, "tid": 31338, + "ts": 667115824048.440, "dur": 23.137, + "args": { + "External id": 233467,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115824087.266, "dur": 26.591, + "args": { + "External id": 233468,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115824131.093, "dur": 19.469, + "args": { + "External id": 233469,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115824162.861, "dur": 15.026, + "args": { + "External id": 233470,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115824186.553, "dur": 34.630, + "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": 4183436, "tid": 31338, + "ts": 667115824224.352, "dur": 29.435, + "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": 4183436, "tid": 31338, + "ts": 667115824340.591, "dur": 194.726, + "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": 4183436, "tid": 31338, + "ts": 667115824420.829, "dur": 6.680, + "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": 4183436, "tid": 31338, + "ts": 667115824429.251, "dur": 2.709, + "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": 4183436, "tid": 31338, + "ts": 667115824566.535, "dur": 30.428, + "args": { + "External id": 233476,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115824609.062, "dur": 14.332, + "args": { + "External id": 233477,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115824632.307, "dur": 99.674, + "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": 4183436, "tid": 31338, + "ts": 667115824743.079, "dur": 38.276, + "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": 4183436, "tid": 31338, + "ts": 667115824787.824, "dur": 28.074, + "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": 4183436, "tid": 31338, + "ts": 667115824820.350, "dur": 30.105, + "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": 4183436, "tid": 31338, + "ts": 667115824856.229, "dur": 26.974, + "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": 4183436, "tid": 31338, + "ts": 667115824890.161, "dur": 29.985, + "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": 4183436, "tid": 31338, + "ts": 667115824939.064, "dur": 24.160, + "args": { + "External id": 233484,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115825022.312, "dur": 34.175, + "args": { + "External id": 233485,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115825076.185, "dur": 17.553, + "args": { + "External id": 233486,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115825108.411, "dur": 14.978, + "args": { + "External id": 233487,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115825135.189, "dur": 18.760, + "args": { + "External id": 233488,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115825228.855, "dur": 14.803, + "args": { + "External id": 233489,"Record function id": 0, "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115825232.036, "dur": 10.766, + "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": 4183436, "tid": 31338, + "ts": 667115825236.084, "dur": 5.823, + "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": 4183436, "tid": 31338, + "ts": 667115825237.479, "dur": 4.347, + "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": 4183436, "tid": 31338, + "ts": 667115825247.704, "dur": 4.900, + "args": { + "External id": 233493,"Record function id": 0, "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115825249.219, "dur": 2.872, + "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": 4183436, "tid": 31338, + "ts": 667115825249.964, "dur": 1.582, + "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": 4183436, "tid": 31338, + "ts": 667115825250.431, "dur": 1.047, + "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": 4183436, "tid": 31338, + "ts": 667115825255.921, "dur": 4.486, + "args": { + "External id": 233497,"Record function id": 0, "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115825257.041, "dur": 2.945, + "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": 4183436, "tid": 31338, + "ts": 667115825257.749, "dur": 1.774, + "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": 4183436, "tid": 31338, + "ts": 667115825258.446, "dur": 0.993, + "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": 4183436, "tid": 31338, + "ts": 667115825263.575, "dur": 8.295, + "args": { + "External id": 233501,"Record function id": 0, "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115825265.207, "dur": 6.203, + "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": 4183436, "tid": 31338, + "ts": 667115825265.696, "dur": 5.304, + "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": 4183436, "tid": 31338, + "ts": 667115825266.004, "dur": 4.917, + "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": 4183436, "tid": 31338, + "ts": 667115825275.002, "dur": 3.943, + "args": { + "External id": 233505,"Record function id": 0, "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115825276.350, "dur": 2.167, + "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": 4183436, "tid": 31338, + "ts": 667115825276.870, "dur": 1.235, + "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": 4183436, "tid": 31338, + "ts": 667115825277.281, "dur": 0.732, + "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": 4183436, "tid": 31338, + "ts": 667115825282.086, "dur": 4.116, + "args": { + "External id": 233509,"Record function id": 0, "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115825283.203, "dur": 2.532, + "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": 4183436, "tid": 31338, + "ts": 667115825283.812, "dur": 1.422, + "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": 4183436, "tid": 31338, + "ts": 667115825284.575, "dur": 0.583, + "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": 4183436, "tid": 31338, + "ts": 667115825289.463, "dur": 4.233, + "args": { + "External id": 233513,"Record function id": 0, "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115825290.990, "dur": 2.297, + "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": 4183436, "tid": 31338, + "ts": 667115825291.457, "dur": 1.391, + "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": 4183436, "tid": 31338, + "ts": 667115825291.999, "dur": 0.783, + "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": 4183436, "tid": 31338, + "ts": 667115825296.765, "dur": 4.228, + "args": { + "External id": 233517,"Record function id": 0, "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115825298.100, "dur": 2.496, + "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": 4183436, "tid": 31338, + "ts": 667115825298.736, "dur": 1.393, + "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": 4183436, "tid": 31338, + "ts": 667115825299.272, "dur": 0.782, + "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": 4183436, "tid": 31338, + "ts": 667115825303.996, "dur": 4.219, + "args": { + "External id": 233521,"Record function id": 0, "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115825305.565, "dur": 2.252, + "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": 4183436, "tid": 31338, + "ts": 667115825306.224, "dur": 1.168, + "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": 4183436, "tid": 31338, + "ts": 667115825306.863, "dur": 0.463, + "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": 4183436, "tid": 31338, + "ts": 667115825312.112, "dur": 15035.006, + "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": 4183436, "tid": 31338, + "ts": 667115825313.329, "dur": 15025.060, + "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": 4183436, "tid": 31338, "ts": 667115825313.329, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 4183436, "tid": 31338, + "ts": 667115825345.532, "dur": 42.298, + "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": 4183436, "tid": 31338, + "ts": 667115825395.747, "dur": 65.964, + "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": 4183436, "tid": 31338, + "ts": 667115825467.619, "dur": 14863.025, + "args": { + "External id": 233529,"Record function id": 0, "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115825582.735, "dur": 7.063, + "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": 4183436, "tid": 31338, + "ts": 667115825600.128, "dur": 4.908, + "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": 4183436, "tid": 31338, + "ts": 667115825619.584, "dur": 14062.853, + "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": 4183436, "tid": 31338, + "ts": 667115825633.031, "dur": 14017.399, + "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": 4183436, "tid": 31338, + "ts": 667115825735.998, "dur": 15.799, + "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": 4183436, "tid": 31338, + "ts": 667115825756.828, "dur": 13859.026, + "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": 4183436, "tid": 31338, + "ts": 667115825759.603, "dur": 13855.596, + "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": 4183436, "tid": 31338, + "ts": 667115825764.027, "dur": 5.563, + "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": 4183436, "tid": 31338, + "ts": 667115825771.171, "dur": 13840.256, + "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": 4183436, "tid": 31338, + "ts": 667115839773.967, "dur": 9.592, + "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": 4183436, "tid": 31338, + "ts": 667115839776.847, "dur": 6.386, + "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": 4183436, "tid": 31338, + "ts": 667115839809.998, "dur": 254.922, + "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": 4183436, "tid": 31338, + "ts": 667115839835.570, "dur": 225.016, + "args": { + "External id": 233542,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115839847.010, "dur": 209.123, + "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": 4183436, "tid": 31338, + "ts": 667115840081.080, "dur": 1.892, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115840133.381, "dur": 6.212, + "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": 4183436, "tid": 31338, + "ts": 667115840183.506, "dur": 1.281, + "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": 4183436, "tid": 31338, + "ts": 667115840199.753, "dur": 1.193, + "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": 4183436, "tid": 31338, + "ts": 667115840212.007, "dur": 2.787, + "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": 4183436, "tid": 31338, + "ts": 667115840225.096, "dur": 0.873, + "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": 4183436, "tid": 31338, + "ts": 667115840235.432, "dur": 0.697, + "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": 4183436, "tid": 31338, + "ts": 667115840247.289, "dur": 0.692, + "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": 4183436, "tid": 31338, + "ts": 667115840258.917, "dur": 3.458, + "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": 4183436, "tid": 31338, + "ts": 667115840271.968, "dur": 0.826, + "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": 4183436, "tid": 31338, + "ts": 667115840361.184, "dur": 2588.925, + "args": { + "External id": 233554,"Record function id": 0, "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 4183436, "tid": 31338, + "ts": 667115840379.998, "dur": 962.801, + "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": 4183436, "tid": 31338, + "ts": 667115840394.108, "dur": 356.769, + "args": { + "External id": 233556,"Record function id": 0, "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115840468.922, "dur": 4.041, + "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": 4183436, "tid": 31338, + "ts": 667115840476.036, "dur": 1.098, + "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": 4183436, "tid": 31338, + "ts": 667115840479.127, "dur": 0.920, + "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": 4183436, "tid": 31338, + "ts": 667115840481.859, "dur": 0.760, + "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": 4183436, "tid": 31338, + "ts": 667115840484.353, "dur": 1.796, + "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": 4183436, "tid": 31338, + "ts": 667115840487.713, "dur": 0.842, + "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": 4183436, "tid": 31338, + "ts": 667115840490.336, "dur": 21.281, + "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": 4183436, "tid": 31338, + "ts": 667115840515.776, "dur": 1.123, + "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": 4183436, "tid": 31338, + "ts": 667115840518.427, "dur": 0.589, + "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": 4183436, "tid": 31338, + "ts": 667115840520.380, "dur": 0.696, + "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": 4183436, "tid": 31338, + "ts": 667115840540.024, "dur": 177.452, + "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": 4183436, "tid": 31338, + "ts": 667115840556.084, "dur": 156.419, + "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": 4183436, "tid": 31338, + "ts": 667115840568.714, "dur": 12.050, + "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": 4183436, "tid": 31338, + "ts": 667115840583.716, "dur": 62.492, + "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": 4183436, "tid": 31338, + "ts": 667115840586.491, "dur": 59.348, + "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": 4183436, "tid": 31338, + "ts": 667115840590.505, "dur": 5.833, + "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": 4183436, "tid": 31338, + "ts": 667115840597.905, "dur": 47.126, + "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": 4183436, "tid": 31338, + "ts": 667115840828.335, "dur": 507.576, + "args": { + "External id": 233574,"Record function id": 0, "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 4183436, "tid": 31338, + "ts": 667115840845.770, "dur": 478.229, + "args": { + "External id": 233575,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115840902.889, "dur": 6.849, + "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": 4183436, "tid": 31338, + "ts": 667115840925.831, "dur": 27.002, + "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": 4183436, "tid": 31338, + "ts": 667115840930.566, "dur": 1.631, + "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": 4183436, "tid": 31338, + "ts": 667115840934.284, "dur": 0.632, + "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": 4183436, "tid": 31338, + "ts": 667115840935.995, "dur": 0.625, + "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": 4183436, "tid": 31338, + "ts": 667115840938.362, "dur": 0.444, + "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": 4183436, "tid": 31338, + "ts": 667115840939.959, "dur": 0.307, + "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": 4183436, "tid": 31338, + "ts": 667115840941.554, "dur": 0.579, + "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": 4183436, "tid": 31338, + "ts": 667115840943.229, "dur": 0.547, + "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": 4183436, "tid": 31338, + "ts": 667115840944.853, "dur": 2.382, + "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": 4183436, "tid": 31338, + "ts": 667115840948.511, "dur": 0.287, + "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": 4183436, "tid": 31338, + "ts": 667115840962.279, "dur": 30.253, + "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": 4183436, "tid": 31338, + "ts": 667115841022.762, "dur": 87.334, + "args": { + "External id": 233588,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115841032.135, "dur": 3.054, + "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": 4183436, "tid": 31338, + "ts": 667115841039.925, "dur": 9.115, + "args": { + "External id": 233590,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115841044.234, "dur": 4.423, + "args": { + "External id": 233591,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115841046.999, "dur": 0.512, + "args": { + "External id": 233592,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115841055.455, "dur": 19.618, + "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": 4183436, "tid": 31338, + "ts": 667115841057.440, "dur": 0.387, + "args": { + "External id": 233594,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115841059.030, "dur": 0.336, + "args": { + "External id": 233595,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115841060.953, "dur": 0.630, + "args": { + "External id": 233596,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115841063.248, "dur": 0.540, + "args": { + "External id": 233597,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115841064.953, "dur": 1.407, + "args": { + "External id": 233598,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115841067.221, "dur": 0.317, + "args": { + "External id": 233599,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115841068.683, "dur": 0.235, + "args": { + "External id": 233600,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115841070.277, "dur": 0.351, + "args": { + "External id": 233601,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115841071.901, "dur": 0.619, + "args": { + "External id": 233602,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115841084.414, "dur": 18.683, + "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": 4183436, "tid": 31338, + "ts": 667115841154.343, "dur": 107.316, + "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": 4183436, "tid": 31338, + "ts": 667115841176.881, "dur": 81.429, + "args": { + "External id": 233605,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115841185.504, "dur": 68.863, + "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": 4183436, "tid": 31338, + "ts": 667115841275.218, "dur": 1.878, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115841349.975, "dur": 1580.591, + "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": 4183436, "tid": 31338, "ts": 667115841349.975, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115841453.269, "dur": 123.281, + "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": 4183436, "tid": 31338, + "ts": 667115841617.239, "dur": 79.883, + "args": { + "External id": 233610,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115841716.479, "dur": 48.777, + "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": 4183436, "tid": 31338, + "ts": 667115841774.897, "dur": 26.204, + "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": 4183436, "tid": 31338, + "ts": 667115841806.660, "dur": 33.571, + "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": 4183436, "tid": 31338, + "ts": 667115841847.080, "dur": 22.336, + "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": 4183436, "tid": 31338, + "ts": 667115841876.333, "dur": 27.668, + "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": 4183436, "tid": 31338, + "ts": 667115841928.081, "dur": 23.772, + "args": { + "External id": 233616,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115841971.334, "dur": 27.364, + "args": { + "External id": 233617,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115842015.242, "dur": 19.679, + "args": { + "External id": 233618,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115842046.035, "dur": 14.946, + "args": { + "External id": 233619,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115842068.877, "dur": 39.172, + "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": 4183436, "tid": 31338, + "ts": 667115842111.542, "dur": 30.091, + "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": 4183436, "tid": 31338, + "ts": 667115842169.842, "dur": 165.875, + "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": 4183436, "tid": 31338, + "ts": 667115842246.217, "dur": 5.360, + "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": 4183436, "tid": 31338, + "ts": 667115842253.258, "dur": 2.961, + "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": 4183436, "tid": 31338, + "ts": 667115842366.220, "dur": 23.863, + "args": { + "External id": 233625,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115842405.399, "dur": 13.030, + "args": { + "External id": 233626,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115842425.600, "dur": 41.907, + "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": 4183436, "tid": 31338, + "ts": 667115842473.922, "dur": 51.582, + "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": 4183436, "tid": 31338, + "ts": 667115842534.907, "dur": 33.103, + "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": 4183436, "tid": 31338, + "ts": 667115842572.450, "dur": 28.529, + "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": 4183436, "tid": 31338, + "ts": 667115842606.427, "dur": 25.802, + "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": 4183436, "tid": 31338, + "ts": 667115842639.833, "dur": 63.601, + "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": 4183436, "tid": 31338, + "ts": 667115842724.743, "dur": 24.846, + "args": { + "External id": 233633,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115842767.135, "dur": 24.952, + "args": { + "External id": 233634,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115842813.962, "dur": 26.199, + "args": { + "External id": 233635,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115842859.714, "dur": 15.098, + "args": { + "External id": 233636,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115842885.844, "dur": 16.223, + "args": { + "External id": 233637,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115842976.465, "dur": 14.496, + "args": { + "External id": 233638,"Record function id": 0, "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115842979.294, "dur": 10.860, + "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": 4183436, "tid": 31338, + "ts": 667115842983.423, "dur": 5.814, + "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": 4183436, "tid": 31338, + "ts": 667115842984.984, "dur": 4.167, + "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": 4183436, "tid": 31338, + "ts": 667115842994.618, "dur": 4.242, + "args": { + "External id": 233642,"Record function id": 0, "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115842995.972, "dur": 2.492, + "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": 4183436, "tid": 31338, + "ts": 667115842996.718, "dur": 1.303, + "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": 4183436, "tid": 31338, + "ts": 667115842997.252, "dur": 0.696, + "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": 4183436, "tid": 31338, + "ts": 667115843002.077, "dur": 3.897, + "args": { + "External id": 233646,"Record function id": 0, "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115843003.240, "dur": 2.344, + "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": 4183436, "tid": 31338, + "ts": 667115843003.730, "dur": 1.388, + "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": 4183436, "tid": 31338, + "ts": 667115843004.344, "dur": 0.684, + "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": 4183436, "tid": 31338, + "ts": 667115843009.125, "dur": 5.101, + "args": { + "External id": 233650,"Record function id": 0, "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115843010.332, "dur": 3.500, + "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": 4183436, "tid": 31338, + "ts": 667115843011.157, "dur": 2.213, + "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": 4183436, "tid": 31338, + "ts": 667115843011.724, "dur": 1.564, + "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": 4183436, "tid": 31338, + "ts": 667115843017.299, "dur": 3.813, + "args": { + "External id": 233654,"Record function id": 0, "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115843018.576, "dur": 2.114, + "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": 4183436, "tid": 31338, + "ts": 667115843019.136, "dur": 0.912, + "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": 4183436, "tid": 31338, + "ts": 667115843019.413, "dur": 0.558, + "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": 4183436, "tid": 31338, + "ts": 667115843024.287, "dur": 3.740, + "args": { + "External id": 233658,"Record function id": 0, "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115843025.249, "dur": 2.343, + "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": 4183436, "tid": 31338, + "ts": 667115843025.746, "dur": 1.394, + "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": 4183436, "tid": 31338, + "ts": 667115843026.276, "dur": 0.789, + "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": 4183436, "tid": 31338, + "ts": 667115843031.303, "dur": 4.082, + "args": { + "External id": 233662,"Record function id": 0, "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115843032.722, "dur": 2.280, + "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": 4183436, "tid": 31338, + "ts": 667115843033.359, "dur": 1.244, + "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": 4183436, "tid": 31338, + "ts": 667115843033.909, "dur": 0.629, + "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": 4183436, "tid": 31338, + "ts": 667115843038.396, "dur": 4.380, + "args": { + "External id": 233666,"Record function id": 0, "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115843039.925, "dur": 2.465, + "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": 4183436, "tid": 31338, + "ts": 667115843040.756, "dur": 1.183, + "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": 4183436, "tid": 31338, + "ts": 667115843041.389, "dur": 0.484, + "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": 4183436, "tid": 31338, + "ts": 667115843046.044, "dur": 3.850, + "args": { + "External id": 233670,"Record function id": 0, "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115843047.056, "dur": 2.423, + "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": 4183436, "tid": 31338, + "ts": 667115843047.509, "dur": 1.500, + "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": 4183436, "tid": 31338, + "ts": 667115843048.154, "dur": 0.783, + "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": 4183436, "tid": 31338, + "ts": 667115843053.650, "dur": 15307.052, + "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": 4183436, "tid": 31338, + "ts": 667115843054.888, "dur": 15297.638, + "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": 4183436, "tid": 31338, "ts": 667115843054.888, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 4183436, "tid": 31338, + "ts": 667115843083.764, "dur": 38.050, + "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": 4183436, "tid": 31338, + "ts": 667115843129.288, "dur": 66.499, + "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": 4183436, "tid": 31338, + "ts": 667115843202.358, "dur": 15143.030, + "args": { + "External id": 233678,"Record function id": 0, "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115843291.220, "dur": 9.408, + "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": 4183436, "tid": 31338, + "ts": 667115843309.858, "dur": 4.430, + "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": 4183436, "tid": 31338, + "ts": 667115843327.901, "dur": 14387.838, + "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": 4183436, "tid": 31338, + "ts": 667115843341.101, "dur": 14365.760, + "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": 4183436, "tid": 31338, + "ts": 667115843364.747, "dur": 14.087, + "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": 4183436, "tid": 31338, + "ts": 667115843382.833, "dur": 14265.027, + "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": 4183436, "tid": 31338, + "ts": 667115843385.341, "dur": 14261.937, + "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": 4183436, "tid": 31338, + "ts": 667115843389.410, "dur": 4.408, + "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": 4183436, "tid": 31338, + "ts": 667115843395.394, "dur": 14248.123, + "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": 4183436, "tid": 31338, + "ts": 667115857803.107, "dur": 8.553, + "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": 4183436, "tid": 31338, + "ts": 667115857805.744, "dur": 5.588, + "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": 4183436, "tid": 31338, + "ts": 667115857837.557, "dur": 251.498, + "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": 4183436, "tid": 31338, + "ts": 667115857861.622, "dur": 223.132, + "args": { + "External id": 233691,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115857872.711, "dur": 206.917, + "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": 4183436, "tid": 31338, + "ts": 667115858104.728, "dur": 1.993, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115858156.350, "dur": 6.004, + "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": 4183436, "tid": 31338, + "ts": 667115858205.175, "dur": 1.126, + "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": 4183436, "tid": 31338, + "ts": 667115858220.567, "dur": 1.265, + "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": 4183436, "tid": 31338, + "ts": 667115858233.445, "dur": 1.874, + "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": 4183436, "tid": 31338, + "ts": 667115858244.864, "dur": 0.616, + "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": 4183436, "tid": 31338, + "ts": 667115858254.909, "dur": 0.776, + "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": 4183436, "tid": 31338, + "ts": 667115858265.178, "dur": 1.007, + "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": 4183436, "tid": 31338, + "ts": 667115858276.751, "dur": 2.816, + "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": 4183436, "tid": 31338, + "ts": 667115858288.603, "dur": 0.816, + "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": 4183436, "tid": 31338, + "ts": 667115858374.338, "dur": 2561.874, + "args": { + "External id": 233703,"Record function id": 0, "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 4183436, "tid": 31338, + "ts": 667115858394.231, "dur": 946.926, + "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": 4183436, "tid": 31338, + "ts": 667115858406.887, "dur": 350.923, + "args": { + "External id": 233705,"Record function id": 0, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115858478.465, "dur": 4.030, + "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": 4183436, "tid": 31338, + "ts": 667115858485.523, "dur": 0.897, + "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": 4183436, "tid": 31338, + "ts": 667115858488.063, "dur": 1.101, + "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": 4183436, "tid": 31338, + "ts": 667115858490.906, "dur": 19.786, + "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": 4183436, "tid": 31338, + "ts": 667115858514.720, "dur": 2.314, + "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": 4183436, "tid": 31338, + "ts": 667115858518.762, "dur": 0.534, + "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": 4183436, "tid": 31338, + "ts": 667115858521.050, "dur": 1.275, + "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": 4183436, "tid": 31338, + "ts": 667115858523.927, "dur": 0.878, + "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": 4183436, "tid": 31338, + "ts": 667115858526.273, "dur": 0.861, + "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": 4183436, "tid": 31338, + "ts": 667115858528.502, "dur": 0.847, + "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": 4183436, "tid": 31338, + "ts": 667115858548.152, "dur": 175.786, + "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": 4183436, "tid": 31338, + "ts": 667115858563.676, "dur": 155.579, + "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": 4183436, "tid": 31338, + "ts": 667115858576.620, "dur": 12.545, + "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": 4183436, "tid": 31338, + "ts": 667115858591.876, "dur": 97.037, + "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": 4183436, "tid": 31338, + "ts": 667115858594.455, "dur": 94.095, + "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": 4183436, "tid": 31338, + "ts": 667115858597.928, "dur": 5.064, + "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": 4183436, "tid": 31338, + "ts": 667115858604.682, "dur": 82.636, + "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": 4183436, "tid": 31338, + "ts": 667115858837.976, "dur": 495.591, + "args": { + "External id": 233723,"Record function id": 0, "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 4183436, "tid": 31338, + "ts": 667115858856.791, "dur": 464.980, + "args": { + "External id": 233724,"Record function id": 0, "Ev Idx": 3835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115858913.583, "dur": 6.773, + "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": 4183436, "tid": 31338, + "ts": 667115858935.475, "dur": 22.764, + "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": 4183436, "tid": 31338, + "ts": 667115858940.394, "dur": 1.473, + "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": 4183436, "tid": 31338, + "ts": 667115858943.371, "dur": 0.452, + "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": 4183436, "tid": 31338, + "ts": 667115858945.366, "dur": 0.670, + "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": 4183436, "tid": 31338, + "ts": 667115858946.949, "dur": 0.364, + "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": 4183436, "tid": 31338, + "ts": 667115858948.389, "dur": 0.355, + "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": 4183436, "tid": 31338, + "ts": 667115858949.753, "dur": 0.361, + "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": 4183436, "tid": 31338, + "ts": 667115858951.100, "dur": 0.383, + "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": 4183436, "tid": 31338, + "ts": 667115858952.138, "dur": 1.568, + "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": 4183436, "tid": 31338, + "ts": 667115858954.987, "dur": 0.266, + "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": 4183436, "tid": 31338, + "ts": 667115858968.435, "dur": 28.389, + "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": 4183436, "tid": 31338, + "ts": 667115859027.016, "dur": 85.106, + "args": { + "External id": 233737,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115859036.531, "dur": 3.213, + "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": 4183436, "tid": 31338, + "ts": 667115859044.735, "dur": 9.573, + "args": { + "External id": 233739,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115859048.936, "dur": 4.962, + "args": { + "External id": 233740,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115859052.015, "dur": 0.753, + "args": { + "External id": 233741,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115859060.780, "dur": 17.224, + "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": 4183436, "tid": 31338, + "ts": 667115859063.054, "dur": 0.233, + "args": { + "External id": 233743,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115859064.593, "dur": 0.409, + "args": { + "External id": 233744,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115859065.953, "dur": 0.356, + "args": { + "External id": 233745,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115859067.077, "dur": 0.304, + "args": { + "External id": 233746,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115859068.613, "dur": 1.246, + "args": { + "External id": 233747,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115859070.693, "dur": 0.175, + "args": { + "External id": 233748,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115859071.683, "dur": 0.325, + "args": { + "External id": 233749,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115859072.858, "dur": 0.599, + "args": { + "External id": 233750,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115859074.580, "dur": 0.171, + "args": { + "External id": 233751,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115859087.304, "dur": 17.343, + "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": 4183436, "tid": 31338, + "ts": 667115859153.469, "dur": 107.174, + "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": 4183436, "tid": 31338, + "ts": 667115859174.524, "dur": 82.848, + "args": { + "External id": 233754,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115859183.515, "dur": 69.804, + "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": 4183436, "tid": 31338, + "ts": 667115859274.188, "dur": 1.989, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115859347.759, "dur": 1567.952, + "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": 4183436, "tid": 31338, "ts": 667115859347.759, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115859449.573, "dur": 123.797, + "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": 4183436, "tid": 31338, + "ts": 667115859614.660, "dur": 77.168, + "args": { + "External id": 233759,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115859711.182, "dur": 48.828, + "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": 4183436, "tid": 31338, + "ts": 667115859769.600, "dur": 28.351, + "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": 4183436, "tid": 31338, + "ts": 667115859803.898, "dur": 33.274, + "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": 4183436, "tid": 31338, + "ts": 667115859844.099, "dur": 21.993, + "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": 4183436, "tid": 31338, + "ts": 667115859872.144, "dur": 28.563, + "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": 4183436, "tid": 31338, + "ts": 667115859922.737, "dur": 26.547, + "args": { + "External id": 233765,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115859965.435, "dur": 27.070, + "args": { + "External id": 233766,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115860013.233, "dur": 19.609, + "args": { + "External id": 233767,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115860043.078, "dur": 14.387, + "args": { + "External id": 233768,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115860069.929, "dur": 36.907, + "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": 4183436, "tid": 31338, + "ts": 667115860110.092, "dur": 32.571, + "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": 4183436, "tid": 31338, + "ts": 667115860166.670, "dur": 167.742, + "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": 4183436, "tid": 31338, + "ts": 667115860243.071, "dur": 5.439, + "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": 4183436, "tid": 31338, + "ts": 667115860250.335, "dur": 2.362, + "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": 4183436, "tid": 31338, + "ts": 667115860361.631, "dur": 22.212, + "args": { + "External id": 233774,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115860393.363, "dur": 12.633, + "args": { + "External id": 233775,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115860413.306, "dur": 39.327, + "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": 4183436, "tid": 31338, + "ts": 667115860459.299, "dur": 50.785, + "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": 4183436, "tid": 31338, + "ts": 667115860518.939, "dur": 30.769, + "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": 4183436, "tid": 31338, + "ts": 667115860554.107, "dur": 27.504, + "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": 4183436, "tid": 31338, + "ts": 667115860586.962, "dur": 26.180, + "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": 4183436, "tid": 31338, + "ts": 667115860620.809, "dur": 27.366, + "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": 4183436, "tid": 31338, + "ts": 667115860702.866, "dur": 25.485, + "args": { + "External id": 233782,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115860745.145, "dur": 24.131, + "args": { + "External id": 233783,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115860794.695, "dur": 24.071, + "args": { + "External id": 233784,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115860840.447, "dur": 15.198, + "args": { + "External id": 233785,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115860867.180, "dur": 16.094, + "args": { + "External id": 233786,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115860961.532, "dur": 15.122, + "args": { + "External id": 233787,"Record function id": 0, "Ev Idx": 3898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115860964.893, "dur": 10.772, + "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": 4183436, "tid": 31338, + "ts": 667115860969.361, "dur": 5.494, + "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": 4183436, "tid": 31338, + "ts": 667115860970.853, "dur": 3.887, + "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": 4183436, "tid": 31338, + "ts": 667115860980.644, "dur": 4.260, + "args": { + "External id": 233791,"Record function id": 0, "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115860982.097, "dur": 2.369, + "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": 4183436, "tid": 31338, + "ts": 667115860982.728, "dur": 1.300, + "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": 4183436, "tid": 31338, + "ts": 667115860983.311, "dur": 0.646, + "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": 4183436, "tid": 31338, + "ts": 667115860988.175, "dur": 3.812, + "args": { + "External id": 233795,"Record function id": 0, "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115860989.316, "dur": 2.264, + "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": 4183436, "tid": 31338, + "ts": 667115860989.972, "dur": 1.224, + "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": 4183436, "tid": 31338, + "ts": 667115860990.375, "dur": 0.731, + "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": 4183436, "tid": 31338, + "ts": 667115860995.561, "dur": 4.832, + "args": { + "External id": 233799,"Record function id": 0, "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115860996.731, "dur": 3.229, + "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": 4183436, "tid": 31338, + "ts": 667115860997.263, "dur": 2.265, + "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": 4183436, "tid": 31338, + "ts": 667115860997.747, "dur": 1.712, + "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": 4183436, "tid": 31338, + "ts": 667115861003.459, "dur": 3.853, + "args": { + "External id": 233803,"Record function id": 0, "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115861004.625, "dur": 2.260, + "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": 4183436, "tid": 31338, + "ts": 667115861005.264, "dur": 1.220, + "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": 4183436, "tid": 31338, + "ts": 667115861005.838, "dur": 0.571, + "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": 4183436, "tid": 31338, + "ts": 667115861013.671, "dur": 3.931, + "args": { + "External id": 233807,"Record function id": 0, "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115861014.822, "dur": 2.333, + "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": 4183436, "tid": 31338, + "ts": 667115861015.284, "dur": 1.445, + "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": 4183436, "tid": 31338, + "ts": 667115861015.961, "dur": 0.693, + "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": 4183436, "tid": 31338, + "ts": 667115861020.857, "dur": 4.442, + "args": { + "External id": 233811,"Record function id": 0, "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115861022.377, "dur": 2.488, + "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": 4183436, "tid": 31338, + "ts": 667115861023.145, "dur": 1.312, + "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": 4183436, "tid": 31338, + "ts": 667115861023.767, "dur": 0.615, + "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": 4183436, "tid": 31338, + "ts": 667115861028.532, "dur": 4.011, + "args": { + "External id": 233815,"Record function id": 0, "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115861029.767, "dur": 2.364, + "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": 4183436, "tid": 31338, + "ts": 667115861030.257, "dur": 1.435, + "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": 4183436, "tid": 31338, + "ts": 667115861030.839, "dur": 0.778, + "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": 4183436, "tid": 31338, + "ts": 667115861035.633, "dur": 5.595, + "args": { + "External id": 233819,"Record function id": 0, "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115861036.641, "dur": 4.162, + "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": 4183436, "tid": 31338, + "ts": 667115861037.378, "dur": 3.017, + "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": 4183436, "tid": 31338, + "ts": 667115861039.895, "dur": 0.432, + "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": 4183436, "tid": 31338, + "ts": 667115861045.115, "dur": 14999.005, + "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": 4183436, "tid": 31338, + "ts": 667115861046.489, "dur": 14989.301, + "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": 4183436, "tid": 31338, "ts": 667115861046.489, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 4183436, "tid": 31338, + "ts": 667115861073.800, "dur": 39.352, + "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": 4183436, "tid": 31338, + "ts": 667115861121.103, "dur": 61.225, + "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": 4183436, "tid": 31338, + "ts": 667115861187.951, "dur": 14840.360, + "args": { + "External id": 233827,"Record function id": 0, "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115861273.633, "dur": 6.015, + "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": 4183436, "tid": 31338, + "ts": 667115861289.192, "dur": 4.300, + "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": 4183436, "tid": 31338, + "ts": 667115861310.654, "dur": 13978.681, + "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": 4183436, "tid": 31338, + "ts": 667115861323.654, "dur": 13956.913, + "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": 4183436, "tid": 31338, + "ts": 667115861344.668, "dur": 12.848, + "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": 4183436, "tid": 31338, + "ts": 667115861361.811, "dur": 13883.996, + "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": 4183436, "tid": 31338, + "ts": 667115861364.559, "dur": 13880.354, + "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": 4183436, "tid": 31338, + "ts": 667115861368.468, "dur": 4.181, + "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": 4183436, "tid": 31338, + "ts": 667115861374.295, "dur": 13867.325, + "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": 4183436, "tid": 31338, + "ts": 667115875375.884, "dur": 8.942, + "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": 4183436, "tid": 31338, + "ts": 667115875378.935, "dur": 5.579, + "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": 4183436, "tid": 31338, + "ts": 667115875411.844, "dur": 338.364, + "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": 4183436, "tid": 31338, + "ts": 667115875435.545, "dur": 309.360, + "args": { + "External id": 233840,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115875446.311, "dur": 292.919, + "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": 4183436, "tid": 31338, + "ts": 667115875771.242, "dur": 2.336, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115875831.425, "dur": 6.621, + "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": 4183436, "tid": 31338, + "ts": 667115875884.519, "dur": 1.405, + "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": 4183436, "tid": 31338, + "ts": 667115875901.505, "dur": 0.976, + "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": 4183436, "tid": 31338, + "ts": 667115875913.566, "dur": 1.229, + "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": 4183436, "tid": 31338, + "ts": 667115875924.975, "dur": 0.962, + "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": 4183436, "tid": 31338, + "ts": 667115875934.948, "dur": 0.921, + "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": 4183436, "tid": 31338, + "ts": 667115875945.462, "dur": 1.333, + "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": 4183436, "tid": 31338, + "ts": 667115875957.077, "dur": 1.664, + "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": 4183436, "tid": 31338, + "ts": 667115875968.482, "dur": 1.031, + "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": 4183436, "tid": 31338, + "ts": 667115876057.642, "dur": 2568.022, + "args": { + "External id": 233852,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 4183436, "tid": 31338, + "ts": 667115876077.675, "dur": 980.526, + "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": 4183436, "tid": 31338, + "ts": 667115876092.634, "dur": 296.526, + "args": { + "External id": 233854,"Record function id": 0, "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115876168.317, "dur": 3.793, + "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": 4183436, "tid": 31338, + "ts": 667115876175.099, "dur": 0.983, + "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": 4183436, "tid": 31338, + "ts": 667115876177.763, "dur": 1.171, + "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": 4183436, "tid": 31338, + "ts": 667115876180.824, "dur": 1.332, + "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": 4183436, "tid": 31338, + "ts": 667115876183.583, "dur": 1.163, + "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": 4183436, "tid": 31338, + "ts": 667115876186.357, "dur": 1.066, + "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": 4183436, "tid": 31338, + "ts": 667115876189.263, "dur": 1.050, + "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": 4183436, "tid": 31338, + "ts": 667115876191.691, "dur": 1.086, + "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": 4183436, "tid": 31338, + "ts": 667115876194.559, "dur": 0.760, + "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": 4183436, "tid": 31338, + "ts": 667115876196.866, "dur": 0.955, + "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": 4183436, "tid": 31338, + "ts": 667115876215.276, "dur": 145.853, + "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": 4183436, "tid": 31338, + "ts": 667115876229.694, "dur": 127.201, + "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": 4183436, "tid": 31338, + "ts": 667115876253.540, "dur": 13.320, + "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": 4183436, "tid": 31338, + "ts": 667115876269.492, "dur": 61.444, + "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": 4183436, "tid": 31338, + "ts": 667115876271.999, "dur": 58.532, + "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": 4183436, "tid": 31338, + "ts": 667115876275.943, "dur": 5.116, + "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": 4183436, "tid": 31338, + "ts": 667115876283.030, "dur": 46.806, + "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": 4183436, "tid": 31338, + "ts": 667115876465.580, "dur": 585.038, + "args": { + "External id": 233872,"Record function id": 0, "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 4183436, "tid": 31338, + "ts": 667115876482.165, "dur": 556.030, + "args": { + "External id": 233873,"Record function id": 0, "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115876557.906, "dur": 6.064, + "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": 4183436, "tid": 31338, + "ts": 667115876579.664, "dur": 23.102, + "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": 4183436, "tid": 31338, + "ts": 667115876584.598, "dur": 1.381, + "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": 4183436, "tid": 31338, + "ts": 667115876587.794, "dur": 0.529, + "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": 4183436, "tid": 31338, + "ts": 667115876589.787, "dur": 0.476, + "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": 4183436, "tid": 31338, + "ts": 667115876591.365, "dur": 0.343, + "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": 4183436, "tid": 31338, + "ts": 667115876592.686, "dur": 0.330, + "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": 4183436, "tid": 31338, + "ts": 667115876594.557, "dur": 0.315, + "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": 4183436, "tid": 31338, + "ts": 667115876596.068, "dur": 0.431, + "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": 4183436, "tid": 31338, + "ts": 667115876598.170, "dur": 0.376, + "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": 4183436, "tid": 31338, + "ts": 667115876599.561, "dur": 0.266, + "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": 4183436, "tid": 31338, + "ts": 667115876612.147, "dur": 30.906, + "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": 4183436, "tid": 31338, + "ts": 667115876714.383, "dur": 102.056, + "args": { + "External id": 233886,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115876725.897, "dur": 4.256, + "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": 4183436, "tid": 31338, + "ts": 667115876735.671, "dur": 10.909, + "args": { + "External id": 233888,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115876739.851, "dur": 6.275, + "args": { + "External id": 233889,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115876743.531, "dur": 1.029, + "args": { + "External id": 233890,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115876753.682, "dur": 24.088, + "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": 4183436, "tid": 31338, + "ts": 667115876755.792, "dur": 0.845, + "args": { + "External id": 233892,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115876757.848, "dur": 0.799, + "args": { + "External id": 233893,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115876760.123, "dur": 0.876, + "args": { + "External id": 233894,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115876762.299, "dur": 0.874, + "args": { + "External id": 233895,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115876764.478, "dur": 0.796, + "args": { + "External id": 233896,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115876766.953, "dur": 0.484, + "args": { + "External id": 233897,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115876768.770, "dur": 0.986, + "args": { + "External id": 233898,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115876770.857, "dur": 0.532, + "args": { + "External id": 233899,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115876772.669, "dur": 1.000, + "args": { + "External id": 233900,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115876787.456, "dur": 21.036, + "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": 4183436, "tid": 31338, + "ts": 667115876862.707, "dur": 110.518, + "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": 4183436, "tid": 31338, + "ts": 667115876886.109, "dur": 83.440, + "args": { + "External id": 233903,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115876895.829, "dur": 68.791, + "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": 4183436, "tid": 31338, + "ts": 667115876988.328, "dur": 1.997, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115877064.922, "dur": 1536.443, + "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": 4183436, "tid": 31338, "ts": 667115877064.922, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115877170.003, "dur": 97.877, + "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": 4183436, "tid": 31338, + "ts": 667115877304.606, "dur": 35.597, + "args": { + "External id": 233908,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115877359.709, "dur": 40.391, + "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": 4183436, "tid": 31338, + "ts": 667115877412.300, "dur": 25.486, + "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": 4183436, "tid": 31338, + "ts": 667115877444.606, "dur": 33.107, + "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": 4183436, "tid": 31338, + "ts": 667115877484.410, "dur": 41.358, + "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": 4183436, "tid": 31338, + "ts": 667115877535.819, "dur": 31.469, + "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": 4183436, "tid": 31338, + "ts": 667115877591.332, "dur": 22.295, + "args": { + "External id": 233914,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115877630.889, "dur": 67.058, + "args": { + "External id": 233915,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115877720.925, "dur": 19.936, + "args": { + "External id": 233916,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115877753.080, "dur": 13.747, + "args": { + "External id": 233917,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115877778.924, "dur": 40.293, + "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": 4183436, "tid": 31338, + "ts": 667115877822.768, "dur": 33.188, + "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": 4183436, "tid": 31338, + "ts": 667115877881.432, "dur": 164.044, + "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": 4183436, "tid": 31338, + "ts": 667115877956.417, "dur": 6.734, + "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": 4183436, "tid": 31338, + "ts": 667115877965.168, "dur": 2.985, + "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": 4183436, "tid": 31338, + "ts": 667115878076.382, "dur": 28.615, + "args": { + "External id": 233923,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115878116.781, "dur": 12.763, + "args": { + "External id": 233924,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115878137.256, "dur": 44.661, + "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": 4183436, "tid": 31338, + "ts": 667115878188.404, "dur": 29.804, + "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": 4183436, "tid": 31338, + "ts": 667115878224.555, "dur": 27.609, + "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": 4183436, "tid": 31338, + "ts": 667115878256.970, "dur": 27.874, + "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": 4183436, "tid": 31338, + "ts": 667115878290.106, "dur": 27.067, + "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": 4183436, "tid": 31338, + "ts": 667115878324.098, "dur": 26.974, + "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": 4183436, "tid": 31338, + "ts": 667115878368.287, "dur": 21.356, + "args": { + "External id": 233931,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115878405.322, "dur": 37.587, + "args": { + "External id": 233932,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115878463.430, "dur": 22.958, + "args": { + "External id": 233933,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115878525.880, "dur": 15.799, + "args": { + "External id": 233934,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115878554.190, "dur": 18.333, + "args": { + "External id": 233935,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115878647.716, "dur": 57.570, + "args": { + "External id": 233936,"Record function id": 0, "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115878690.388, "dur": 13.071, + "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": 4183436, "tid": 31338, + "ts": 667115878695.140, "dur": 6.908, + "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": 4183436, "tid": 31338, + "ts": 667115878696.927, "dur": 4.843, + "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": 4183436, "tid": 31338, + "ts": 667115878711.674, "dur": 6.060, + "args": { + "External id": 233940,"Record function id": 0, "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115878713.944, "dur": 3.314, + "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": 4183436, "tid": 31338, + "ts": 667115878714.921, "dur": 1.705, + "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": 4183436, "tid": 31338, + "ts": 667115878715.610, "dur": 0.923, + "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": 4183436, "tid": 31338, + "ts": 667115878721.046, "dur": 4.400, + "args": { + "External id": 233944,"Record function id": 0, "Ev Idx": 4055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115878722.232, "dur": 2.798, + "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": 4183436, "tid": 31338, + "ts": 667115878722.960, "dur": 1.657, + "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": 4183436, "tid": 31338, + "ts": 667115878723.536, "dur": 1.003, + "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": 4183436, "tid": 31338, + "ts": 667115878728.663, "dur": 4.563, + "args": { + "External id": 233948,"Record function id": 0, "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115878729.868, "dur": 2.940, + "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": 4183436, "tid": 31338, + "ts": 667115878730.774, "dur": 1.627, + "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": 4183436, "tid": 31338, + "ts": 667115878731.341, "dur": 0.986, + "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": 4183436, "tid": 31338, + "ts": 667115878736.312, "dur": 4.326, + "args": { + "External id": 233952,"Record function id": 0, "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115878737.609, "dur": 2.625, + "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": 4183436, "tid": 31338, + "ts": 667115878738.474, "dur": 1.362, + "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": 4183436, "tid": 31338, + "ts": 667115878739.085, "dur": 0.684, + "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": 4183436, "tid": 31338, + "ts": 667115878743.739, "dur": 5.146, + "args": { + "External id": 233956,"Record function id": 0, "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115878745.383, "dur": 3.085, + "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": 4183436, "tid": 31338, + "ts": 667115878746.070, "dur": 1.995, + "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": 4183436, "tid": 31338, + "ts": 667115878747.200, "dur": 0.790, + "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": 4183436, "tid": 31338, + "ts": 667115878752.084, "dur": 4.712, + "args": { + "External id": 233960,"Record function id": 0, "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115878753.437, "dur": 2.957, + "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": 4183436, "tid": 31338, + "ts": 667115878754.101, "dur": 1.889, + "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": 4183436, "tid": 31338, + "ts": 667115878755.050, "dur": 0.867, + "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": 4183436, "tid": 31338, + "ts": 667115878759.959, "dur": 3.946, + "args": { + "External id": 233964,"Record function id": 0, "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115878761.404, "dur": 2.103, + "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": 4183436, "tid": 31338, + "ts": 667115878761.890, "dur": 1.221, + "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": 4183436, "tid": 31338, + "ts": 667115878762.361, "dur": 0.687, + "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": 4183436, "tid": 31338, + "ts": 667115878767.463, "dur": 4.496, + "args": { + "External id": 233968,"Record function id": 0, "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115878768.562, "dur": 2.970, + "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": 4183436, "tid": 31338, + "ts": 667115878769.019, "dur": 2.110, + "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": 4183436, "tid": 31338, + "ts": 667115878770.003, "dur": 1.049, + "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": 4183436, "tid": 31338, + "ts": 667115878776.074, "dur": 14836.432, + "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": 4183436, "tid": 31338, + "ts": 667115878777.332, "dur": 14826.408, + "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": 4183436, "tid": 31338, "ts": 667115878777.332, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 4183436, "tid": 31338, + "ts": 667115878807.846, "dur": 37.303, + "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": 4183436, "tid": 31338, + "ts": 667115878853.517, "dur": 67.842, + "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": 4183436, "tid": 31338, + "ts": 667115878927.150, "dur": 14668.231, + "args": { + "External id": 233976,"Record function id": 0, "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115879017.461, "dur": 6.547, + "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": 4183436, "tid": 31338, + "ts": 667115879036.686, "dur": 4.723, + "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": 4183436, "tid": 31338, + "ts": 667115879056.463, "dur": 13868.730, + "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": 4183436, "tid": 31338, + "ts": 667115879068.924, "dur": 13847.245, + "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": 4183436, "tid": 31338, + "ts": 667115879094.848, "dur": 13.940, + "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": 4183436, "tid": 31338, + "ts": 667115879113.138, "dur": 13766.438, + "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": 4183436, "tid": 31338, + "ts": 667115879115.656, "dur": 13763.180, + "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": 4183436, "tid": 31338, + "ts": 667115879119.117, "dur": 5.325, + "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": 4183436, "tid": 31338, + "ts": 667115879181.984, "dur": 13692.772, + "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": 4183436, "tid": 31338, + "ts": 667115893017.402, "dur": 9.897, + "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": 4183436, "tid": 31338, + "ts": 667115893020.418, "dur": 6.600, + "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": 4183436, "tid": 31338, + "ts": 667115893055.423, "dur": 248.937, + "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": 4183436, "tid": 31338, + "ts": 667115893082.095, "dur": 218.036, + "args": { + "External id": 233989,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115893092.888, "dur": 202.630, + "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": 4183436, "tid": 31338, + "ts": 667115893320.551, "dur": 2.127, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115893371.560, "dur": 6.066, + "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": 4183436, "tid": 31338, + "ts": 667115893420.764, "dur": 1.656, + "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": 4183436, "tid": 31338, + "ts": 667115893438.437, "dur": 1.512, + "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": 4183436, "tid": 31338, + "ts": 667115893450.777, "dur": 1.290, + "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": 4183436, "tid": 31338, + "ts": 667115893463.198, "dur": 0.932, + "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": 4183436, "tid": 31338, + "ts": 667115893473.596, "dur": 1.005, + "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": 4183436, "tid": 31338, + "ts": 667115893487.821, "dur": 1.096, + "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": 4183436, "tid": 31338, + "ts": 667115893521.805, "dur": 1.738, + "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": 4183436, "tid": 31338, + "ts": 667115893533.493, "dur": 0.955, + "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": 4183436, "tid": 31338, + "ts": 667115893627.043, "dur": 2585.820, + "args": { + "External id": 234001,"Record function id": 0, "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 4183436, "tid": 31338, + "ts": 667115893646.998, "dur": 994.490, + "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": 4183436, "tid": 31338, + "ts": 667115893697.842, "dur": 315.966, + "args": { + "External id": 234003,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115893778.017, "dur": 4.971, + "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": 4183436, "tid": 31338, + "ts": 667115893785.984, "dur": 1.455, + "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": 4183436, "tid": 31338, + "ts": 667115893789.114, "dur": 0.946, + "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": 4183436, "tid": 31338, + "ts": 667115893792.026, "dur": 1.163, + "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": 4183436, "tid": 31338, + "ts": 667115893794.964, "dur": 1.349, + "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": 4183436, "tid": 31338, + "ts": 667115893798.131, "dur": 1.441, + "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": 4183436, "tid": 31338, + "ts": 667115893801.161, "dur": 1.005, + "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": 4183436, "tid": 31338, + "ts": 667115893803.727, "dur": 1.099, + "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": 4183436, "tid": 31338, + "ts": 667115893806.379, "dur": 1.569, + "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": 4183436, "tid": 31338, + "ts": 667115893809.733, "dur": 0.966, + "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": 4183436, "tid": 31338, + "ts": 667115893828.549, "dur": 154.502, + "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": 4183436, "tid": 31338, + "ts": 667115893843.747, "dur": 134.922, + "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": 4183436, "tid": 31338, + "ts": 667115893870.919, "dur": 13.143, + "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": 4183436, "tid": 31338, + "ts": 667115893887.061, "dur": 63.402, + "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": 4183436, "tid": 31338, + "ts": 667115893889.638, "dur": 60.474, + "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": 4183436, "tid": 31338, + "ts": 667115893893.490, "dur": 5.789, + "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": 4183436, "tid": 31338, + "ts": 667115893900.876, "dur": 48.499, + "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": 4183436, "tid": 31338, + "ts": 667115894089.898, "dur": 543.937, + "args": { + "External id": 234021,"Record function id": 0, "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 4183436, "tid": 31338, + "ts": 667115894107.119, "dur": 513.916, + "args": { + "External id": 234022,"Record function id": 0, "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115894160.884, "dur": 5.218, + "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": 4183436, "tid": 31338, + "ts": 667115894181.802, "dur": 34.641, + "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": 4183436, "tid": 31338, + "ts": 667115894186.274, "dur": 1.484, + "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": 4183436, "tid": 31338, + "ts": 667115894190.271, "dur": 0.613, + "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": 4183436, "tid": 31338, + "ts": 667115894192.050, "dur": 0.649, + "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": 4183436, "tid": 31338, + "ts": 667115894194.404, "dur": 0.673, + "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": 4183436, "tid": 31338, + "ts": 667115894196.211, "dur": 0.666, + "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": 4183436, "tid": 31338, + "ts": 667115894198.210, "dur": 0.898, + "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": 4183436, "tid": 31338, + "ts": 667115894208.363, "dur": 0.860, + "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": 4183436, "tid": 31338, + "ts": 667115894210.154, "dur": 0.776, + "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": 4183436, "tid": 31338, + "ts": 667115894211.884, "dur": 0.606, + "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": 4183436, "tid": 31338, + "ts": 667115894225.932, "dur": 31.960, + "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": 4183436, "tid": 31338, + "ts": 667115894287.593, "dur": 92.231, + "args": { + "External id": 234035,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115894296.900, "dur": 3.652, + "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": 4183436, "tid": 31338, + "ts": 667115894305.289, "dur": 10.187, + "args": { + "External id": 234037,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115894309.730, "dur": 5.343, + "args": { + "External id": 234038,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115894313.085, "dur": 0.684, + "args": { + "External id": 234039,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115894323.790, "dur": 20.409, + "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": 4183436, "tid": 31338, + "ts": 667115894326.037, "dur": 0.621, + "args": { + "External id": 234041,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115894327.936, "dur": 0.653, + "args": { + "External id": 234042,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115894329.632, "dur": 0.728, + "args": { + "External id": 234043,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115894331.298, "dur": 0.591, + "args": { + "External id": 234044,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115894333.176, "dur": 0.775, + "args": { + "External id": 234045,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115894335.093, "dur": 0.741, + "args": { + "External id": 234046,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115894337.148, "dur": 0.652, + "args": { + "External id": 234047,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115894338.883, "dur": 0.506, + "args": { + "External id": 234048,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115894340.334, "dur": 0.970, + "args": { + "External id": 234049,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115894353.624, "dur": 19.032, + "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": 4183436, "tid": 31338, + "ts": 667115894421.769, "dur": 130.345, + "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": 4183436, "tid": 31338, + "ts": 667115894444.298, "dur": 104.030, + "args": { + "External id": 234052,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115894452.800, "dur": 90.698, + "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": 4183436, "tid": 31338, + "ts": 667115894567.189, "dur": 1.834, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115894648.848, "dur": 1540.321, + "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": 4183436, "tid": 31338, "ts": 667115894648.848, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115894798.380, "dur": 104.235, + "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": 4183436, "tid": 31338, + "ts": 667115894942.178, "dur": 36.124, + "args": { + "External id": 234057,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115894994.687, "dur": 39.210, + "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": 4183436, "tid": 31338, + "ts": 667115895043.098, "dur": 24.498, + "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": 4183436, "tid": 31338, + "ts": 667115895076.809, "dur": 31.853, + "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": 4183436, "tid": 31338, + "ts": 667115895115.405, "dur": 22.348, + "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": 4183436, "tid": 31338, + "ts": 667115895144.466, "dur": 28.340, + "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": 4183436, "tid": 31338, + "ts": 667115895194.560, "dur": 20.659, + "args": { + "External id": 234063,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115895238.475, "dur": 25.505, + "args": { + "External id": 234064,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115895281.364, "dur": 16.664, + "args": { + "External id": 234065,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115895309.221, "dur": 12.994, + "args": { + "External id": 234066,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115895329.570, "dur": 35.445, + "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": 4183436, "tid": 31338, + "ts": 667115895368.258, "dur": 29.264, + "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": 4183436, "tid": 31338, + "ts": 667115895426.493, "dur": 189.362, + "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": 4183436, "tid": 31338, + "ts": 667115895525.276, "dur": 6.403, + "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": 4183436, "tid": 31338, + "ts": 667115895533.644, "dur": 3.495, + "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": 4183436, "tid": 31338, + "ts": 667115895647.296, "dur": 62.823, + "args": { + "External id": 234072,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115895723.945, "dur": 13.388, + "args": { + "External id": 234073,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115895746.498, "dur": 54.791, + "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": 4183436, "tid": 31338, + "ts": 667115895807.508, "dur": 34.370, + "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": 4183436, "tid": 31338, + "ts": 667115895847.972, "dur": 27.302, + "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": 4183436, "tid": 31338, + "ts": 667115895879.662, "dur": 27.503, + "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": 4183436, "tid": 31338, + "ts": 667115895912.689, "dur": 26.080, + "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": 4183436, "tid": 31338, + "ts": 667115895945.029, "dur": 26.691, + "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": 4183436, "tid": 31338, + "ts": 667115895990.148, "dur": 39.572, + "args": { + "External id": 234080,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115896052.065, "dur": 21.748, + "args": { + "External id": 234081,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115896090.181, "dur": 14.725, + "args": { + "External id": 234082,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115896118.876, "dur": 13.399, + "args": { + "External id": 234083,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115896147.329, "dur": 14.824, + "args": { + "External id": 234084,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115896234.543, "dur": 15.037, + "args": { + "External id": 234085,"Record function id": 0, "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115896237.599, "dur": 11.018, + "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": 4183436, "tid": 31338, + "ts": 667115896241.843, "dur": 5.879, + "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": 4183436, "tid": 31338, + "ts": 667115896243.159, "dur": 4.463, + "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": 4183436, "tid": 31338, + "ts": 667115896253.464, "dur": 4.621, + "args": { + "External id": 234089,"Record function id": 0, "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115896254.595, "dur": 3.006, + "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": 4183436, "tid": 31338, + "ts": 667115896255.243, "dur": 1.921, + "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": 4183436, "tid": 31338, + "ts": 667115896255.930, "dur": 1.149, + "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": 4183436, "tid": 31338, + "ts": 667115896261.226, "dur": 4.656, + "args": { + "External id": 234093,"Record function id": 0, "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115896262.620, "dur": 2.834, + "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": 4183436, "tid": 31338, + "ts": 667115896263.654, "dur": 1.381, + "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": 4183436, "tid": 31338, + "ts": 667115896264.268, "dur": 0.700, + "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": 4183436, "tid": 31338, + "ts": 667115896269.235, "dur": 4.325, + "args": { + "External id": 234097,"Record function id": 0, "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115896270.621, "dur": 2.505, + "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": 4183436, "tid": 31338, + "ts": 667115896271.353, "dur": 1.332, + "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": 4183436, "tid": 31338, + "ts": 667115896271.675, "dur": 0.926, + "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": 4183436, "tid": 31338, + "ts": 667115896276.868, "dur": 4.139, + "args": { + "External id": 234101,"Record function id": 0, "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115896277.933, "dur": 2.636, + "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": 4183436, "tid": 31338, + "ts": 667115896278.793, "dur": 1.351, + "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": 4183436, "tid": 31338, + "ts": 667115896279.191, "dur": 0.877, + "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": 4183436, "tid": 31338, + "ts": 667115896284.168, "dur": 4.104, + "args": { + "External id": 234105,"Record function id": 0, "Ev Idx": 4216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115896285.484, "dur": 2.365, + "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": 4183436, "tid": 31338, + "ts": 667115896285.943, "dur": 1.481, + "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": 4183436, "tid": 31338, + "ts": 667115896286.540, "dur": 0.808, + "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": 4183436, "tid": 31338, + "ts": 667115896291.462, "dur": 4.233, + "args": { + "External id": 234109,"Record function id": 0, "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115896292.715, "dur": 2.583, + "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": 4183436, "tid": 31338, + "ts": 667115896293.228, "dur": 1.652, + "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": 4183436, "tid": 31338, + "ts": 667115896294.043, "dur": 0.764, + "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": 4183436, "tid": 31338, + "ts": 667115896298.742, "dur": 4.111, + "args": { + "External id": 234113,"Record function id": 0, "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115896299.860, "dur": 2.580, + "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": 4183436, "tid": 31338, + "ts": 667115896300.342, "dur": 1.675, + "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": 4183436, "tid": 31338, + "ts": 667115896301.095, "dur": 0.857, + "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": 4183436, "tid": 31338, + "ts": 667115896306.288, "dur": 4.235, + "args": { + "External id": 234117,"Record function id": 0, "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115896307.265, "dur": 2.862, + "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": 4183436, "tid": 31338, + "ts": 667115896307.909, "dur": 1.835, + "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": 4183436, "tid": 31338, + "ts": 667115896308.833, "dur": 0.837, + "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": 4183436, "tid": 31338, + "ts": 667115896314.485, "dur": 16001.407, + "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": 4183436, "tid": 31338, + "ts": 667115896315.923, "dur": 15991.177, + "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": 4183436, "tid": 31338, "ts": 667115896315.923, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 4183436, "tid": 31338, + "ts": 667115896342.888, "dur": 34.855, + "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": 4183436, "tid": 31338, + "ts": 667115896385.265, "dur": 64.065, + "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": 4183436, "tid": 31338, + "ts": 667115896455.601, "dur": 15843.609, + "args": { + "External id": 234125,"Record function id": 0, "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115896559.887, "dur": 7.262, + "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": 4183436, "tid": 31338, + "ts": 667115896577.707, "dur": 5.399, + "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": 4183436, "tid": 31338, + "ts": 667115896597.001, "dur": 14976.865, + "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": 4183436, "tid": 31338, + "ts": 667115896610.839, "dur": 14954.277, + "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": 4183436, "tid": 31338, + "ts": 667115896631.518, "dur": 13.366, + "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": 4183436, "tid": 31338, + "ts": 667115896648.965, "dur": 14880.511, + "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": 4183436, "tid": 31338, + "ts": 667115896689.068, "dur": 14839.559, + "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": 4183436, "tid": 31338, + "ts": 667115896693.099, "dur": 6.603, + "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": 4183436, "tid": 31338, + "ts": 667115896701.656, "dur": 14823.031, + "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": 4183436, "tid": 31338, + "ts": 667115911700.281, "dur": 10.198, + "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": 4183436, "tid": 31338, + "ts": 667115911703.063, "dur": 6.749, + "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": 4183436, "tid": 31338, + "ts": 667115911740.657, "dur": 292.268, + "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": 4183436, "tid": 31338, + "ts": 667115911765.812, "dur": 262.581, + "args": { + "External id": 234138,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115911777.796, "dur": 245.284, + "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": 4183436, "tid": 31338, + "ts": 667115912049.887, "dur": 1.881, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115912105.707, "dur": 6.389, + "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": 4183436, "tid": 31338, + "ts": 667115912156.726, "dur": 1.161, + "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": 4183436, "tid": 31338, + "ts": 667115912172.773, "dur": 1.155, + "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": 4183436, "tid": 31338, + "ts": 667115912184.592, "dur": 0.947, + "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": 4183436, "tid": 31338, + "ts": 667115912196.525, "dur": 1.043, + "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": 4183436, "tid": 31338, + "ts": 667115912206.326, "dur": 1.071, + "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": 4183436, "tid": 31338, + "ts": 667115912217.847, "dur": 1.108, + "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": 4183436, "tid": 31338, + "ts": 667115912229.844, "dur": 0.775, + "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": 4183436, "tid": 31338, + "ts": 667115912239.866, "dur": 1.381, + "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": 4183436, "tid": 31338, + "ts": 667115912329.013, "dur": 2557.894, + "args": { + "External id": 234150,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 4183436, "tid": 31338, + "ts": 667115912348.398, "dur": 968.032, + "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": 4183436, "tid": 31338, + "ts": 667115912361.171, "dur": 342.674, + "args": { + "External id": 234152,"Record function id": 0, "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115912432.974, "dur": 4.151, + "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": 4183436, "tid": 31338, + "ts": 667115912440.220, "dur": 1.512, + "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": 4183436, "tid": 31338, + "ts": 667115912443.320, "dur": 1.036, + "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": 4183436, "tid": 31338, + "ts": 667115912446.197, "dur": 1.354, + "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": 4183436, "tid": 31338, + "ts": 667115912449.206, "dur": 0.863, + "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": 4183436, "tid": 31338, + "ts": 667115912451.864, "dur": 1.083, + "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": 4183436, "tid": 31338, + "ts": 667115912454.440, "dur": 0.967, + "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": 4183436, "tid": 31338, + "ts": 667115912456.967, "dur": 0.939, + "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": 4183436, "tid": 31338, + "ts": 667115912459.345, "dur": 0.941, + "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": 4183436, "tid": 31338, + "ts": 667115912461.826, "dur": 0.860, + "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": 4183436, "tid": 31338, + "ts": 667115912479.716, "dur": 155.585, + "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": 4183436, "tid": 31338, + "ts": 667115912513.206, "dur": 117.801, + "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": 4183436, "tid": 31338, + "ts": 667115912525.882, "dur": 13.257, + "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": 4183436, "tid": 31338, + "ts": 667115912541.793, "dur": 63.980, + "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": 4183436, "tid": 31338, + "ts": 667115912544.376, "dur": 61.047, + "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": 4183436, "tid": 31338, + "ts": 667115912549.437, "dur": 6.443, + "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": 4183436, "tid": 31338, + "ts": 667115912557.970, "dur": 46.875, + "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": 4183436, "tid": 31338, + "ts": 667115912787.776, "dur": 520.639, + "args": { + "External id": 234170,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 4183436, "tid": 31338, + "ts": 667115912804.716, "dur": 492.017, + "args": { + "External id": 234171,"Record function id": 0, "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115912865.078, "dur": 5.642, + "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": 4183436, "tid": 31338, + "ts": 667115912886.080, "dur": 31.688, + "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": 4183436, "tid": 31338, + "ts": 667115912890.730, "dur": 1.523, + "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": 4183436, "tid": 31338, + "ts": 667115912894.571, "dur": 0.630, + "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": 4183436, "tid": 31338, + "ts": 667115912897.444, "dur": 0.608, + "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": 4183436, "tid": 31338, + "ts": 667115912902.475, "dur": 0.463, + "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": 4183436, "tid": 31338, + "ts": 667115912903.926, "dur": 0.675, + "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": 4183436, "tid": 31338, + "ts": 667115912906.834, "dur": 0.374, + "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": 4183436, "tid": 31338, + "ts": 667115912908.285, "dur": 0.527, + "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": 4183436, "tid": 31338, + "ts": 667115912910.437, "dur": 1.478, + "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": 4183436, "tid": 31338, + "ts": 667115912913.131, "dur": 0.683, + "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": 4183436, "tid": 31338, + "ts": 667115912927.740, "dur": 31.694, + "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": 4183436, "tid": 31338, + "ts": 667115912991.472, "dur": 91.665, + "args": { + "External id": 234184,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 31338, + "ts": 667115913001.024, "dur": 3.326, + "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": 4183436, "tid": 31338, + "ts": 667115913009.081, "dur": 10.158, + "args": { + "External id": 234186,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 31338, + "ts": 667115913013.379, "dur": 5.455, + "args": { + "External id": 234187,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 31338, + "ts": 667115913016.654, "dur": 1.009, + "args": { + "External id": 234188,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115913025.933, "dur": 20.475, + "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": 4183436, "tid": 31338, + "ts": 667115913027.465, "dur": 0.834, + "args": { + "External id": 234190,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 31338, + "ts": 667115913029.686, "dur": 0.977, + "args": { + "External id": 234191,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 31338, + "ts": 667115913032.057, "dur": 0.624, + "args": { + "External id": 234192,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 31338, + "ts": 667115913034.228, "dur": 0.511, + "args": { + "External id": 234193,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 31338, + "ts": 667115913036.571, "dur": 0.747, + "args": { + "External id": 234194,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 31338, + "ts": 667115913038.372, "dur": 0.600, + "args": { + "External id": 234195,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 31338, + "ts": 667115913039.932, "dur": 0.671, + "args": { + "External id": 234196,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 31338, + "ts": 667115913041.859, "dur": 0.520, + "args": { + "External id": 234197,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 31338, + "ts": 667115913043.573, "dur": 0.480, + "args": { + "External id": 234198,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 31338, + "ts": 667115913055.989, "dur": 20.032, + "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": 4183436, "tid": 31338, + "ts": 667115913129.378, "dur": 105.311, + "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": 4183436, "tid": 31338, + "ts": 667115913149.564, "dur": 81.878, + "args": { + "External id": 234201,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115913161.929, "dur": 65.388, + "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": 4183436, "tid": 31338, + "ts": 667115913249.516, "dur": 1.697, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 667115913323.333, "dur": 1540.482, + "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": 4183436, "tid": 31338, "ts": 667115913323.333, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115913425.495, "dur": 126.132, + "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": 4183436, "tid": 31338, + "ts": 667115913595.834, "dur": 39.047, + "args": { + "External id": 234206,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115913688.997, "dur": 51.090, + "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": 4183436, "tid": 31338, + "ts": 667115913753.025, "dur": 26.930, + "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": 4183436, "tid": 31338, + "ts": 667115913786.694, "dur": 32.263, + "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": 4183436, "tid": 31338, + "ts": 667115913825.487, "dur": 24.742, + "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": 4183436, "tid": 31338, + "ts": 667115913856.963, "dur": 27.823, + "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": 4183436, "tid": 31338, + "ts": 667115913910.330, "dur": 22.750, + "args": { + "External id": 234212,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115913949.931, "dur": 25.909, + "args": { + "External id": 234213,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115913992.371, "dur": 18.929, + "args": { + "External id": 234214,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115914031.375, "dur": 15.929, + "args": { + "External id": 234215,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115914055.122, "dur": 36.262, + "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": 4183436, "tid": 31338, + "ts": 667115914094.808, "dur": 29.765, + "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": 4183436, "tid": 31338, + "ts": 667115914151.252, "dur": 160.802, + "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": 4183436, "tid": 31338, + "ts": 667115914223.723, "dur": 6.687, + "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": 4183436, "tid": 31338, + "ts": 667115914232.941, "dur": 3.315, + "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": 4183436, "tid": 31338, + "ts": 667115914339.746, "dur": 21.594, + "args": { + "External id": 234221,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115914373.074, "dur": 11.714, + "args": { + "External id": 234222,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115914391.282, "dur": 39.106, + "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": 4183436, "tid": 31338, + "ts": 667115914436.402, "dur": 31.506, + "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": 4183436, "tid": 31338, + "ts": 667115914474.037, "dur": 40.533, + "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": 4183436, "tid": 31338, + "ts": 667115914526.288, "dur": 30.111, + "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": 4183436, "tid": 31338, + "ts": 667115914562.447, "dur": 30.663, + "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": 4183436, "tid": 31338, + "ts": 667115914600.678, "dur": 26.879, + "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": 4183436, "tid": 31338, + "ts": 667115914647.574, "dur": 60.802, + "args": { + "External id": 234229,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115914727.323, "dur": 21.554, + "args": { + "External id": 234230,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115914764.718, "dur": 15.596, + "args": { + "External id": 234231,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115914793.944, "dur": 12.755, + "args": { + "External id": 234232,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115914821.808, "dur": 13.413, + "args": { + "External id": 234233,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115914908.748, "dur": 15.291, + "args": { + "External id": 234234,"Record function id": 0, "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115914912.000, "dur": 11.000, + "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": 4183436, "tid": 31338, + "ts": 667115914915.879, "dur": 6.234, + "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": 4183436, "tid": 31338, + "ts": 667115914917.455, "dur": 4.571, + "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": 4183436, "tid": 31338, + "ts": 667115914931.155, "dur": 4.998, + "args": { + "External id": 234238,"Record function id": 0, "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115914932.539, "dur": 3.106, + "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": 4183436, "tid": 31338, + "ts": 667115914933.254, "dur": 1.839, + "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": 4183436, "tid": 31338, + "ts": 667115914934.017, "dur": 0.997, + "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": 4183436, "tid": 31338, + "ts": 667115914939.538, "dur": 4.687, + "args": { + "External id": 234242,"Record function id": 0, "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115914940.885, "dur": 2.912, + "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": 4183436, "tid": 31338, + "ts": 667115914941.625, "dur": 1.754, + "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": 4183436, "tid": 31338, + "ts": 667115914942.069, "dur": 1.248, + "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": 4183436, "tid": 31338, + "ts": 667115914947.491, "dur": 3.985, + "args": { + "External id": 234246,"Record function id": 0, "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115914948.656, "dur": 2.421, + "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": 4183436, "tid": 31338, + "ts": 667115914949.283, "dur": 1.373, + "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": 4183436, "tid": 31338, + "ts": 667115914949.716, "dur": 0.857, + "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": 4183436, "tid": 31338, + "ts": 667115914954.696, "dur": 3.635, + "args": { + "External id": 234250,"Record function id": 0, "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115914955.698, "dur": 2.227, + "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": 4183436, "tid": 31338, + "ts": 667115914956.298, "dur": 1.209, + "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": 4183436, "tid": 31338, + "ts": 667115914956.624, "dur": 0.796, + "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": 4183436, "tid": 31338, + "ts": 667115914961.503, "dur": 3.934, + "args": { + "External id": 234254,"Record function id": 0, "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115914962.636, "dur": 2.351, + "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": 4183436, "tid": 31338, + "ts": 667115914963.165, "dur": 1.411, + "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": 4183436, "tid": 31338, + "ts": 667115914963.570, "dur": 0.921, + "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": 4183436, "tid": 31338, + "ts": 667115914968.607, "dur": 3.873, + "args": { + "External id": 234258,"Record function id": 0, "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115914969.634, "dur": 2.429, + "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": 4183436, "tid": 31338, + "ts": 667115914970.156, "dur": 1.504, + "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": 4183436, "tid": 31338, + "ts": 667115914970.574, "dur": 1.015, + "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": 4183436, "tid": 31338, + "ts": 667115914975.594, "dur": 3.632, + "args": { + "External id": 234262,"Record function id": 0, "Ev Idx": 4373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115914976.697, "dur": 2.094, + "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": 4183436, "tid": 31338, + "ts": 667115914977.194, "dur": 1.179, + "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": 4183436, "tid": 31338, + "ts": 667115914977.478, "dur": 0.805, + "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": 4183436, "tid": 31338, + "ts": 667115914983.000, "dur": 6.589, + "args": { + "External id": 234266,"Record function id": 0, "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115914984.069, "dur": 5.100, + "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": 4183436, "tid": 31338, + "ts": 667115914987.630, "dur": 1.086, + "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": 4183436, "tid": 31338, + "ts": 667115914987.968, "dur": 0.681, + "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": 4183436, "tid": 31338, + "ts": 667115914994.102, "dur": 15332.261, + "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": 4183436, "tid": 31338, + "ts": 667115914995.376, "dur": 15322.667, + "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": 4183436, "tid": 31338, "ts": 667115914995.376, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 4183436, "tid": 31338, + "ts": 667115915023.553, "dur": 37.086, + "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": 4183436, "tid": 31338, + "ts": 667115915068.582, "dur": 65.683, + "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": 4183436, "tid": 31338, + "ts": 667115915140.579, "dur": 15169.974, + "args": { + "External id": 234274,"Record function id": 0, "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115915250.769, "dur": 6.962, + "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": 4183436, "tid": 31338, + "ts": 667115915267.956, "dur": 5.235, + "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": 4183436, "tid": 31338, + "ts": 667115915286.812, "dur": 14388.724, + "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": 4183436, "tid": 31338, + "ts": 667115915303.772, "dur": 14342.233, + "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": 4183436, "tid": 31338, + "ts": 667115915328.286, "dur": 14.766, + "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": 4183436, "tid": 31338, + "ts": 667115915347.047, "dur": 14265.157, + "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": 4183436, "tid": 31338, + "ts": 667115915349.869, "dur": 14261.568, + "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": 4183436, "tid": 31338, + "ts": 667115915357.768, "dur": 4.939, + "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": 4183436, "tid": 31338, + "ts": 667115915364.273, "dur": 14243.997, + "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": 4183436, "tid": 31338, + "ts": 667115929766.053, "dur": 9.806, + "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": 4183436, "tid": 31338, + "ts": 667115929769.027, "dur": 6.511, + "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": 4183436, "tid": 31338, + "ts": 667115929802.141, "dur": 249.768, + "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": 4183436, "tid": 31338, + "ts": 667115929827.633, "dur": 220.078, + "args": { + "External id": 234287,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115929838.570, "dur": 203.151, + "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": 4183436, "tid": 31338, + "ts": 667115930067.485, "dur": 2.272, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115930119.170, "dur": 6.239, + "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": 4183436, "tid": 31338, + "ts": 667115930168.203, "dur": 1.455, + "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": 4183436, "tid": 31338, + "ts": 667115930184.631, "dur": 1.382, + "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": 4183436, "tid": 31338, + "ts": 667115930196.920, "dur": 0.916, + "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": 4183436, "tid": 31338, + "ts": 667115930208.772, "dur": 1.033, + "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": 4183436, "tid": 31338, + "ts": 667115930219.301, "dur": 1.143, + "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": 4183436, "tid": 31338, + "ts": 667115930230.920, "dur": 1.201, + "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": 4183436, "tid": 31338, + "ts": 667115930242.209, "dur": 0.965, + "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": 4183436, "tid": 31338, + "ts": 667115930252.155, "dur": 1.169, + "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": 4183436, "tid": 31338, + "ts": 667115930340.091, "dur": 1978.655, + "args": { + "External id": 234299,"Record function id": 0, "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 4183436, "tid": 31338, + "ts": 667115930360.251, "dur": 470.009, + "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": 4183436, "tid": 31338, + "ts": 667115930375.412, "dur": 358.243, + "args": { + "External id": 234301,"Record function id": 0, "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 667115930453.784, "dur": 4.135, + "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": 4183436, "tid": 31338, + "ts": 667115930460.729, "dur": 1.564, + "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": 4183436, "tid": 31338, + "ts": 667115930464.161, "dur": 1.271, + "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": 4183436, "tid": 31338, + "ts": 667115930466.955, "dur": 1.049, + "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": 4183436, "tid": 31338, + "ts": 667115930469.849, "dur": 1.109, + "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": 4183436, "tid": 31338, + "ts": 667115930472.664, "dur": 0.981, + "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": 4183436, "tid": 31338, + "ts": 667115930475.034, "dur": 1.033, + "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": 4183436, "tid": 31338, + "ts": 667115930478.273, "dur": 1.014, + "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": 4183436, "tid": 31338, + "ts": 667115930480.573, "dur": 1.172, + "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": 4183436, "tid": 31338, + "ts": 667115930482.979, "dur": 1.138, + "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": 4183436, "tid": 31338, + "ts": 667115930522.976, "dur": 178.185, + "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": 4183436, "tid": 31338, + "ts": 667115930539.344, "dur": 156.825, + "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": 4183436, "tid": 31338, + "ts": 667115930551.946, "dur": 12.814, + "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": 4183436, "tid": 31338, + "ts": 667115930567.598, "dur": 63.728, + "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": 4183436, "tid": 31338, + "ts": 667115930570.449, "dur": 60.488, + "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": 4183436, "tid": 31338, + "ts": 667115930574.823, "dur": 6.257, + "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": 4183436, "tid": 31338, + "ts": 667115930582.808, "dur": 47.680, + "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": 4183436, "tid": 31338, + "ts": 667115930838.437, "dur": 1458.922, + "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": 4183436, "tid": 31338, "ts": 667115930838.437, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 667115930946.430, "dur": 104.896, + "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": 4183436, "tid": 31338, + "ts": 667115931087.690, "dur": 36.236, + "args": { + "External id": 234321,"kernel_hash": "cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/yn/cynpuzjrlv5pbp2xypn2qunxj2lm5i33k7rsbghp5vrwhqcidsje.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": 4183436, "tid": 31338, + "ts": 667115931138.643, "dur": 39.002, + "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": 4183436, "tid": 31338, + "ts": 667115931186.700, "dur": 28.638, + "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": 4183436, "tid": 31338, + "ts": 667115931221.111, "dur": 31.663, + "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": 4183436, "tid": 31338, + "ts": 667115931259.424, "dur": 23.529, + "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": 4183436, "tid": 31338, + "ts": 667115931290.669, "dur": 28.005, + "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": 4183436, "tid": 31338, + "ts": 667115931340.291, "dur": 21.427, + "args": { + "External id": 234327,"kernel_hash": "ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwyguwmoo5q4aqqdvjcf6fkvl35eh5iawqq5fl22ourxscb5yc2.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": 4183436, "tid": 31338, + "ts": 667115931378.493, "dur": 26.782, + "args": { + "External id": 234328,"kernel_hash": "coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq", "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/oq/coqhzcai2zpjlz7zliclrore2qgfaixhiqj5reumopduvgs7hgkq.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": 4183436, "tid": 31338, + "ts": 667115931422.663, "dur": 17.153, + "args": { + "External id": 234329,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115931453.298, "dur": 13.139, + "args": { + "External id": 234330,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115931473.687, "dur": 55.037, + "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": 4183436, "tid": 31338, + "ts": 667115931533.785, "dur": 32.653, + "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": 4183436, "tid": 31338, + "ts": 667115931593.653, "dur": 204.744, + "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": 4183436, "tid": 31338, + "ts": 667115931703.445, "dur": 6.805, + "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": 4183436, "tid": 31338, + "ts": 667115931712.791, "dur": 4.020, + "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": 4183436, "tid": 31338, + "ts": 667115931829.854, "dur": 24.394, + "args": { + "External id": 234336,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115931865.339, "dur": 12.814, + "args": { + "External id": 234337,"kernel_hash": "cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn", "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/c4/cc43cchabr3xqqbhvyq2k5zli7drjm7tuupmfuwbvpbmcavpzuyn.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": 4183436, "tid": 31338, + "ts": 667115931886.168, "dur": 47.450, + "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": 4183436, "tid": 31338, + "ts": 667115931939.923, "dur": 30.058, + "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": 4183436, "tid": 31338, + "ts": 667115931976.087, "dur": 26.805, + "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": 4183436, "tid": 31338, + "ts": 667115932007.726, "dur": 26.592, + "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": 4183436, "tid": 31338, + "ts": 667115932039.689, "dur": 26.605, + "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": 4183436, "tid": 31338, + "ts": 667115932073.415, "dur": 27.536, + "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": 4183436, "tid": 31338, + "ts": 667115932116.498, "dur": 22.092, + "args": { + "External id": 234344,"kernel_hash": "cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgexdmejamjrx4oie7m7uazxd6bbvd77iwrxr6ahie37yzk4rdo4.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": 4183436, "tid": 31338, + "ts": 667115932154.296, "dur": 24.227, + "args": { + "External id": 234345,"kernel_hash": "c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2", "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/5o/c5omne4ch7c257ysksxmpllicgdj2qdvlyymj6wnjpzllogjpll2.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": 4183436, "tid": 31338, + "ts": 667115932192.067, "dur": 17.354, + "args": { + "External id": 234346,"kernel_hash": "ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/a4/ca43jqag24oztgxmf7j3jkrqbdg4w7e2lj7inx6wnctdgm27tgyd.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": 4183436, "tid": 31338, + "ts": 667115932226.004, "dur": 14.619, + "args": { + "External id": 234347,"kernel_hash": "c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7p3ah3xbynhnurb6dknuamyaejgrltpdysttkxsh5q2sltw4rm5.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": 4183436, "tid": 31338, + "ts": 667115932252.023, "dur": 14.941, + "args": { + "External id": 234348,"kernel_hash": "cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ld/cldlvyxlliadukab7izuzfxjbw636jakujq7fcee4gne46kaoxjl.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": 4183436, "tid": 31338, + "ts": 667115932344.154, "dur": 15.201, + "args": { + "External id": 234349,"Record function id": 0, "Ev Idx": 4460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115932347.737, "dur": 10.783, + "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": 4183436, "tid": 31338, + "ts": 667115932351.853, "dur": 5.760, + "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": 4183436, "tid": 31338, + "ts": 667115932353.209, "dur": 4.300, + "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": 4183436, "tid": 31338, + "ts": 667115932363.389, "dur": 5.046, + "args": { + "External id": 234353,"Record function id": 0, "Ev Idx": 4464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115932364.913, "dur": 3.042, + "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": 4183436, "tid": 31338, + "ts": 667115932365.866, "dur": 1.515, + "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": 4183436, "tid": 31338, + "ts": 667115932366.356, "dur": 0.941, + "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": 4183436, "tid": 31338, + "ts": 667115932371.797, "dur": 5.233, + "args": { + "External id": 234357,"Record function id": 0, "Ev Idx": 4468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115932373.449, "dur": 3.146, + "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": 4183436, "tid": 31338, + "ts": 667115932374.146, "dur": 1.991, + "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": 4183436, "tid": 31338, + "ts": 667115932375.237, "dur": 0.789, + "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": 4183436, "tid": 31338, + "ts": 667115932380.269, "dur": 4.723, + "args": { + "External id": 234361,"Record function id": 0, "Ev Idx": 4472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115932381.908, "dur": 2.677, + "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": 4183436, "tid": 31338, + "ts": 667115932382.771, "dur": 1.358, + "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": 4183436, "tid": 31338, + "ts": 667115932383.292, "dur": 0.763, + "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": 4183436, "tid": 31338, + "ts": 667115932388.112, "dur": 8.279, + "args": { + "External id": 234365,"Record function id": 0, "Ev Idx": 4476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115932392.599, "dur": 3.345, + "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": 4183436, "tid": 31338, + "ts": 667115932393.565, "dur": 1.957, + "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": 4183436, "tid": 31338, + "ts": 667115932394.105, "dur": 1.351, + "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": 4183436, "tid": 31338, + "ts": 667115932399.591, "dur": 4.700, + "args": { + "External id": 234369,"Record function id": 0, "Ev Idx": 4480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115932401.128, "dur": 2.746, + "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": 4183436, "tid": 31338, + "ts": 667115932402.105, "dur": 1.341, + "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": 4183436, "tid": 31338, + "ts": 667115932402.710, "dur": 0.659, + "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": 4183436, "tid": 31338, + "ts": 667115932407.584, "dur": 3.961, + "args": { + "External id": 234373,"Record function id": 0, "Ev Idx": 4484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115932408.802, "dur": 2.301, + "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": 4183436, "tid": 31338, + "ts": 667115932409.517, "dur": 1.152, + "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": 4183436, "tid": 31338, + "ts": 667115932409.875, "dur": 0.724, + "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": 4183436, "tid": 31338, + "ts": 667115932415.275, "dur": 4.384, + "args": { + "External id": 234377,"Record function id": 0, "Ev Idx": 4488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115932416.742, "dur": 2.515, + "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": 4183436, "tid": 31338, + "ts": 667115932417.445, "dur": 1.369, + "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": 4183436, "tid": 31338, + "ts": 667115932417.896, "dur": 0.843, + "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": 4183436, "tid": 31338, + "ts": 667115932423.212, "dur": 4.111, + "args": { + "External id": 234381,"Record function id": 0, "Ev Idx": 4492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115932424.490, "dur": 2.425, + "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": 4183436, "tid": 31338, + "ts": 667115932424.977, "dur": 1.473, + "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": 4183436, "tid": 31338, + "ts": 667115932425.510, "dur": 0.870, + "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": 4183436, "tid": 31338, + "ts": 667115932431.297, "dur": 16057.206, + "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": 4183436, "tid": 31338, + "ts": 667115932432.470, "dur": 16047.438, + "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": 4183436, "tid": 31338, "ts": 667115932432.470, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 4183436, "tid": 31338, + "ts": 667115932463.006, "dur": 56.381, + "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": 4183436, "tid": 31338, + "ts": 667115932528.350, "dur": 72.857, + "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": 4183436, "tid": 31338, + "ts": 667115932607.449, "dur": 15864.961, + "args": { + "External id": 234389,"Record function id": 0, "Ev Idx": 4500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115932734.889, "dur": 7.484, + "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": 4183436, "tid": 31338, + "ts": 667115932753.140, "dur": 5.788, + "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": 4183436, "tid": 31338, + "ts": 667115932773.557, "dur": 15081.759, + "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": 4183436, "tid": 31338, + "ts": 667115932786.993, "dur": 15060.183, + "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": 4183436, "tid": 31338, + "ts": 667115932809.972, "dur": 14.108, + "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": 4183436, "tid": 31338, + "ts": 667115932828.063, "dur": 14982.952, + "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": 4183436, "tid": 31338, + "ts": 667115932830.942, "dur": 14979.316, + "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": 4183436, "tid": 31338, + "ts": 667115932835.262, "dur": 13.513, + "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": 4183436, "tid": 31338, + "ts": 667115932852.490, "dur": 14955.312, + "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": 4183436, "tid": 31338, + "ts": 667115947942.494, "dur": 9.225, + "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": 4183436, "tid": 31338, + "ts": 667115947945.552, "dur": 5.780, + "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": 4183436, "tid": 31338, + "ts": 667115947979.795, "dur": 239.896, + "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": 4183436, "tid": 31338, + "ts": 667115948005.472, "dur": 210.176, + "args": { + "External id": 234402,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115948016.479, "dur": 194.461, + "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": 4183436, "tid": 31338, + "ts": 667115948235.352, "dur": 1.894, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115948282.775, "dur": 6.241, + "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": 4183436, "tid": 31338, + "ts": 667115948331.444, "dur": 1.524, + "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": 4183436, "tid": 31338, + "ts": 667115948348.730, "dur": 1.279, + "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": 4183436, "tid": 31338, + "ts": 667115948361.060, "dur": 1.245, + "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": 4183436, "tid": 31338, + "ts": 667115948372.117, "dur": 1.091, + "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": 4183436, "tid": 31338, + "ts": 667115948382.794, "dur": 1.140, + "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": 4183436, "tid": 31338, + "ts": 667115948394.780, "dur": 0.913, + "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": 4183436, "tid": 31338, + "ts": 667115948406.487, "dur": 1.154, + "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": 4183436, "tid": 31338, + "ts": 667115948416.754, "dur": 0.937, + "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": 4183436, "tid": 31338, + "ts": 667115948521.081, "dur": 321.743, + "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": 4183436, "tid": 31338, + "ts": 667115948524.212, "dur": 310.087, + "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": 4183436, "tid": 31338, "ts": 667115948524.212, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 4183436, "tid": 31338, + "ts": 667115948642.111, "dur": 88.352, + "args": { + "External id": 234416,"kernel_hash": "csyvayit356g2m3psiv74x25w7xwre5r4uwbcwmidzayvaxwaf53", "grid": "grid(32768000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "32768000"], "kernel_file": "/tmp/torchinductor_cvm/sy/csyvayit356g2m3psiv74x25w7xwre5r4uwbcwmidzayvaxwaf53.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": 4183436, "tid": 31338, + "ts": 667115948750.415, "dur": 28.712, + "args": { + "External id": 234417,"kernel_hash": "citdojgwnoigpqelwefwsv3wq5esgn435pm7pmd4oenv22f63gex", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/it/citdojgwnoigpqelwefwsv3wq5esgn435pm7pmd4oenv22f63gex.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": 4183436, "tid": 31338, + "ts": 667115948797.333, "dur": 21.140, + "args": { + "External id": 234418,"kernel_hash": "cfqhyrci7bswjdkqr7mejgwm2xvy5fegyocdjaam4le6heje7y6d", "grid": "grid(32768000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "32768000"], "kernel_file": "/tmp/torchinductor_cvm/fq/cfqhyrci7bswjdkqr7mejgwm2xvy5fegyocdjaam4le6heje7y6d.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": 4183436, "tid": 31338, + "ts": 667115948854.196, "dur": 13.977, + "args": { + "External id": 234419,"Record function id": 0, "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 667115948856.818, "dur": 10.458, + "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": 4183436, "tid": 31338, + "ts": 667115948860.919, "dur": 5.615, + "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": 4183436, "tid": 31338, + "ts": 667115948862.345, "dur": 4.090, + "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": 4183436, "tid": 31338, + "ts": 667115948889.611, "dur": 6473.979, + "args": { + "External id": 234423,"Record function id": 0, "Ev Idx": 4534 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 4183436, "tid": 31338, + "ts": 667115948910.771, "dur": 29.678, + "args": { + "External id": 234424,"Record function id": 0, "Ev Idx": 4535 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 4183436, "tid": 31338, + "ts": 667115948946.096, "dur": 203.397, + "args": { + "External id": 234425,"Record function id": 0, "Ev Idx": 4536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 4183436, "tid": 31338, + "ts": 667115949155.717, "dur": 6005.661, + "args": { + "External id": 234426,"Record function id": 0, "Ev Idx": 4537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 667115949263.109, "dur": 6.634, + "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": 4183436, "tid": 31338, + "ts": 667115949279.215, "dur": 4.661, + "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": 4183436, "tid": 31338, + "ts": 667115949303.206, "dur": 4697.680, + "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": 4183436, "tid": 31338, + "ts": 667115949319.997, "dur": 4670.173, + "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": 4183436, "tid": 31338, + "ts": 667115949417.761, "dur": 11.948, + "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": 4183436, "tid": 31338, + "ts": 667115949455.315, "dur": 4495.727, + "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": 4183436, "tid": 31338, + "ts": 667115949457.949, "dur": 4492.372, + "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": 4183436, "tid": 31338, + "ts": 667115949461.851, "dur": 6.077, + "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": 4183436, "tid": 31338, + "ts": 667115949469.639, "dur": 4476.420, + "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": 4183436, "tid": 31338, + "ts": 667115954119.851, "dur": 9.955, + "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": 4183436, "tid": 31338, + "ts": 667115954123.068, "dur": 6.401, + "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": 4183436, "tid": 31338, + "ts": 667115954155.308, "dur": 380.491, + "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": 4183436, "tid": 31338, + "ts": 667115954179.471, "dur": 351.073, + "args": { + "External id": 234439,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 31338, + "ts": 667115954189.929, "dur": 335.026, + "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": 4183436, "tid": 31338, + "ts": 667115954560.224, "dur": 2.342, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 31338, + "ts": 667115954617.727, "dur": 6.387, + "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": 4183436, "tid": 31338, + "ts": 667115954702.210, "dur": 2.079, + "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": 4183436, "tid": 31338, + "ts": 667115954720.488, "dur": 1.931, + "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": 4183436, "tid": 31338, + "ts": 667115954734.392, "dur": 1.502, + "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": 4183436, "tid": 31338, + "ts": 667115954745.536, "dur": 1.450, + "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": 4183436, "tid": 31338, + "ts": 667115954756.467, "dur": 1.418, + "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": 4183436, "tid": 31338, + "ts": 667115954767.162, "dur": 1.479, + "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": 4183436, "tid": 31338, + "ts": 667115954778.374, "dur": 1.450, + "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": 4183436, "tid": 31338, + "ts": 667115954789.583, "dur": 1.206, + "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": 4183436, "tid": 31338, + "ts": 667115954799.787, "dur": 1.173, + "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": 4183436, "tid": 31338, + "ts": 667115954810.406, "dur": 1.282, + "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": 4183436, "tid": 31338, + "ts": 667115954820.741, "dur": 1.550, + "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": 4183436, "tid": 31338, + "ts": 667115954831.895, "dur": 1.235, + "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": 4183436, "tid": 31338, + "ts": 667115954842.167, "dur": 1.253, + "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": 4183436, "tid": 31338, + "ts": 667115954851.539, "dur": 1.457, + "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": 4183436, "tid": 31338, + "ts": 667115954861.473, "dur": 1.305, + "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": 4183436, "tid": 31338, + "ts": 667115954871.022, "dur": 1.329, + "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": 4183436, "tid": 31338, + "ts": 667115954881.313, "dur": 1.225, + "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": 4183436, "tid": 31338, + "ts": 667115954891.586, "dur": 1.225, + "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": 4183436, "tid": 31338, + "ts": 667115954902.143, "dur": 0.973, + "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": 4183436, "tid": 31338, + "ts": 667115954912.879, "dur": 1.260, + "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": 4183436, "tid": 31338, + "ts": 667115954922.704, "dur": 1.415, + "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": 4183436, "tid": 31338, + "ts": 667115954933.249, "dur": 1.687, + "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": 4183436, "tid": 31338, + "ts": 667115954943.597, "dur": 1.232, + "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": 4183436, "tid": 31338, + "ts": 667115954953.589, "dur": 1.253, + "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": 4183436, "tid": 31338, + "ts": 667115954963.154, "dur": 1.088, + "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": 4183436, "tid": 31338, + "ts": 667115954972.544, "dur": 1.380, + "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": 4183436, "tid": 31338, + "ts": 667115954982.285, "dur": 1.335, + "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": 4183436, "tid": 31338, + "ts": 667115954992.850, "dur": 1.637, + "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": 4183436, "tid": 31338, + "ts": 667115955004.239, "dur": 1.075, + "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": 4183436, "tid": 31338, + "ts": 667115955014.714, "dur": 1.238, + "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": 4183436, "tid": 31338, + "ts": 667115955025.075, "dur": 1.050, + "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": 4183436, "tid": 31338, + "ts": 667115955035.211, "dur": 0.964, + "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": 4183436, "tid": 31338, + "ts": 667115955044.992, "dur": 1.918, + "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": 4183436, "tid": 31338, + "ts": 667115955057.019, "dur": 1.011, + "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": 4183436, "tid": 31338, + "ts": 667115955066.952, "dur": 1.115, + "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": 4183436, "tid": 31338, + "ts": 667115955078.244, "dur": 1.281, + "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": 4183436, "tid": 31338, + "ts": 667115955088.459, "dur": 1.114, + "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": 4183436, "tid": 31338, + "ts": 667115955098.687, "dur": 1.259, + "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": 4183436, "tid": 4183436, + "ts": 667115182947.779, "dur": 786125.575, + "args": { + "External id": 225793,"Record function id": 0, "Ev Idx": 4592 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 4183436, "tid": 4183436, + "ts": 667115182980.811, "dur": 372.300, + "args": { + "External id": 225794,"Record function id": 0, "Ev Idx": 4593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 4183436, "tid": 4183436, + "ts": 667115183386.321, "dur": 2062.463, + "args": { + "External id": 225795,"Record function id": 0, "Ev Idx": 4594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115184395.111, "dur": 7.929, + "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": 4183436, "tid": 4183436, + "ts": 667115184423.456, "dur": 6.432, + "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": 4183436, "tid": 4183436, + "ts": 667115184920.772, "dur": 2.359, + "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": 4183436, "tid": 4183436, + "ts": 667115184930.699, "dur": 2.577, + "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": 4183436, "tid": 4183436, + "ts": 667115185345.020, "dur": 1.943, + "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": 4183436, "tid": 4183436, + "ts": 667115185354.075, "dur": 1.764, + "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": 4183436, "tid": 4183436, + "ts": 667115186195.001, "dur": 13.948, + "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": 4183436, "tid": 4183436, + "ts": 667115186202.990, "dur": 2.269, + "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": 4183436, "tid": 4183436, + "ts": 667115186210.483, "dur": 4.078, + "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": 4183436, "tid": 4183436, + "ts": 667115186212.572, "dur": 0.819, + "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": 4183436, "tid": 4183436, + "ts": 667115186240.335, "dur": 566.036, + "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": 4183436, "tid": 4183436, + "ts": 667115186247.505, "dur": 557.772, + "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": 4183436, "tid": 4183436, + "ts": 667115186256.163, "dur": 9.631, + "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": 4183436, "tid": 4183436, + "ts": 667115186268.605, "dur": 534.684, + "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": 4183436, "tid": 4183436, + "ts": 667115186278.241, "dur": 0.579, + "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": 4183436, "tid": 4183436, + "ts": 667115186281.754, "dur": 8.885, + "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": 4183436, "tid": 4183436, + "ts": 667115186287.082, "dur": 3.403, + "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": 4183436, "tid": 4183436, + "ts": 667115186289.642, "dur": 0.576, + "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": 4183436, "tid": 4183436, + "ts": 667115186292.584, "dur": 188.266, + "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": 4183436, "tid": 4183436, + "ts": 667115186295.022, "dur": 185.377, + "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": 4183436, "tid": 4183436, + "ts": 667115186297.564, "dur": 16.627, + "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": 4183436, "tid": 4183436, + "ts": 667115186299.615, "dur": 14.014, + "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": 4183436, "tid": 4183436, + "ts": 667115186314.781, "dur": 165.089, + "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": 4183436, "tid": 4183436, + "ts": 667115186482.799, "dur": 315.312, + "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": 4183436, "tid": 4183436, + "ts": 667115186828.557, "dur": 525.226, + "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": 4183436, "tid": 4183436, + "ts": 667115186830.916, "dur": 521.756, + "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": 4183436, "tid": 4183436, + "ts": 667115186839.756, "dur": 9.211, + "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": 4183436, "tid": 4183436, + "ts": 667115186850.828, "dur": 498.583, + "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": 4183436, "tid": 4183436, + "ts": 667115187380.184, "dur": 50.130, + "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": 4183436, "tid": 4183436, + "ts": 667115187384.946, "dur": 5.138, + "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": 4183436, "tid": 4183436, + "ts": 667115187392.692, "dur": 37.137, + "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": 4183436, "tid": 4183436, + "ts": 667115187397.305, "dur": 6.671, + "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": 4183436, "tid": 4183436, + "ts": 667115187443.506, "dur": 94.136, + "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": 4183436, "tid": 4183436, + "ts": 667115187448.728, "dur": 8.174, + "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": 4183436, "tid": 4183436, + "ts": 667115187454.453, "dur": 2.208, + "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": 4183436, "tid": 4183436, + "ts": 667115187457.868, "dur": 4.470, + "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": 4183436, "tid": 4183436, + "ts": 667115187467.807, "dur": 3.306, + "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": 4183436, "tid": 4183436, + "ts": 667115187473.903, "dur": 4.879, + "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": 4183436, "tid": 4183436, + "ts": 667115187478.081, "dur": 0.559, + "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": 4183436, "tid": 4183436, + "ts": 667115187479.956, "dur": 4.750, + "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": 4183436, "tid": 4183436, + "ts": 667115187483.786, "dur": 0.834, + "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": 4183436, "tid": 4183436, + "ts": 667115187486.860, "dur": 21.152, + "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": 4183436, "tid": 4183436, + "ts": 667115187488.626, "dur": 19.232, + "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": 4183436, "tid": 4183436, + "ts": 667115187506.179, "dur": 1.281, + "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": 4183436, "tid": 4183436, + "ts": 667115187509.413, "dur": 27.532, + "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": 4183436, "tid": 4183436, + "ts": 667115187547.659, "dur": 32.489, + "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": 4183436, "tid": 4183436, + "ts": 667115187549.337, "dur": 30.643, + "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": 4183436, "tid": 4183436, + "ts": 667115187557.184, "dur": 3.755, + "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": 4183436, "tid": 4183436, + "ts": 667115187561.793, "dur": 17.782, + "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": 4183436, "tid": 4183436, + "ts": 667115187730.046, "dur": 150.375, + "args": { + "External id": 225845,"Record function id": 0, "Ev Idx": 4644 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 4183436, "tid": 4183436, + "ts": 667115187812.227, "dur": 57.824, + "args": { + "External id": 225846,"Record function id": 0, "Ev Idx": 4645 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115187887.237, "dur": 43.423, + "args": { + "External id": 225847,"Record function id": 0, "Ev Idx": 4646 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 4183436, "tid": 4183436, + "ts": 667115187938.793, "dur": 7881.248, + "args": { + "External id": 225848,"Record function id": 0, "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 4183436, "tid": 4183436, + "ts": 667115187947.199, "dur": 1308.459, + "args": { + "External id": 225849,"Record function id": 0, "Ev Idx": 4648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115188046.838, "dur": 7.258, + "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": 4183436, "tid": 4183436, + "ts": 667115188070.519, "dur": 128.688, + "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": 4183436, "tid": 4183436, + "ts": 667115188075.521, "dur": 1.822, + "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": 4183436, "tid": 4183436, + "ts": 667115188084.022, "dur": 0.332, + "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": 4183436, "tid": 4183436, + "ts": 667115188085.394, "dur": 0.318, + "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": 4183436, "tid": 4183436, + "ts": 667115188086.834, "dur": 1.521, + "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": 4183436, "tid": 4183436, + "ts": 667115188094.424, "dur": 0.384, + "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": 4183436, "tid": 4183436, + "ts": 667115188095.724, "dur": 0.192, + "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": 4183436, "tid": 4183436, + "ts": 667115188096.789, "dur": 2.456, + "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": 4183436, "tid": 4183436, + "ts": 667115188102.532, "dur": 0.186, + "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": 4183436, "tid": 4183436, + "ts": 667115188103.728, "dur": 0.330, + "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": 4183436, "tid": 4183436, + "ts": 667115188109.328, "dur": 0.189, + "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": 4183436, "tid": 4183436, + "ts": 667115188110.171, "dur": 0.190, + "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": 4183436, "tid": 4183436, + "ts": 667115188111.088, "dur": 1.366, + "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": 4183436, "tid": 4183436, + "ts": 667115188117.485, "dur": 0.355, + "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": 4183436, "tid": 4183436, + "ts": 667115188118.590, "dur": 0.404, + "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": 4183436, "tid": 4183436, + "ts": 667115188119.595, "dur": 2.961, + "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": 4183436, "tid": 4183436, + "ts": 667115188125.698, "dur": 0.331, + "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": 4183436, "tid": 4183436, + "ts": 667115188126.659, "dur": 0.275, + "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": 4183436, "tid": 4183436, + "ts": 667115188132.096, "dur": 0.139, + "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": 4183436, "tid": 4183436, + "ts": 667115188132.934, "dur": 0.296, + "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": 4183436, "tid": 4183436, + "ts": 667115188133.708, "dur": 1.437, + "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": 4183436, "tid": 4183436, + "ts": 667115188138.547, "dur": 0.216, + "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": 4183436, "tid": 4183436, + "ts": 667115188139.716, "dur": 0.179, + "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": 4183436, "tid": 4183436, + "ts": 667115188140.661, "dur": 2.253, + "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": 4183436, "tid": 4183436, + "ts": 667115188146.161, "dur": 0.150, + "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": 4183436, "tid": 4183436, + "ts": 667115188146.977, "dur": 0.281, + "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": 4183436, "tid": 4183436, + "ts": 667115188152.374, "dur": 0.152, + "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": 4183436, "tid": 4183436, + "ts": 667115188153.253, "dur": 0.284, + "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": 4183436, "tid": 4183436, + "ts": 667115188154.183, "dur": 1.246, + "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": 4183436, "tid": 4183436, + "ts": 667115188158.596, "dur": 0.297, + "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": 4183436, "tid": 4183436, + "ts": 667115188159.512, "dur": 0.421, + "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": 4183436, "tid": 4183436, + "ts": 667115188160.355, "dur": 2.602, + "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": 4183436, "tid": 4183436, + "ts": 667115188165.817, "dur": 0.185, + "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": 4183436, "tid": 4183436, + "ts": 667115188166.798, "dur": 0.294, + "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": 4183436, "tid": 4183436, + "ts": 667115188172.551, "dur": 0.139, + "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": 4183436, "tid": 4183436, + "ts": 667115188173.330, "dur": 0.255, + "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": 4183436, "tid": 4183436, + "ts": 667115188174.457, "dur": 1.461, + "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": 4183436, "tid": 4183436, + "ts": 667115188179.396, "dur": 0.180, + "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": 4183436, "tid": 4183436, + "ts": 667115188180.317, "dur": 0.268, + "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": 4183436, "tid": 4183436, + "ts": 667115188181.599, "dur": 2.677, + "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": 4183436, "tid": 4183436, + "ts": 667115188221.884, "dur": 49.294, + "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": 4183436, "tid": 4183436, + "ts": 667115188332.759, "dur": 307.290, + "args": { + "External id": 225892,"Record function id": 0, "Concrete Inputs": ["", "", "14615680", "8", "0", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 4691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115188346.715, "dur": 4.287, + "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": 4183436, "tid": 4183436, + "ts": 667115188357.478, "dur": 13.441, + "args": { + "External id": 225894,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115188361.990, "dur": 8.507, + "args": { + "External id": 225895,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "14615680", "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": 4183436, "tid": 4183436, + "ts": 667115188367.232, "dur": 0.649, + "args": { + "External id": 225896,"Record function id": 0, "Concrete Inputs": ["", "[14615680]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115188378.426, "dur": 179.198, + "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": 4183436, "tid": 4183436, + "ts": 667115188380.106, "dur": 0.526, + "args": { + "External id": 225898,"Record function id": 0, "Concrete Inputs": ["", "[4096000]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115188381.830, "dur": 0.210, + "args": { + "External id": 225899,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "4096000"], "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": 4183436, "tid": 4183436, + "ts": 667115188385.036, "dur": 1.779, + "args": { + "External id": 225900,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "4096128"], "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": 4183436, "tid": 4183436, + "ts": 667115188387.370, "dur": 0.677, + "args": { + "External id": 225901,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "4227200"], "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": 4183436, "tid": 4183436, + "ts": 667115188391.901, "dur": 0.373, + "args": { + "External id": 225902,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "4358272"], "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": 4183436, "tid": 4183436, + "ts": 667115188393.122, "dur": 0.318, + "args": { + "External id": 225903,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "4489344"], "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": 4183436, "tid": 4183436, + "ts": 667115188394.331, "dur": 0.309, + "args": { + "External id": 225904,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "4620416"], "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": 4183436, "tid": 4183436, + "ts": 667115188397.675, "dur": 0.299, + "args": { + "External id": 225905,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "4620544"], "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": 4183436, "tid": 4183436, + "ts": 667115188398.681, "dur": 0.738, + "args": { + "External id": 225906,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "4980992"], "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": 4183436, "tid": 4183436, + "ts": 667115188400.152, "dur": 0.145, + "args": { + "External id": 225907,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "5341440"], "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": 4183436, "tid": 4183436, + "ts": 667115188403.332, "dur": 1.204, + "args": { + "External id": 225908,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "5701888"], "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": 4183436, "tid": 4183436, + "ts": 667115188405.477, "dur": 0.309, + "args": { + "External id": 225909,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "5702016"], "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": 4183436, "tid": 4183436, + "ts": 667115188408.300, "dur": 2.137, + "args": { + "External id": 225910,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "5833088"], "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": 4183436, "tid": 4183436, + "ts": 667115188411.537, "dur": 0.192, + "args": { + "External id": 225911,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "5964160"], "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": 4183436, "tid": 4183436, + "ts": 667115188412.715, "dur": 0.306, + "args": { + "External id": 225912,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6095232"], "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": 4183436, "tid": 4183436, + "ts": 667115188418.758, "dur": 0.192, + "args": { + "External id": 225913,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6226304"], "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": 4183436, "tid": 4183436, + "ts": 667115188419.683, "dur": 0.263, + "args": { + "External id": 225914,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6226432"], "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": 4183436, "tid": 4183436, + "ts": 667115188420.971, "dur": 0.169, + "args": { + "External id": 225915,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6586880"], "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": 4183436, "tid": 4183436, + "ts": 667115188426.173, "dur": 1.231, + "args": { + "External id": 225916,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6947328"], "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": 4183436, "tid": 4183436, + "ts": 667115188428.093, "dur": 0.283, + "args": { + "External id": 225917,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "7307776"], "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": 4183436, "tid": 4183436, + "ts": 667115188431.100, "dur": 2.468, + "args": { + "External id": 225918,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "7307904"], "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": 4183436, "tid": 4183436, + "ts": 667115188434.442, "dur": 0.321, + "args": { + "External id": 225919,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "7438976"], "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": 4183436, "tid": 4183436, + "ts": 667115188435.195, "dur": 0.313, + "args": { + "External id": 225920,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "7570048"], "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": 4183436, "tid": 4183436, + "ts": 667115188440.565, "dur": 0.285, + "args": { + "External id": 225921,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "7701120"], "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": 4183436, "tid": 4183436, + "ts": 667115188441.522, "dur": 0.333, + "args": { + "External id": 225922,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "7832192"], "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": 4183436, "tid": 4183436, + "ts": 667115188442.753, "dur": 0.163, + "args": { + "External id": 225923,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7832320"], "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": 4183436, "tid": 4183436, + "ts": 667115188448.395, "dur": 0.977, + "args": { + "External id": 225924,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "8192768"], "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": 4183436, "tid": 4183436, + "ts": 667115188450.211, "dur": 0.290, + "args": { + "External id": 225925,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "8553216"], "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": 4183436, "tid": 4183436, + "ts": 667115188453.486, "dur": 2.009, + "args": { + "External id": 225926,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "8913664"], "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": 4183436, "tid": 4183436, + "ts": 667115188456.353, "dur": 0.317, + "args": { + "External id": 225927,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "8913792"], "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": 4183436, "tid": 4183436, + "ts": 667115188457.495, "dur": 0.289, + "args": { + "External id": 225928,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "9044864"], "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": 4183436, "tid": 4183436, + "ts": 667115188463.019, "dur": 0.358, + "args": { + "External id": 225929,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "9175936"], "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": 4183436, "tid": 4183436, + "ts": 667115188464.024, "dur": 0.282, + "args": { + "External id": 225930,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "9307008"], "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": 4183436, "tid": 4183436, + "ts": 667115188465.188, "dur": 0.177, + "args": { + "External id": 225931,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "9438080"], "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": 4183436, "tid": 4183436, + "ts": 667115188469.171, "dur": 1.320, + "args": { + "External id": 225932,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "9438208"], "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": 4183436, "tid": 4183436, + "ts": 667115188470.946, "dur": 0.166, + "args": { + "External id": 225933,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "9798656"], "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": 4183436, "tid": 4183436, + "ts": 667115188474.079, "dur": 2.573, + "args": { + "External id": 225934,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "10159104"], "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": 4183436, "tid": 4183436, + "ts": 667115188477.336, "dur": 0.333, + "args": { + "External id": 225935,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "10519552"], "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": 4183436, "tid": 4183436, + "ts": 667115188478.303, "dur": 0.313, + "args": { + "External id": 225936,"Record function id": 0, "Concrete Inputs": ["", "[4096000]", "[1]", "10519680"], "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": 4183436, "tid": 4183436, + "ts": 667115188585.171, "dur": 38.916, + "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": 4183436, "tid": 4183436, + "ts": 667115188740.914, "dur": 387.170, + "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": 4183436, "tid": 4183436, + "ts": 667115188778.277, "dur": 343.859, + "args": { + "External id": 225939,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115188788.068, "dur": 326.591, + "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": 4183436, "tid": 4183436, + "ts": 667115189159.879, "dur": 3.176, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 4183436, "tid": 4183436, + "ts": 667115189272.300, "dur": 6322.258, + "args": { + "External id": 225942,"Record function id": 0, "Ev Idx": 4741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115189444.069, "dur": 6.706, + "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": 4183436, "tid": 4183436, + "ts": 667115189454.613, "dur": 1.177, + "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": 4183436, "tid": 4183436, + "ts": 667115189457.674, "dur": 0.881, + "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": 4183436, "tid": 4183436, + "ts": 667115189460.493, "dur": 1.773, + "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": 4183436, "tid": 4183436, + "ts": 667115189466.421, "dur": 0.622, + "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": 4183436, "tid": 4183436, + "ts": 667115189468.686, "dur": 0.753, + "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": 4183436, "tid": 4183436, + "ts": 667115189470.883, "dur": 0.472, + "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": 4183436, "tid": 4183436, + "ts": 667115189472.851, "dur": 1.956, + "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": 4183436, "tid": 4183436, + "ts": 667115189481.377, "dur": 0.763, + "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": 4183436, "tid": 4183436, + "ts": 667115189483.709, "dur": 0.594, + "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": 4183436, "tid": 4183436, + "ts": 667115189485.674, "dur": 0.457, + "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": 4183436, "tid": 4183436, + "ts": 667115189487.484, "dur": 1.556, + "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": 4183436, "tid": 4183436, + "ts": 667115189511.011, "dur": 1.518, + "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": 4183436, "tid": 4183436, + "ts": 667115189515.442, "dur": 0.438, + "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": 4183436, "tid": 4183436, + "ts": 667115189517.305, "dur": 0.449, + "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": 4183436, "tid": 4183436, + "ts": 667115189518.959, "dur": 1.809, + "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": 4183436, "tid": 4183436, + "ts": 667115189526.038, "dur": 0.412, + "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": 4183436, "tid": 4183436, + "ts": 667115189527.372, "dur": 0.715, + "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": 4183436, "tid": 4183436, + "ts": 667115189529.845, "dur": 0.767, + "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": 4183436, "tid": 4183436, + "ts": 667115189531.784, "dur": 1.492, + "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": 4183436, "tid": 4183436, + "ts": 667115189536.345, "dur": 0.480, + "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": 4183436, "tid": 4183436, + "ts": 667115189537.878, "dur": 0.753, + "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": 4183436, "tid": 4183436, + "ts": 667115189539.878, "dur": 0.819, + "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": 4183436, "tid": 4183436, + "ts": 667115189542.018, "dur": 1.665, + "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": 4183436, "tid": 4183436, + "ts": 667115189566.274, "dur": 0.603, + "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": 4183436, "tid": 4183436, + "ts": 667115189568.177, "dur": 0.606, + "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": 4183436, "tid": 4183436, + "ts": 667115189570.210, "dur": 0.402, + "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": 4183436, "tid": 4183436, + "ts": 667115189571.870, "dur": 1.438, + "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": 4183436, "tid": 4183436, + "ts": 667115189576.783, "dur": 0.469, + "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": 4183436, "tid": 4183436, + "ts": 667115189578.467, "dur": 0.636, + "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": 4183436, "tid": 4183436, + "ts": 667115189580.229, "dur": 0.520, + "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": 4183436, "tid": 4183436, + "ts": 667115189581.919, "dur": 1.713, + "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": 4183436, "tid": 4183436, + "ts": 667115189589.765, "dur": 0.606, + "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": 4183436, "tid": 4183436, + "ts": 667115189591.356, "dur": 0.526, + "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": 4183436, "tid": 4183436, + "ts": 667115189593.362, "dur": 0.532, + "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": 4183436, "tid": 4183436, + "ts": 667115189595.131, "dur": 1.951, + "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": 4183436, "tid": 4183436, + "ts": 667115189600.473, "dur": 0.507, + "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": 4183436, "tid": 4183436, + "ts": 667115189602.015, "dur": 0.751, + "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": 4183436, "tid": 4183436, + "ts": 667115189604.168, "dur": 0.393, + "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": 4183436, "tid": 4183436, + "ts": 667115189605.816, "dur": 1.373, + "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": 4183436, "tid": 4183436, + "ts": 667115189638.171, "dur": 5887.694, + "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": 4183436, "tid": 4183436, + "ts": 667115189697.104, "dur": 5815.573, + "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": 4183436, "tid": 4183436, + "ts": 667115189718.449, "dur": 6.111, + "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": 4183436, "tid": 4183436, + "ts": 667115189728.748, "dur": 5723.140, + "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": 4183436, "tid": 4183436, + "ts": 667115189731.350, "dur": 5719.411, + "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": 4183436, "tid": 4183436, + "ts": 667115189739.803, "dur": 6.829, + "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": 4183436, "tid": 4183436, + "ts": 667115189748.378, "dur": 5697.956, + "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": 4183436, "tid": 4183436, + "ts": 667115195900.801, "dur": 39.040, + "args": { + "External id": 225990,"Record function id": 0, "Ev Idx": 4789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 4183436, "tid": 4183436, + "ts": 667115195941.715, "dur": 206.737, + "args": { + "External id": 225991,"Record function id": 0, "Ev Idx": 4790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115195982.740, "dur": 156.452, + "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": 4183436, "tid": 4183436, "ts": 667115195982.740, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 4183436, "tid": 4183436, + "ts": 667115196057.129, "dur": 47.028, + "args": { + "External id": 225993,"kernel_hash": "c4537borpfhjort7hk5hezwlzisk5kehpabf4vrjydoonzbpg6ph", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/45/c4537borpfhjort7hk5hezwlzisk5kehpabf4vrjydoonzbpg6ph.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": 4183436, "tid": 4183436, + "ts": 667115196209.423, "dur": 55.869, + "args": { + "External id": 225994,"Record function id": 0, "Ev Idx": 4793 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 4183436, "tid": 4183436, + "ts": 667115196275.927, "dur": 6962.529, + "args": { + "External id": 225995,"Record function id": 0, "Ev Idx": 4794 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 4183436, "tid": 4183436, + "ts": 667115196284.650, "dur": 855.788, + "args": { + "External id": 225996,"Record function id": 0, "Ev Idx": 4795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115196354.771, "dur": 10.671, + "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": 4183436, "tid": 4183436, + "ts": 667115196377.791, "dur": 39.368, + "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": 4183436, "tid": 4183436, + "ts": 667115196388.038, "dur": 2.313, + "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": 4183436, "tid": 4183436, + "ts": 667115196392.006, "dur": 0.249, + "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": 4183436, "tid": 4183436, + "ts": 667115196393.197, "dur": 2.291, + "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": 4183436, "tid": 4183436, + "ts": 667115196398.464, "dur": 0.225, + "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": 4183436, "tid": 4183436, + "ts": 667115196399.476, "dur": 0.164, + "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": 4183436, "tid": 4183436, + "ts": 667115196402.658, "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": 4183436, "tid": 4183436, + "ts": 667115196406.028, "dur": 0.253, + "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": 4183436, "tid": 4183436, + "ts": 667115196406.858, "dur": 1.252, + "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": 4183436, "tid": 4183436, + "ts": 667115196411.548, "dur": 0.181, + "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": 4183436, "tid": 4183436, + "ts": 667115196427.894, "dur": 34.911, + "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": 4183436, "tid": 4183436, + "ts": 667115196512.421, "dur": 121.870, + "args": { + "External id": 226009,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115196524.325, "dur": 7.091, + "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": 4183436, "tid": 4183436, + "ts": 667115196537.381, "dur": 12.627, + "args": { + "External id": 226011,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115196541.594, "dur": 7.993, + "args": { + "External id": 226012,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115196547.294, "dur": 0.729, + "args": { + "External id": 226013,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115196556.986, "dur": 30.461, + "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": 4183436, "tid": 4183436, + "ts": 667115196558.828, "dur": 0.361, + "args": { + "External id": 226015,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115196562.769, "dur": 0.326, + "args": { + "External id": 226016,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115196566.390, "dur": 0.356, + "args": { + "External id": 226017,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115196567.405, "dur": 0.194, + "args": { + "External id": 226018,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115196570.839, "dur": 3.555, + "args": { + "External id": 226019,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115196575.470, "dur": 0.315, + "args": { + "External id": 226020,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115196578.376, "dur": 0.304, + "args": { + "External id": 226021,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115196581.699, "dur": 0.202, + "args": { + "External id": 226022,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115196582.724, "dur": 0.308, + "args": { + "External id": 226023,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115196600.417, "dur": 24.908, + "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": 4183436, "tid": 4183436, + "ts": 667115196727.512, "dur": 303.302, + "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": 4183436, "tid": 4183436, + "ts": 667115196757.719, "dur": 266.753, + "args": { + "External id": 226026,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115196769.162, "dur": 248.092, + "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": 4183436, "tid": 4183436, + "ts": 667115197060.062, "dur": 3.294, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 4183436, "tid": 4183436, + "ts": 667115197161.712, "dur": 5879.297, + "args": { + "External id": 226029,"Record function id": 0, "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115197259.608, "dur": 6.659, + "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": 4183436, "tid": 4183436, + "ts": 667115197269.569, "dur": 0.996, + "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": 4183436, "tid": 4183436, + "ts": 667115197272.214, "dur": 0.873, + "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": 4183436, "tid": 4183436, + "ts": 667115197274.997, "dur": 2.401, + "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": 4183436, "tid": 4183436, + "ts": 667115197278.852, "dur": 0.807, + "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": 4183436, "tid": 4183436, + "ts": 667115197283.206, "dur": 0.797, + "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": 4183436, "tid": 4183436, + "ts": 667115197285.836, "dur": 0.911, + "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": 4183436, "tid": 4183436, + "ts": 667115197288.570, "dur": 1.644, + "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": 4183436, "tid": 4183436, + "ts": 667115197293.842, "dur": 0.674, + "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": 4183436, "tid": 4183436, + "ts": 667115197298.144, "dur": 0.566, + "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": 4183436, "tid": 4183436, + "ts": 667115197315.239, "dur": 5681.714, + "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": 4183436, "tid": 4183436, + "ts": 667115197332.888, "dur": 5656.710, + "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": 4183436, "tid": 4183436, + "ts": 667115197357.330, "dur": 13.454, + "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": 4183436, "tid": 4183436, + "ts": 667115197373.792, "dur": 5583.439, + "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": 4183436, "tid": 4183436, + "ts": 667115197376.461, "dur": 5580.130, + "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": 4183436, "tid": 4183436, + "ts": 667115197382.714, "dur": 5.497, + "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": 4183436, "tid": 4183436, + "ts": 667115197390.040, "dur": 5563.270, + "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": 4183436, "tid": 4183436, + "ts": 667115203182.037, "dur": 31.609, + "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": 4183436, "tid": 4183436, "ts": 667115203182.037, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115203198.228, "dur": 10.902, + "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": 4183436, "tid": 4183436, + "ts": 667115203204.033, "dur": 4.906, + "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": 4183436, "tid": 4183436, + "ts": 667115203278.815, "dur": 84.503, + "args": { + "External id": 226050,"Record function id": 0, "Ev Idx": 4849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115203364.811, "dur": 1549.182, + "args": { + "External id": 226051,"Record function id": 0, "Ev Idx": 4850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115203406.543, "dur": 1487.759, + "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": 4183436, "tid": 4183436, "ts": 667115203406.543, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115203473.752, "dur": 69.901, + "args": { + "External id": 226053,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115203559.247, "dur": 90.071, + "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": 4183436, "tid": 4183436, + "ts": 667115203731.084, "dur": 43.288, + "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": 4183436, "tid": 4183436, + "ts": 667115203785.704, "dur": 29.558, + "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": 4183436, "tid": 4183436, + "ts": 667115203849.356, "dur": 35.584, + "args": { + "External id": 226057,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115203917.809, "dur": 21.445, + "args": { + "External id": 226058,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115203965.033, "dur": 164.251, + "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": 4183436, "tid": 4183436, + "ts": 667115204027.816, "dur": 15.607, + "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": 4183436, "tid": 4183436, + "ts": 667115204033.450, "dur": 8.868, + "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": 4183436, "tid": 4183436, + "ts": 667115204046.623, "dur": 4.513, + "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": 4183436, "tid": 4183436, + "ts": 667115204055.294, "dur": 1.224, + "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": 4183436, "tid": 4183436, + "ts": 667115204059.798, "dur": 3.621, + "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": 4183436, "tid": 4183436, + "ts": 667115204146.407, "dur": 109.700, + "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": 4183436, "tid": 4183436, + "ts": 667115204305.535, "dur": 39.447, + "args": { + "External id": 226066,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115204355.340, "dur": 55.528, + "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": 4183436, "tid": 4183436, + "ts": 667115204422.547, "dur": 43.377, + "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": 4183436, "tid": 4183436, + "ts": 667115204543.374, "dur": 36.352, + "args": { + "External id": 226069,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115204590.367, "dur": 49.370, + "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": 4183436, "tid": 4183436, + "ts": 667115204756.843, "dur": 30.933, + "args": { + "External id": 226071,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115204994.879, "dur": 99.560, + "args": { + "External id": 226072,"Record function id": 0, "Ev Idx": 4871 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115205188.993, "dur": 63.805, + "args": { + "External id": 226073,"Record function id": 0, "Ev Idx": 4872 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 4183436, "tid": 4183436, + "ts": 667115205265.091, "dur": 9157.649, + "args": { + "External id": 226074,"Record function id": 0, "Ev Idx": 4873 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 4183436, "tid": 4183436, + "ts": 667115205279.050, "dur": 1209.448, + "args": { + "External id": 226075,"Record function id": 0, "Ev Idx": 4874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115205374.133, "dur": 11.646, + "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": 4183436, "tid": 4183436, + "ts": 667115205401.951, "dur": 51.970, + "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": 4183436, "tid": 4183436, + "ts": 667115205410.238, "dur": 4.794, + "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": 4183436, "tid": 4183436, + "ts": 667115205417.622, "dur": 0.467, + "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": 4183436, "tid": 4183436, + "ts": 667115205419.211, "dur": 0.541, + "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": 4183436, "tid": 4183436, + "ts": 667115205425.781, "dur": 0.580, + "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": 4183436, "tid": 4183436, + "ts": 667115205428.185, "dur": 2.031, + "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": 4183436, "tid": 4183436, + "ts": 667115205433.810, "dur": 0.295, + "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": 4183436, "tid": 4183436, + "ts": 667115205437.855, "dur": 0.306, + "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": 4183436, "tid": 4183436, + "ts": 667115205439.856, "dur": 0.271, + "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": 4183436, "tid": 4183436, + "ts": 667115205443.687, "dur": 2.746, + "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": 4183436, "tid": 4183436, + "ts": 667115205466.985, "dur": 74.178, + "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": 4183436, "tid": 4183436, + "ts": 667115205591.696, "dur": 227.980, + "args": { + "External id": 226088,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115205606.369, "dur": 7.901, + "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": 4183436, "tid": 4183436, + "ts": 667115205621.023, "dur": 14.406, + "args": { + "External id": 226090,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115205626.144, "dur": 8.758, + "args": { + "External id": 226091,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115205631.731, "dur": 0.950, + "args": { + "External id": 226092,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115205645.114, "dur": 95.697, + "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": 4183436, "tid": 4183436, + "ts": 667115205647.518, "dur": 0.588, + "args": { + "External id": 226094,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115205707.032, "dur": 2.039, + "args": { + "External id": 226095,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115205711.036, "dur": 3.074, + "args": { + "External id": 226096,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115205718.310, "dur": 0.320, + "args": { + "External id": 226097,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115205719.983, "dur": 0.419, + "args": { + "External id": 226098,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115205724.113, "dur": 0.343, + "args": { + "External id": 226099,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115205728.000, "dur": 0.390, + "args": { + "External id": 226100,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115205729.954, "dur": 0.405, + "args": { + "External id": 226101,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115205733.852, "dur": 0.394, + "args": { + "External id": 226102,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115205763.031, "dur": 42.468, + "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": 4183436, "tid": 4183436, + "ts": 667115205897.962, "dur": 459.504, + "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": 4183436, "tid": 4183436, + "ts": 667115205935.146, "dur": 414.000, + "args": { + "External id": 226105,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115205949.442, "dur": 391.902, + "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": 4183436, "tid": 4183436, + "ts": 667115206387.561, "dur": 3.465, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 4183436, "tid": 4183436, + "ts": 667115206561.605, "dur": 7600.130, + "args": { + "External id": 226108,"Record function id": 0, "Ev Idx": 4907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115206763.789, "dur": 8.655, + "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": 4183436, "tid": 4183436, + "ts": 667115206777.835, "dur": 1.220, + "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": 4183436, "tid": 4183436, + "ts": 667115206781.770, "dur": 1.095, + "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": 4183436, "tid": 4183436, + "ts": 667115206785.934, "dur": 1.543, + "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": 4183436, "tid": 4183436, + "ts": 667115206789.607, "dur": 1.147, + "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": 4183436, "tid": 4183436, + "ts": 667115206795.683, "dur": 1.310, + "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": 4183436, "tid": 4183436, + "ts": 667115206799.933, "dur": 1.091, + "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": 4183436, "tid": 4183436, + "ts": 667115206807.660, "dur": 3.696, + "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": 4183436, "tid": 4183436, + "ts": 667115206814.265, "dur": 0.895, + "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": 4183436, "tid": 4183436, + "ts": 667115206820.362, "dur": 0.829, + "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": 4183436, "tid": 4183436, + "ts": 667115206845.919, "dur": 7243.417, + "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": 4183436, "tid": 4183436, + "ts": 667115206869.821, "dur": 7206.468, + "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": 4183436, "tid": 4183436, + "ts": 667115206902.778, "dur": 17.598, + "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": 4183436, "tid": 4183436, + "ts": 667115206923.902, "dur": 7097.354, + "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": 4183436, "tid": 4183436, + "ts": 667115206927.180, "dur": 7092.864, + "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": 4183436, "tid": 4183436, + "ts": 667115206934.046, "dur": 6.955, + "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": 4183436, "tid": 4183436, + "ts": 667115206943.264, "dur": 7070.309, + "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": 4183436, "tid": 4183436, + "ts": 667115214346.147, "dur": 41.047, + "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": 4183436, "tid": 4183436, "ts": 667115214346.147, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115214365.653, "dur": 15.680, + "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": 4183436, "tid": 4183436, + "ts": 667115214374.003, "dur": 6.887, + "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": 4183436, "tid": 4183436, + "ts": 667115214472.156, "dur": 148.830, + "args": { + "External id": 226129,"Record function id": 0, "Ev Idx": 4928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115214626.868, "dur": 1407.553, + "args": { + "External id": 226130,"Record function id": 0, "Ev Idx": 4929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115214744.505, "dur": 1274.970, + "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": 4183436, "tid": 4183436, "ts": 667115214744.505, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115214859.648, "dur": 63.333, + "args": { + "External id": 226132,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115214945.170, "dur": 125.501, + "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": 4183436, "tid": 4183436, + "ts": 667115215084.510, "dur": 51.237, + "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": 4183436, "tid": 4183436, + "ts": 667115215145.209, "dur": 41.387, + "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": 4183436, "tid": 4183436, + "ts": 667115215229.610, "dur": 34.286, + "args": { + "External id": 226136,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115215288.586, "dur": 25.484, + "args": { + "External id": 226137,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115215334.812, "dur": 186.327, + "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": 4183436, "tid": 4183436, + "ts": 667115215396.218, "dur": 16.627, + "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": 4183436, "tid": 4183436, + "ts": 667115215401.776, "dur": 9.693, + "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": 4183436, "tid": 4183436, + "ts": 667115215418.534, "dur": 7.618, + "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": 4183436, "tid": 4183436, + "ts": 667115215427.701, "dur": 3.435, + "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": 4183436, "tid": 4183436, + "ts": 667115215434.523, "dur": 3.090, + "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": 4183436, "tid": 4183436, + "ts": 667115215537.034, "dur": 60.853, + "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": 4183436, "tid": 4183436, + "ts": 667115215634.205, "dur": 71.365, + "args": { + "External id": 226145,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115215718.021, "dur": 58.151, + "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": 4183436, "tid": 4183436, + "ts": 667115215783.596, "dur": 35.075, + "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": 4183436, "tid": 4183436, + "ts": 667115215843.621, "dur": 25.767, + "args": { + "External id": 226148,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115215875.060, "dur": 32.893, + "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": 4183436, "tid": 4183436, + "ts": 667115215928.273, "dur": 21.037, + "args": { + "External id": 226150,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115216100.065, "dur": 75.115, + "args": { + "External id": 226151,"Record function id": 0, "Ev Idx": 4950 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115216250.933, "dur": 48.054, + "args": { + "External id": 226152,"Record function id": 0, "Ev Idx": 4951 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 4183436, "tid": 4183436, + "ts": 667115216309.151, "dur": 9465.925, + "args": { + "External id": 226153,"Record function id": 0, "Ev Idx": 4952 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 4183436, "tid": 4183436, + "ts": 667115216318.247, "dur": 1016.131, + "args": { + "External id": 226154,"Record function id": 0, "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115216401.172, "dur": 10.677, + "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": 4183436, "tid": 4183436, + "ts": 667115216427.641, "dur": 51.429, + "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": 4183436, "tid": 4183436, + "ts": 667115216436.437, "dur": 2.625, + "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": 4183436, "tid": 4183436, + "ts": 667115216443.896, "dur": 0.558, + "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": 4183436, "tid": 4183436, + "ts": 667115216448.125, "dur": 0.489, + "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": 4183436, "tid": 4183436, + "ts": 667115216449.962, "dur": 0.468, + "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": 4183436, "tid": 4183436, + "ts": 667115216454.152, "dur": 0.666, + "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": 4183436, "tid": 4183436, + "ts": 667115216458.460, "dur": 0.463, + "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": 4183436, "tid": 4183436, + "ts": 667115216460.594, "dur": 4.213, + "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": 4183436, "tid": 4183436, + "ts": 667115216466.223, "dur": 1.112, + "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": 4183436, "tid": 4183436, + "ts": 667115216471.070, "dur": 0.384, + "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": 4183436, "tid": 4183436, + "ts": 667115216513.185, "dur": 51.424, + "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": 4183436, "tid": 4183436, + "ts": 667115216603.187, "dur": 167.679, + "args": { + "External id": 226167,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115216619.641, "dur": 6.035, + "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": 4183436, "tid": 4183436, + "ts": 667115216631.312, "dur": 10.306, + "args": { + "External id": 226169,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115216635.753, "dur": 5.480, + "args": { + "External id": 226170,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115216638.983, "dur": 0.623, + "args": { + "External id": 226171,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115216648.892, "dur": 71.026, + "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": 4183436, "tid": 4183436, + "ts": 667115216652.800, "dur": 37.029, + "args": { + "External id": 226173,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115216692.441, "dur": 0.368, + "args": { + "External id": 226174,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115216693.955, "dur": 0.483, + "args": { + "External id": 226175,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115216699.826, "dur": 1.521, + "args": { + "External id": 226176,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115216702.498, "dur": 0.379, + "args": { + "External id": 226177,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115216703.500, "dur": 0.412, + "args": { + "External id": 226178,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115216709.162, "dur": 0.269, + "args": { + "External id": 226179,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115216710.275, "dur": 0.196, + "args": { + "External id": 226180,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115216713.682, "dur": 2.139, + "args": { + "External id": 226181,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115216733.530, "dur": 28.226, + "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": 4183436, "tid": 4183436, + "ts": 667115216833.423, "dur": 409.202, + "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": 4183436, "tid": 4183436, + "ts": 667115216870.655, "dur": 366.823, + "args": { + "External id": 226184,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115216881.152, "dur": 348.726, + "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": 4183436, "tid": 4183436, + "ts": 667115217263.651, "dur": 2.392, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 4183436, "tid": 4183436, + "ts": 667115217355.371, "dur": 8163.882, + "args": { + "External id": 226187,"Record function id": 0, "Ev Idx": 4986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115217443.461, "dur": 5.730, + "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": 4183436, "tid": 4183436, + "ts": 667115217452.590, "dur": 1.007, + "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": 4183436, "tid": 4183436, + "ts": 667115217455.248, "dur": 2.020, + "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": 4183436, "tid": 4183436, + "ts": 667115217459.433, "dur": 0.628, + "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": 4183436, "tid": 4183436, + "ts": 667115217461.555, "dur": 0.780, + "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": 4183436, "tid": 4183436, + "ts": 667115217466.201, "dur": 1.014, + "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": 4183436, "tid": 4183436, + "ts": 667115217471.286, "dur": 0.875, + "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": 4183436, "tid": 4183436, + "ts": 667115217473.719, "dur": 1.865, + "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": 4183436, "tid": 4183436, + "ts": 667115217476.975, "dur": 0.585, + "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": 4183436, "tid": 4183436, + "ts": 667115217480.987, "dur": 0.604, + "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": 4183436, "tid": 4183436, + "ts": 667115217523.949, "dur": 7907.404, + "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": 4183436, "tid": 4183436, + "ts": 667115217542.660, "dur": 7875.995, + "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": 4183436, "tid": 4183436, + "ts": 667115217560.674, "dur": 14.406, + "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": 4183436, "tid": 4183436, + "ts": 667115217578.095, "dur": 7785.907, + "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": 4183436, "tid": 4183436, + "ts": 667115217580.796, "dur": 7781.995, + "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": 4183436, "tid": 4183436, + "ts": 667115217586.824, "dur": 5.378, + "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": 4183436, "tid": 4183436, + "ts": 667115217593.937, "dur": 7762.389, + "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": 4183436, "tid": 4183436, + "ts": 667115225708.399, "dur": 36.864, + "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": 4183436, "tid": 4183436, "ts": 667115225708.399, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115225726.027, "dur": 14.155, + "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": 4183436, "tid": 4183436, + "ts": 667115225732.989, "dur": 6.781, + "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": 4183436, "tid": 4183436, + "ts": 667115225815.120, "dur": 83.383, + "args": { + "External id": 226208,"Record function id": 0, "Ev Idx": 5007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115225900.549, "dur": 1086.865, + "args": { + "External id": 226209,"Record function id": 0, "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115225939.175, "dur": 1033.695, + "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": 4183436, "tid": 4183436, "ts": 667115225939.175, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115226009.192, "dur": 46.397, + "args": { + "External id": 226211,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115226068.345, "dur": 91.342, + "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": 4183436, "tid": 4183436, + "ts": 667115226170.253, "dur": 34.537, + "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": 4183436, "tid": 4183436, + "ts": 667115226212.776, "dur": 29.623, + "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": 4183436, "tid": 4183436, + "ts": 667115226267.989, "dur": 26.633, + "args": { + "External id": 226215,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115226314.790, "dur": 14.396, + "args": { + "External id": 226216,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115226347.358, "dur": 125.839, + "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": 4183436, "tid": 4183436, + "ts": 667115226395.094, "dur": 12.086, + "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": 4183436, "tid": 4183436, + "ts": 667115226399.895, "dur": 6.497, + "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": 4183436, "tid": 4183436, + "ts": 667115226411.898, "dur": 3.762, + "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": 4183436, "tid": 4183436, + "ts": 667115226417.247, "dur": 1.014, + "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": 4183436, "tid": 4183436, + "ts": 667115226420.419, "dur": 3.667, + "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": 4183436, "tid": 4183436, + "ts": 667115226483.824, "dur": 68.315, + "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": 4183436, "tid": 4183436, + "ts": 667115226584.382, "dur": 28.694, + "args": { + "External id": 226224,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115226621.963, "dur": 71.615, + "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": 4183436, "tid": 4183436, + "ts": 667115226706.247, "dur": 36.972, + "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": 4183436, "tid": 4183436, + "ts": 667115226768.950, "dur": 25.978, + "args": { + "External id": 226227,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115226800.916, "dur": 54.384, + "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": 4183436, "tid": 4183436, + "ts": 667115226876.965, "dur": 19.421, + "args": { + "External id": 226229,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115227054.649, "dur": 74.306, + "args": { + "External id": 226230,"Record function id": 0, "Ev Idx": 5029 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115227205.345, "dur": 49.400, + "args": { + "External id": 226231,"Record function id": 0, "Ev Idx": 5030 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 4183436, "tid": 4183436, + "ts": 667115227263.662, "dur": 8604.205, + "args": { + "External id": 226232,"Record function id": 0, "Ev Idx": 5031 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 4183436, "tid": 4183436, + "ts": 667115227274.308, "dur": 936.161, + "args": { + "External id": 226233,"Record function id": 0, "Ev Idx": 5032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115227349.504, "dur": 7.659, + "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": 4183436, "tid": 4183436, + "ts": 667115227369.142, "dur": 45.338, + "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": 4183436, "tid": 4183436, + "ts": 667115227376.896, "dur": 2.295, + "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": 4183436, "tid": 4183436, + "ts": 667115227383.262, "dur": 0.220, + "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": 4183436, "tid": 4183436, + "ts": 667115227386.622, "dur": 0.478, + "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": 4183436, "tid": 4183436, + "ts": 667115227393.781, "dur": 0.395, + "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": 4183436, "tid": 4183436, + "ts": 667115227397.406, "dur": 0.256, + "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": 4183436, "tid": 4183436, + "ts": 667115227400.469, "dur": 0.512, + "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": 4183436, "tid": 4183436, + "ts": 667115227401.460, "dur": 3.161, + "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": 4183436, "tid": 4183436, + "ts": 667115227405.141, "dur": 0.223, + "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": 4183436, "tid": 4183436, + "ts": 667115227407.853, "dur": 0.158, + "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": 4183436, "tid": 4183436, + "ts": 667115227425.049, "dur": 42.103, + "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": 4183436, "tid": 4183436, + "ts": 667115227520.453, "dur": 177.771, + "args": { + "External id": 226246,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115227536.513, "dur": 4.988, + "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": 4183436, "tid": 4183436, + "ts": 667115227547.510, "dur": 10.462, + "args": { + "External id": 226248,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115227552.012, "dur": 5.575, + "args": { + "External id": 226249,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115227555.156, "dur": 0.781, + "args": { + "External id": 226250,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115227564.727, "dur": 32.992, + "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": 4183436, "tid": 4183436, + "ts": 667115227568.320, "dur": 2.880, + "args": { + "External id": 226252,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115227572.347, "dur": 0.493, + "args": { + "External id": 226253,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115227573.491, "dur": 0.376, + "args": { + "External id": 226254,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115227579.200, "dur": 1.126, + "args": { + "External id": 226255,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115227581.055, "dur": 0.315, + "args": { + "External id": 226256,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115227582.325, "dur": 0.300, + "args": { + "External id": 226257,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115227587.183, "dur": 0.293, + "args": { + "External id": 226258,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115227588.301, "dur": 0.175, + "args": { + "External id": 226259,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115227590.764, "dur": 2.610, + "args": { + "External id": 226260,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115227621.467, "dur": 29.451, + "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": 4183436, "tid": 4183436, + "ts": 667115227757.654, "dur": 367.003, + "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": 4183436, "tid": 4183436, + "ts": 667115227790.590, "dur": 329.405, + "args": { + "External id": 226263,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115227802.845, "dur": 311.216, + "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": 4183436, "tid": 4183436, + "ts": 667115228144.290, "dur": 2.213, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 4183436, "tid": 4183436, + "ts": 667115228231.318, "dur": 7402.734, + "args": { + "External id": 226266,"Record function id": 0, "Ev Idx": 5065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115228320.280, "dur": 6.147, + "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": 4183436, "tid": 4183436, + "ts": 667115228329.593, "dur": 1.147, + "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": 4183436, "tid": 4183436, + "ts": 667115228332.817, "dur": 2.117, + "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": 4183436, "tid": 4183436, + "ts": 667115228336.578, "dur": 0.926, + "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": 4183436, "tid": 4183436, + "ts": 667115228339.031, "dur": 0.874, + "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": 4183436, "tid": 4183436, + "ts": 667115228343.555, "dur": 0.879, + "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": 4183436, "tid": 4183436, + "ts": 667115228347.901, "dur": 0.736, + "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": 4183436, "tid": 4183436, + "ts": 667115228349.913, "dur": 1.829, + "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": 4183436, "tid": 4183436, + "ts": 667115228352.937, "dur": 0.747, + "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": 4183436, "tid": 4183436, + "ts": 667115228357.438, "dur": 0.524, + "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": 4183436, "tid": 4183436, + "ts": 667115228374.804, "dur": 7212.005, + "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": 4183436, "tid": 4183436, + "ts": 667115228391.362, "dur": 7187.148, + "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": 4183436, "tid": 4183436, + "ts": 667115228407.732, "dur": 12.835, + "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": 4183436, "tid": 4183436, + "ts": 667115228423.314, "dur": 7119.217, + "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": 4183436, "tid": 4183436, + "ts": 667115228426.087, "dur": 7115.551, + "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": 4183436, "tid": 4183436, + "ts": 667115228431.800, "dur": 6.363, + "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": 4183436, "tid": 4183436, + "ts": 667115228440.249, "dur": 7097.921, + "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": 4183436, "tid": 4183436, + "ts": 667115235797.679, "dur": 43.459, + "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": 4183436, "tid": 4183436, "ts": 667115235797.679, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115235823.770, "dur": 12.601, + "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": 4183436, "tid": 4183436, + "ts": 667115235830.155, "dur": 5.777, + "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": 4183436, "tid": 4183436, + "ts": 667115235908.260, "dur": 83.809, + "args": { + "External id": 226287,"Record function id": 0, "Ev Idx": 5086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115235993.824, "dur": 1107.515, + "args": { + "External id": 226288,"Record function id": 0, "Ev Idx": 5087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115236034.308, "dur": 1052.673, + "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": 4183436, "tid": 4183436, "ts": 667115236034.308, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115236100.177, "dur": 42.619, + "args": { + "External id": 226290,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115236154.567, "dur": 93.007, + "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": 4183436, "tid": 4183436, + "ts": 667115236259.091, "dur": 34.062, + "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": 4183436, "tid": 4183436, + "ts": 667115236298.494, "dur": 29.122, + "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": 4183436, "tid": 4183436, + "ts": 667115236358.551, "dur": 23.592, + "args": { + "External id": 226294,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115236397.895, "dur": 14.759, + "args": { + "External id": 226295,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115236429.479, "dur": 155.031, + "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": 4183436, "tid": 4183436, + "ts": 667115236479.028, "dur": 31.176, + "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": 4183436, "tid": 4183436, + "ts": 667115236483.632, "dur": 5.390, + "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": 4183436, "tid": 4183436, + "ts": 667115236516.111, "dur": 5.871, + "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": 4183436, "tid": 4183436, + "ts": 667115236523.308, "dur": 0.773, + "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": 4183436, "tid": 4183436, + "ts": 667115236528.681, "dur": 3.498, + "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": 4183436, "tid": 4183436, + "ts": 667115236595.620, "dur": 49.576, + "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": 4183436, "tid": 4183436, + "ts": 667115236718.721, "dur": 30.865, + "args": { + "External id": 226303,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115236759.396, "dur": 42.244, + "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": 4183436, "tid": 4183436, + "ts": 667115236832.658, "dur": 46.898, + "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": 4183436, "tid": 4183436, + "ts": 667115236907.602, "dur": 23.674, + "args": { + "External id": 226306,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115236936.886, "dur": 45.572, + "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": 4183436, "tid": 4183436, + "ts": 667115237000.014, "dur": 21.619, + "args": { + "External id": 226308,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115237168.527, "dur": 72.793, + "args": { + "External id": 226309,"Record function id": 0, "Ev Idx": 5108 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115237314.404, "dur": 48.109, + "args": { + "External id": 226310,"Record function id": 0, "Ev Idx": 5109 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 4183436, "tid": 4183436, + "ts": 667115237371.219, "dur": 9444.390, + "args": { + "External id": 226311,"Record function id": 0, "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 4183436, "tid": 4183436, + "ts": 667115237380.106, "dur": 917.536, + "args": { + "External id": 226312,"Record function id": 0, "Ev Idx": 5111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115237456.872, "dur": 7.830, + "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": 4183436, "tid": 4183436, + "ts": 667115237476.934, "dur": 61.186, + "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": 4183436, "tid": 4183436, + "ts": 667115237484.023, "dur": 2.097, + "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": 4183436, "tid": 4183436, + "ts": 667115237509.312, "dur": 0.727, + "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": 4183436, "tid": 4183436, + "ts": 667115237513.880, "dur": 0.499, + "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": 4183436, "tid": 4183436, + "ts": 667115237515.066, "dur": 0.401, + "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": 4183436, "tid": 4183436, + "ts": 667115237518.463, "dur": 0.256, + "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": 4183436, "tid": 4183436, + "ts": 667115237521.777, "dur": 0.743, + "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": 4183436, "tid": 4183436, + "ts": 667115237523.214, "dur": 4.218, + "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": 4183436, "tid": 4183436, + "ts": 667115237528.319, "dur": 0.362, + "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": 4183436, "tid": 4183436, + "ts": 667115237531.198, "dur": 0.152, + "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": 4183436, "tid": 4183436, + "ts": 667115237549.532, "dur": 43.599, + "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": 4183436, "tid": 4183436, + "ts": 667115237626.174, "dur": 160.269, + "args": { + "External id": 226325,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115237641.236, "dur": 4.982, + "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": 4183436, "tid": 4183436, + "ts": 667115237688.703, "dur": 11.355, + "args": { + "External id": 226327,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115237693.659, "dur": 5.988, + "args": { + "External id": 226328,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115237696.953, "dur": 0.849, + "args": { + "External id": 226329,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115237708.602, "dur": 30.975, + "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": 4183436, "tid": 4183436, + "ts": 667115237712.138, "dur": 2.371, + "args": { + "External id": 226331,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115237715.362, "dur": 0.382, + "args": { + "External id": 226332,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115237716.689, "dur": 0.323, + "args": { + "External id": 226333,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115237721.747, "dur": 1.279, + "args": { + "External id": 226334,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115237723.653, "dur": 0.292, + "args": { + "External id": 226335,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115237724.560, "dur": 0.271, + "args": { + "External id": 226336,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115237729.205, "dur": 0.158, + "args": { + "External id": 226337,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115237730.217, "dur": 0.167, + "args": { + "External id": 226338,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115237733.313, "dur": 2.394, + "args": { + "External id": 226339,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115237751.035, "dur": 27.434, + "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": 4183436, "tid": 4183436, + "ts": 667115237843.925, "dur": 365.127, + "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": 4183436, "tid": 4183436, + "ts": 667115237877.627, "dur": 326.593, + "args": { + "External id": 226342,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115237888.177, "dur": 310.734, + "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": 4183436, "tid": 4183436, + "ts": 667115238230.497, "dur": 2.389, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 4183436, "tid": 4183436, + "ts": 667115238318.596, "dur": 8249.274, + "args": { + "External id": 226345,"Record function id": 0, "Ev Idx": 5144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115238403.416, "dur": 5.142, + "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": 4183436, "tid": 4183436, + "ts": 667115238411.752, "dur": 0.985, + "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": 4183436, "tid": 4183436, + "ts": 667115238414.486, "dur": 2.046, + "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": 4183436, "tid": 4183436, + "ts": 667115238418.392, "dur": 0.699, + "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": 4183436, "tid": 4183436, + "ts": 667115238420.590, "dur": 0.865, + "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": 4183436, "tid": 4183436, + "ts": 667115238422.568, "dur": 1.038, + "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": 4183436, "tid": 4183436, + "ts": 667115238428.111, "dur": 0.874, + "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": 4183436, "tid": 4183436, + "ts": 667115238430.403, "dur": 1.835, + "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": 4183436, "tid": 4183436, + "ts": 667115238433.519, "dur": 0.734, + "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": 4183436, "tid": 4183436, + "ts": 667115238435.442, "dur": 0.551, + "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": 4183436, "tid": 4183436, + "ts": 667115238453.902, "dur": 8050.471, + "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": 4183436, "tid": 4183436, + "ts": 667115238470.263, "dur": 8012.236, + "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": 4183436, "tid": 4183436, + "ts": 667115238486.219, "dur": 33.290, + "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": 4183436, "tid": 4183436, + "ts": 667115238523.127, "dur": 7914.607, + "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": 4183436, "tid": 4183436, + "ts": 667115238525.639, "dur": 7911.092, + "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": 4183436, "tid": 4183436, + "ts": 667115238531.614, "dur": 5.463, + "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": 4183436, "tid": 4183436, + "ts": 667115238539.046, "dur": 7891.477, + "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": 4183436, "tid": 4183436, + "ts": 667115246750.300, "dur": 35.974, + "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": 4183436, "tid": 4183436, "ts": 667115246750.300, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115246767.803, "dur": 13.502, + "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": 4183436, "tid": 4183436, + "ts": 667115246774.150, "dur": 6.693, + "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": 4183436, "tid": 4183436, + "ts": 667115246858.604, "dur": 86.680, + "args": { + "External id": 226366,"Record function id": 0, "Ev Idx": 5165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115246947.109, "dur": 1117.581, + "args": { + "External id": 226367,"Record function id": 0, "Ev Idx": 5166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115246989.322, "dur": 1060.448, + "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": 4183436, "tid": 4183436, "ts": 667115246989.322, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115247055.904, "dur": 45.954, + "args": { + "External id": 226369,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115247114.145, "dur": 94.756, + "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": 4183436, "tid": 4183436, + "ts": 667115247219.180, "dur": 37.175, + "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": 4183436, "tid": 4183436, + "ts": 667115247265.646, "dur": 29.874, + "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": 4183436, "tid": 4183436, + "ts": 667115247320.895, "dur": 25.197, + "args": { + "External id": 226373,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115247363.124, "dur": 14.944, + "args": { + "External id": 226374,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115247396.181, "dur": 150.422, + "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": 4183436, "tid": 4183436, + "ts": 667115247443.448, "dur": 10.551, + "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": 4183436, "tid": 4183436, + "ts": 667115247447.946, "dur": 5.123, + "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": 4183436, "tid": 4183436, + "ts": 667115247457.723, "dur": 6.551, + "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": 4183436, "tid": 4183436, + "ts": 667115247465.396, "dur": 0.934, + "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": 4183436, "tid": 4183436, + "ts": 667115247468.431, "dur": 3.711, + "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": 4183436, "tid": 4183436, + "ts": 667115247558.828, "dur": 52.241, + "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": 4183436, "tid": 4183436, + "ts": 667115247643.940, "dur": 70.465, + "args": { + "External id": 226382,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115247726.028, "dur": 42.307, + "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": 4183436, "tid": 4183436, + "ts": 667115247777.127, "dur": 51.523, + "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": 4183436, "tid": 4183436, + "ts": 667115247852.765, "dur": 24.457, + "args": { + "External id": 226385,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115247883.242, "dur": 51.340, + "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": 4183436, "tid": 4183436, + "ts": 667115247954.776, "dur": 18.648, + "args": { + "External id": 226387,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115248131.152, "dur": 75.805, + "args": { + "External id": 226388,"Record function id": 0, "Ev Idx": 5187 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115248282.853, "dur": 47.986, + "args": { + "External id": 226389,"Record function id": 0, "Ev Idx": 5188 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 4183436, "tid": 4183436, + "ts": 667115248340.069, "dur": 9402.216, + "args": { + "External id": 226390,"Record function id": 0, "Ev Idx": 5189 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 4183436, "tid": 4183436, + "ts": 667115248350.418, "dur": 912.318, + "args": { + "External id": 226391,"Record function id": 0, "Ev Idx": 5190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115248426.473, "dur": 7.930, + "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": 4183436, "tid": 4183436, + "ts": 667115248446.853, "dur": 37.541, + "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": 4183436, "tid": 4183436, + "ts": 667115248453.356, "dur": 2.218, + "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": 4183436, "tid": 4183436, + "ts": 667115248459.365, "dur": 0.227, + "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": 4183436, "tid": 4183436, + "ts": 667115248462.713, "dur": 0.329, + "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": 4183436, "tid": 4183436, + "ts": 667115248463.833, "dur": 0.343, + "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": 4183436, "tid": 4183436, + "ts": 667115248466.947, "dur": 0.495, + "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": 4183436, "tid": 4183436, + "ts": 667115248469.851, "dur": 0.330, + "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": 4183436, "tid": 4183436, + "ts": 667115248470.914, "dur": 3.758, + "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": 4183436, "tid": 4183436, + "ts": 667115248475.419, "dur": 0.189, + "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": 4183436, "tid": 4183436, + "ts": 667115248478.267, "dur": 0.286, + "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": 4183436, "tid": 4183436, + "ts": 667115248514.747, "dur": 43.464, + "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": 4183436, "tid": 4183436, + "ts": 667115248594.161, "dur": 163.163, + "args": { + "External id": 226404,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115248608.103, "dur": 5.108, + "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": 4183436, "tid": 4183436, + "ts": 667115248618.207, "dur": 9.925, + "args": { + "External id": 226406,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115248622.732, "dur": 5.029, + "args": { + "External id": 226407,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115248625.672, "dur": 0.560, + "args": { + "External id": 226408,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115248634.586, "dur": 71.157, + "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": 4183436, "tid": 4183436, + "ts": 667115248637.917, "dur": 2.850, + "args": { + "External id": 226410,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115248641.658, "dur": 0.401, + "args": { + "External id": 226411,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115248643.016, "dur": 0.370, + "args": { + "External id": 226412,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115248648.324, "dur": 1.262, + "args": { + "External id": 226413,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115248650.283, "dur": 0.396, + "args": { + "External id": 226414,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115248651.265, "dur": 0.327, + "args": { + "External id": 226415,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115248692.694, "dur": 0.526, + "args": { + "External id": 226416,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115248694.634, "dur": 0.226, + "args": { + "External id": 226417,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115248697.237, "dur": 3.386, + "args": { + "External id": 226418,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115248722.667, "dur": 26.394, + "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": 4183436, "tid": 4183436, + "ts": 667115248813.399, "dur": 359.981, + "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": 4183436, "tid": 4183436, + "ts": 667115248846.876, "dur": 322.165, + "args": { + "External id": 226421,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115248856.967, "dur": 306.848, + "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": 4183436, "tid": 4183436, + "ts": 667115249193.449, "dur": 2.292, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 4183436, "tid": 4183436, + "ts": 667115249283.674, "dur": 8186.246, + "args": { + "External id": 226424,"Record function id": 0, "Ev Idx": 5223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115249371.697, "dur": 5.631, + "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": 4183436, "tid": 4183436, + "ts": 667115249380.793, "dur": 1.211, + "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": 4183436, "tid": 4183436, + "ts": 667115249383.972, "dur": 2.124, + "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": 4183436, "tid": 4183436, + "ts": 667115249387.991, "dur": 1.174, + "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": 4183436, "tid": 4183436, + "ts": 667115249390.533, "dur": 1.082, + "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": 4183436, "tid": 4183436, + "ts": 667115249392.950, "dur": 0.783, + "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": 4183436, "tid": 4183436, + "ts": 667115249398.030, "dur": 0.736, + "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": 4183436, "tid": 4183436, + "ts": 667115249399.999, "dur": 1.819, + "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": 4183436, "tid": 4183436, + "ts": 667115249403.124, "dur": 0.613, + "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": 4183436, "tid": 4183436, + "ts": 667115249405.138, "dur": 0.701, + "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": 4183436, "tid": 4183436, + "ts": 667115249423.840, "dur": 7980.115, + "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": 4183436, "tid": 4183436, + "ts": 667115249445.369, "dur": 7946.561, + "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": 4183436, "tid": 4183436, + "ts": 667115249458.004, "dur": 15.732, + "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": 4183436, "tid": 4183436, + "ts": 667115249476.470, "dur": 7871.215, + "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": 4183436, "tid": 4183436, + "ts": 667115249479.107, "dur": 7867.317, + "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": 4183436, "tid": 4183436, + "ts": 667115249484.991, "dur": 4.282, + "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": 4183436, "tid": 4183436, + "ts": 667115249510.024, "dur": 7830.418, + "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": 4183436, "tid": 4183436, + "ts": 667115257642.176, "dur": 69.336, + "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": 4183436, "tid": 4183436, "ts": 667115257642.176, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115257692.563, "dur": 13.666, + "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": 4183436, "tid": 4183436, + "ts": 667115257699.394, "dur": 6.420, + "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": 4183436, "tid": 4183436, + "ts": 667115257786.363, "dur": 89.349, + "args": { + "External id": 226445,"Record function id": 0, "Ev Idx": 5244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115257877.346, "dur": 1113.855, + "args": { + "External id": 226446,"Record function id": 0, "Ev Idx": 5245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115257918.408, "dur": 1058.505, + "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": 4183436, "tid": 4183436, "ts": 667115257918.408, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115257988.477, "dur": 45.599, + "args": { + "External id": 226448,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115258047.010, "dur": 91.190, + "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": 4183436, "tid": 4183436, + "ts": 667115258147.378, "dur": 35.853, + "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": 4183436, "tid": 4183436, + "ts": 667115258193.048, "dur": 29.488, + "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": 4183436, "tid": 4183436, + "ts": 667115258248.497, "dur": 26.082, + "args": { + "External id": 226452,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115258291.313, "dur": 15.079, + "args": { + "External id": 226453,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115258333.219, "dur": 125.198, + "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": 4183436, "tid": 4183436, + "ts": 667115258382.497, "dur": 12.394, + "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": 4183436, "tid": 4183436, + "ts": 667115258387.129, "dur": 6.918, + "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": 4183436, "tid": 4183436, + "ts": 667115258398.454, "dur": 3.392, + "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": 4183436, "tid": 4183436, + "ts": 667115258402.926, "dur": 1.022, + "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": 4183436, "tid": 4183436, + "ts": 667115258405.882, "dur": 3.531, + "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": 4183436, "tid": 4183436, + "ts": 667115258468.573, "dur": 67.467, + "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": 4183436, "tid": 4183436, + "ts": 667115258574.059, "dur": 30.279, + "args": { + "External id": 226461,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115258613.216, "dur": 77.657, + "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": 4183436, "tid": 4183436, + "ts": 667115258703.925, "dur": 55.049, + "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": 4183436, "tid": 4183436, + "ts": 667115258781.810, "dur": 24.419, + "args": { + "External id": 226464,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115258811.898, "dur": 54.506, + "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": 4183436, "tid": 4183436, + "ts": 667115258889.053, "dur": 19.061, + "args": { + "External id": 226466,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115259057.807, "dur": 74.430, + "args": { + "External id": 226467,"Record function id": 0, "Ev Idx": 5266 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115259210.138, "dur": 47.734, + "args": { + "External id": 226468,"Record function id": 0, "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 4183436, "tid": 4183436, + "ts": 667115259266.988, "dur": 8654.608, + "args": { + "External id": 226469,"Record function id": 0, "Ev Idx": 5268 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 4183436, "tid": 4183436, + "ts": 667115259279.149, "dur": 923.355, + "args": { + "External id": 226470,"Record function id": 0, "Ev Idx": 5269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115259356.544, "dur": 7.849, + "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": 4183436, "tid": 4183436, + "ts": 667115259378.565, "dur": 32.523, + "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": 4183436, "tid": 4183436, + "ts": 667115259383.350, "dur": 1.999, + "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": 4183436, "tid": 4183436, + "ts": 667115259389.236, "dur": 0.274, + "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": 4183436, "tid": 4183436, + "ts": 667115259391.458, "dur": 0.378, + "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": 4183436, "tid": 4183436, + "ts": 667115259392.771, "dur": 0.441, + "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": 4183436, "tid": 4183436, + "ts": 667115259395.111, "dur": 0.466, + "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": 4183436, "tid": 4183436, + "ts": 667115259397.364, "dur": 0.575, + "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": 4183436, "tid": 4183436, + "ts": 667115259398.667, "dur": 3.648, + "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": 4183436, "tid": 4183436, + "ts": 667115259403.233, "dur": 0.441, + "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": 4183436, "tid": 4183436, + "ts": 667115259404.862, "dur": 0.189, + "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": 4183436, "tid": 4183436, + "ts": 667115259422.898, "dur": 36.816, + "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": 4183436, "tid": 4183436, + "ts": 667115259513.928, "dur": 124.727, + "args": { + "External id": 226483,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115259528.712, "dur": 5.510, + "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": 4183436, "tid": 4183436, + "ts": 667115259539.780, "dur": 11.322, + "args": { + "External id": 226485,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115259544.215, "dur": 6.491, + "args": { + "External id": 226486,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115259548.286, "dur": 0.892, + "args": { + "External id": 226487,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115259558.929, "dur": 32.267, + "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": 4183436, "tid": 4183436, + "ts": 667115259561.583, "dur": 2.709, + "args": { + "External id": 226489,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115259566.250, "dur": 0.380, + "args": { + "External id": 226490,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115259568.107, "dur": 0.229, + "args": { + "External id": 226491,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115259572.886, "dur": 1.348, + "args": { + "External id": 226492,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115259575.844, "dur": 0.192, + "args": { + "External id": 226493,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115259577.694, "dur": 0.315, + "args": { + "External id": 226494,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115259581.063, "dur": 0.143, + "args": { + "External id": 226495,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115259583.024, "dur": 0.170, + "args": { + "External id": 226496,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115259585.219, "dur": 2.298, + "args": { + "External id": 226497,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115259606.099, "dur": 24.298, + "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": 4183436, "tid": 4183436, + "ts": 667115259736.867, "dur": 369.936, + "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": 4183436, "tid": 4183436, + "ts": 667115259771.516, "dur": 330.626, + "args": { + "External id": 226500,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115259782.205, "dur": 314.051, + "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": 4183436, "tid": 4183436, + "ts": 667115260129.111, "dur": 2.501, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 4183436, "tid": 4183436, + "ts": 667115260223.437, "dur": 7471.803, + "args": { + "External id": 226503,"Record function id": 0, "Ev Idx": 5302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115260309.238, "dur": 6.168, + "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": 4183436, "tid": 4183436, + "ts": 667115260319.150, "dur": 0.643, + "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": 4183436, "tid": 4183436, + "ts": 667115260321.696, "dur": 2.122, + "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": 4183436, "tid": 4183436, + "ts": 667115260325.766, "dur": 0.787, + "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": 4183436, "tid": 4183436, + "ts": 667115260328.219, "dur": 0.851, + "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": 4183436, "tid": 4183436, + "ts": 667115260330.525, "dur": 0.928, + "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": 4183436, "tid": 4183436, + "ts": 667115260335.281, "dur": 0.797, + "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": 4183436, "tid": 4183436, + "ts": 667115260337.719, "dur": 2.494, + "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": 4183436, "tid": 4183436, + "ts": 667115260341.743, "dur": 0.894, + "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": 4183436, "tid": 4183436, + "ts": 667115260344.311, "dur": 0.455, + "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": 4183436, "tid": 4183436, + "ts": 667115260364.032, "dur": 7228.833, + "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": 4183436, "tid": 4183436, + "ts": 667115260379.533, "dur": 7202.298, + "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": 4183436, "tid": 4183436, + "ts": 667115260395.058, "dur": 14.599, + "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": 4183436, "tid": 4183436, + "ts": 667115260412.262, "dur": 7123.824, + "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": 4183436, "tid": 4183436, + "ts": 667115260414.937, "dur": 7119.804, + "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": 4183436, "tid": 4183436, + "ts": 667115260421.175, "dur": 6.507, + "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": 4183436, "tid": 4183436, + "ts": 667115260429.475, "dur": 7098.614, + "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": 4183436, "tid": 4183436, + "ts": 667115267856.945, "dur": 35.411, + "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": 4183436, "tid": 4183436, "ts": 667115267856.945, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115267875.194, "dur": 12.372, + "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": 4183436, "tid": 4183436, + "ts": 667115267880.388, "dur": 6.903, + "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": 4183436, "tid": 4183436, + "ts": 667115267963.028, "dur": 84.364, + "args": { + "External id": 226524,"Record function id": 0, "Ev Idx": 5323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115268049.417, "dur": 1115.381, + "args": { + "External id": 226525,"Record function id": 0, "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115268092.013, "dur": 1058.688, + "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": 4183436, "tid": 4183436, "ts": 667115268092.013, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115268158.137, "dur": 46.874, + "args": { + "External id": 226527,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115268217.472, "dur": 93.682, + "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": 4183436, "tid": 4183436, + "ts": 667115268320.077, "dur": 34.656, + "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": 4183436, "tid": 4183436, + "ts": 667115268364.849, "dur": 29.382, + "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": 4183436, "tid": 4183436, + "ts": 667115268418.085, "dur": 27.547, + "args": { + "External id": 226531,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115268464.171, "dur": 15.233, + "args": { + "External id": 226532,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115268515.716, "dur": 131.222, + "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": 4183436, "tid": 4183436, + "ts": 667115268565.481, "dur": 13.157, + "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": 4183436, "tid": 4183436, + "ts": 667115268570.688, "dur": 6.705, + "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": 4183436, "tid": 4183436, + "ts": 667115268581.572, "dur": 6.275, + "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": 4183436, "tid": 4183436, + "ts": 667115268589.053, "dur": 0.850, + "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": 4183436, "tid": 4183436, + "ts": 667115268592.369, "dur": 3.605, + "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": 4183436, "tid": 4183436, + "ts": 667115268702.645, "dur": 64.254, + "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": 4183436, "tid": 4183436, + "ts": 667115268804.792, "dur": 31.378, + "args": { + "External id": 226540,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115268844.816, "dur": 39.205, + "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": 4183436, "tid": 4183436, + "ts": 667115268892.583, "dur": 44.493, + "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": 4183436, "tid": 4183436, + "ts": 667115268960.602, "dur": 23.720, + "args": { + "External id": 226543,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115268989.859, "dur": 46.741, + "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": 4183436, "tid": 4183436, + "ts": 667115269056.383, "dur": 19.213, + "args": { + "External id": 226545,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115269232.341, "dur": 74.763, + "args": { + "External id": 226546,"Record function id": 0, "Ev Idx": 5345 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115269381.960, "dur": 47.245, + "args": { + "External id": 226547,"Record function id": 0, "Ev Idx": 5346 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 4183436, "tid": 4183436, + "ts": 667115269438.422, "dur": 8470.968, + "args": { + "External id": 226548,"Record function id": 0, "Ev Idx": 5347 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 4183436, "tid": 4183436, + "ts": 667115269445.992, "dur": 979.146, + "args": { + "External id": 226549,"Record function id": 0, "Ev Idx": 5348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115269543.453, "dur": 9.869, + "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": 4183436, "tid": 4183436, + "ts": 667115269567.359, "dur": 39.159, + "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": 4183436, "tid": 4183436, + "ts": 667115269573.250, "dur": 2.335, + "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": 4183436, "tid": 4183436, + "ts": 667115269580.233, "dur": 0.331, + "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": 4183436, "tid": 4183436, + "ts": 667115269582.092, "dur": 0.279, + "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": 4183436, "tid": 4183436, + "ts": 667115269583.992, "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": 4183436, "tid": 4183436, + "ts": 667115269588.576, "dur": 0.567, + "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": 4183436, "tid": 4183436, + "ts": 667115269591.287, "dur": 0.547, + "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": 4183436, "tid": 4183436, + "ts": 667115269593.406, "dur": 2.705, + "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": 4183436, "tid": 4183436, + "ts": 667115269597.804, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115269599.725, "dur": 0.349, + "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": 4183436, "tid": 4183436, + "ts": 667115269616.827, "dur": 83.438, + "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": 4183436, "tid": 4183436, + "ts": 667115269743.900, "dur": 128.201, + "args": { + "External id": 226562,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115269758.185, "dur": 6.164, + "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": 4183436, "tid": 4183436, + "ts": 667115269769.875, "dur": 11.435, + "args": { + "External id": 226564,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115269774.233, "dur": 6.686, + "args": { + "External id": 226565,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115269778.487, "dur": 0.748, + "args": { + "External id": 226566,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115269789.110, "dur": 32.630, + "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": 4183436, "tid": 4183436, + "ts": 667115269791.718, "dur": 2.957, + "args": { + "External id": 226568,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115269796.597, "dur": 0.231, + "args": { + "External id": 226569,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115269798.530, "dur": 0.561, + "args": { + "External id": 226570,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115269803.194, "dur": 1.427, + "args": { + "External id": 226571,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115269806.486, "dur": 0.164, + "args": { + "External id": 226572,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115269807.949, "dur": 0.172, + "args": { + "External id": 226573,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115269811.766, "dur": 0.325, + "args": { + "External id": 226574,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115269813.490, "dur": 0.160, + "args": { + "External id": 226575,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115269815.078, "dur": 2.268, + "args": { + "External id": 226576,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115269837.417, "dur": 26.529, + "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": 4183436, "tid": 4183436, + "ts": 667115269931.364, "dur": 403.184, + "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": 4183436, "tid": 4183436, + "ts": 667115269962.727, "dur": 366.563, + "args": { + "External id": 226579,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115269973.088, "dur": 349.803, + "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": 4183436, "tid": 4183436, + "ts": 667115270356.067, "dur": 2.230, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 4183436, "tid": 4183436, + "ts": 667115270446.566, "dur": 7253.978, + "args": { + "External id": 226582,"Record function id": 0, "Ev Idx": 5381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115270565.230, "dur": 7.169, + "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": 4183436, "tid": 4183436, + "ts": 667115270576.920, "dur": 0.968, + "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": 4183436, "tid": 4183436, + "ts": 667115270579.652, "dur": 2.003, + "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": 4183436, "tid": 4183436, + "ts": 667115270584.676, "dur": 0.566, + "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": 4183436, "tid": 4183436, + "ts": 667115270586.938, "dur": 0.821, + "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": 4183436, "tid": 4183436, + "ts": 667115270589.291, "dur": 0.679, + "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": 4183436, "tid": 4183436, + "ts": 667115270591.499, "dur": 0.982, + "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": 4183436, "tid": 4183436, + "ts": 667115270595.565, "dur": 2.566, + "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": 4183436, "tid": 4183436, + "ts": 667115270599.743, "dur": 0.849, + "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": 4183436, "tid": 4183436, + "ts": 667115270602.085, "dur": 0.644, + "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": 4183436, "tid": 4183436, + "ts": 667115270623.152, "dur": 6990.818, + "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": 4183436, "tid": 4183436, + "ts": 667115270638.967, "dur": 6967.573, + "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": 4183436, "tid": 4183436, + "ts": 667115270653.228, "dur": 55.273, + "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": 4183436, "tid": 4183436, + "ts": 667115270714.665, "dur": 6858.139, + "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": 4183436, "tid": 4183436, + "ts": 667115270717.694, "dur": 6854.609, + "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": 4183436, "tid": 4183436, + "ts": 667115270725.350, "dur": 7.455, + "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": 4183436, "tid": 4183436, + "ts": 667115270734.467, "dur": 6834.887, + "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": 4183436, "tid": 4183436, + "ts": 667115277849.291, "dur": 32.291, + "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": 4183436, "tid": 4183436, "ts": 667115277849.291, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115277867.439, "dur": 9.292, + "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": 4183436, "tid": 4183436, + "ts": 667115277871.055, "dur": 5.401, + "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": 4183436, "tid": 4183436, + "ts": 667115277949.485, "dur": 84.672, + "args": { + "External id": 226603,"Record function id": 0, "Ev Idx": 5402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115278035.830, "dur": 1111.409, + "args": { + "External id": 226604,"Record function id": 0, "Ev Idx": 5403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115278077.250, "dur": 1055.798, + "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": 4183436, "tid": 4183436, "ts": 667115278077.250, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115278144.344, "dur": 45.141, + "args": { + "External id": 226606,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115278202.520, "dur": 89.442, + "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": 4183436, "tid": 4183436, + "ts": 667115278300.481, "dur": 33.707, + "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": 4183436, "tid": 4183436, + "ts": 667115278343.186, "dur": 28.599, + "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": 4183436, "tid": 4183436, + "ts": 667115278392.884, "dur": 23.849, + "args": { + "External id": 226610,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115278434.680, "dur": 13.983, + "args": { + "External id": 226611,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115278466.227, "dur": 158.786, + "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": 4183436, "tid": 4183436, + "ts": 667115278536.740, "dur": 12.836, + "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": 4183436, "tid": 4183436, + "ts": 667115278541.733, "dur": 6.786, + "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": 4183436, "tid": 4183436, + "ts": 667115278552.290, "dur": 5.987, + "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": 4183436, "tid": 4183436, + "ts": 667115278566.067, "dur": 1.066, + "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": 4183436, "tid": 4183436, + "ts": 667115278569.526, "dur": 3.195, + "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": 4183436, "tid": 4183436, + "ts": 667115278636.102, "dur": 100.688, + "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": 4183436, "tid": 4183436, + "ts": 667115278775.703, "dur": 31.437, + "args": { + "External id": 226619,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115278815.776, "dur": 43.557, + "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": 4183436, "tid": 4183436, + "ts": 667115278867.438, "dur": 51.128, + "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": 4183436, "tid": 4183436, + "ts": 667115278939.039, "dur": 25.331, + "args": { + "External id": 226622,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115278969.473, "dur": 54.925, + "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": 4183436, "tid": 4183436, + "ts": 667115279043.501, "dur": 20.634, + "args": { + "External id": 226624,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115279212.689, "dur": 73.998, + "args": { + "External id": 226625,"Record function id": 0, "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115279359.995, "dur": 47.527, + "args": { + "External id": 226626,"Record function id": 0, "Ev Idx": 5425 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 4183436, "tid": 4183436, + "ts": 667115279416.683, "dur": 8539.772, + "args": { + "External id": 226627,"Record function id": 0, "Ev Idx": 5426 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 4183436, "tid": 4183436, + "ts": 667115279424.970, "dur": 939.136, + "args": { + "External id": 226628,"Record function id": 0, "Ev Idx": 5427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115279522.665, "dur": 10.025, + "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": 4183436, "tid": 4183436, + "ts": 667115279546.843, "dur": 38.932, + "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": 4183436, "tid": 4183436, + "ts": 667115279552.390, "dur": 2.034, + "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": 4183436, "tid": 4183436, + "ts": 667115279559.903, "dur": 0.683, + "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": 4183436, "tid": 4183436, + "ts": 667115279562.309, "dur": 0.254, + "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": 4183436, "tid": 4183436, + "ts": 667115279564.048, "dur": 0.379, + "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": 4183436, "tid": 4183436, + "ts": 667115279568.543, "dur": 0.138, + "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": 4183436, "tid": 4183436, + "ts": 667115279570.579, "dur": 0.268, + "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": 4183436, "tid": 4183436, + "ts": 667115279572.479, "dur": 3.897, + "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": 4183436, "tid": 4183436, + "ts": 667115279578.142, "dur": 0.189, + "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": 4183436, "tid": 4183436, + "ts": 667115279579.576, "dur": 0.341, + "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": 4183436, "tid": 4183436, + "ts": 667115279596.910, "dur": 41.615, + "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": 4183436, "tid": 4183436, + "ts": 667115279722.230, "dur": 135.158, + "args": { + "External id": 226641,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115279737.764, "dur": 7.396, + "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": 4183436, "tid": 4183436, + "ts": 667115279750.801, "dur": 12.064, + "args": { + "External id": 226643,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115279755.167, "dur": 7.299, + "args": { + "External id": 226644,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115279759.606, "dur": 1.155, + "args": { + "External id": 226645,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115279771.574, "dur": 33.799, + "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": 4183436, "tid": 4183436, + "ts": 667115279774.546, "dur": 2.845, + "args": { + "External id": 226647,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115279779.460, "dur": 0.733, + "args": { + "External id": 226648,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115279781.929, "dur": 0.291, + "args": { + "External id": 226649,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115279785.793, "dur": 1.480, + "args": { + "External id": 226650,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115279788.490, "dur": 0.352, + "args": { + "External id": 226651,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115279790.548, "dur": 0.326, + "args": { + "External id": 226652,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115279794.292, "dur": 0.404, + "args": { + "External id": 226653,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115279796.072, "dur": 0.492, + "args": { + "External id": 226654,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115279797.728, "dur": 3.329, + "args": { + "External id": 226655,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115279820.195, "dur": 28.615, + "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": 4183436, "tid": 4183436, + "ts": 667115279917.582, "dur": 359.241, + "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": 4183436, "tid": 4183436, + "ts": 667115279948.120, "dur": 323.929, + "args": { + "External id": 226658,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115279958.409, "dur": 308.081, + "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": 4183436, "tid": 4183436, + "ts": 667115280296.017, "dur": 2.093, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 4183436, "tid": 4183436, + "ts": 667115280384.594, "dur": 7378.355, + "args": { + "External id": 226661,"Record function id": 0, "Ev Idx": 5460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115280470.344, "dur": 5.358, + "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": 4183436, "tid": 4183436, + "ts": 667115280479.874, "dur": 0.938, + "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": 4183436, "tid": 4183436, + "ts": 667115280482.840, "dur": 2.357, + "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": 4183436, "tid": 4183436, + "ts": 667115280487.169, "dur": 0.822, + "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": 4183436, "tid": 4183436, + "ts": 667115280507.674, "dur": 2.019, + "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": 4183436, "tid": 4183436, + "ts": 667115280514.023, "dur": 0.738, + "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": 4183436, "tid": 4183436, + "ts": 667115280517.711, "dur": 0.898, + "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": 4183436, "tid": 4183436, + "ts": 667115280520.277, "dur": 1.580, + "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": 4183436, "tid": 4183436, + "ts": 667115280523.251, "dur": 0.918, + "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": 4183436, "tid": 4183436, + "ts": 667115280525.704, "dur": 0.680, + "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": 4183436, "tid": 4183436, + "ts": 667115280556.373, "dur": 7152.254, + "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": 4183436, "tid": 4183436, + "ts": 667115280572.821, "dur": 7127.159, + "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": 4183436, "tid": 4183436, + "ts": 667115280587.316, "dur": 14.768, + "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": 4183436, "tid": 4183436, + "ts": 667115280604.471, "dur": 7027.879, + "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": 4183436, "tid": 4183436, + "ts": 667115280607.228, "dur": 7024.423, + "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": 4183436, "tid": 4183436, + "ts": 667115280613.472, "dur": 6.811, + "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": 4183436, "tid": 4183436, + "ts": 667115280622.081, "dur": 7006.231, + "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": 4183436, "tid": 4183436, + "ts": 667115287900.817, "dur": 30.364, + "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": 4183436, "tid": 4183436, "ts": 667115287900.817, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115287917.450, "dur": 9.116, + "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": 4183436, "tid": 4183436, + "ts": 667115287921.190, "dur": 5.121, + "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": 4183436, "tid": 4183436, + "ts": 667115287997.052, "dur": 85.312, + "args": { + "External id": 226682,"Record function id": 0, "Ev Idx": 5481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115288084.089, "dur": 1090.299, + "args": { + "External id": 226683,"Record function id": 0, "Ev Idx": 5482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115288124.294, "dur": 1036.294, + "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": 4183436, "tid": 4183436, "ts": 667115288124.294, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115288189.051, "dur": 45.299, + "args": { + "External id": 226685,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115288247.119, "dur": 90.582, + "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": 4183436, "tid": 4183436, + "ts": 667115288346.538, "dur": 35.517, + "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": 4183436, "tid": 4183436, + "ts": 667115288391.610, "dur": 29.357, + "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": 4183436, "tid": 4183436, + "ts": 667115288445.195, "dur": 25.439, + "args": { + "External id": 226689,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115288488.024, "dur": 35.578, + "args": { + "External id": 226690,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115288544.427, "dur": 167.706, + "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": 4183436, "tid": 4183436, + "ts": 667115288593.797, "dur": 12.454, + "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": 4183436, "tid": 4183436, + "ts": 667115288598.852, "dur": 6.679, + "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": 4183436, "tid": 4183436, + "ts": 667115288609.064, "dur": 5.258, + "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": 4183436, "tid": 4183436, + "ts": 667115288615.802, "dur": 0.909, + "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": 4183436, "tid": 4183436, + "ts": 667115288619.228, "dur": 3.870, + "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": 4183436, "tid": 4183436, + "ts": 667115288724.947, "dur": 55.551, + "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": 4183436, "tid": 4183436, + "ts": 667115288813.145, "dur": 27.930, + "args": { + "External id": 226698,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115288849.667, "dur": 38.819, + "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": 4183436, "tid": 4183436, + "ts": 667115288897.415, "dur": 45.511, + "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": 4183436, "tid": 4183436, + "ts": 667115288963.652, "dur": 25.222, + "args": { + "External id": 226701,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115288994.894, "dur": 54.703, + "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": 4183436, "tid": 4183436, + "ts": 667115289068.678, "dur": 18.074, + "args": { + "External id": 226703,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115289238.719, "dur": 71.750, + "args": { + "External id": 226704,"Record function id": 0, "Ev Idx": 5503 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115289384.650, "dur": 50.342, + "args": { + "External id": 226705,"Record function id": 0, "Ev Idx": 5504 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 4183436, "tid": 4183436, + "ts": 667115289444.762, "dur": 8927.245, + "args": { + "External id": 226706,"Record function id": 0, "Ev Idx": 5505 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 4183436, "tid": 4183436, + "ts": 667115289453.161, "dur": 927.638, + "args": { + "External id": 226707,"Record function id": 0, "Ev Idx": 5506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115289551.354, "dur": 8.407, + "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": 4183436, "tid": 4183436, + "ts": 667115289574.225, "dur": 38.839, + "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": 4183436, "tid": 4183436, + "ts": 667115289580.019, "dur": 2.196, + "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": 4183436, "tid": 4183436, + "ts": 667115289587.106, "dur": 0.482, + "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": 4183436, "tid": 4183436, + "ts": 667115289589.431, "dur": 0.344, + "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": 4183436, "tid": 4183436, + "ts": 667115289591.145, "dur": 0.241, + "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": 4183436, "tid": 4183436, + "ts": 667115289595.378, "dur": 0.187, + "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": 4183436, "tid": 4183436, + "ts": 667115289596.786, "dur": 0.524, + "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": 4183436, "tid": 4183436, + "ts": 667115289598.959, "dur": 3.769, + "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": 4183436, "tid": 4183436, + "ts": 667115289604.413, "dur": 0.193, + "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": 4183436, "tid": 4183436, + "ts": 667115289606.229, "dur": 0.182, + "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": 4183436, "tid": 4183436, + "ts": 667115289624.153, "dur": 75.935, + "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": 4183436, "tid": 4183436, + "ts": 667115289738.761, "dur": 130.252, + "args": { + "External id": 226720,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115289749.815, "dur": 4.948, + "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": 4183436, "tid": 4183436, + "ts": 667115289759.944, "dur": 11.050, + "args": { + "External id": 226722,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115289764.491, "dur": 6.117, + "args": { + "External id": 226723,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115289768.265, "dur": 0.855, + "args": { + "External id": 226724,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115289778.390, "dur": 35.165, + "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": 4183436, "tid": 4183436, + "ts": 667115289780.332, "dur": 2.890, + "args": { + "External id": 226726,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115289788.050, "dur": 0.420, + "args": { + "External id": 226727,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115289789.815, "dur": 0.387, + "args": { + "External id": 226728,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115289793.474, "dur": 1.291, + "args": { + "External id": 226729,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115289796.466, "dur": 0.317, + "args": { + "External id": 226730,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115289798.158, "dur": 2.999, + "args": { + "External id": 226731,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115289802.496, "dur": 0.367, + "args": { + "External id": 226732,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115289804.600, "dur": 0.559, + "args": { + "External id": 226733,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115289808.719, "dur": 0.440, + "args": { + "External id": 226734,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115289835.792, "dur": 25.497, + "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": 4183436, "tid": 4183436, + "ts": 667115289924.151, "dur": 368.607, + "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": 4183436, "tid": 4183436, + "ts": 667115289953.125, "dur": 334.937, + "args": { + "External id": 226737,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115289964.884, "dur": 317.852, + "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": 4183436, "tid": 4183436, + "ts": 667115290314.438, "dur": 2.168, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 4183436, "tid": 4183436, + "ts": 667115290400.456, "dur": 7756.604, + "args": { + "External id": 226740,"Record function id": 0, "Ev Idx": 5539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115290489.405, "dur": 24.355, + "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": 4183436, "tid": 4183436, + "ts": 667115290519.584, "dur": 0.984, + "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": 4183436, "tid": 4183436, + "ts": 667115290522.674, "dur": 1.989, + "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": 4183436, "tid": 4183436, + "ts": 667115290526.347, "dur": 0.769, + "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": 4183436, "tid": 4183436, + "ts": 667115290528.723, "dur": 0.733, + "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": 4183436, "tid": 4183436, + "ts": 667115290532.486, "dur": 0.564, + "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": 4183436, "tid": 4183436, + "ts": 667115290534.609, "dur": 1.077, + "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": 4183436, "tid": 4183436, + "ts": 667115290537.396, "dur": 1.717, + "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": 4183436, "tid": 4183436, + "ts": 667115290540.940, "dur": 0.732, + "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": 4183436, "tid": 4183436, + "ts": 667115290545.081, "dur": 0.502, + "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": 4183436, "tid": 4183436, + "ts": 667115290564.196, "dur": 7521.318, + "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": 4183436, "tid": 4183436, + "ts": 667115290579.447, "dur": 7494.759, + "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": 4183436, "tid": 4183436, + "ts": 667115290594.624, "dur": 14.677, + "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": 4183436, "tid": 4183436, + "ts": 667115290611.723, "dur": 7418.393, + "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": 4183436, "tid": 4183436, + "ts": 667115290614.472, "dur": 7414.438, + "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": 4183436, "tid": 4183436, + "ts": 667115290620.207, "dur": 7.125, + "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": 4183436, "tid": 4183436, + "ts": 667115290628.927, "dur": 7394.667, + "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": 4183436, "tid": 4183436, + "ts": 667115298309.066, "dur": 33.699, + "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": 4183436, "tid": 4183436, "ts": 667115298309.066, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115298326.388, "dur": 11.441, + "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": 4183436, "tid": 4183436, + "ts": 667115298331.489, "dur": 6.048, + "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": 4183436, "tid": 4183436, + "ts": 667115298413.224, "dur": 96.481, + "args": { + "External id": 226761,"Record function id": 0, "Ev Idx": 5560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115298513.114, "dur": 1062.046, + "args": { + "External id": 226762,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115298553.055, "dur": 1007.657, + "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": 4183436, "tid": 4183436, "ts": 667115298553.055, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115298622.279, "dur": 84.126, + "args": { + "External id": 226764,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115298723.237, "dur": 93.618, + "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": 4183436, "tid": 4183436, + "ts": 667115298826.569, "dur": 34.466, + "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": 4183436, "tid": 4183436, + "ts": 667115298870.335, "dur": 29.687, + "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": 4183436, "tid": 4183436, + "ts": 667115298926.548, "dur": 27.592, + "args": { + "External id": 226768,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115298971.366, "dur": 14.302, + "args": { + "External id": 226769,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115299004.621, "dur": 125.882, + "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": 4183436, "tid": 4183436, + "ts": 667115299052.131, "dur": 11.564, + "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": 4183436, "tid": 4183436, + "ts": 667115299057.288, "dur": 5.551, + "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": 4183436, "tid": 4183436, + "ts": 667115299066.401, "dur": 5.675, + "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": 4183436, "tid": 4183436, + "ts": 667115299073.333, "dur": 1.507, + "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": 4183436, "tid": 4183436, + "ts": 667115299077.046, "dur": 4.475, + "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": 4183436, "tid": 4183436, + "ts": 667115299140.721, "dur": 42.462, + "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": 4183436, "tid": 4183436, + "ts": 667115299212.998, "dur": 26.342, + "args": { + "External id": 226777,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115299257.479, "dur": 38.519, + "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": 4183436, "tid": 4183436, + "ts": 667115299304.715, "dur": 31.359, + "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": 4183436, "tid": 4183436, + "ts": 667115299357.765, "dur": 23.857, + "args": { + "External id": 226780,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115299387.352, "dur": 51.005, + "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": 4183436, "tid": 4183436, + "ts": 667115299457.691, "dur": 17.450, + "args": { + "External id": 226782,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115299641.515, "dur": 114.556, + "args": { + "External id": 226783,"Record function id": 0, "Ev Idx": 5582 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115299834.225, "dur": 49.391, + "args": { + "External id": 226784,"Record function id": 0, "Ev Idx": 5583 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 4183436, "tid": 4183436, + "ts": 667115299892.579, "dur": 8978.481, + "args": { + "External id": 226785,"Record function id": 0, "Ev Idx": 5584 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 4183436, "tid": 4183436, + "ts": 667115299899.532, "dur": 932.014, + "args": { + "External id": 226786,"Record function id": 0, "Ev Idx": 5585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115299976.770, "dur": 8.963, + "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": 4183436, "tid": 4183436, + "ts": 667115299999.474, "dur": 35.364, + "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": 4183436, "tid": 4183436, + "ts": 667115300004.942, "dur": 2.182, + "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": 4183436, "tid": 4183436, + "ts": 667115300011.866, "dur": 0.219, + "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": 4183436, "tid": 4183436, + "ts": 667115300013.260, "dur": 0.531, + "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": 4183436, "tid": 4183436, + "ts": 667115300015.066, "dur": 0.407, + "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": 4183436, "tid": 4183436, + "ts": 667115300019.252, "dur": 0.270, + "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": 4183436, "tid": 4183436, + "ts": 667115300020.728, "dur": 0.288, + "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": 4183436, "tid": 4183436, + "ts": 667115300021.978, "dur": 3.793, + "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": 4183436, "tid": 4183436, + "ts": 667115300027.056, "dur": 0.305, + "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": 4183436, "tid": 4183436, + "ts": 667115300028.584, "dur": 0.311, + "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": 4183436, "tid": 4183436, + "ts": 667115300045.586, "dur": 41.435, + "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": 4183436, "tid": 4183436, + "ts": 667115300120.362, "dur": 105.290, + "args": { + "External id": 226799,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115300130.721, "dur": 3.941, + "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": 4183436, "tid": 4183436, + "ts": 667115300140.003, "dur": 9.998, + "args": { + "External id": 226801,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115300144.317, "dur": 5.291, + "args": { + "External id": 226802,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115300147.670, "dur": 0.627, + "args": { + "External id": 226803,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115300156.270, "dur": 30.276, + "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": 4183436, "tid": 4183436, + "ts": 667115300157.987, "dur": 2.751, + "args": { + "External id": 226805,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115300161.938, "dur": 0.436, + "args": { + "External id": 226806,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115300164.245, "dur": 0.563, + "args": { + "External id": 226807,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115300168.857, "dur": 1.320, + "args": { + "External id": 226808,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115300172.144, "dur": 0.148, + "args": { + "External id": 226809,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115300173.758, "dur": 0.319, + "args": { + "External id": 226810,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115300177.319, "dur": 0.325, + "args": { + "External id": 226811,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115300178.731, "dur": 0.333, + "args": { + "External id": 226812,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115300180.077, "dur": 2.443, + "args": { + "External id": 226813,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115300196.904, "dur": 21.425, + "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": 4183436, "tid": 4183436, + "ts": 667115300277.450, "dur": 451.411, + "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": 4183436, "tid": 4183436, + "ts": 667115300304.876, "dur": 417.623, + "args": { + "External id": 226816,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115300338.685, "dur": 374.806, + "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": 4183436, "tid": 4183436, + "ts": 667115300752.560, "dur": 2.313, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 4183436, "tid": 4183436, + "ts": 667115300853.515, "dur": 7820.785, + "args": { + "External id": 226819,"Record function id": 0, "Ev Idx": 5618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115300949.888, "dur": 6.501, + "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": 4183436, "tid": 4183436, + "ts": 667115300960.068, "dur": 0.972, + "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": 4183436, "tid": 4183436, + "ts": 667115300962.622, "dur": 2.270, + "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": 4183436, "tid": 4183436, + "ts": 667115300966.589, "dur": 0.786, + "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": 4183436, "tid": 4183436, + "ts": 667115300968.661, "dur": 0.810, + "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": 4183436, "tid": 4183436, + "ts": 667115300971.469, "dur": 0.763, + "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": 4183436, "tid": 4183436, + "ts": 667115300974.135, "dur": 0.897, + "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": 4183436, "tid": 4183436, + "ts": 667115300976.325, "dur": 2.007, + "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": 4183436, "tid": 4183436, + "ts": 667115300980.259, "dur": 0.815, + "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": 4183436, "tid": 4183436, + "ts": 667115300982.721, "dur": 0.552, + "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": 4183436, "tid": 4183436, + "ts": 667115301000.585, "dur": 7599.636, + "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": 4183436, "tid": 4183436, + "ts": 667115301017.079, "dur": 7575.311, + "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": 4183436, "tid": 4183436, + "ts": 667115301031.512, "dur": 15.309, + "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": 4183436, "tid": 4183436, + "ts": 667115301049.471, "dur": 7507.544, + "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": 4183436, "tid": 4183436, + "ts": 667115301052.297, "dur": 7504.045, + "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": 4183436, "tid": 4183436, + "ts": 667115301058.684, "dur": 7.003, + "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": 4183436, "tid": 4183436, + "ts": 667115301067.842, "dur": 7485.251, + "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": 4183436, "tid": 4183436, + "ts": 667115308813.700, "dur": 29.900, + "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": 4183436, "tid": 4183436, "ts": 667115308813.700, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115308829.675, "dur": 9.291, + "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": 4183436, "tid": 4183436, + "ts": 667115308833.250, "dur": 5.427, + "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": 4183436, "tid": 4183436, + "ts": 667115308909.884, "dur": 83.956, + "args": { + "External id": 226840,"Record function id": 0, "Ev Idx": 5639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115308995.492, "dur": 1070.405, + "args": { + "External id": 226841,"Record function id": 0, "Ev Idx": 5640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115309033.914, "dur": 1017.902, + "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": 4183436, "tid": 4183436, "ts": 667115309033.914, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115309099.504, "dur": 45.234, + "args": { + "External id": 226843,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115309157.966, "dur": 92.983, + "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": 4183436, "tid": 4183436, + "ts": 667115309260.732, "dur": 33.891, + "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": 4183436, "tid": 4183436, + "ts": 667115309302.414, "dur": 28.183, + "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": 4183436, "tid": 4183436, + "ts": 667115309353.912, "dur": 22.913, + "args": { + "External id": 226847,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115309393.660, "dur": 13.303, + "args": { + "External id": 226848,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115309424.276, "dur": 152.573, + "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": 4183436, "tid": 4183436, + "ts": 667115309472.889, "dur": 11.636, + "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": 4183436, "tid": 4183436, + "ts": 667115309477.484, "dur": 6.035, + "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": 4183436, "tid": 4183436, + "ts": 667115309487.397, "dur": 27.129, + "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": 4183436, "tid": 4183436, + "ts": 667115309517.114, "dur": 1.696, + "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": 4183436, "tid": 4183436, + "ts": 667115309521.514, "dur": 4.304, + "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": 4183436, "tid": 4183436, + "ts": 667115309587.884, "dur": 47.913, + "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": 4183436, "tid": 4183436, + "ts": 667115309709.434, "dur": 32.434, + "args": { + "External id": 226856,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115309753.059, "dur": 43.251, + "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": 4183436, "tid": 4183436, + "ts": 667115309805.208, "dur": 31.622, + "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": 4183436, "tid": 4183436, + "ts": 667115309857.681, "dur": 23.621, + "args": { + "External id": 226859,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115309887.283, "dur": 52.225, + "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": 4183436, "tid": 4183436, + "ts": 667115309959.828, "dur": 18.514, + "args": { + "External id": 226861,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115310130.992, "dur": 73.568, + "args": { + "External id": 226862,"Record function id": 0, "Ev Idx": 5661 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115310279.811, "dur": 48.677, + "args": { + "External id": 226863,"Record function id": 0, "Ev Idx": 5662 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 4183436, "tid": 4183436, + "ts": 667115310337.853, "dur": 8915.901, + "args": { + "External id": 226864,"Record function id": 0, "Ev Idx": 5663 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 4183436, "tid": 4183436, + "ts": 667115310345.627, "dur": 905.954, + "args": { + "External id": 226865,"Record function id": 0, "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115310421.297, "dur": 8.379, + "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": 4183436, "tid": 4183436, + "ts": 667115310442.409, "dur": 35.173, + "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": 4183436, "tid": 4183436, + "ts": 667115310447.519, "dur": 2.229, + "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": 4183436, "tid": 4183436, + "ts": 667115310453.963, "dur": 0.365, + "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": 4183436, "tid": 4183436, + "ts": 667115310455.235, "dur": 0.319, + "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": 4183436, "tid": 4183436, + "ts": 667115310456.455, "dur": 0.327, + "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": 4183436, "tid": 4183436, + "ts": 667115310459.631, "dur": 0.339, + "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": 4183436, "tid": 4183436, + "ts": 667115310461.508, "dur": 0.157, + "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": 4183436, "tid": 4183436, + "ts": 667115310463.246, "dur": 4.002, + "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": 4183436, "tid": 4183436, + "ts": 667115310469.339, "dur": 0.426, + "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": 4183436, "tid": 4183436, + "ts": 667115310471.110, "dur": 0.449, + "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": 4183436, "tid": 4183436, + "ts": 667115310508.391, "dur": 39.349, + "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": 4183436, "tid": 4183436, + "ts": 667115310583.797, "dur": 157.281, + "args": { + "External id": 226878,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115310594.595, "dur": 7.963, + "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": 4183436, "tid": 4183436, + "ts": 667115310607.773, "dur": 10.945, + "args": { + "External id": 226880,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115310612.173, "dur": 6.187, + "args": { + "External id": 226881,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115310616.161, "dur": 0.657, + "args": { + "External id": 226882,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115310626.094, "dur": 65.618, + "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": 4183436, "tid": 4183436, + "ts": 667115310628.457, "dur": 0.415, + "args": { + "External id": 226884,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115310630.448, "dur": 2.676, + "args": { + "External id": 226885,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115310634.495, "dur": 0.229, + "args": { + "External id": 226886,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115310636.469, "dur": 1.653, + "args": { + "External id": 226887,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115310641.958, "dur": 0.202, + "args": { + "External id": 226888,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115310643.755, "dur": 0.167, + "args": { + "External id": 226889,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115310645.235, "dur": 0.161, + "args": { + "External id": 226890,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115310648.702, "dur": 0.162, + "args": { + "External id": 226891,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115310650.210, "dur": 0.183, + "args": { + "External id": 226892,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115310707.587, "dur": 25.169, + "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": 4183436, "tid": 4183436, + "ts": 667115310796.691, "dur": 367.937, + "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": 4183436, "tid": 4183436, + "ts": 667115310826.283, "dur": 334.325, + "args": { + "External id": 226895,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115310836.706, "dur": 318.576, + "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": 4183436, "tid": 4183436, + "ts": 667115311184.837, "dur": 2.557, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 4183436, "tid": 4183436, + "ts": 667115311271.779, "dur": 7777.175, + "args": { + "External id": 226898,"Record function id": 0, "Ev Idx": 5697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115311363.970, "dur": 5.783, + "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": 4183436, "tid": 4183436, + "ts": 667115311372.672, "dur": 1.043, + "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": 4183436, "tid": 4183436, + "ts": 667115311375.199, "dur": 2.167, + "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": 4183436, "tid": 4183436, + "ts": 667115311378.865, "dur": 0.878, + "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": 4183436, "tid": 4183436, + "ts": 667115311381.337, "dur": 0.925, + "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": 4183436, "tid": 4183436, + "ts": 667115311384.010, "dur": 0.926, + "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": 4183436, "tid": 4183436, + "ts": 667115311386.546, "dur": 0.713, + "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": 4183436, "tid": 4183436, + "ts": 667115311389.062, "dur": 2.143, + "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": 4183436, "tid": 4183436, + "ts": 667115311392.713, "dur": 0.732, + "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": 4183436, "tid": 4183436, + "ts": 667115311395.119, "dur": 0.671, + "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": 4183436, "tid": 4183436, + "ts": 667115311413.533, "dur": 7585.372, + "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": 4183436, "tid": 4183436, + "ts": 667115311430.083, "dur": 7560.467, + "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": 4183436, "tid": 4183436, + "ts": 667115311444.323, "dur": 15.413, + "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": 4183436, "tid": 4183436, + "ts": 667115311462.237, "dur": 7491.257, + "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": 4183436, "tid": 4183436, + "ts": 667115311465.030, "dur": 7487.779, + "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": 4183436, "tid": 4183436, + "ts": 667115311471.486, "dur": 5.215, + "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": 4183436, "tid": 4183436, + "ts": 667115311478.712, "dur": 7470.848, + "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": 4183436, "tid": 4183436, + "ts": 667115319186.324, "dur": 41.211, + "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": 4183436, "tid": 4183436, "ts": 667115319186.324, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115319212.912, "dur": 9.616, + "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": 4183436, "tid": 4183436, + "ts": 667115319216.803, "dur": 5.411, + "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": 4183436, "tid": 4183436, + "ts": 667115319294.825, "dur": 83.871, + "args": { + "External id": 226919,"Record function id": 0, "Ev Idx": 5718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115319380.707, "dur": 1062.308, + "args": { + "External id": 226920,"Record function id": 0, "Ev Idx": 5719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115319419.489, "dur": 1009.382, + "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": 4183436, "tid": 4183436, "ts": 667115319419.489, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115319484.668, "dur": 59.740, + "args": { + "External id": 226922,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115319559.553, "dur": 89.597, + "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": 4183436, "tid": 4183436, + "ts": 667115319698.616, "dur": 46.014, + "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": 4183436, "tid": 4183436, + "ts": 667115319754.767, "dur": 30.021, + "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": 4183436, "tid": 4183436, + "ts": 667115319810.856, "dur": 25.731, + "args": { + "External id": 226926,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115319853.634, "dur": 16.201, + "args": { + "External id": 226927,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115319888.598, "dur": 132.569, + "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": 4183436, "tid": 4183436, + "ts": 667115319941.215, "dur": 12.127, + "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": 4183436, "tid": 4183436, + "ts": 667115319946.399, "dur": 5.918, + "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": 4183436, "tid": 4183436, + "ts": 667115319956.313, "dur": 5.313, + "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": 4183436, "tid": 4183436, + "ts": 667115319962.947, "dur": 1.280, + "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": 4183436, "tid": 4183436, + "ts": 667115319966.816, "dur": 4.659, + "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": 4183436, "tid": 4183436, + "ts": 667115320030.911, "dur": 45.593, + "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": 4183436, "tid": 4183436, + "ts": 667115320105.236, "dur": 28.702, + "args": { + "External id": 226935,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115320142.399, "dur": 39.036, + "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": 4183436, "tid": 4183436, + "ts": 667115320190.165, "dur": 31.263, + "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": 4183436, "tid": 4183436, + "ts": 667115320241.671, "dur": 26.397, + "args": { + "External id": 226938,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115320272.951, "dur": 43.924, + "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": 4183436, "tid": 4183436, + "ts": 667115320336.144, "dur": 20.834, + "args": { + "External id": 226940,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115320524.638, "dur": 75.113, + "args": { + "External id": 226941,"Record function id": 0, "Ev Idx": 5740 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115320714.722, "dur": 50.908, + "args": { + "External id": 226942,"Record function id": 0, "Ev Idx": 5741 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 4183436, "tid": 4183436, + "ts": 667115320775.938, "dur": 8912.676, + "args": { + "External id": 226943,"Record function id": 0, "Ev Idx": 5742 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 4183436, "tid": 4183436, + "ts": 667115320784.137, "dur": 952.594, + "args": { + "External id": 226944,"Record function id": 0, "Ev Idx": 5743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115320862.422, "dur": 9.833, + "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": 4183436, "tid": 4183436, + "ts": 667115320888.114, "dur": 38.913, + "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": 4183436, "tid": 4183436, + "ts": 667115320894.063, "dur": 2.338, + "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": 4183436, "tid": 4183436, + "ts": 667115320900.840, "dur": 0.431, + "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": 4183436, "tid": 4183436, + "ts": 667115320903.000, "dur": 0.319, + "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": 4183436, "tid": 4183436, + "ts": 667115320904.873, "dur": 2.425, + "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": 4183436, "tid": 4183436, + "ts": 667115320908.932, "dur": 0.484, + "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": 4183436, "tid": 4183436, + "ts": 667115320910.927, "dur": 0.525, + "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": 4183436, "tid": 4183436, + "ts": 667115320915.126, "dur": 1.679, + "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": 4183436, "tid": 4183436, + "ts": 667115320918.401, "dur": 0.441, + "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": 4183436, "tid": 4183436, + "ts": 667115320920.298, "dur": 0.264, + "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": 4183436, "tid": 4183436, + "ts": 667115320938.670, "dur": 41.399, + "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": 4183436, "tid": 4183436, + "ts": 667115321012.635, "dur": 111.173, + "args": { + "External id": 226957,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115321023.258, "dur": 4.301, + "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": 4183436, "tid": 4183436, + "ts": 667115321032.635, "dur": 12.454, + "args": { + "External id": 226959,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115321037.084, "dur": 7.575, + "args": { + "External id": 226960,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115321040.698, "dur": 2.667, + "args": { + "External id": 226961,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115321052.348, "dur": 29.534, + "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": 4183436, "tid": 4183436, + "ts": 667115321054.739, "dur": 0.478, + "args": { + "External id": 226963,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115321056.832, "dur": 0.475, + "args": { + "External id": 226964,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115321058.733, "dur": 0.346, + "args": { + "External id": 226965,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115321062.496, "dur": 1.794, + "args": { + "External id": 226966,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115321065.923, "dur": 0.345, + "args": { + "External id": 226967,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115321067.570, "dur": 2.276, + "args": { + "External id": 226968,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115321071.607, "dur": 0.404, + "args": { + "External id": 226969,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115321073.252, "dur": 0.316, + "args": { + "External id": 226970,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115321077.524, "dur": 0.218, + "args": { + "External id": 226971,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115321092.306, "dur": 23.702, + "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": 4183436, "tid": 4183436, + "ts": 667115321177.183, "dur": 421.343, + "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": 4183436, "tid": 4183436, + "ts": 667115321203.625, "dur": 388.915, + "args": { + "External id": 226974,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115321213.991, "dur": 372.442, + "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": 4183436, "tid": 4183436, + "ts": 667115321622.227, "dur": 2.651, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 4183436, "tid": 4183436, + "ts": 667115321760.685, "dur": 7685.622, + "args": { + "External id": 226977,"Record function id": 0, "Ev Idx": 5776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115321860.724, "dur": 6.668, + "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": 4183436, "tid": 4183436, + "ts": 667115321870.936, "dur": 1.089, + "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": 4183436, "tid": 4183436, + "ts": 667115321873.566, "dur": 2.478, + "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": 4183436, "tid": 4183436, + "ts": 667115321877.706, "dur": 0.746, + "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": 4183436, "tid": 4183436, + "ts": 667115321880.104, "dur": 0.886, + "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": 4183436, "tid": 4183436, + "ts": 667115321883.131, "dur": 0.721, + "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": 4183436, "tid": 4183436, + "ts": 667115321885.687, "dur": 0.848, + "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": 4183436, "tid": 4183436, + "ts": 667115321888.308, "dur": 1.749, + "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": 4183436, "tid": 4183436, + "ts": 667115321891.982, "dur": 0.556, + "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": 4183436, "tid": 4183436, + "ts": 667115321894.326, "dur": 0.558, + "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": 4183436, "tid": 4183436, + "ts": 667115321912.856, "dur": 7487.938, + "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": 4183436, "tid": 4183436, + "ts": 667115321928.847, "dur": 7464.331, + "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": 4183436, "tid": 4183436, + "ts": 667115321948.092, "dur": 15.035, + "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": 4183436, "tid": 4183436, + "ts": 667115321965.664, "dur": 7391.815, + "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": 4183436, "tid": 4183436, + "ts": 667115321968.584, "dur": 7388.092, + "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": 4183436, "tid": 4183436, + "ts": 667115321975.069, "dur": 6.851, + "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": 4183436, "tid": 4183436, + "ts": 667115321983.629, "dur": 7369.814, + "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": 4183436, "tid": 4183436, + "ts": 667115329596.177, "dur": 35.529, + "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": 4183436, "tid": 4183436, "ts": 667115329596.177, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115329617.678, "dur": 9.410, + "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": 4183436, "tid": 4183436, + "ts": 667115329621.466, "dur": 5.243, + "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": 4183436, "tid": 4183436, + "ts": 667115329731.138, "dur": 83.329, + "args": { + "External id": 226998,"Record function id": 0, "Ev Idx": 5797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115329816.412, "dur": 1095.424, + "args": { + "External id": 226999,"Record function id": 0, "Ev Idx": 5798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115329855.088, "dur": 1042.790, + "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": 4183436, "tid": 4183436, "ts": 667115329855.088, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115329920.802, "dur": 47.775, + "args": { + "External id": 227001,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115329981.123, "dur": 94.645, + "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": 4183436, "tid": 4183436, + "ts": 667115330086.019, "dur": 35.567, + "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": 4183436, "tid": 4183436, + "ts": 667115330130.042, "dur": 29.475, + "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": 4183436, "tid": 4183436, + "ts": 667115330183.239, "dur": 26.977, + "args": { + "External id": 227005,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115330228.094, "dur": 14.902, + "args": { + "External id": 227006,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115330261.256, "dur": 128.047, + "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": 4183436, "tid": 4183436, + "ts": 667115330309.425, "dur": 11.159, + "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": 4183436, "tid": 4183436, + "ts": 667115330314.408, "dur": 5.334, + "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": 4183436, "tid": 4183436, + "ts": 667115330323.523, "dur": 5.580, + "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": 4183436, "tid": 4183436, + "ts": 667115330330.643, "dur": 1.393, + "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": 4183436, "tid": 4183436, + "ts": 667115330334.339, "dur": 4.081, + "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": 4183436, "tid": 4183436, + "ts": 667115330399.490, "dur": 43.447, + "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": 4183436, "tid": 4183436, + "ts": 667115330472.295, "dur": 48.139, + "args": { + "External id": 227014,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115330532.674, "dur": 41.745, + "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": 4183436, "tid": 4183436, + "ts": 667115330583.453, "dur": 31.136, + "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": 4183436, "tid": 4183436, + "ts": 667115330644.421, "dur": 65.119, + "args": { + "External id": 227017,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115330720.497, "dur": 62.845, + "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": 4183436, "tid": 4183436, + "ts": 667115330804.073, "dur": 26.900, + "args": { + "External id": 227019,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115330977.688, "dur": 75.401, + "args": { + "External id": 227020,"Record function id": 0, "Ev Idx": 5819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115331127.844, "dur": 46.340, + "args": { + "External id": 227021,"Record function id": 0, "Ev Idx": 5820 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 4183436, "tid": 4183436, + "ts": 667115331183.675, "dur": 8868.067, + "args": { + "External id": 227022,"Record function id": 0, "Ev Idx": 5821 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 4183436, "tid": 4183436, + "ts": 667115331194.896, "dur": 926.498, + "args": { + "External id": 227023,"Record function id": 0, "Ev Idx": 5822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115331271.871, "dur": 8.431, + "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": 4183436, "tid": 4183436, + "ts": 667115331293.311, "dur": 36.092, + "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": 4183436, "tid": 4183436, + "ts": 667115331298.689, "dur": 2.122, + "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": 4183436, "tid": 4183436, + "ts": 667115331305.163, "dur": 0.222, + "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": 4183436, "tid": 4183436, + "ts": 667115331307.074, "dur": 0.384, + "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": 4183436, "tid": 4183436, + "ts": 667115331309.075, "dur": 0.374, + "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": 4183436, "tid": 4183436, + "ts": 667115331312.397, "dur": 0.662, + "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": 4183436, "tid": 4183436, + "ts": 667115331314.490, "dur": 0.323, + "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": 4183436, "tid": 4183436, + "ts": 667115331316.594, "dur": 3.770, + "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": 4183436, "tid": 4183436, + "ts": 667115331321.813, "dur": 0.228, + "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": 4183436, "tid": 4183436, + "ts": 667115331323.290, "dur": 0.270, + "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": 4183436, "tid": 4183436, + "ts": 667115331340.470, "dur": 37.138, + "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": 4183436, "tid": 4183436, + "ts": 667115331409.466, "dur": 137.154, + "args": { + "External id": 227036,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115331419.721, "dur": 4.798, + "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": 4183436, "tid": 4183436, + "ts": 667115331429.268, "dur": 10.243, + "args": { + "External id": 227038,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115331433.605, "dur": 5.525, + "args": { + "External id": 227039,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115331437.428, "dur": 0.530, + "args": { + "External id": 227040,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115331446.614, "dur": 32.379, + "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": 4183436, "tid": 4183436, + "ts": 667115331449.038, "dur": 2.556, + "args": { + "External id": 227042,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115331453.265, "dur": 0.346, + "args": { + "External id": 227043,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115331455.296, "dur": 0.362, + "args": { + "External id": 227044,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115331460.094, "dur": 1.294, + "args": { + "External id": 227045,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115331462.957, "dur": 0.309, + "args": { + "External id": 227046,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115331464.707, "dur": 0.286, + "args": { + "External id": 227047,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115331468.752, "dur": 0.182, + "args": { + "External id": 227048,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115331470.480, "dur": 0.165, + "args": { + "External id": 227049,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115331472.014, "dur": 2.453, + "args": { + "External id": 227050,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115331511.305, "dur": 26.492, + "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": 4183436, "tid": 4183436, + "ts": 667115331603.356, "dur": 421.727, + "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": 4183436, "tid": 4183436, + "ts": 667115331630.916, "dur": 389.070, + "args": { + "External id": 227053,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115331641.042, "dur": 373.023, + "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": 4183436, "tid": 4183436, + "ts": 667115332047.872, "dur": 2.467, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 4183436, "tid": 4183436, + "ts": 667115332142.326, "dur": 7713.474, + "args": { + "External id": 227056,"Record function id": 0, "Ev Idx": 5855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115332234.141, "dur": 6.538, + "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": 4183436, "tid": 4183436, + "ts": 667115332243.901, "dur": 0.985, + "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": 4183436, "tid": 4183436, + "ts": 667115332246.634, "dur": 1.727, + "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": 4183436, "tid": 4183436, + "ts": 667115332249.834, "dur": 0.762, + "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": 4183436, "tid": 4183436, + "ts": 667115332252.092, "dur": 0.565, + "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": 4183436, "tid": 4183436, + "ts": 667115332254.337, "dur": 1.064, + "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": 4183436, "tid": 4183436, + "ts": 667115332257.346, "dur": 0.890, + "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": 4183436, "tid": 4183436, + "ts": 667115332260.076, "dur": 2.036, + "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": 4183436, "tid": 4183436, + "ts": 667115332264.349, "dur": 0.637, + "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": 4183436, "tid": 4183436, + "ts": 667115332266.553, "dur": 0.934, + "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": 4183436, "tid": 4183436, + "ts": 667115332286.586, "dur": 7524.929, + "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": 4183436, "tid": 4183436, + "ts": 667115332302.793, "dur": 7500.733, + "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": 4183436, "tid": 4183436, + "ts": 667115332323.431, "dur": 14.395, + "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": 4183436, "tid": 4183436, + "ts": 667115332340.311, "dur": 7427.909, + "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": 4183436, "tid": 4183436, + "ts": 667115332343.423, "dur": 7424.041, + "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": 4183436, "tid": 4183436, + "ts": 667115332349.824, "dur": 6.842, + "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": 4183436, "tid": 4183436, + "ts": 667115332358.671, "dur": 7405.499, + "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": 4183436, "tid": 4183436, + "ts": 667115339989.555, "dur": 37.097, + "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": 4183436, "tid": 4183436, "ts": 667115339989.555, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115340011.912, "dur": 9.228, + "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": 4183436, "tid": 4183436, + "ts": 667115340015.792, "dur": 5.078, + "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": 4183436, "tid": 4183436, + "ts": 667115340091.556, "dur": 83.326, + "args": { + "External id": 227077,"Record function id": 0, "Ev Idx": 5876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115340176.588, "dur": 1104.822, + "args": { + "External id": 227078,"Record function id": 0, "Ev Idx": 5877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115340215.473, "dur": 1052.206, + "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": 4183436, "tid": 4183436, "ts": 667115340215.473, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115340283.344, "dur": 43.110, + "args": { + "External id": 227080,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115340339.156, "dur": 88.002, + "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": 4183436, "tid": 4183436, + "ts": 667115340435.867, "dur": 33.850, + "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": 4183436, "tid": 4183436, + "ts": 667115340478.363, "dur": 50.112, + "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": 4183436, "tid": 4183436, + "ts": 667115340555.391, "dur": 26.788, + "args": { + "External id": 227084,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115340600.294, "dur": 15.749, + "args": { + "External id": 227085,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115340634.086, "dur": 176.130, + "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": 4183436, "tid": 4183436, + "ts": 667115340726.750, "dur": 14.098, + "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": 4183436, "tid": 4183436, + "ts": 667115340732.717, "dur": 7.022, + "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": 4183436, "tid": 4183436, + "ts": 667115340743.598, "dur": 5.362, + "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": 4183436, "tid": 4183436, + "ts": 667115340750.211, "dur": 1.821, + "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": 4183436, "tid": 4183436, + "ts": 667115340754.354, "dur": 2.965, + "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": 4183436, "tid": 4183436, + "ts": 667115340822.400, "dur": 53.861, + "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": 4183436, "tid": 4183436, + "ts": 667115340908.441, "dur": 28.612, + "args": { + "External id": 227093,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115340944.405, "dur": 39.045, + "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": 4183436, "tid": 4183436, + "ts": 667115340992.948, "dur": 49.311, + "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": 4183436, "tid": 4183436, + "ts": 667115341063.603, "dur": 26.380, + "args": { + "External id": 227096,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115341095.634, "dur": 57.709, + "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": 4183436, "tid": 4183436, + "ts": 667115341173.046, "dur": 19.942, + "args": { + "External id": 227098,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115341347.461, "dur": 75.226, + "args": { + "External id": 227099,"Record function id": 0, "Ev Idx": 5898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115341518.862, "dur": 52.109, + "args": { + "External id": 227100,"Record function id": 0, "Ev Idx": 5899 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 4183436, "tid": 4183436, + "ts": 667115341581.309, "dur": 8933.924, + "args": { + "External id": 227101,"Record function id": 0, "Ev Idx": 5900 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 4183436, "tid": 4183436, + "ts": 667115341590.142, "dur": 875.017, + "args": { + "External id": 227102,"Record function id": 0, "Ev Idx": 5901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115341706.950, "dur": 10.122, + "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": 4183436, "tid": 4183436, + "ts": 667115341731.731, "dur": 47.819, + "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": 4183436, "tid": 4183436, + "ts": 667115341743.303, "dur": 2.459, + "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": 4183436, "tid": 4183436, + "ts": 667115341750.686, "dur": 0.602, + "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": 4183436, "tid": 4183436, + "ts": 667115341752.816, "dur": 0.487, + "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": 4183436, "tid": 4183436, + "ts": 667115341754.691, "dur": 2.645, + "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": 4183436, "tid": 4183436, + "ts": 667115341758.685, "dur": 0.565, + "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": 4183436, "tid": 4183436, + "ts": 667115341762.346, "dur": 0.553, + "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": 4183436, "tid": 4183436, + "ts": 667115341766.326, "dur": 0.717, + "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": 4183436, "tid": 4183436, + "ts": 667115341768.621, "dur": 0.653, + "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": 4183436, "tid": 4183436, + "ts": 667115341770.630, "dur": 2.613, + "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": 4183436, "tid": 4183436, + "ts": 667115341790.848, "dur": 39.846, + "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": 4183436, "tid": 4183436, + "ts": 667115341864.561, "dur": 107.737, + "args": { + "External id": 227115,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115341875.518, "dur": 4.763, + "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": 4183436, "tid": 4183436, + "ts": 667115341885.173, "dur": 9.903, + "args": { + "External id": 227117,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115341889.220, "dur": 5.455, + "args": { + "External id": 227118,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115341892.869, "dur": 0.652, + "args": { + "External id": 227119,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115341902.601, "dur": 29.737, + "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": 4183436, "tid": 4183436, + "ts": 667115341904.910, "dur": 0.717, + "args": { + "External id": 227121,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115341907.063, "dur": 0.711, + "args": { + "External id": 227122,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115341909.310, "dur": 3.180, + "args": { + "External id": 227123,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115341913.801, "dur": 0.713, + "args": { + "External id": 227124,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115341915.769, "dur": 0.469, + "args": { + "External id": 227125,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115341920.150, "dur": 0.439, + "args": { + "External id": 227126,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115341921.950, "dur": 0.552, + "args": { + "External id": 227127,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115341923.391, "dur": 0.677, + "args": { + "External id": 227128,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115341927.515, "dur": 0.416, + "args": { + "External id": 227129,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115341942.791, "dur": 21.564, + "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": 4183436, "tid": 4183436, + "ts": 667115342027.149, "dur": 354.149, + "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": 4183436, "tid": 4183436, + "ts": 667115342052.091, "dur": 324.804, + "args": { + "External id": 227132,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115342063.017, "dur": 308.941, + "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": 4183436, "tid": 4183436, + "ts": 667115342398.732, "dur": 2.034, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 4183436, "tid": 4183436, + "ts": 667115342485.981, "dur": 7816.407, + "args": { + "External id": 227135,"Record function id": 0, "Ev Idx": 5934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115342600.716, "dur": 6.875, + "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": 4183436, "tid": 4183436, + "ts": 667115342611.308, "dur": 1.446, + "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": 4183436, "tid": 4183436, + "ts": 667115342614.285, "dur": 1.010, + "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": 4183436, "tid": 4183436, + "ts": 667115342616.820, "dur": 1.102, + "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": 4183436, "tid": 4183436, + "ts": 667115342619.544, "dur": 1.349, + "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": 4183436, "tid": 4183436, + "ts": 667115342622.308, "dur": 1.261, + "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": 4183436, "tid": 4183436, + "ts": 667115342625.415, "dur": 1.226, + "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": 4183436, "tid": 4183436, + "ts": 667115342628.093, "dur": 2.426, + "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": 4183436, "tid": 4183436, + "ts": 667115342632.124, "dur": 0.924, + "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": 4183436, "tid": 4183436, + "ts": 667115342634.482, "dur": 0.864, + "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": 4183436, "tid": 4183436, + "ts": 667115342690.285, "dur": 7566.432, + "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": 4183436, "tid": 4183436, + "ts": 667115342707.518, "dur": 7542.218, + "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": 4183436, "tid": 4183436, + "ts": 667115342728.049, "dur": 14.535, + "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": 4183436, "tid": 4183436, + "ts": 667115342745.342, "dur": 7469.737, + "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": 4183436, "tid": 4183436, + "ts": 667115342747.906, "dur": 7466.604, + "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": 4183436, "tid": 4183436, + "ts": 667115342754.008, "dur": 7.266, + "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": 4183436, "tid": 4183436, + "ts": 667115342763.142, "dur": 7447.770, + "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": 4183436, "tid": 4183436, + "ts": 667115350437.847, "dur": 36.437, + "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": 4183436, "tid": 4183436, "ts": 667115350437.847, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115350459.906, "dur": 9.280, + "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": 4183436, "tid": 4183436, + "ts": 667115350463.613, "dur": 5.294, + "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": 4183436, "tid": 4183436, + "ts": 667115350557.943, "dur": 84.808, + "args": { + "External id": 227156,"Record function id": 0, "Ev Idx": 5955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115350644.612, "dur": 1148.568, + "args": { + "External id": 227157,"Record function id": 0, "Ev Idx": 5956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115350716.316, "dur": 1062.525, + "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": 4183436, "tid": 4183436, "ts": 667115350716.316, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115350781.940, "dur": 45.837, + "args": { + "External id": 227159,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115350841.347, "dur": 90.982, + "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": 4183436, "tid": 4183436, + "ts": 667115350940.826, "dur": 34.097, + "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": 4183436, "tid": 4183436, + "ts": 667115350983.706, "dur": 28.720, + "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": 4183436, "tid": 4183436, + "ts": 667115351034.638, "dur": 27.013, + "args": { + "External id": 227163,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115351079.437, "dur": 15.170, + "args": { + "External id": 227164,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115351114.236, "dur": 158.601, + "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": 4183436, "tid": 4183436, + "ts": 667115351178.179, "dur": 15.454, + "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": 4183436, "tid": 4183436, + "ts": 667115351184.352, "dur": 8.217, + "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": 4183436, "tid": 4183436, + "ts": 667115351196.778, "dur": 6.467, + "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": 4183436, "tid": 4183436, + "ts": 667115351205.182, "dur": 1.837, + "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": 4183436, "tid": 4183436, + "ts": 667115351209.706, "dur": 4.355, + "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": 4183436, "tid": 4183436, + "ts": 667115351285.604, "dur": 62.968, + "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": 4183436, "tid": 4183436, + "ts": 667115351382.336, "dur": 29.834, + "args": { + "External id": 227172,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115351419.806, "dur": 38.339, + "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": 4183436, "tid": 4183436, + "ts": 667115351466.994, "dur": 48.193, + "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": 4183436, "tid": 4183436, + "ts": 667115351539.421, "dur": 26.718, + "args": { + "External id": 227175,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115351573.055, "dur": 58.556, + "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": 4183436, "tid": 4183436, + "ts": 667115351683.130, "dur": 25.692, + "args": { + "External id": 227177,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115351857.242, "dur": 73.428, + "args": { + "External id": 227178,"Record function id": 0, "Ev Idx": 5977 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115352005.413, "dur": 48.464, + "args": { + "External id": 227179,"Record function id": 0, "Ev Idx": 5978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 4183436, "tid": 4183436, + "ts": 667115352063.361, "dur": 9296.939, + "args": { + "External id": 227180,"Record function id": 0, "Ev Idx": 5979 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 4183436, "tid": 4183436, + "ts": 667115352071.890, "dur": 917.412, + "args": { + "External id": 227181,"Record function id": 0, "Ev Idx": 5980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115352148.444, "dur": 9.074, + "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": 4183436, "tid": 4183436, + "ts": 667115352170.284, "dur": 36.114, + "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": 4183436, "tid": 4183436, + "ts": 667115352175.944, "dur": 2.619, + "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": 4183436, "tid": 4183436, + "ts": 667115352183.617, "dur": 0.463, + "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": 4183436, "tid": 4183436, + "ts": 667115352185.621, "dur": 0.712, + "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": 4183436, "tid": 4183436, + "ts": 667115352187.342, "dur": 0.483, + "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": 4183436, "tid": 4183436, + "ts": 667115352191.364, "dur": 0.772, + "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": 4183436, "tid": 4183436, + "ts": 667115352192.979, "dur": 0.614, + "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": 4183436, "tid": 4183436, + "ts": 667115352194.983, "dur": 2.395, + "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": 4183436, "tid": 4183436, + "ts": 667115352198.363, "dur": 0.537, + "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": 4183436, "tid": 4183436, + "ts": 667115352199.936, "dur": 0.542, + "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": 4183436, "tid": 4183436, + "ts": 667115352216.121, "dur": 38.303, + "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": 4183436, "tid": 4183436, + "ts": 667115352286.324, "dur": 118.077, + "args": { + "External id": 227194,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115352296.954, "dur": 5.177, + "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": 4183436, "tid": 4183436, + "ts": 667115352307.033, "dur": 9.975, + "args": { + "External id": 227196,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115352311.522, "dur": 5.109, + "args": { + "External id": 227197,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115352314.664, "dur": 0.647, + "args": { + "External id": 227198,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115352323.411, "dur": 30.881, + "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": 4183436, "tid": 4183436, + "ts": 667115352325.437, "dur": 2.937, + "args": { + "External id": 227200,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115352329.454, "dur": 0.523, + "args": { + "External id": 227201,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115352331.306, "dur": 0.744, + "args": { + "External id": 227202,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115352335.327, "dur": 0.508, + "args": { + "External id": 227203,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115352337.378, "dur": 0.705, + "args": { + "External id": 227204,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115352338.984, "dur": 0.670, + "args": { + "External id": 227205,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115352343.062, "dur": 0.637, + "args": { + "External id": 227206,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115352344.673, "dur": 0.906, + "args": { + "External id": 227207,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115352347.262, "dur": 2.821, + "args": { + "External id": 227208,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115352374.734, "dur": 20.754, + "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": 4183436, "tid": 4183436, + "ts": 667115352458.497, "dur": 432.608, + "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": 4183436, "tid": 4183436, + "ts": 667115352484.685, "dur": 400.527, + "args": { + "External id": 227211,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115352518.312, "dur": 360.277, + "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": 4183436, "tid": 4183436, + "ts": 667115352913.587, "dur": 2.413, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 4183436, "tid": 4183436, + "ts": 667115353011.230, "dur": 8137.116, + "args": { + "External id": 227214,"Record function id": 0, "Ev Idx": 6013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115353101.464, "dur": 6.851, + "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": 4183436, "tid": 4183436, + "ts": 667115353111.828, "dur": 1.045, + "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": 4183436, "tid": 4183436, + "ts": 667115353114.455, "dur": 1.263, + "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": 4183436, "tid": 4183436, + "ts": 667115353117.390, "dur": 1.120, + "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": 4183436, "tid": 4183436, + "ts": 667115353120.086, "dur": 1.197, + "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": 4183436, "tid": 4183436, + "ts": 667115353123.066, "dur": 0.947, + "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": 4183436, "tid": 4183436, + "ts": 667115353126.103, "dur": 0.960, + "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": 4183436, "tid": 4183436, + "ts": 667115353128.923, "dur": 2.304, + "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": 4183436, "tid": 4183436, + "ts": 667115353132.817, "dur": 1.104, + "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": 4183436, "tid": 4183436, + "ts": 667115353135.743, "dur": 0.852, + "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": 4183436, "tid": 4183436, + "ts": 667115353153.945, "dur": 7957.599, + "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": 4183436, "tid": 4183436, + "ts": 667115353169.462, "dur": 7935.202, + "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": 4183436, "tid": 4183436, + "ts": 667115353183.288, "dur": 12.925, + "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": 4183436, "tid": 4183436, + "ts": 667115353199.087, "dur": 7873.611, + "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": 4183436, "tid": 4183436, + "ts": 667115353201.650, "dur": 7870.597, + "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": 4183436, "tid": 4183436, + "ts": 667115353207.923, "dur": 7.306, + "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": 4183436, "tid": 4183436, + "ts": 667115353216.988, "dur": 7852.403, + "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": 4183436, "tid": 4183436, + "ts": 667115361291.882, "dur": 36.095, + "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": 4183436, "tid": 4183436, "ts": 667115361291.882, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115361312.032, "dur": 10.285, + "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": 4183436, "tid": 4183436, + "ts": 667115361316.106, "dur": 5.726, + "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": 4183436, "tid": 4183436, + "ts": 667115361402.749, "dur": 83.371, + "args": { + "External id": 227235,"Record function id": 0, "Ev Idx": 6034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115361487.809, "dur": 1081.676, + "args": { + "External id": 227236,"Record function id": 0, "Ev Idx": 6035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115361547.475, "dur": 1006.452, + "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": 4183436, "tid": 4183436, "ts": 667115361547.475, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115361616.950, "dur": 77.103, + "args": { + "External id": 227238,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115361710.763, "dur": 96.018, + "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": 4183436, "tid": 4183436, + "ts": 667115361815.494, "dur": 34.835, + "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": 4183436, "tid": 4183436, + "ts": 667115361858.744, "dur": 29.326, + "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": 4183436, "tid": 4183436, + "ts": 667115361913.070, "dur": 25.114, + "args": { + "External id": 227242,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115361955.820, "dur": 15.800, + "args": { + "External id": 227243,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115361989.068, "dur": 132.025, + "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": 4183436, "tid": 4183436, + "ts": 667115362040.864, "dur": 11.953, + "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": 4183436, "tid": 4183436, + "ts": 667115362046.334, "dur": 5.734, + "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": 4183436, "tid": 4183436, + "ts": 667115362055.533, "dur": 5.722, + "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": 4183436, "tid": 4183436, + "ts": 667115362062.706, "dur": 1.622, + "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": 4183436, "tid": 4183436, + "ts": 667115362066.719, "dur": 3.168, + "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": 4183436, "tid": 4183436, + "ts": 667115362132.156, "dur": 42.940, + "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": 4183436, "tid": 4183436, + "ts": 667115362206.158, "dur": 29.504, + "args": { + "External id": 227251,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115362244.068, "dur": 37.765, + "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": 4183436, "tid": 4183436, + "ts": 667115362291.642, "dur": 33.055, + "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": 4183436, "tid": 4183436, + "ts": 667115362346.232, "dur": 24.140, + "args": { + "External id": 227254,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115362376.294, "dur": 51.638, + "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": 4183436, "tid": 4183436, + "ts": 667115362448.570, "dur": 17.702, + "args": { + "External id": 227256,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115362636.497, "dur": 127.535, + "args": { + "External id": 227257,"Record function id": 0, "Ev Idx": 6056 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115362845.270, "dur": 50.224, + "args": { + "External id": 227258,"Record function id": 0, "Ev Idx": 6057 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 4183436, "tid": 4183436, + "ts": 667115362904.818, "dur": 9375.949, + "args": { + "External id": 227259,"Record function id": 0, "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 4183436, "tid": 4183436, + "ts": 667115362913.284, "dur": 905.664, + "args": { + "External id": 227260,"Record function id": 0, "Ev Idx": 6059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115362992.280, "dur": 10.468, + "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": 4183436, "tid": 4183436, + "ts": 667115363016.429, "dur": 36.281, + "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": 4183436, "tid": 4183436, + "ts": 667115363021.753, "dur": 2.175, + "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": 4183436, "tid": 4183436, + "ts": 667115363029.057, "dur": 0.621, + "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": 4183436, "tid": 4183436, + "ts": 667115363031.031, "dur": 0.624, + "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": 4183436, "tid": 4183436, + "ts": 667115363032.893, "dur": 0.793, + "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": 4183436, "tid": 4183436, + "ts": 667115363036.796, "dur": 0.654, + "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": 4183436, "tid": 4183436, + "ts": 667115363038.815, "dur": 0.581, + "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": 4183436, "tid": 4183436, + "ts": 667115363040.684, "dur": 2.555, + "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": 4183436, "tid": 4183436, + "ts": 667115363044.650, "dur": 0.501, + "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": 4183436, "tid": 4183436, + "ts": 667115363046.042, "dur": 0.729, + "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": 4183436, "tid": 4183436, + "ts": 667115363066.040, "dur": 41.010, + "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": 4183436, "tid": 4183436, + "ts": 667115363139.077, "dur": 105.868, + "args": { + "External id": 227273,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115363149.229, "dur": 7.087, + "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": 4183436, "tid": 4183436, + "ts": 667115363161.319, "dur": 10.242, + "args": { + "External id": 227275,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115363165.665, "dur": 5.518, + "args": { + "External id": 227276,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115363168.990, "dur": 0.807, + "args": { + "External id": 227277,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115363178.103, "dur": 27.405, + "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": 4183436, "tid": 4183436, + "ts": 667115363179.961, "dur": 0.806, + "args": { + "External id": 227279,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115363182.417, "dur": 2.764, + "args": { + "External id": 227280,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115363186.424, "dur": 0.382, + "args": { + "External id": 227281,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115363188.084, "dur": 0.536, + "args": { + "External id": 227282,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115363191.905, "dur": 0.458, + "args": { + "External id": 227283,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115363193.641, "dur": 0.478, + "args": { + "External id": 227284,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115363195.115, "dur": 0.717, + "args": { + "External id": 227285,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115363199.123, "dur": 0.481, + "args": { + "External id": 227286,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115363200.557, "dur": 0.786, + "args": { + "External id": 227287,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115363215.502, "dur": 21.531, + "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": 4183436, "tid": 4183436, + "ts": 667115363297.732, "dur": 422.965, + "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": 4183436, "tid": 4183436, + "ts": 667115363323.519, "dur": 390.677, + "args": { + "External id": 227290,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115363334.226, "dur": 373.918, + "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": 4183436, "tid": 4183436, + "ts": 667115363745.163, "dur": 2.929, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 4183436, "tid": 4183436, + "ts": 667115363839.499, "dur": 8245.707, + "args": { + "External id": 227293,"Record function id": 0, "Ev Idx": 6092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115363934.145, "dur": 6.289, + "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": 4183436, "tid": 4183436, + "ts": 667115363943.497, "dur": 1.289, + "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": 4183436, "tid": 4183436, + "ts": 667115363946.612, "dur": 1.299, + "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": 4183436, "tid": 4183436, + "ts": 667115363949.624, "dur": 1.013, + "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": 4183436, "tid": 4183436, + "ts": 667115363952.522, "dur": 1.398, + "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": 4183436, "tid": 4183436, + "ts": 667115363955.665, "dur": 1.126, + "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": 4183436, "tid": 4183436, + "ts": 667115363958.826, "dur": 1.100, + "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": 4183436, "tid": 4183436, + "ts": 667115363962.085, "dur": 2.156, + "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": 4183436, "tid": 4183436, + "ts": 667115363966.311, "dur": 0.770, + "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": 4183436, "tid": 4183436, + "ts": 667115363968.838, "dur": 1.403, + "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": 4183436, "tid": 4183436, + "ts": 667115363988.469, "dur": 8054.070, + "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": 4183436, "tid": 4183436, + "ts": 667115364004.072, "dur": 8030.875, + "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": 4183436, "tid": 4183436, + "ts": 667115364017.593, "dur": 14.125, + "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": 4183436, "tid": 4183436, + "ts": 667115364034.469, "dur": 7967.493, + "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": 4183436, "tid": 4183436, + "ts": 667115364036.987, "dur": 7964.300, + "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": 4183436, "tid": 4183436, + "ts": 667115364043.369, "dur": 6.960, + "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": 4183436, "tid": 4183436, + "ts": 667115364052.245, "dur": 7945.785, + "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": 4183436, "tid": 4183436, + "ts": 667115372224.546, "dur": 30.086, + "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": 4183436, "tid": 4183436, "ts": 667115372224.546, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115372240.741, "dur": 8.964, + "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": 4183436, "tid": 4183436, + "ts": 667115372244.159, "dur": 5.292, + "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": 4183436, "tid": 4183436, + "ts": 667115372320.013, "dur": 83.572, + "args": { + "External id": 227314,"Record function id": 0, "Ev Idx": 6113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115372405.228, "dur": 1113.876, + "args": { + "External id": 227315,"Record function id": 0, "Ev Idx": 6114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115372443.651, "dur": 1042.757, + "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": 4183436, "tid": 4183436, "ts": 667115372443.651, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115372528.721, "dur": 45.750, + "args": { + "External id": 227317,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115372589.062, "dur": 132.174, + "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": 4183436, "tid": 4183436, + "ts": 667115372735.346, "dur": 40.153, + "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": 4183436, "tid": 4183436, + "ts": 667115372784.576, "dur": 30.087, + "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": 4183436, "tid": 4183436, + "ts": 667115372846.187, "dur": 30.033, + "args": { + "External id": 227321,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115372892.432, "dur": 14.342, + "args": { + "External id": 227322,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115372924.373, "dur": 131.268, + "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": 4183436, "tid": 4183436, + "ts": 667115372975.045, "dur": 12.083, + "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": 4183436, "tid": 4183436, + "ts": 667115372980.233, "dur": 6.125, + "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": 4183436, "tid": 4183436, + "ts": 667115372990.324, "dur": 6.247, + "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": 4183436, "tid": 4183436, + "ts": 667115372997.726, "dur": 1.524, + "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": 4183436, "tid": 4183436, + "ts": 667115373001.571, "dur": 4.866, + "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": 4183436, "tid": 4183436, + "ts": 667115373094.562, "dur": 47.989, + "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": 4183436, "tid": 4183436, + "ts": 667115373175.178, "dur": 26.474, + "args": { + "External id": 227330,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115373209.841, "dur": 36.948, + "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": 4183436, "tid": 4183436, + "ts": 667115373255.576, "dur": 31.851, + "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": 4183436, "tid": 4183436, + "ts": 667115373308.371, "dur": 24.025, + "args": { + "External id": 227333,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115373338.091, "dur": 42.969, + "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": 4183436, "tid": 4183436, + "ts": 667115373400.129, "dur": 19.063, + "args": { + "External id": 227335,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115373586.310, "dur": 110.574, + "args": { + "External id": 227336,"Record function id": 0, "Ev Idx": 6135 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115373775.236, "dur": 48.074, + "args": { + "External id": 227337,"Record function id": 0, "Ev Idx": 6136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 4183436, "tid": 4183436, + "ts": 667115373832.284, "dur": 9371.291, + "args": { + "External id": 227338,"Record function id": 0, "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 4183436, "tid": 4183436, + "ts": 667115373840.355, "dur": 907.108, + "args": { + "External id": 227339,"Record function id": 0, "Ev Idx": 6138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115373918.188, "dur": 9.952, + "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": 4183436, "tid": 4183436, + "ts": 667115373942.093, "dur": 35.852, + "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": 4183436, "tid": 4183436, + "ts": 667115373947.744, "dur": 2.200, + "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": 4183436, "tid": 4183436, + "ts": 667115373954.366, "dur": 0.612, + "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": 4183436, "tid": 4183436, + "ts": 667115373956.453, "dur": 0.412, + "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": 4183436, "tid": 4183436, + "ts": 667115373958.052, "dur": 0.542, + "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": 4183436, "tid": 4183436, + "ts": 667115373961.706, "dur": 0.809, + "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": 4183436, "tid": 4183436, + "ts": 667115373963.757, "dur": 0.625, + "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": 4183436, "tid": 4183436, + "ts": 667115373965.792, "dur": 2.311, + "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": 4183436, "tid": 4183436, + "ts": 667115373969.842, "dur": 0.613, + "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": 4183436, "tid": 4183436, + "ts": 667115373971.230, "dur": 0.809, + "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": 4183436, "tid": 4183436, + "ts": 667115373988.961, "dur": 39.524, + "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": 4183436, "tid": 4183436, + "ts": 667115374061.118, "dur": 111.118, + "args": { + "External id": 227352,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115374071.703, "dur": 5.219, + "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": 4183436, "tid": 4183436, + "ts": 667115374081.702, "dur": 10.612, + "args": { + "External id": 227354,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115374086.363, "dur": 5.536, + "args": { + "External id": 227355,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115374089.811, "dur": 0.882, + "args": { + "External id": 227356,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115374099.047, "dur": 30.881, + "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": 4183436, "tid": 4183436, + "ts": 667115374101.122, "dur": 2.795, + "args": { + "External id": 227358,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115374105.872, "dur": 0.458, + "args": { + "External id": 227359,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115374107.458, "dur": 0.633, + "args": { + "External id": 227360,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115374111.577, "dur": 0.449, + "args": { + "External id": 227361,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115374113.506, "dur": 0.558, + "args": { + "External id": 227362,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115374115.197, "dur": 0.671, + "args": { + "External id": 227363,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115374119.475, "dur": 0.577, + "args": { + "External id": 227364,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115374121.333, "dur": 0.660, + "args": { + "External id": 227365,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115374123.308, "dur": 2.612, + "args": { + "External id": 227366,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115374142.318, "dur": 21.772, + "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": 4183436, "tid": 4183436, + "ts": 667115374223.077, "dur": 388.464, + "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": 4183436, "tid": 4183436, + "ts": 667115374249.399, "dur": 356.979, + "args": { + "External id": 227369,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115374259.319, "dur": 340.628, + "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": 4183436, "tid": 4183436, + "ts": 667115374634.135, "dur": 2.573, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 4183436, "tid": 4183436, + "ts": 667115374775.147, "dur": 8236.737, + "args": { + "External id": 227372,"Record function id": 0, "Ev Idx": 6171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115374898.021, "dur": 7.432, + "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": 4183436, "tid": 4183436, + "ts": 667115374909.165, "dur": 1.001, + "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": 4183436, "tid": 4183436, + "ts": 667115374911.739, "dur": 0.944, + "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": 4183436, "tid": 4183436, + "ts": 667115374914.456, "dur": 1.239, + "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": 4183436, "tid": 4183436, + "ts": 667115374917.307, "dur": 1.056, + "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": 4183436, "tid": 4183436, + "ts": 667115374920.314, "dur": 1.001, + "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": 4183436, "tid": 4183436, + "ts": 667115374923.405, "dur": 1.238, + "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": 4183436, "tid": 4183436, + "ts": 667115374926.401, "dur": 1.918, + "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": 4183436, "tid": 4183436, + "ts": 667115374930.059, "dur": 0.844, + "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": 4183436, "tid": 4183436, + "ts": 667115374932.578, "dur": 1.010, + "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": 4183436, "tid": 4183436, + "ts": 667115374953.426, "dur": 8017.434, + "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": 4183436, "tid": 4183436, + "ts": 667115374969.983, "dur": 7994.575, + "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": 4183436, "tid": 4183436, + "ts": 667115374987.505, "dur": 14.298, + "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": 4183436, "tid": 4183436, + "ts": 667115375004.564, "dur": 7928.541, + "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": 4183436, "tid": 4183436, + "ts": 667115375007.110, "dur": 7925.558, + "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": 4183436, "tid": 4183436, + "ts": 667115375014.523, "dur": 7.141, + "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": 4183436, "tid": 4183436, + "ts": 667115375023.605, "dur": 7906.306, + "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": 4183436, "tid": 4183436, + "ts": 667115383147.905, "dur": 29.192, + "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": 4183436, "tid": 4183436, "ts": 667115383147.905, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115383164.406, "dur": 7.797, + "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": 4183436, "tid": 4183436, + "ts": 667115383167.258, "dur": 4.671, + "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": 4183436, "tid": 4183436, + "ts": 667115383242.766, "dur": 81.333, + "args": { + "External id": 227393,"Record function id": 0, "Ev Idx": 6192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115383325.467, "dur": 1046.559, + "args": { + "External id": 227394,"Record function id": 0, "Ev Idx": 6193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115383363.120, "dur": 995.257, + "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": 4183436, "tid": 4183436, "ts": 667115383363.120, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115383429.350, "dur": 39.315, + "args": { + "External id": 227396,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115383482.017, "dur": 106.905, + "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": 4183436, "tid": 4183436, + "ts": 667115383601.084, "dur": 36.271, + "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": 4183436, "tid": 4183436, + "ts": 667115383646.072, "dur": 67.342, + "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": 4183436, "tid": 4183436, + "ts": 667115383742.315, "dur": 25.508, + "args": { + "External id": 227400,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115383787.085, "dur": 18.926, + "args": { + "External id": 227401,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115383823.552, "dur": 127.556, + "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": 4183436, "tid": 4183436, + "ts": 667115383874.701, "dur": 11.671, + "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": 4183436, "tid": 4183436, + "ts": 667115383879.601, "dur": 6.088, + "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": 4183436, "tid": 4183436, + "ts": 667115383889.227, "dur": 5.379, + "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": 4183436, "tid": 4183436, + "ts": 667115383895.753, "dur": 1.908, + "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": 4183436, "tid": 4183436, + "ts": 667115383899.865, "dur": 2.430, + "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": 4183436, "tid": 4183436, + "ts": 667115383962.440, "dur": 47.151, + "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": 4183436, "tid": 4183436, + "ts": 667115384041.094, "dur": 26.234, + "args": { + "External id": 227409,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115384075.266, "dur": 38.182, + "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": 4183436, "tid": 4183436, + "ts": 667115384121.976, "dur": 30.863, + "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": 4183436, "tid": 4183436, + "ts": 667115384172.990, "dur": 25.480, + "args": { + "External id": 227412,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115384204.291, "dur": 43.594, + "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": 4183436, "tid": 4183436, + "ts": 667115384268.594, "dur": 20.615, + "args": { + "External id": 227414,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115384436.336, "dur": 94.139, + "args": { + "External id": 227415,"Record function id": 0, "Ev Idx": 6214 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115384608.831, "dur": 89.321, + "args": { + "External id": 227416,"Record function id": 0, "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 4183436, "tid": 4183436, + "ts": 667115384709.140, "dur": 9413.787, + "args": { + "External id": 227417,"Record function id": 0, "Ev Idx": 6216 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 4183436, "tid": 4183436, + "ts": 667115384717.140, "dur": 914.324, + "args": { + "External id": 227418,"Record function id": 0, "Ev Idx": 6217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115384795.810, "dur": 10.638, + "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": 4183436, "tid": 4183436, + "ts": 667115384819.938, "dur": 35.710, + "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": 4183436, "tid": 4183436, + "ts": 667115384825.288, "dur": 2.594, + "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": 4183436, "tid": 4183436, + "ts": 667115384832.528, "dur": 0.842, + "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": 4183436, "tid": 4183436, + "ts": 667115384834.715, "dur": 0.404, + "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": 4183436, "tid": 4183436, + "ts": 667115384836.317, "dur": 0.836, + "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": 4183436, "tid": 4183436, + "ts": 667115384840.417, "dur": 0.612, + "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": 4183436, "tid": 4183436, + "ts": 667115384842.212, "dur": 0.731, + "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": 4183436, "tid": 4183436, + "ts": 667115384844.099, "dur": 1.751, + "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": 4183436, "tid": 4183436, + "ts": 667115384847.193, "dur": 0.790, + "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": 4183436, "tid": 4183436, + "ts": 667115384848.990, "dur": 0.867, + "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": 4183436, "tid": 4183436, + "ts": 667115384866.875, "dur": 42.578, + "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": 4183436, "tid": 4183436, + "ts": 667115384941.867, "dur": 110.998, + "args": { + "External id": 227431,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115384955.298, "dur": 6.012, + "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": 4183436, "tid": 4183436, + "ts": 667115384966.434, "dur": 11.090, + "args": { + "External id": 227433,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115384970.921, "dur": 5.970, + "args": { + "External id": 227434,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115384974.217, "dur": 1.341, + "args": { + "External id": 227435,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115384984.304, "dur": 28.210, + "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": 4183436, "tid": 4183436, + "ts": 667115384985.874, "dur": 0.725, + "args": { + "External id": 227437,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115384988.076, "dur": 2.640, + "args": { + "External id": 227438,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115384991.858, "dur": 0.478, + "args": { + "External id": 227439,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115384993.268, "dur": 0.759, + "args": { + "External id": 227440,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115384998.295, "dur": 0.817, + "args": { + "External id": 227441,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115385000.242, "dur": 0.587, + "args": { + "External id": 227442,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115385001.994, "dur": 0.784, + "args": { + "External id": 227443,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115385005.848, "dur": 0.458, + "args": { + "External id": 227444,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115385007.917, "dur": 0.408, + "args": { + "External id": 227445,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115385022.844, "dur": 21.792, + "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": 4183436, "tid": 4183436, + "ts": 667115385103.235, "dur": 430.390, + "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": 4183436, "tid": 4183436, + "ts": 667115385129.595, "dur": 397.797, + "args": { + "External id": 227448,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115385139.669, "dur": 378.689, + "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": 4183436, "tid": 4183436, + "ts": 667115385557.183, "dur": 2.773, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 4183436, "tid": 4183436, + "ts": 667115385688.989, "dur": 8249.362, + "args": { + "External id": 227451,"Record function id": 0, "Ev Idx": 6250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115385790.041, "dur": 7.320, + "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": 4183436, "tid": 4183436, + "ts": 667115385800.682, "dur": 1.187, + "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": 4183436, "tid": 4183436, + "ts": 667115385803.680, "dur": 1.018, + "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": 4183436, "tid": 4183436, + "ts": 667115385806.290, "dur": 0.954, + "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": 4183436, "tid": 4183436, + "ts": 667115385809.032, "dur": 0.909, + "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": 4183436, "tid": 4183436, + "ts": 667115385811.749, "dur": 1.056, + "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": 4183436, "tid": 4183436, + "ts": 667115385815.172, "dur": 0.842, + "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": 4183436, "tid": 4183436, + "ts": 667115385817.853, "dur": 2.737, + "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": 4183436, "tid": 4183436, + "ts": 667115385822.591, "dur": 0.969, + "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": 4183436, "tid": 4183436, + "ts": 667115385825.466, "dur": 0.958, + "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": 4183436, "tid": 4183436, + "ts": 667115385845.679, "dur": 8054.281, + "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": 4183436, "tid": 4183436, + "ts": 667115385861.213, "dur": 8031.395, + "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": 4183436, "tid": 4183436, + "ts": 667115385875.521, "dur": 13.400, + "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": 4183436, "tid": 4183436, + "ts": 667115385891.721, "dur": 7968.144, + "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": 4183436, "tid": 4183436, + "ts": 667115385894.580, "dur": 7964.768, + "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": 4183436, "tid": 4183436, + "ts": 667115385901.461, "dur": 5.610, + "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": 4183436, "tid": 4183436, + "ts": 667115385909.040, "dur": 7947.197, + "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": 4183436, "tid": 4183436, + "ts": 667115394069.750, "dur": 28.482, + "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": 4183436, "tid": 4183436, "ts": 667115394069.750, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115394085.556, "dur": 7.661, + "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": 4183436, "tid": 4183436, + "ts": 667115394088.609, "dur": 4.361, + "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": 4183436, "tid": 4183436, + "ts": 667115394160.872, "dur": 80.710, + "args": { + "External id": 227472,"Record function id": 0, "Ev Idx": 6271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115394243.450, "dur": 1073.813, + "args": { + "External id": 227473,"Record function id": 0, "Ev Idx": 6272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115394279.447, "dur": 1024.496, + "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": 4183436, "tid": 4183436, "ts": 667115394279.447, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115394346.951, "dur": 42.506, + "args": { + "External id": 227475,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115394405.061, "dur": 109.438, + "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": 4183436, "tid": 4183436, + "ts": 667115394527.028, "dur": 40.759, + "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": 4183436, "tid": 4183436, + "ts": 667115394574.261, "dur": 29.574, + "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": 4183436, "tid": 4183436, + "ts": 667115394632.504, "dur": 62.560, + "args": { + "External id": 227479,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115394715.093, "dur": 21.869, + "args": { + "External id": 227480,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115394752.952, "dur": 131.077, + "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": 4183436, "tid": 4183436, + "ts": 667115394805.106, "dur": 13.112, + "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": 4183436, "tid": 4183436, + "ts": 667115394810.053, "dur": 7.196, + "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": 4183436, "tid": 4183436, + "ts": 667115394820.779, "dur": 4.644, + "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": 4183436, "tid": 4183436, + "ts": 667115394826.679, "dur": 3.531, + "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": 4183436, "tid": 4183436, + "ts": 667115394832.458, "dur": 2.901, + "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": 4183436, "tid": 4183436, + "ts": 667115394895.180, "dur": 53.590, + "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": 4183436, "tid": 4183436, + "ts": 667115394981.064, "dur": 28.521, + "args": { + "External id": 227488,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115395017.749, "dur": 38.102, + "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": 4183436, "tid": 4183436, + "ts": 667115395062.834, "dur": 31.332, + "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": 4183436, "tid": 4183436, + "ts": 667115395117.035, "dur": 24.515, + "args": { + "External id": 227491,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115395147.398, "dur": 51.349, + "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": 4183436, "tid": 4183436, + "ts": 667115395216.379, "dur": 22.483, + "args": { + "External id": 227493,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115395381.091, "dur": 71.898, + "args": { + "External id": 227494,"Record function id": 0, "Ev Idx": 6293 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 667115395546.237, "dur": 50.036, + "args": { + "External id": 227495,"Record function id": 0, "Ev Idx": 6294 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 4183436, "tid": 4183436, + "ts": 667115395605.894, "dur": 9239.220, + "args": { + "External id": 227496,"Record function id": 0, "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 4183436, "tid": 4183436, + "ts": 667115395614.705, "dur": 952.146, + "args": { + "External id": 227497,"Record function id": 0, "Ev Idx": 6296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115395735.207, "dur": 10.677, + "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": 4183436, "tid": 4183436, + "ts": 667115395759.828, "dur": 35.992, + "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": 4183436, "tid": 4183436, + "ts": 667115395765.327, "dur": 2.432, + "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": 4183436, "tid": 4183436, + "ts": 667115395772.386, "dur": 0.487, + "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": 4183436, "tid": 4183436, + "ts": 667115395774.158, "dur": 0.306, + "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": 4183436, "tid": 4183436, + "ts": 667115395775.844, "dur": 0.258, + "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": 4183436, "tid": 4183436, + "ts": 667115395779.118, "dur": 0.747, + "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": 4183436, "tid": 4183436, + "ts": 667115395781.158, "dur": 0.386, + "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": 4183436, "tid": 4183436, + "ts": 667115395782.477, "dur": 2.390, + "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": 4183436, "tid": 4183436, + "ts": 667115395786.829, "dur": 0.426, + "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": 4183436, "tid": 4183436, + "ts": 667115395788.316, "dur": 0.512, + "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": 4183436, "tid": 4183436, + "ts": 667115395810.537, "dur": 51.783, + "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": 4183436, "tid": 4183436, + "ts": 667115395907.695, "dur": 120.020, + "args": { + "External id": 227510,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "0", "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": 4183436, "tid": 4183436, + "ts": 667115395921.278, "dur": 5.721, + "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": 4183436, "tid": 4183436, + "ts": 667115395932.450, "dur": 10.983, + "args": { + "External id": 227512,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 4183436, "tid": 4183436, + "ts": 667115395937.167, "dur": 5.894, + "args": { + "External id": 227513,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "1605888", "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": 4183436, "tid": 4183436, + "ts": 667115395940.695, "dur": 0.826, + "args": { + "External id": 227514,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115395951.134, "dur": 30.740, + "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": 4183436, "tid": 4183436, + "ts": 667115395953.670, "dur": 2.886, + "args": { + "External id": 227516,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "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": 4183436, "tid": 4183436, + "ts": 667115395958.012, "dur": 0.604, + "args": { + "External id": 227517,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "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": 4183436, "tid": 4183436, + "ts": 667115395959.692, "dur": 0.660, + "args": { + "External id": 227518,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "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": 4183436, "tid": 4183436, + "ts": 667115395964.379, "dur": 0.287, + "args": { + "External id": 227519,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "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": 4183436, "tid": 4183436, + "ts": 667115395965.782, "dur": 0.540, + "args": { + "External id": 227520,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "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": 4183436, "tid": 4183436, + "ts": 667115395967.696, "dur": 0.416, + "args": { + "External id": 227521,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "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": 4183436, "tid": 4183436, + "ts": 667115395971.404, "dur": 0.584, + "args": { + "External id": 227522,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "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": 4183436, "tid": 4183436, + "ts": 667115395973.045, "dur": 0.474, + "args": { + "External id": 227523,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "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": 4183436, "tid": 4183436, + "ts": 667115395974.575, "dur": 2.524, + "args": { + "External id": 227524,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "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": 4183436, "tid": 4183436, + "ts": 667115395994.661, "dur": 24.551, + "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": 4183436, "tid": 4183436, + "ts": 667115396086.020, "dur": 369.113, + "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": 4183436, "tid": 4183436, + "ts": 667115396112.207, "dur": 337.931, + "args": { + "External id": 227527,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115396122.367, "dur": 322.592, + "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": 4183436, "tid": 4183436, + "ts": 667115396474.359, "dur": 2.160, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 4183436, "tid": 4183436, + "ts": 667115396588.313, "dur": 8030.479, + "args": { + "External id": 227530,"Record function id": 0, "Ev Idx": 6329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115396728.597, "dur": 6.756, + "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": 4183436, "tid": 4183436, + "ts": 667115396747.884, "dur": 1.549, + "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": 4183436, "tid": 4183436, + "ts": 667115396751.475, "dur": 1.221, + "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": 4183436, "tid": 4183436, + "ts": 667115396754.459, "dur": 0.718, + "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": 4183436, "tid": 4183436, + "ts": 667115396756.845, "dur": 0.911, + "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": 4183436, "tid": 4183436, + "ts": 667115396759.246, "dur": 1.114, + "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": 4183436, "tid": 4183436, + "ts": 667115396762.245, "dur": 0.947, + "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": 4183436, "tid": 4183436, + "ts": 667115396764.656, "dur": 2.037, + "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": 4183436, "tid": 4183436, + "ts": 667115396768.556, "dur": 0.743, + "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": 4183436, "tid": 4183436, + "ts": 667115396771.256, "dur": 1.086, + "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": 4183436, "tid": 4183436, + "ts": 667115396793.830, "dur": 7787.068, + "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": 4183436, "tid": 4183436, + "ts": 667115396810.154, "dur": 7764.280, + "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": 4183436, "tid": 4183436, + "ts": 667115396823.720, "dur": 14.324, + "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": 4183436, "tid": 4183436, + "ts": 667115396840.624, "dur": 7700.982, + "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": 4183436, "tid": 4183436, + "ts": 667115396843.062, "dur": 7698.051, + "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": 4183436, "tid": 4183436, + "ts": 667115396848.627, "dur": 5.074, + "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": 4183436, "tid": 4183436, + "ts": 667115396855.313, "dur": 7682.833, + "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": 4183436, "tid": 4183436, + "ts": 667115404786.955, "dur": 30.780, + "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": 4183436, "tid": 4183436, "ts": 667115404786.955, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 667115404804.441, "dur": 8.085, + "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": 4183436, "tid": 4183436, + "ts": 667115404807.623, "dur": 4.473, + "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": 4183436, "tid": 4183436, + "ts": 667115404884.392, "dur": 83.326, + "args": { + "External id": 227551,"Record function id": 0, "Ev Idx": 6350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 667115404969.639, "dur": 1105.536, + "args": { + "External id": 227552,"Record function id": 0, "Ev Idx": 6351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115405007.325, "dur": 1050.102, + "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": 4183436, "tid": 4183436, "ts": 667115405007.325, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115405072.093, "dur": 44.162, + "args": { + "External id": 227554,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115405129.437, "dur": 91.732, + "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": 4183436, "tid": 4183436, + "ts": 667115405230.100, "dur": 34.620, + "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": 4183436, "tid": 4183436, + "ts": 667115405274.004, "dur": 29.552, + "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": 4183436, "tid": 4183436, + "ts": 667115405327.696, "dur": 26.868, + "args": { + "External id": 227558,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115405371.936, "dur": 14.732, + "args": { + "External id": 227559,"kernel_hash": "cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6", "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/th/cthlvtwayb4ptqrbdreaphyxlkjrqnn6jgg4u6ixfsxwcdgpfvg6.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": 4183436, "tid": 4183436, + "ts": 667115405402.397, "dur": 145.992, + "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": 4183436, "tid": 4183436, + "ts": 667115405450.750, "dur": 10.943, + "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": 4183436, "tid": 4183436, + "ts": 667115405455.377, "dur": 5.565, + "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": 4183436, "tid": 4183436, + "ts": 667115405464.290, "dur": 4.544, + "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": 4183436, "tid": 4183436, + "ts": 667115405470.143, "dur": 1.580, + "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": 4183436, "tid": 4183436, + "ts": 667115405473.762, "dur": 3.165, + "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": 4183436, "tid": 4183436, + "ts": 667115405560.669, "dur": 48.721, + "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": 4183436, "tid": 4183436, + "ts": 667115405642.449, "dur": 65.878, + "args": { + "External id": 227567,"kernel_hash": "cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/r7/cr7xcyv4kj3usqdiz4r6tg6yudqevgqnnicv5hcf24hdcdlqpq27.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": 4183436, "tid": 4183436, + "ts": 667115405720.286, "dur": 43.649, + "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": 4183436, "tid": 4183436, + "ts": 667115405773.197, "dur": 32.531, + "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": 4183436, "tid": 4183436, + "ts": 667115405829.588, "dur": 26.764, + "args": { + "External id": 227570,"kernel_hash": "cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/qd/cqdi2u6ocz34i5s74jt2w4w3nvhsanbincejs3f4rvbiy6mbpcsl.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": 4183436, "tid": 4183436, + "ts": 667115405862.982, "dur": 53.247, + "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": 4183436, "tid": 4183436, + "ts": 667115405941.355, "dur": 27.239, + "args": { + "External id": 227572,"kernel_hash": "caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ae/caerchakyisvrygew55fzblsi7b6tbxkb7uyip3qde2udhout4rk.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": 4183436, "tid": 4183436, + "ts": 667115406150.441, "dur": 38.694, + "args": { + "External id": 227573,"Record function id": 0, "Ev Idx": 6372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115406279.288, "dur": 279.029, + "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": 4183436, "tid": 4183436, "ts": 667115406279.288, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115406309.637, "dur": 8.315, + "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": 4183436, "tid": 4183436, + "ts": 667115406311.929, "dur": 5.705, + "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": 4183436, "tid": 4183436, + "ts": 667115406326.873, "dur": 14.525, + "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": 4183436, "tid": 4183436, + "ts": 667115406330.716, "dur": 10.040, + "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": 4183436, "tid": 4183436, + "ts": 667115406349.192, "dur": 4.665, + "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": 4183436, "tid": 4183436, + "ts": 667115406534.512, "dur": 8.840, + "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": 4183436, "tid": 4183436, + "ts": 667115406539.170, "dur": 3.761, + "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": 4183436, "tid": 4183436, + "ts": 667115406586.397, "dur": 173.697, + "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": 4183436, "tid": 4183436, + "ts": 667115406589.439, "dur": 13.162, + "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": 4183436, "tid": 4183436, "ts": 667115406589.439, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115406594.399, "dur": 6.505, + "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": 4183436, "tid": 4183436, + "ts": 667115406598.304, "dur": 2.224, + "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": 4183436, "tid": 4183436, + "ts": 667115406605.524, "dur": 154.127, + "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": 4183436, "tid": 4183436, + "ts": 667115406608.199, "dur": 5.188, + "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": 4183436, "tid": 4183436, + "ts": 667115406609.637, "dur": 3.620, + "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": 4183436, "tid": 4183436, "ts": 667115406609.637, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115406615.443, "dur": 132.820, + "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": 4183436, "tid": 4183436, "ts": 667115406615.443, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115406752.786, "dur": 5.606, + "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": 4183436, "tid": 4183436, "ts": 667115406752.786, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115406772.668, "dur": 72.328, + "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": 4183436, "tid": 4183436, + "ts": 667115406773.827, "dur": 8.441, + "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": 4183436, "tid": 4183436, "ts": 667115406773.827, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115406777.109, "dur": 3.931, + "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": 4183436, "tid": 4183436, + "ts": 667115406779.400, "dur": 1.417, + "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": 4183436, "tid": 4183436, + "ts": 667115406783.294, "dur": 61.460, + "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": 4183436, "tid": 4183436, + "ts": 667115406784.948, "dur": 6.829, + "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": 4183436, "tid": 4183436, + "ts": 667115406786.845, "dur": 4.773, + "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": 4183436, "tid": 4183436, "ts": 667115406786.845, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115406792.871, "dur": 44.712, + "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": 4183436, "tid": 4183436, "ts": 667115406792.871, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115406839.228, "dur": 4.830, + "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": 4183436, "tid": 4183436, "ts": 667115406839.228, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115406853.707, "dur": 60.075, + "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": 4183436, "tid": 4183436, + "ts": 667115406854.662, "dur": 6.955, + "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": 4183436, "tid": 4183436, "ts": 667115406854.662, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115406857.327, "dur": 3.098, + "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": 4183436, "tid": 4183436, + "ts": 667115406859.277, "dur": 0.983, + "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": 4183436, "tid": 4183436, + "ts": 667115406862.571, "dur": 50.996, + "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": 4183436, "tid": 4183436, + "ts": 667115406863.774, "dur": 4.854, + "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": 4183436, "tid": 4183436, + "ts": 667115406865.281, "dur": 3.212, + "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": 4183436, "tid": 4183436, "ts": 667115406865.281, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115406869.358, "dur": 38.178, + "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": 4183436, "tid": 4183436, "ts": 667115406869.358, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115406909.249, "dur": 3.916, + "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": 4183436, "tid": 4183436, "ts": 667115406909.249, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115406932.830, "dur": 4.126, + "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": 4183436, "tid": 4183436, + "ts": 667115406933.846, "dur": 2.987, + "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": 4183436, "tid": 4183436, "ts": 667115406933.846, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115406946.973, "dur": 5.308, + "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": 4183436, "tid": 4183436, + "ts": 667115406948.214, "dur": 3.934, + "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": 4183436, "tid": 4183436, "ts": 667115406948.214, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115406956.652, "dur": 3.286, + "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": 4183436, "tid": 4183436, + "ts": 667115406958.189, "dur": 1.608, + "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": 4183436, "tid": 4183436, "ts": 667115406958.189, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115406994.435, "dur": 177.753, + "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": 4183436, "tid": 4183436, "ts": 667115406994.435, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 667115407016.738, "dur": 9.396, + "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": 4183436, "tid": 4183436, + "ts": 667115407019.983, "dur": 5.681, + "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": 4183436, "tid": 4183436, + "ts": 667115407188.290, "dur": 133.254, + "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": 4183436, "tid": 4183436, "ts": 667115407188.290, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 667115407203.288, "dur": 8.371, + "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": 4183436, "tid": 4183436, + "ts": 667115407205.716, "dur": 5.427, + "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": 4183436, "tid": 4183436, + "ts": 667115407362.040, "dur": 245.283, + "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": 4183436, "tid": 4183436, "ts": 667115407362.040, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183436, "tid": 4183436, + "ts": 667115407393.782, "dur": 176.100, + "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": 4183436, "tid": 4183436, + "ts": 667115407452.395, "dur": 11.594, + "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": 4183436, "tid": 4183436, + "ts": 667115407456.244, "dur": 6.691, + "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": 4183436, "tid": 4183436, + "ts": 667115407467.124, "dur": 5.633, + "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": 4183436, "tid": 4183436, + "ts": 667115407475.044, "dur": 2.232, + "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": 4183436, "tid": 4183436, + "ts": 667115407480.595, "dur": 5.305, + "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": 4183436, "tid": 4183436, + "ts": 667115407586.218, "dur": 6.559, + "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": 4183436, "tid": 4183436, + "ts": 667115407614.561, "dur": 9.652, + "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": 4183436, "tid": 4183436, + "ts": 667115407617.071, "dur": 6.961, + "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": 4183436, "tid": 4183436, "ts": 667115407617.071, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115407641.815, "dur": 187.110, + "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": 4183436, "tid": 4183436, + "ts": 667115407643.920, "dur": 48.204, + "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": 4183436, "tid": 4183436, "ts": 667115407643.920, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115407648.606, "dur": 40.977, + "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": 4183436, "tid": 4183436, + "ts": 667115407686.212, "dur": 2.498, + "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": 4183436, "tid": 4183436, + "ts": 667115407694.613, "dur": 133.959, + "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": 4183436, "tid": 4183436, + "ts": 667115407697.717, "dur": 8.256, + "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": 4183436, "tid": 4183436, + "ts": 667115407699.938, "dur": 5.775, + "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": 4183436, "tid": 4183436, "ts": 667115407699.938, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115407708.072, "dur": 112.205, + "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": 4183436, "tid": 4183436, "ts": 667115407708.072, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115407823.346, "dur": 4.225, + "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": 4183436, "tid": 4183436, "ts": 667115407823.346, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115407875.901, "dur": 241.324, + "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": 4183436, "tid": 4183436, "ts": 667115407875.901, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115407898.293, "dur": 3.738, + "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": 4183436, "tid": 4183436, + "ts": 667115407899.889, "dur": 2.029, + "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": 4183436, "tid": 4183436, + "ts": 667115407907.498, "dur": 4.913, + "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": 4183436, "tid": 4183436, + "ts": 667115407909.577, "dur": 2.719, + "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": 4183436, "tid": 4183436, + "ts": 667115407910.748, "dur": 1.443, + "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": 4183436, "tid": 4183436, + "ts": 667115407921.203, "dur": 9.159, + "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": 4183436, "tid": 4183436, + "ts": 667115407924.158, "dur": 5.768, + "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": 4183436, "tid": 4183436, + "ts": 667115407938.001, "dur": 3.668, + "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": 4183436, "tid": 4183436, + "ts": 667115407945.409, "dur": 4.592, + "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": 4183436, "tid": 4183436, + "ts": 667115408091.917, "dur": 6.344, + "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": 4183436, "tid": 4183436, + "ts": 667115408093.763, "dur": 4.244, + "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": 4183436, "tid": 4183436, + "ts": 667115408101.188, "dur": 2.808, + "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": 4183436, "tid": 4183436, + "ts": 667115408102.514, "dur": 1.340, + "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": 4183436, "tid": 4183436, + "ts": 667115408139.099, "dur": 105.627, + "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": 4183436, "tid": 4183436, + "ts": 667115408140.830, "dur": 8.989, + "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": 4183436, "tid": 4183436, "ts": 667115408140.830, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115408144.081, "dur": 4.529, + "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": 4183436, "tid": 4183436, + "ts": 667115408146.820, "dur": 1.501, + "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": 4183436, "tid": 4183436, + "ts": 667115408151.198, "dur": 93.183, + "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": 4183436, "tid": 4183436, + "ts": 667115408153.681, "dur": 7.005, + "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": 4183436, "tid": 4183436, + "ts": 667115408155.234, "dur": 5.283, + "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": 4183436, "tid": 4183436, "ts": 667115408155.234, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115408161.835, "dur": 75.757, + "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": 4183436, "tid": 4183436, "ts": 667115408161.835, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115408240.662, "dur": 3.048, + "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": 4183436, "tid": 4183436, "ts": 667115408240.662, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115408253.761, "dur": 66.670, + "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": 4183436, "tid": 4183436, + "ts": 667115408254.705, "dur": 8.262, + "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": 4183436, "tid": 4183436, "ts": 667115408254.705, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115408256.394, "dur": 5.620, + "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": 4183436, "tid": 4183436, + "ts": 667115408260.876, "dur": 0.965, + "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": 4183436, "tid": 4183436, + "ts": 667115408264.055, "dur": 56.158, + "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": 4183436, "tid": 4183436, + "ts": 667115408265.760, "dur": 5.362, + "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": 4183436, "tid": 4183436, + "ts": 667115408266.929, "dur": 3.842, + "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": 4183436, "tid": 4183436, "ts": 667115408266.929, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115408272.120, "dur": 42.080, + "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": 4183436, "tid": 4183436, "ts": 667115408272.120, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115408315.799, "dur": 4.080, + "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": 4183436, "tid": 4183436, "ts": 667115408315.799, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115408343.337, "dur": 141.697, + "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": 4183436, "tid": 4183436, "ts": 667115408343.337, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115408380.813, "dur": 4.432, + "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": 4183436, "tid": 4183436, + "ts": 667115408415.317, "dur": 55.875, + "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": 4183436, "tid": 4183436, + "ts": 667115408416.162, "dur": 5.286, + "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": 4183436, "tid": 4183436, + "ts": 667115408417.341, "dur": 3.297, + "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": 4183436, "tid": 4183436, + "ts": 667115408419.528, "dur": 0.741, + "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": 4183436, "tid": 4183436, + "ts": 667115408422.234, "dur": 48.460, + "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": 4183436, "tid": 4183436, + "ts": 667115408423.914, "dur": 2.402, + "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": 4183436, "tid": 4183436, + "ts": 667115408424.931, "dur": 1.276, + "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": 4183436, "tid": 4183436, + "ts": 667115408427.346, "dur": 39.945, + "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": 4183436, "tid": 4183436, + "ts": 667115408469.185, "dur": 0.950, + "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": 4183436, "tid": 4183436, + "ts": 667115408514.813, "dur": 29.724, + "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": 4183436, "tid": 4183436, "ts": 667115408514.813, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115408583.940, "dur": 244.264, + "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": 4183436, "tid": 4183436, "ts": 667115408583.940, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115408606.145, "dur": 4.144, + "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": 4183436, "tid": 4183436, + "ts": 667115408607.657, "dur": 2.288, + "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": 4183436, "tid": 4183436, + "ts": 667115408617.996, "dur": 7.613, + "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": 4183436, "tid": 4183436, + "ts": 667115408620.833, "dur": 4.378, + "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": 4183436, "tid": 4183436, + "ts": 667115408631.793, "dur": 3.371, + "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": 4183436, "tid": 4183436, + "ts": 667115408808.701, "dur": 7.294, + "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": 4183436, "tid": 4183436, + "ts": 667115408812.287, "dur": 3.230, + "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": 4183436, "tid": 4183436, + "ts": 667115408849.281, "dur": 95.098, + "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": 4183436, "tid": 4183436, + "ts": 667115408850.474, "dur": 8.048, + "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": 4183436, "tid": 4183436, "ts": 667115408850.474, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115408852.940, "dur": 4.251, + "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": 4183436, "tid": 4183436, + "ts": 667115408855.483, "dur": 1.503, + "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": 4183436, "tid": 4183436, + "ts": 667115408860.051, "dur": 84.078, + "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": 4183436, "tid": 4183436, + "ts": 667115408861.798, "dur": 4.173, + "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": 4183436, "tid": 4183436, + "ts": 667115408862.933, "dur": 2.917, + "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": 4183436, "tid": 4183436, "ts": 667115408862.933, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115408866.970, "dur": 71.247, + "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": 4183436, "tid": 4183436, "ts": 667115408866.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115408940.285, "dur": 3.097, + "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": 4183436, "tid": 4183436, "ts": 667115408940.285, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115408953.409, "dur": 65.596, + "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": 4183436, "tid": 4183436, + "ts": 667115408954.438, "dur": 8.292, + "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": 4183436, "tid": 4183436, "ts": 667115408954.438, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115408958.807, "dur": 2.958, + "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": 4183436, "tid": 4183436, + "ts": 667115408960.781, "dur": 0.859, + "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": 4183436, "tid": 4183436, + "ts": 667115408963.532, "dur": 55.200, + "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": 4183436, "tid": 4183436, + "ts": 667115408965.145, "dur": 5.694, + "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": 4183436, "tid": 4183436, + "ts": 667115408966.382, "dur": 4.267, + "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": 4183436, "tid": 4183436, "ts": 667115408966.382, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115408972.039, "dur": 40.231, + "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": 4183436, "tid": 4183436, "ts": 667115408972.039, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115409013.689, "dur": 4.612, + "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": 4183436, "tid": 4183436, "ts": 667115409013.689, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115409027.142, "dur": 58.504, + "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": 4183436, "tid": 4183436, + "ts": 667115409027.904, "dur": 5.803, + "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": 4183436, "tid": 4183436, "ts": 667115409027.904, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115409029.615, "dur": 2.897, + "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": 4183436, "tid": 4183436, + "ts": 667115409031.505, "dur": 0.870, + "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": 4183436, "tid": 4183436, + "ts": 667115409034.695, "dur": 50.762, + "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": 4183436, "tid": 4183436, + "ts": 667115409035.762, "dur": 6.080, + "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": 4183436, "tid": 4183436, + "ts": 667115409037.554, "dur": 4.136, + "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": 4183436, "tid": 4183436, "ts": 667115409037.554, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115409042.620, "dur": 37.306, + "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": 4183436, "tid": 4183436, "ts": 667115409042.620, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115409081.500, "dur": 3.376, + "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": 4183436, "tid": 4183436, "ts": 667115409081.500, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115409101.328, "dur": 3.882, + "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": 4183436, "tid": 4183436, + "ts": 667115409102.067, "dur": 2.994, + "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": 4183436, "tid": 4183436, "ts": 667115409102.067, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115409111.688, "dur": 4.628, + "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": 4183436, "tid": 4183436, + "ts": 667115409112.912, "dur": 3.268, + "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": 4183436, "tid": 4183436, "ts": 667115409112.912, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115409120.306, "dur": 5.367, + "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": 4183436, "tid": 4183436, + "ts": 667115409121.361, "dur": 4.179, + "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": 4183436, "tid": 4183436, "ts": 667115409121.361, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115409154.341, "dur": 151.981, + "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": 4183436, "tid": 4183436, "ts": 667115409154.341, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 667115409173.667, "dur": 8.269, + "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": 4183436, "tid": 4183436, + "ts": 667115409176.314, "dur": 5.297, + "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": 4183436, "tid": 4183436, + "ts": 667115409318.863, "dur": 98.768, + "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": 4183436, "tid": 4183436, "ts": 667115409318.863, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 667115409331.019, "dur": 6.975, + "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": 4183436, "tid": 4183436, + "ts": 667115409333.204, "dur": 4.377, + "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": 4183436, "tid": 4183436, + "ts": 667115409443.343, "dur": 195.757, + "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": 4183436, "tid": 4183436, "ts": 667115409443.343, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183436, "tid": 4183436, + "ts": 667115409469.027, "dur": 144.498, + "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": 4183436, "tid": 4183436, + "ts": 667115409539.248, "dur": 9.073, + "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": 4183436, "tid": 4183436, + "ts": 667115409541.588, "dur": 6.058, + "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": 4183436, "tid": 4183436, + "ts": 667115409550.899, "dur": 3.595, + "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": 4183436, "tid": 4183436, + "ts": 667115409556.126, "dur": 1.453, + "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": 4183436, "tid": 4183436, + "ts": 667115409562.245, "dur": 3.122, + "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": 4183436, "tid": 4183436, + "ts": 667115409624.479, "dur": 4.518, + "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": 4183436, "tid": 4183436, + "ts": 667115409644.563, "dur": 40.806, + "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": 4183436, "tid": 4183436, + "ts": 667115409646.090, "dur": 38.731, + "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": 4183436, "tid": 4183436, "ts": 667115409646.090, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115409700.052, "dur": 114.659, + "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": 4183436, "tid": 4183436, + "ts": 667115409701.217, "dur": 10.275, + "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": 4183436, "tid": 4183436, "ts": 667115409701.217, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115409705.008, "dur": 5.092, + "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": 4183436, "tid": 4183436, + "ts": 667115409708.143, "dur": 1.684, + "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": 4183436, "tid": 4183436, + "ts": 667115409712.906, "dur": 101.541, + "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": 4183436, "tid": 4183436, + "ts": 667115409715.771, "dur": 4.621, + "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": 4183436, "tid": 4183436, + "ts": 667115409717.096, "dur": 3.153, + "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": 4183436, "tid": 4183436, "ts": 667115409717.096, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115409721.664, "dur": 86.062, + "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": 4183436, "tid": 4183436, "ts": 667115409721.664, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115409810.321, "dur": 3.370, + "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": 4183436, "tid": 4183436, "ts": 667115409810.321, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115409849.874, "dur": 260.771, + "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": 4183436, "tid": 4183436, "ts": 667115409849.874, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115409869.995, "dur": 3.241, + "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": 4183436, "tid": 4183436, + "ts": 667115409871.341, "dur": 1.750, + "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": 4183436, "tid": 4183436, + "ts": 667115409877.217, "dur": 4.046, + "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": 4183436, "tid": 4183436, + "ts": 667115409878.545, "dur": 2.602, + "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": 4183436, "tid": 4183436, + "ts": 667115409879.655, "dur": 1.336, + "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": 4183436, "tid": 4183436, + "ts": 667115409888.820, "dur": 8.289, + "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": 4183436, "tid": 4183436, + "ts": 667115409891.525, "dur": 5.240, + "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": 4183436, "tid": 4183436, + "ts": 667115409903.777, "dur": 3.243, + "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": 4183436, "tid": 4183436, + "ts": 667115409911.412, "dur": 3.680, + "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": 4183436, "tid": 4183436, + "ts": 667115410077.635, "dur": 8.729, + "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": 4183436, "tid": 4183436, + "ts": 667115410082.270, "dur": 3.559, + "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": 4183436, "tid": 4183436, + "ts": 667115410089.916, "dur": 3.555, + "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": 4183436, "tid": 4183436, + "ts": 667115410091.716, "dur": 1.517, + "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": 4183436, "tid": 4183436, + "ts": 667115410136.194, "dur": 152.431, + "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": 4183436, "tid": 4183436, + "ts": 667115410137.851, "dur": 10.786, + "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": 4183436, "tid": 4183436, "ts": 667115410137.851, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115410141.780, "dur": 5.327, + "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": 4183436, "tid": 4183436, + "ts": 667115410144.891, "dur": 1.669, + "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": 4183436, "tid": 4183436, + "ts": 667115410150.091, "dur": 138.212, + "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": 4183436, "tid": 4183436, + "ts": 667115410152.406, "dur": 7.625, + "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": 4183436, "tid": 4183436, + "ts": 667115410154.034, "dur": 5.691, + "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": 4183436, "tid": 4183436, "ts": 667115410154.034, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115410161.265, "dur": 99.113, + "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": 4183436, "tid": 4183436, "ts": 667115410161.265, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115410280.219, "dur": 7.137, + "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": 4183436, "tid": 4183436, "ts": 667115410280.219, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115410299.844, "dur": 93.118, + "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": 4183436, "tid": 4183436, + "ts": 667115410300.993, "dur": 8.832, + "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": 4183436, "tid": 4183436, "ts": 667115410300.993, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115410303.826, "dur": 4.426, + "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": 4183436, "tid": 4183436, + "ts": 667115410306.509, "dur": 1.400, + "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": 4183436, "tid": 4183436, + "ts": 667115410310.872, "dur": 81.841, + "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": 4183436, "tid": 4183436, + "ts": 667115410313.008, "dur": 6.812, + "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": 4183436, "tid": 4183436, + "ts": 667115410314.572, "dur": 4.970, + "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": 4183436, "tid": 4183436, "ts": 667115410314.572, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115410320.656, "dur": 65.644, + "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": 4183436, "tid": 4183436, "ts": 667115410320.656, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115410388.926, "dur": 3.252, + "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": 4183436, "tid": 4183436, "ts": 667115410388.926, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115410423.761, "dur": 214.005, + "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": 4183436, "tid": 4183436, "ts": 667115410423.761, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115410467.226, "dur": 6.247, + "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": 4183436, "tid": 4183436, + "ts": 667115410530.625, "dur": 87.942, + "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": 4183436, "tid": 4183436, + "ts": 667115410532.076, "dur": 11.912, + "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": 4183436, "tid": 4183436, + "ts": 667115410534.317, "dur": 8.163, + "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": 4183436, "tid": 4183436, + "ts": 667115410540.033, "dur": 1.875, + "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": 4183436, "tid": 4183436, + "ts": 667115410545.668, "dur": 72.492, + "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": 4183436, "tid": 4183436, + "ts": 667115410548.034, "dur": 4.341, + "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": 4183436, "tid": 4183436, + "ts": 667115410549.584, "dur": 2.518, + "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": 4183436, "tid": 4183436, + "ts": 667115410553.795, "dur": 58.751, + "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": 4183436, "tid": 4183436, + "ts": 667115410615.154, "dur": 1.858, + "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": 4183436, "tid": 4183436, + "ts": 667115410649.678, "dur": 70.855, + "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": 4183436, "tid": 4183436, "ts": 667115410649.678, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115410773.416, "dur": 244.317, + "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": 4183436, "tid": 4183436, "ts": 667115410773.416, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115410800.267, "dur": 6.132, + "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": 4183436, "tid": 4183436, + "ts": 667115410802.438, "dur": 3.608, + "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": 4183436, "tid": 4183436, + "ts": 667115410816.698, "dur": 10.226, + "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": 4183436, "tid": 4183436, + "ts": 667115410820.729, "dur": 5.662, + "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": 4183436, "tid": 4183436, + "ts": 667115410835.484, "dur": 4.116, + "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": 4183436, "tid": 4183436, + "ts": 667115410998.507, "dur": 4.114, + "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": 4183436, "tid": 4183436, + "ts": 667115410999.641, "dur": 2.649, + "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": 4183436, "tid": 4183436, + "ts": 667115411038.489, "dur": 101.346, + "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": 4183436, "tid": 4183436, + "ts": 667115411039.828, "dur": 8.790, + "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": 4183436, "tid": 4183436, "ts": 667115411039.828, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115411042.672, "dur": 4.681, + "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": 4183436, "tid": 4183436, + "ts": 667115411045.339, "dur": 1.752, + "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": 4183436, "tid": 4183436, + "ts": 667115411050.283, "dur": 89.249, + "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": 4183436, "tid": 4183436, + "ts": 667115411052.250, "dur": 4.306, + "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": 4183436, "tid": 4183436, + "ts": 667115411053.353, "dur": 3.046, + "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": 4183436, "tid": 4183436, "ts": 667115411053.353, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115411057.970, "dur": 71.178, + "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": 4183436, "tid": 4183436, "ts": 667115411057.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115411131.616, "dur": 7.060, + "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": 4183436, "tid": 4183436, "ts": 667115411131.616, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115411148.727, "dur": 63.129, + "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": 4183436, "tid": 4183436, + "ts": 667115411150.245, "dur": 7.342, + "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": 4183436, "tid": 4183436, "ts": 667115411150.245, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115411152.390, "dur": 3.935, + "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": 4183436, "tid": 4183436, + "ts": 667115411154.625, "dur": 1.288, + "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": 4183436, "tid": 4183436, + "ts": 667115411158.564, "dur": 53.060, + "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": 4183436, "tid": 4183436, + "ts": 667115411159.923, "dur": 3.635, + "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": 4183436, "tid": 4183436, + "ts": 667115411161.238, "dur": 2.187, + "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": 4183436, "tid": 4183436, "ts": 667115411161.238, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115411165.025, "dur": 42.746, + "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": 4183436, "tid": 4183436, "ts": 667115411165.025, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115411209.454, "dur": 1.819, + "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": 4183436, "tid": 4183436, "ts": 667115411209.454, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115411218.604, "dur": 58.046, + "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": 4183436, "tid": 4183436, + "ts": 667115411219.181, "dur": 6.878, + "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": 4183436, "tid": 4183436, "ts": 667115411219.181, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115411222.108, "dur": 3.012, + "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": 4183436, "tid": 4183436, + "ts": 667115411224.102, "dur": 0.888, + "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": 4183436, "tid": 4183436, + "ts": 667115411227.354, "dur": 49.106, + "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": 4183436, "tid": 4183436, + "ts": 667115411228.579, "dur": 4.909, + "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": 4183436, "tid": 4183436, + "ts": 667115411229.708, "dur": 3.674, + "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": 4183436, "tid": 4183436, "ts": 667115411229.708, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115411234.495, "dur": 37.856, + "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": 4183436, "tid": 4183436, "ts": 667115411234.495, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115411274.010, "dur": 2.160, + "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": 4183436, "tid": 4183436, "ts": 667115411274.010, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115411292.047, "dur": 3.935, + "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": 4183436, "tid": 4183436, + "ts": 667115411292.876, "dur": 2.983, + "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": 4183436, "tid": 4183436, "ts": 667115411292.876, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115411302.104, "dur": 5.802, + "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": 4183436, "tid": 4183436, + "ts": 667115411303.147, "dur": 4.591, + "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": 4183436, "tid": 4183436, "ts": 667115411303.147, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115411312.408, "dur": 3.451, + "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": 4183436, "tid": 4183436, + "ts": 667115411313.651, "dur": 2.062, + "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": 4183436, "tid": 4183436, "ts": 667115411313.651, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115411344.245, "dur": 173.491, + "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": 4183436, "tid": 4183436, "ts": 667115411344.245, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 667115411364.732, "dur": 7.685, + "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": 4183436, "tid": 4183436, + "ts": 667115411367.184, "dur": 4.802, + "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": 4183436, "tid": 4183436, + "ts": 667115411533.989, "dur": 111.613, + "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": 4183436, "tid": 4183436, "ts": 667115411533.989, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 667115411549.182, "dur": 8.152, + "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": 4183436, "tid": 4183436, + "ts": 667115411551.448, "dur": 5.581, + "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": 4183436, "tid": 4183436, + "ts": 667115411738.886, "dur": 181.660, + "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": 4183436, "tid": 4183436, "ts": 667115411738.886, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183436, "tid": 4183436, + "ts": 667115411767.264, "dur": 127.582, + "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": 4183436, "tid": 4183436, + "ts": 667115411815.496, "dur": 10.727, + "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": 4183436, "tid": 4183436, + "ts": 667115411817.824, "dur": 7.817, + "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": 4183436, "tid": 4183436, + "ts": 667115411831.132, "dur": 4.650, + "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": 4183436, "tid": 4183436, + "ts": 667115411837.088, "dur": 1.267, + "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": 4183436, "tid": 4183436, + "ts": 667115411840.785, "dur": 3.119, + "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": 4183436, "tid": 4183436, + "ts": 667115411905.709, "dur": 4.800, + "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": 4183436, "tid": 4183436, + "ts": 667115411925.574, "dur": 5.809, + "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": 4183436, "tid": 4183436, + "ts": 667115411927.051, "dur": 4.213, + "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": 4183436, "tid": 4183436, "ts": 667115411927.051, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115411943.727, "dur": 111.186, + "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": 4183436, "tid": 4183436, + "ts": 667115411944.916, "dur": 12.161, + "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": 4183436, "tid": 4183436, "ts": 667115411944.916, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115411950.906, "dur": 5.038, + "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": 4183436, "tid": 4183436, + "ts": 667115411954.131, "dur": 1.536, + "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": 4183436, "tid": 4183436, + "ts": 667115411958.253, "dur": 96.368, + "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": 4183436, "tid": 4183436, + "ts": 667115411960.603, "dur": 3.733, + "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": 4183436, "tid": 4183436, + "ts": 667115411961.570, "dur": 2.582, + "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": 4183436, "tid": 4183436, "ts": 667115411961.570, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115411965.389, "dur": 80.241, + "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": 4183436, "tid": 4183436, "ts": 667115411965.389, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115412048.409, "dur": 5.499, + "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": 4183436, "tid": 4183436, "ts": 667115412048.409, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115412086.016, "dur": 208.185, + "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": 4183436, "tid": 4183436, "ts": 667115412086.016, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115412104.312, "dur": 3.203, + "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": 4183436, "tid": 4183436, + "ts": 667115412105.702, "dur": 1.647, + "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": 4183436, "tid": 4183436, + "ts": 667115412111.598, "dur": 3.744, + "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": 4183436, "tid": 4183436, + "ts": 667115412113.005, "dur": 2.232, + "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": 4183436, "tid": 4183436, + "ts": 667115412114.017, "dur": 1.075, + "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": 4183436, "tid": 4183436, + "ts": 667115412122.391, "dur": 6.660, + "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": 4183436, "tid": 4183436, + "ts": 667115412124.618, "dur": 4.149, + "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": 4183436, "tid": 4183436, + "ts": 667115412135.478, "dur": 3.009, + "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": 4183436, "tid": 4183436, + "ts": 667115412142.359, "dur": 4.195, + "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": 4183436, "tid": 4183436, + "ts": 667115412272.835, "dur": 3.115, + "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": 4183436, "tid": 4183436, + "ts": 667115412273.668, "dur": 2.048, + "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": 4183436, "tid": 4183436, + "ts": 667115412278.595, "dur": 2.465, + "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": 4183436, "tid": 4183436, + "ts": 667115412279.676, "dur": 1.275, + "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": 4183436, "tid": 4183436, + "ts": 667115412313.833, "dur": 90.524, + "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": 4183436, "tid": 4183436, + "ts": 667115412314.827, "dur": 7.700, + "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": 4183436, "tid": 4183436, "ts": 667115412314.827, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115412317.723, "dur": 3.737, + "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": 4183436, "tid": 4183436, + "ts": 667115412319.815, "dur": 1.316, + "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": 4183436, "tid": 4183436, + "ts": 667115412323.555, "dur": 80.562, + "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": 4183436, "tid": 4183436, + "ts": 667115412325.103, "dur": 4.285, + "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": 4183436, "tid": 4183436, + "ts": 667115412326.388, "dur": 2.849, + "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": 4183436, "tid": 4183436, "ts": 667115412326.388, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115412330.220, "dur": 66.501, + "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": 4183436, "tid": 4183436, "ts": 667115412330.220, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115412399.210, "dur": 4.278, + "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": 4183436, "tid": 4183436, "ts": 667115412399.210, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115412412.608, "dur": 64.447, + "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": 4183436, "tid": 4183436, + "ts": 667115412413.209, "dur": 5.809, + "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": 4183436, "tid": 4183436, "ts": 667115412413.209, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115412414.762, "dur": 3.121, + "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": 4183436, "tid": 4183436, + "ts": 667115412416.571, "dur": 1.137, + "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": 4183436, "tid": 4183436, + "ts": 667115412419.663, "dur": 57.178, + "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": 4183436, "tid": 4183436, + "ts": 667115412421.365, "dur": 6.462, + "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": 4183436, "tid": 4183436, + "ts": 667115412422.433, "dur": 5.227, + "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": 4183436, "tid": 4183436, "ts": 667115412422.433, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115412428.645, "dur": 41.527, + "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": 4183436, "tid": 4183436, "ts": 667115412428.645, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115412472.372, "dur": 4.109, + "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": 4183436, "tid": 4183436, "ts": 667115412472.372, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115412518.785, "dur": 200.418, + "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": 4183436, "tid": 4183436, "ts": 667115412518.785, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115412557.629, "dur": 5.045, + "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": 4183436, "tid": 4183436, + "ts": 667115412596.358, "dur": 105.751, + "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": 4183436, "tid": 4183436, + "ts": 667115412597.272, "dur": 5.595, + "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": 4183436, "tid": 4183436, + "ts": 667115412598.667, "dur": 3.405, + "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": 4183436, "tid": 4183436, + "ts": 667115412600.480, "dur": 1.420, + "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": 4183436, "tid": 4183436, + "ts": 667115412603.901, "dur": 97.848, + "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": 4183436, "tid": 4183436, + "ts": 667115412606.053, "dur": 2.740, + "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": 4183436, "tid": 4183436, + "ts": 667115412607.157, "dur": 1.524, + "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": 4183436, "tid": 4183436, + "ts": 667115412609.706, "dur": 85.967, + "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": 4183436, "tid": 4183436, + "ts": 667115412699.218, "dur": 1.800, + "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": 4183436, "tid": 4183436, + "ts": 667115412729.444, "dur": 29.494, + "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": 4183436, "tid": 4183436, "ts": 667115412729.444, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115412797.273, "dur": 190.310, + "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": 4183436, "tid": 4183436, "ts": 667115412797.273, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115412817.846, "dur": 4.803, + "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": 4183436, "tid": 4183436, + "ts": 667115412820.182, "dur": 2.306, + "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": 4183436, "tid": 4183436, + "ts": 667115412830.697, "dur": 8.251, + "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": 4183436, "tid": 4183436, + "ts": 667115412833.838, "dur": 4.744, + "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": 4183436, "tid": 4183436, + "ts": 667115412845.656, "dur": 3.659, + "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": 4183436, "tid": 4183436, + "ts": 667115412972.037, "dur": 3.350, + "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": 4183436, "tid": 4183436, + "ts": 667115412973.403, "dur": 1.761, + "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": 4183436, "tid": 4183436, + "ts": 667115413007.244, "dur": 91.980, + "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": 4183436, "tid": 4183436, + "ts": 667115413009.077, "dur": 8.504, + "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": 4183436, "tid": 4183436, "ts": 667115413009.077, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115413011.726, "dur": 4.519, + "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": 4183436, "tid": 4183436, + "ts": 667115413014.325, "dur": 1.742, + "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": 4183436, "tid": 4183436, + "ts": 667115413018.672, "dur": 80.229, + "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": 4183436, "tid": 4183436, + "ts": 667115413020.949, "dur": 4.522, + "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": 4183436, "tid": 4183436, + "ts": 667115413021.887, "dur": 3.462, + "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": 4183436, "tid": 4183436, "ts": 667115413021.887, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115413026.379, "dur": 66.890, + "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": 4183436, "tid": 4183436, "ts": 667115413026.379, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115413095.652, "dur": 2.725, + "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": 4183436, "tid": 4183436, "ts": 667115413095.652, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115413107.479, "dur": 61.061, + "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": 4183436, "tid": 4183436, + "ts": 667115413108.266, "dur": 6.764, + "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": 4183436, "tid": 4183436, "ts": 667115413108.266, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115413110.163, "dur": 3.747, + "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": 4183436, "tid": 4183436, + "ts": 667115413112.477, "dur": 1.260, + "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": 4183436, "tid": 4183436, + "ts": 667115413115.626, "dur": 52.735, + "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": 4183436, "tid": 4183436, + "ts": 667115413117.100, "dur": 3.568, + "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": 4183436, "tid": 4183436, + "ts": 667115413118.047, "dur": 2.489, + "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": 4183436, "tid": 4183436, "ts": 667115413118.047, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115413121.297, "dur": 40.687, + "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": 4183436, "tid": 4183436, "ts": 667115413121.297, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115413163.710, "dur": 4.365, + "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": 4183436, "tid": 4183436, "ts": 667115413163.710, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115413175.469, "dur": 64.083, + "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": 4183436, "tid": 4183436, + "ts": 667115413176.075, "dur": 7.771, + "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": 4183436, "tid": 4183436, "ts": 667115413176.075, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115413177.672, "dur": 5.246, + "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": 4183436, "tid": 4183436, + "ts": 667115413179.686, "dur": 3.028, + "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": 4183436, "tid": 4183436, + "ts": 667115413184.663, "dur": 54.678, + "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": 4183436, "tid": 4183436, + "ts": 667115413186.019, "dur": 5.260, + "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": 4183436, "tid": 4183436, + "ts": 667115413187.388, "dur": 3.758, + "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": 4183436, "tid": 4183436, "ts": 667115413187.388, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115413191.916, "dur": 35.265, + "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": 4183436, "tid": 4183436, "ts": 667115413191.916, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115413229.093, "dur": 9.857, + "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": 4183436, "tid": 4183436, "ts": 667115413229.093, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115413254.938, "dur": 5.572, + "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": 4183436, "tid": 4183436, + "ts": 667115413256.810, "dur": 3.362, + "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": 4183436, "tid": 4183436, "ts": 667115413256.810, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115413269.714, "dur": 4.428, + "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": 4183436, "tid": 4183436, + "ts": 667115413271.779, "dur": 2.254, + "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": 4183436, "tid": 4183436, "ts": 667115413271.779, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115413278.123, "dur": 3.105, + "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": 4183436, "tid": 4183436, + "ts": 667115413279.316, "dur": 1.787, + "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": 4183436, "tid": 4183436, "ts": 667115413279.316, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115413309.126, "dur": 146.254, + "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": 4183436, "tid": 4183436, "ts": 667115413309.126, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 667115413326.966, "dur": 10.649, + "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": 4183436, "tid": 4183436, + "ts": 667115413330.006, "dur": 7.221, + "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": 4183436, "tid": 4183436, + "ts": 667115413474.171, "dur": 132.363, + "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": 4183436, "tid": 4183436, "ts": 667115413474.171, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 667115413488.225, "dur": 27.787, + "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": 4183436, "tid": 4183436, + "ts": 667115413508.821, "dur": 6.517, + "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": 4183436, "tid": 4183436, + "ts": 667115413634.148, "dur": 220.260, + "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": 4183436, "tid": 4183436, "ts": 667115413634.148, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183436, "tid": 4183436, + "ts": 667115413696.858, "dur": 131.229, + "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": 4183436, "tid": 4183436, + "ts": 667115413747.342, "dur": 9.327, + "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": 4183436, "tid": 4183436, + "ts": 667115413750.098, "dur": 5.760, + "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": 4183436, "tid": 4183436, + "ts": 667115413759.348, "dur": 4.611, + "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": 4183436, "tid": 4183436, + "ts": 667115413765.559, "dur": 1.644, + "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": 4183436, "tid": 4183436, + "ts": 667115413769.740, "dur": 5.379, + "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": 4183436, "tid": 4183436, + "ts": 667115413838.912, "dur": 4.755, + "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": 4183436, "tid": 4183436, + "ts": 667115413859.704, "dur": 6.209, + "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": 4183436, "tid": 4183436, + "ts": 667115413861.388, "dur": 4.385, + "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": 4183436, "tid": 4183436, "ts": 667115413861.388, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115413877.563, "dur": 103.986, + "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": 4183436, "tid": 4183436, + "ts": 667115413878.794, "dur": 9.591, + "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": 4183436, "tid": 4183436, "ts": 667115413878.794, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115413882.244, "dur": 5.170, + "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": 4183436, "tid": 4183436, + "ts": 667115413885.454, "dur": 1.697, + "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": 4183436, "tid": 4183436, + "ts": 667115413889.748, "dur": 91.441, + "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": 4183436, "tid": 4183436, + "ts": 667115413892.104, "dur": 4.201, + "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": 4183436, "tid": 4183436, + "ts": 667115413893.357, "dur": 2.772, + "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": 4183436, "tid": 4183436, "ts": 667115413893.357, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115413897.302, "dur": 77.488, + "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": 4183436, "tid": 4183436, "ts": 667115413897.302, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115413977.304, "dur": 3.242, + "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": 4183436, "tid": 4183436, "ts": 667115413977.304, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115414015.864, "dur": 199.393, + "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": 4183436, "tid": 4183436, "ts": 667115414015.864, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 667115414034.170, "dur": 3.269, + "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": 4183436, "tid": 4183436, + "ts": 667115414035.563, "dur": 1.708, + "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": 4183436, "tid": 4183436, + "ts": 667115414041.579, "dur": 3.921, + "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": 4183436, "tid": 4183436, + "ts": 667115414043.260, "dur": 2.135, + "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": 4183436, "tid": 4183436, + "ts": 667115414044.396, "dur": 0.898, + "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": 4183436, "tid": 4183436, + "ts": 667115414052.621, "dur": 7.352, + "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": 4183436, "tid": 4183436, + "ts": 667115414055.346, "dur": 4.293, + "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": 4183436, "tid": 4183436, + "ts": 667115414066.745, "dur": 3.278, + "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": 4183436, "tid": 4183436, + "ts": 667115414073.264, "dur": 3.261, + "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": 4183436, "tid": 4183436, + "ts": 667115414194.081, "dur": 5.416, + "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": 4183436, "tid": 4183436, + "ts": 667115414195.169, "dur": 4.070, + "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": 4183436, "tid": 4183436, + "ts": 667115414202.021, "dur": 2.871, + "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": 4183436, "tid": 4183436, + "ts": 667115414203.410, "dur": 1.156, + "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": 4183436, "tid": 4183436, + "ts": 667115414231.386, "dur": 84.095, + "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": 4183436, "tid": 4183436, + "ts": 667115414232.336, "dur": 6.723, + "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": 4183436, "tid": 4183436, "ts": 667115414232.336, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115414234.178, "dur": 3.620, + "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": 4183436, "tid": 4183436, + "ts": 667115414236.504, "dur": 1.108, + "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": 4183436, "tid": 4183436, + "ts": 667115414240.511, "dur": 74.697, + "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": 4183436, "tid": 4183436, + "ts": 667115414242.397, "dur": 5.630, + "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": 4183436, "tid": 4183436, + "ts": 667115414243.437, "dur": 4.445, + "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": 4183436, "tid": 4183436, "ts": 667115414243.437, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115414249.077, "dur": 60.600, + "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": 4183436, "tid": 4183436, "ts": 667115414249.077, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115414311.870, "dur": 2.836, + "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": 4183436, "tid": 4183436, "ts": 667115414311.870, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 667115414323.522, "dur": 68.862, + "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": 4183436, "tid": 4183436, + "ts": 667115414324.567, "dur": 11.086, + "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": 4183436, "tid": 4183436, "ts": 667115414324.567, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 667115414329.088, "dur": 5.579, + "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": 4183436, "tid": 4183436, + "ts": 667115414333.553, "dur": 0.961, + "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": 4183436, "tid": 4183436, + "ts": 667115414336.541, "dur": 55.548, + "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": 4183436, "tid": 4183436, + "ts": 667115414337.570, "dur": 4.819, + "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": 4183436, "tid": 4183436, + "ts": 667115414338.794, "dur": 3.469, + "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": 4183436, "tid": 4183436, "ts": 667115414338.794, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 667115414343.366, "dur": 42.381, + "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": 4183436, "tid": 4183436, "ts": 667115414343.366, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 667115414387.231, "dur": 4.545, + "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": 4183436, "tid": 4183436, "ts": 667115414387.231, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115414410.240, "dur": 168.451, + "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": 4183436, "tid": 4183436, "ts": 667115414410.240, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 667115414445.494, "dur": 4.218, + "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": 4183436, "tid": 4183436, + "ts": 667115414480.130, "dur": 84.047, + "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": 4183436, "tid": 4183436, + "ts": 667115414480.891, "dur": 4.811, + "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": 4183436, "tid": 4183436, + "ts": 667115414482.117, "dur": 2.810, + "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": 4183436, "tid": 4183436, + "ts": 667115414483.623, "dur": 1.125, + "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": 4183436, "tid": 4183436, + "ts": 667115414486.545, "dur": 77.246, + "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": 4183436, "tid": 4183436, + "ts": 667115414487.825, "dur": 22.327, + "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": 4183436, "tid": 4183436, + "ts": 667115414489.331, "dur": 20.363, + "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": 4183436, "tid": 4183436, + "ts": 667115414511.493, "dur": 47.947, + "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": 4183436, "tid": 4183436, + "ts": 667115414561.624, "dur": 1.389, + "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": 4183436, "tid": 4183436, + "ts": 667115414587.875, "dur": 25.332, + "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": 4183436, "tid": 4183436, "ts": 667115414587.875, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 4183436, "tid": 4183436, + "ts": 667115414631.067, "dur": 75.523, + "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": 4183436, "tid": 4183436, "ts": 667115414631.067, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 4183436, "tid": 4183436, + "ts": 667115414638.404, "dur": 61.223, + "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": 4183436, "tid": 4183436, + "ts": 667115414702.612, "dur": 1.691, + "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": 4183436, "tid": 4183436, + "ts": 667115414746.727, "dur": 51.044, + "args": { + "External id": 228017,"Record function id": 0, "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 4183436, "tid": 4183436, + "ts": 667115414799.378, "dur": 189.435, + "args": { + "External id": 228018,"Record function id": 0, "Ev Idx": 6817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 667115414835.698, "dur": 144.928, + "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": 4183436, "tid": 4183436, "ts": 667115414835.698, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 667115414903.969, "dur": 40.359, + "args": { + "External id": 228020,"kernel_hash": "cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/xg/cxgt35iir7yuxpd5sgaxksro4hnykwg2cj7p5wemlrboaeof7dgg.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": 4183436, "tid": 4183436, + "ts": 667115415061.266, "dur": 39.204, + "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": 4183436, "tid": 4183436, + "ts": 667115415064.489, "dur": 5.377, + "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": 4183436, "tid": 4183436, + "ts": 667115415072.874, "dur": 27.296, + "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": 4183436, "tid": 4183436, + "ts": 667115415076.269, "dur": 23.439, + "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": 4183436, "tid": 4183436, + "ts": 667115415105.051, "dur": 20.488, + "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": 4183436, "tid": 4183436, + "ts": 667115415106.117, "dur": 2.707, + "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": 4183436, "tid": 4183436, + "ts": 667115415109.662, "dur": 15.615, + "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": 4183436, "tid": 4183436, + "ts": 667115415110.404, "dur": 14.384, + "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": 4183436, "tid": 4183436, + "ts": 667115415128.683, "dur": 17.829, + "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": 4183436, "tid": 4183436, + "ts": 667115415129.574, "dur": 2.442, + "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": 4183436, "tid": 4183436, + "ts": 667115415132.755, "dur": 13.494, + "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": 4183436, "tid": 4183436, + "ts": 667115415133.419, "dur": 12.472, + "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": 4183436, "tid": 4183436, + "ts": 667115415155.813, "dur": 0.751, + "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": 4183436, "tid": 4183436, + "ts": 667115415164.225, "dur": 9.414, + "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": 4183436, "tid": 4183436, + "ts": 667115415169.592, "dur": 2.248, + "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": 4183436, "tid": 4183436, + "ts": 667115415179.631, "dur": 6.218, + "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": 4183436, "tid": 4183436, + "ts": 667115415183.508, "dur": 0.797, + "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": 4183436, "tid": 4183436, + "ts": 667115415187.032, "dur": 3.419, + "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": 4183436, "tid": 4183436, + "ts": 667115415189.067, "dur": 0.653, + "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": 4183436, "tid": 4183436, + "ts": 667115415191.767, "dur": 3.556, + "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": 4183436, "tid": 4183436, + "ts": 667115415193.895, "dur": 0.879, + "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": 4183436, "tid": 4183436, + "ts": 667115415198.882, "dur": 3.258, + "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": 4183436, "tid": 4183436, + "ts": 667115415200.835, "dur": 0.798, + "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": 4183436, "tid": 4183436, + "ts": 667115415203.195, "dur": 3.200, + "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": 4183436, "tid": 4183436, + "ts": 667115415204.869, "dur": 0.834, + "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": 4183436, "tid": 4183436, + "ts": 667115415207.630, "dur": 2.858, + "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": 4183436, "tid": 4183436, + "ts": 667115415209.065, "dur": 0.892, + "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": 4183436, "tid": 4183436, + "ts": 667115415214.757, "dur": 5.218, + "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": 4183436, "tid": 4183436, + "ts": 667115415218.292, "dur": 0.959, + "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": 4183436, "tid": 4183436, + "ts": 667115415223.660, "dur": 3.689, + "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": 4183436, "tid": 4183436, + "ts": 667115415225.692, "dur": 1.078, + "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": 4183436, "tid": 4183436, + "ts": 667115415230.608, "dur": 6.637, + "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": 4183436, "tid": 4183436, + "ts": 667115415235.473, "dur": 0.720, + "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": 4183436, "tid": 4183436, + "ts": 667115415238.283, "dur": 3.588, + "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": 4183436, "tid": 4183436, + "ts": 667115415240.109, "dur": 1.195, + "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": 4183436, "tid": 4183436, + "ts": 667115415244.262, "dur": 5.998, + "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": 4183436, "tid": 4183436, "ts": 667115415244.262, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115415248.065, "dur": 0.895, + "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": 4183436, "tid": 4183436, + "ts": 667115415251.493, "dur": 5.167, + "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": 4183436, "tid": 4183436, "ts": 667115415251.493, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115415255.198, "dur": 0.649, + "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": 4183436, "tid": 4183436, + "ts": 667115415257.740, "dur": 5.247, + "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": 4183436, "tid": 4183436, "ts": 667115415257.740, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115415261.396, "dur": 0.758, + "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": 4183436, "tid": 4183436, + "ts": 667115415263.941, "dur": 4.529, + "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": 4183436, "tid": 4183436, "ts": 667115415263.941, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115415266.533, "dur": 1.230, + "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": 4183436, "tid": 4183436, + "ts": 667115415272.552, "dur": 39.734, + "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": 4183436, "tid": 4183436, + "ts": 667115415274.700, "dur": 37.360, + "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": 4183436, "tid": 4183436, + "ts": 667115415277.498, "dur": 8.198, + "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": 4183436, "tid": 4183436, + "ts": 667115415279.586, "dur": 5.476, + "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": 4183436, "tid": 4183436, + "ts": 667115415287.376, "dur": 24.261, + "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": 4183436, "tid": 4183436, + "ts": 667115415333.947, "dur": 4.672, + "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": 4183436, "tid": 4183436, "ts": 667115415333.947, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115415340.984, "dur": 1.164, + "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": 4183436, "tid": 4183436, + "ts": 667115415365.822, "dur": 21475.687, + "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": 4183436, "tid": 4183436, "ts": 667115415365.822, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 4183436, + "ts": 667115415378.072, "dur": 27.672, + "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": 4183436, "tid": 4183436, + "ts": 667115415378.662, "dur": 26.868, + "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": 4183436, "tid": 4183436, + "ts": 667115415380.031, "dur": 5.065, + "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": 4183436, "tid": 4183436, + "ts": 667115415381.348, "dur": 3.289, + "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": 4183436, "tid": 4183436, + "ts": 667115415385.791, "dur": 19.268, + "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": 4183436, "tid": 4183436, + "ts": 667115415420.602, "dur": 33.146, + "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": 4183436, "tid": 4183436, + "ts": 667115415429.082, "dur": 7.140, + "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": 4183436, "tid": 4183436, + "ts": 667115415431.841, "dur": 3.960, + "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": 4183436, "tid": 4183436, + "ts": 667115415437.179, "dur": 16.362, + "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": 4183436, "tid": 4183436, + "ts": 667115415438.128, "dur": 15.090, + "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": 4183436, "tid": 4183436, + "ts": 667115415457.513, "dur": 21.195, + "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": 4183436, "tid": 4183436, + "ts": 667115415458.141, "dur": 5.086, + "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": 4183436, "tid": 4183436, + "ts": 667115415460.241, "dur": 2.661, + "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": 4183436, "tid": 4183436, + "ts": 667115415463.791, "dur": 14.695, + "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": 4183436, "tid": 4183436, + "ts": 667115415464.509, "dur": 13.583, + "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": 4183436, "tid": 4183436, + "ts": 667115415482.834, "dur": 35.538, + "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": 4183436, "tid": 4183436, + "ts": 667115415484.164, "dur": 3.037, + "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": 4183436, "tid": 4183436, + "ts": 667115415487.841, "dur": 30.269, + "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": 4183436, "tid": 4183436, + "ts": 667115415488.740, "dur": 28.631, + "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": 4183436, "tid": 4183436, + "ts": 667115415525.458, "dur": 25.983, + "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": 4183436, "tid": 4183436, + "ts": 667115415555.621, "dur": 58.001, + "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": 4183436, "tid": 4183436, + "ts": 667115415558.611, "dur": 54.576, + "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": 4183436, "tid": 4183436, + "ts": 667115415564.563, "dur": 0.980, + "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": 4183436, "tid": 4183436, + "ts": 667115415567.413, "dur": 27.611, + "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": 4183436, "tid": 4183436, + "ts": 667115415571.303, "dur": 23.526, + "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": 4183436, "tid": 4183436, + "ts": 667115415574.169, "dur": 3.404, + "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": 4183436, "tid": 4183436, + "ts": 667115415578.396, "dur": 15.986, + "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": 4183436, "tid": 4183436, + "ts": 667115415618.884, "dur": 14970.271, + "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": 4183436, "tid": 4183436, + "ts": 667115415620.255, "dur": 14966.927, + "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": 4183436, "tid": 4183436, + "ts": 667115430604.992, "dur": 9.372, + "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": 4183436, "tid": 4183436, + "ts": 667115430610.513, "dur": 1.670, + "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": 4183436, "tid": 4183436, + "ts": 667115430619.872, "dur": 137.835, + "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": 4183436, "tid": 4183436, + "ts": 667115430621.815, "dur": 8.019, + "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": 4183436, "tid": 4183436, + "ts": 667115430624.768, "dur": 4.162, + "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": 4183436, "tid": 4183436, + "ts": 667115430627.140, "dur": 1.526, + "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": 4183436, "tid": 4183436, + "ts": 667115430631.043, "dur": 125.852, + "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": 4183436, "tid": 4183436, + "ts": 667115430633.511, "dur": 121.920, + "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": 4183436, "tid": 4183436, + "ts": 667115430763.848, "dur": 6.067, + "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": 4183436, "tid": 4183436, + "ts": 667115430766.917, "dur": 1.238, + "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": 4183436, "tid": 4183436, + "ts": 667115430779.618, "dur": 4.157, + "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": 4183436, "tid": 4183436, + "ts": 667115430795.617, "dur": 8.430, + "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": 4183436, "tid": 4183436, + "ts": 667115430798.371, "dur": 5.380, + "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": 4183436, "tid": 4183436, + "ts": 667115430947.918, "dur": 234.150, + "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": 4183436, "tid": 4183436, + "ts": 667115430951.312, "dur": 4.297, + "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": 4183436, "tid": 4183436, + "ts": 667115430958.533, "dur": 222.843, + "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": 4183436, "tid": 4183436, + "ts": 667115430961.478, "dur": 0.860, + "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": 4183436, "tid": 4183436, + "ts": 667115430965.266, "dur": 30.163, + "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": 4183436, "tid": 4183436, + "ts": 667115430997.977, "dur": 6.621, + "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": 4183436, "tid": 4183436, + "ts": 667115431003.214, "dur": 1.068, + "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": 4183436, "tid": 4183436, + "ts": 667115431007.166, "dur": 27.748, + "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": 4183436, "tid": 4183436, + "ts": 667115431008.922, "dur": 1.564, + "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": 4183436, "tid": 4183436, + "ts": 667115431012.645, "dur": 22.016, + "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": 4183436, "tid": 4183436, + "ts": 667115431016.923, "dur": 3.604, + "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": 4183436, "tid": 4183436, + "ts": 667115431037.176, "dur": 25.351, + "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": 4183436, "tid": 4183436, + "ts": 667115431065.287, "dur": 18.166, + "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": 4183436, "tid": 4183436, + "ts": 667115431087.037, "dur": 16.999, + "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": 4183436, "tid": 4183436, + "ts": 667115431106.311, "dur": 14.381, + "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": 4183436, "tid": 4183436, + "ts": 667115431123.716, "dur": 25.877, + "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": 4183436, "tid": 4183436, + "ts": 667115431126.563, "dur": 1.788, + "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": 4183436, "tid": 4183436, + "ts": 667115431131.023, "dur": 2.866, + "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": 4183436, "tid": 4183436, + "ts": 667115431152.144, "dur": 14.277, + "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": 4183436, "tid": 4183436, + "ts": 667115431168.235, "dur": 12.156, + "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": 4183436, "tid": 4183436, + "ts": 667115431188.620, "dur": 2.225, + "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": 4183436, "tid": 4183436, + "ts": 667115431198.432, "dur": 4.640, + "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": 4183436, "tid": 4183436, + "ts": 667115431201.149, "dur": 0.733, + "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": 4183436, "tid": 4183436, + "ts": 667115431284.376, "dur": 61.958, + "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": 4183436, "tid": 4183436, + "ts": 667115431351.896, "dur": 4.899, + "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": 4183436, "tid": 4183436, + "ts": 667115431354.789, "dur": 0.844, + "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": 4183436, "tid": 4183436, + "ts": 667115431358.975, "dur": 27.357, + "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": 4183436, "tid": 4183436, + "ts": 667115431391.307, "dur": 7.607, + "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": 4183436, "tid": 4183436, + "ts": 667115431393.540, "dur": 4.574, + "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": 4183436, "tid": 4183436, + "ts": 667115431395.912, "dur": 1.917, + "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": 4183436, "tid": 4183436, + "ts": 667115431402.224, "dur": 48.267, + "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": 4183436, "tid": 4183436, + "ts": 667115431403.743, "dur": 46.092, + "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": 4183436, "tid": 4183436, + "ts": 667115431455.442, "dur": 17.454, + "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": 4183436, "tid": 4183436, + "ts": 667115431478.558, "dur": 4.225, + "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": 4183436, "tid": 4183436, + "ts": 667115431481.020, "dur": 0.856, + "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": 4183436, "tid": 4183436, + "ts": 667115431486.849, "dur": 86.709, + "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": 4183436, "tid": 4183436, + "ts": 667115431487.929, "dur": 32.340, + "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": 4183436, "tid": 4183436, + "ts": 667115431489.050, "dur": 30.342, + "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": 4183436, "tid": 4183436, + "ts": 667115431517.622, "dur": 1.274, + "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": 4183436, "tid": 4183436, + "ts": 667115431520.986, "dur": 52.022, + "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": 4183436, "tid": 4183436, + "ts": 667115431522.239, "dur": 50.150, + "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": 4183436, "tid": 4183436, + "ts": 667115431579.416, "dur": 4.787, + "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": 4183436, "tid": 4183436, + "ts": 667115431581.886, "dur": 1.056, + "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": 4183436, "tid": 4183436, + "ts": 667115431592.143, "dur": 2.051, + "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": 4183436, "tid": 4183436, + "ts": 667115431603.101, "dur": 9.125, + "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": 4183436, "tid": 4183436, + "ts": 667115431605.748, "dur": 6.179, + "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": 4183436, "tid": 4183436, + "ts": 667115431763.347, "dur": 278.334, + "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": 4183436, "tid": 4183436, + "ts": 667115431766.671, "dur": 3.570, + "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": 4183436, "tid": 4183436, + "ts": 667115431773.127, "dur": 267.968, + "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": 4183436, "tid": 4183436, + "ts": 667115431775.049, "dur": 0.403, + "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": 4183436, "tid": 4183436, + "ts": 667115431776.969, "dur": 27.475, + "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": 4183436, "tid": 4183436, + "ts": 667115431806.293, "dur": 4.595, + "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": 4183436, "tid": 4183436, + "ts": 667115431809.359, "dur": 1.200, + "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": 4183436, "tid": 4183436, + "ts": 667115431812.085, "dur": 32.689, + "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": 4183436, "tid": 4183436, + "ts": 667115431813.204, "dur": 1.998, + "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": 4183436, "tid": 4183436, + "ts": 667115431817.205, "dur": 27.166, + "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": 4183436, "tid": 4183436, + "ts": 667115431822.651, "dur": 3.141, + "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": 4183436, "tid": 4183436, + "ts": 667115431846.784, "dur": 36.434, + "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": 4183436, "tid": 4183436, + "ts": 667115431885.058, "dur": 45.697, + "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": 4183436, "tid": 4183436, + "ts": 667115431934.101, "dur": 28.794, + "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": 4183436, "tid": 4183436, + "ts": 667115431964.848, "dur": 25.402, + "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": 4183436, "tid": 4183436, + "ts": 667115431992.443, "dur": 20.569, + "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": 4183436, "tid": 4183436, + "ts": 667115431994.644, "dur": 2.014, + "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": 4183436, "tid": 4183436, + "ts": 667115431998.815, "dur": 1.013, + "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": 4183436, "tid": 4183436, + "ts": 667115432015.078, "dur": 11.704, + "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": 4183436, "tid": 4183436, + "ts": 667115432027.963, "dur": 12.247, + "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": 4183436, "tid": 4183436, + "ts": 667115432048.729, "dur": 2.661, + "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": 4183436, "tid": 4183436, + "ts": 667115432061.344, "dur": 4.342, + "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": 4183436, "tid": 4183436, + "ts": 667115432064.193, "dur": 0.434, + "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": 4183436, "tid": 4183436, + "ts": 667115432137.877, "dur": 54.472, + "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": 4183436, "tid": 4183436, + "ts": 667115432197.534, "dur": 5.782, + "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": 4183436, "tid": 4183436, + "ts": 667115432201.000, "dur": 1.207, + "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": 4183436, "tid": 4183436, + "ts": 667115432205.201, "dur": 26.491, + "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": 4183436, "tid": 4183436, + "ts": 667115432236.556, "dur": 12.066, + "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": 4183436, "tid": 4183436, + "ts": 667115432244.157, "dur": 3.741, + "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": 4183436, "tid": 4183436, + "ts": 667115432246.526, "dur": 1.139, + "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": 4183436, "tid": 4183436, + "ts": 667115432251.269, "dur": 45.014, + "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": 4183436, "tid": 4183436, + "ts": 667115432252.587, "dur": 43.093, + "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": 4183436, "tid": 4183436, + "ts": 667115432300.610, "dur": 16.185, + "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": 4183436, "tid": 4183436, + "ts": 667115432322.565, "dur": 4.641, + "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": 4183436, "tid": 4183436, + "ts": 667115432325.353, "dur": 0.897, + "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": 4183436, "tid": 4183436, + "ts": 667115432331.522, "dur": 51.657, + "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": 4183436, "tid": 4183436, + "ts": 667115432332.537, "dur": 6.294, + "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": 4183436, "tid": 4183436, + "ts": 667115432333.191, "dur": 5.070, + "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": 4183436, "tid": 4183436, + "ts": 667115432335.201, "dur": 2.866, + "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": 4183436, "tid": 4183436, + "ts": 667115432339.480, "dur": 43.101, + "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": 4183436, "tid": 4183436, + "ts": 667115432340.512, "dur": 41.525, + "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": 4183436, "tid": 4183436, + "ts": 667115432388.719, "dur": 3.936, + "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": 4183436, "tid": 4183436, + "ts": 667115432390.905, "dur": 0.627, + "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": 4183436, "tid": 4183436, + "ts": 667115432398.991, "dur": 1.401, + "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": 4183436, "tid": 4183436, + "ts": 667115432407.764, "dur": 6.207, + "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": 4183436, "tid": 4183436, + "ts": 667115432410.168, "dur": 3.529, + "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": 4183436, "tid": 4183436, + "ts": 667115432522.412, "dur": 236.125, + "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": 4183436, "tid": 4183436, + "ts": 667115432525.072, "dur": 3.173, + "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": 4183436, "tid": 4183436, + "ts": 667115432530.069, "dur": 227.899, + "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": 4183436, "tid": 4183436, + "ts": 667115432532.131, "dur": 0.530, + "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": 4183436, "tid": 4183436, + "ts": 667115432536.397, "dur": 23.870, + "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": 4183436, "tid": 4183436, + "ts": 667115432562.208, "dur": 3.689, + "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": 4183436, "tid": 4183436, + "ts": 667115432564.323, "dur": 1.229, + "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": 4183436, "tid": 4183436, + "ts": 667115432567.169, "dur": 26.001, + "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": 4183436, "tid": 4183436, + "ts": 667115432568.494, "dur": 3.654, + "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": 4183436, "tid": 4183436, + "ts": 667115432573.747, "dur": 19.164, + "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": 4183436, "tid": 4183436, + "ts": 667115432576.888, "dur": 2.736, + "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": 4183436, "tid": 4183436, + "ts": 667115432595.214, "dur": 20.356, + "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": 4183436, "tid": 4183436, + "ts": 667115432616.974, "dur": 14.473, + "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": 4183436, "tid": 4183436, + "ts": 667115432634.200, "dur": 14.534, + "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": 4183436, "tid": 4183436, + "ts": 667115432650.485, "dur": 51.497, + "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": 4183436, "tid": 4183436, + "ts": 667115432704.890, "dur": 24.214, + "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": 4183436, "tid": 4183436, + "ts": 667115432707.124, "dur": 2.153, + "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": 4183436, "tid": 4183436, + "ts": 667115432711.969, "dur": 1.008, + "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": 4183436, "tid": 4183436, + "ts": 667115432730.975, "dur": 13.120, + "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": 4183436, "tid": 4183436, + "ts": 667115432745.461, "dur": 11.425, + "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": 4183436, "tid": 4183436, + "ts": 667115432766.574, "dur": 2.702, + "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": 4183436, "tid": 4183436, + "ts": 667115432779.255, "dur": 4.084, + "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": 4183436, "tid": 4183436, + "ts": 667115432781.941, "dur": 0.533, + "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": 4183436, "tid": 4183436, + "ts": 667115432858.461, "dur": 52.016, + "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": 4183436, "tid": 4183436, + "ts": 667115432916.042, "dur": 5.599, + "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": 4183436, "tid": 4183436, + "ts": 667115432919.366, "dur": 1.241, + "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": 4183436, "tid": 4183436, + "ts": 667115432923.380, "dur": 24.464, + "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": 4183436, "tid": 4183436, + "ts": 667115432952.625, "dur": 6.921, + "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": 4183436, "tid": 4183436, + "ts": 667115432954.489, "dur": 4.070, + "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": 4183436, "tid": 4183436, + "ts": 667115432957.051, "dur": 1.303, + "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": 4183436, "tid": 4183436, + "ts": 667115432962.256, "dur": 42.691, + "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": 4183436, "tid": 4183436, + "ts": 667115432963.241, "dur": 41.202, + "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": 4183436, "tid": 4183436, + "ts": 667115433009.166, "dur": 15.245, + "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": 4183436, "tid": 4183436, + "ts": 667115433030.297, "dur": 4.204, + "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": 4183436, "tid": 4183436, + "ts": 667115433032.897, "dur": 0.739, + "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": 4183436, "tid": 4183436, + "ts": 667115433038.746, "dur": 51.994, + "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": 4183436, "tid": 4183436, + "ts": 667115433040.059, "dur": 6.558, + "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": 4183436, "tid": 4183436, + "ts": 667115433041.048, "dur": 4.933, + "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": 4183436, "tid": 4183436, + "ts": 667115433044.941, "dur": 0.877, + "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": 4183436, "tid": 4183436, + "ts": 667115433047.224, "dur": 43.109, + "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": 4183436, "tid": 4183436, + "ts": 667115433048.263, "dur": 41.568, + "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": 4183436, "tid": 4183436, + "ts": 667115433095.266, "dur": 4.264, + "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": 4183436, "tid": 4183436, + "ts": 667115433097.225, "dur": 1.214, + "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": 4183436, "tid": 4183436, + "ts": 667115433105.568, "dur": 1.700, + "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": 4183436, "tid": 4183436, + "ts": 667115433114.768, "dur": 6.271, + "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": 4183436, "tid": 4183436, + "ts": 667115433116.945, "dur": 3.794, + "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": 4183436, "tid": 4183436, + "ts": 667115433203.813, "dur": 184.364, + "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": 4183436, "tid": 4183436, + "ts": 667115433206.198, "dur": 2.436, + "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": 4183436, "tid": 4183436, + "ts": 667115433210.560, "dur": 177.106, + "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": 4183436, "tid": 4183436, + "ts": 667115433214.537, "dur": 0.395, + "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": 4183436, "tid": 4183436, + "ts": 667115433216.365, "dur": 20.041, + "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": 4183436, "tid": 4183436, + "ts": 667115433238.004, "dur": 3.209, + "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": 4183436, "tid": 4183436, + "ts": 667115433239.992, "dur": 0.964, + "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": 4183436, "tid": 4183436, + "ts": 667115433242.356, "dur": 24.375, + "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": 4183436, "tid": 4183436, + "ts": 667115433245.946, "dur": 1.555, + "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": 4183436, "tid": 4183436, + "ts": 667115433248.756, "dur": 17.694, + "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": 4183436, "tid": 4183436, + "ts": 667115433251.530, "dur": 2.742, + "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": 4183436, "tid": 4183436, + "ts": 667115433268.295, "dur": 20.645, + "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": 4183436, "tid": 4183436, + "ts": 667115433290.434, "dur": 13.120, + "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": 4183436, "tid": 4183436, + "ts": 667115433306.539, "dur": 15.045, + "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": 4183436, "tid": 4183436, + "ts": 667115433323.161, "dur": 13.373, + "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": 4183436, "tid": 4183436, + "ts": 667115433338.115, "dur": 21.092, + "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": 4183436, "tid": 4183436, + "ts": 667115433339.816, "dur": 1.738, + "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": 4183436, "tid": 4183436, + "ts": 667115433344.670, "dur": 0.765, + "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": 4183436, "tid": 4183436, + "ts": 667115433360.834, "dur": 12.584, + "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": 4183436, "tid": 4183436, + "ts": 667115433374.522, "dur": 11.852, + "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": 4183436, "tid": 4183436, + "ts": 667115433394.210, "dur": 1.884, + "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": 4183436, "tid": 4183436, + "ts": 667115433403.609, "dur": 4.141, + "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": 4183436, "tid": 4183436, + "ts": 667115433406.009, "dur": 0.823, + "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": 4183436, "tid": 4183436, + "ts": 667115433469.966, "dur": 61.390, + "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": 4183436, "tid": 4183436, + "ts": 667115433538.267, "dur": 8.845, + "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": 4183436, "tid": 4183436, + "ts": 667115433542.076, "dur": 3.477, + "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": 4183436, "tid": 4183436, + "ts": 667115433548.658, "dur": 27.910, + "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": 4183436, "tid": 4183436, + "ts": 667115433581.864, "dur": 6.172, + "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": 4183436, "tid": 4183436, + "ts": 667115433583.234, "dur": 3.832, + "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": 4183436, "tid": 4183436, + "ts": 667115433585.894, "dur": 0.999, + "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": 4183436, "tid": 4183436, + "ts": 667115433590.610, "dur": 45.546, + "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": 4183436, "tid": 4183436, + "ts": 667115433592.086, "dur": 43.412, + "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": 4183436, "tid": 4183436, + "ts": 667115433640.283, "dur": 49.384, + "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": 4183436, "tid": 4183436, + "ts": 667115433698.143, "dur": 5.095, + "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": 4183436, "tid": 4183436, + "ts": 667115433700.904, "dur": 1.241, + "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": 4183436, "tid": 4183436, + "ts": 667115433708.011, "dur": 54.746, + "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": 4183436, "tid": 4183436, + "ts": 667115433709.169, "dur": 4.991, + "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": 4183436, "tid": 4183436, + "ts": 667115433710.596, "dur": 2.953, + "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": 4183436, "tid": 4183436, + "ts": 667115433712.389, "dur": 0.933, + "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": 4183436, "tid": 4183436, + "ts": 667115433715.098, "dur": 47.315, + "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": 4183436, "tid": 4183436, + "ts": 667115433715.667, "dur": 46.108, + "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": 4183436, "tid": 4183436, + "ts": 667115433767.535, "dur": 4.829, + "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": 4183436, "tid": 4183436, + "ts": 667115433769.786, "dur": 1.386, + "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": 4183436, "tid": 4183436, + "ts": 667115433778.624, "dur": 1.977, + "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": 4183436, "tid": 4183436, + "ts": 667115433788.188, "dur": 7.208, + "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": 4183436, "tid": 4183436, + "ts": 667115433790.411, "dur": 4.700, + "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": 4183436, "tid": 4183436, + "ts": 667115433881.603, "dur": 191.859, + "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": 4183436, "tid": 4183436, + "ts": 667115433883.983, "dur": 4.084, + "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": 4183436, "tid": 4183436, + "ts": 667115433890.068, "dur": 182.899, + "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": 4183436, "tid": 4183436, + "ts": 667115433891.903, "dur": 0.608, + "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": 4183436, "tid": 4183436, + "ts": 667115433893.918, "dur": 23.521, + "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": 4183436, "tid": 4183436, + "ts": 667115433919.299, "dur": 5.790, + "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": 4183436, "tid": 4183436, + "ts": 667115433924.082, "dur": 0.752, + "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": 4183436, "tid": 4183436, + "ts": 667115433925.967, "dur": 23.543, + "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": 4183436, "tid": 4183436, + "ts": 667115433927.673, "dur": 1.508, + "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": 4183436, "tid": 4183436, + "ts": 667115433930.670, "dur": 18.566, + "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": 4183436, "tid": 4183436, + "ts": 667115433933.451, "dur": 2.836, + "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": 4183436, "tid": 4183436, + "ts": 667115433951.013, "dur": 20.098, + "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": 4183436, "tid": 4183436, + "ts": 667115433972.574, "dur": 14.400, + "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": 4183436, "tid": 4183436, + "ts": 667115433989.813, "dur": 14.693, + "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": 4183436, "tid": 4183436, + "ts": 667115434005.893, "dur": 13.581, + "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": 4183436, "tid": 4183436, + "ts": 667115434021.205, "dur": 22.384, + "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": 4183436, "tid": 4183436, + "ts": 667115434023.283, "dur": 1.618, + "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": 4183436, "tid": 4183436, + "ts": 667115434027.030, "dur": 2.954, + "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": 4183436, "tid": 4183436, + "ts": 667115434045.240, "dur": 13.308, + "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": 4183436, "tid": 4183436, + "ts": 667115434059.866, "dur": 11.690, + "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": 4183436, "tid": 4183436, + "ts": 667115434079.180, "dur": 1.897, + "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": 4183436, "tid": 4183436, + "ts": 667115434100.960, "dur": 3.961, + "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": 4183436, "tid": 4183436, + "ts": 667115434103.499, "dur": 0.659, + "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": 4183436, "tid": 4183436, + "ts": 667115434168.396, "dur": 41.846, + "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": 4183436, "tid": 4183436, + "ts": 667115434214.770, "dur": 4.963, + "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": 4183436, "tid": 4183436, + "ts": 667115434217.748, "dur": 0.883, + "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": 4183436, "tid": 4183436, + "ts": 667115434221.216, "dur": 21.870, + "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": 4183436, "tid": 4183436, + "ts": 667115434247.709, "dur": 8.078, + "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": 4183436, "tid": 4183436, + "ts": 667115434249.237, "dur": 5.834, + "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": 4183436, "tid": 4183436, + "ts": 667115434251.711, "dur": 3.147, + "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": 4183436, "tid": 4183436, + "ts": 667115434258.212, "dur": 42.572, + "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": 4183436, "tid": 4183436, + "ts": 667115434259.645, "dur": 40.472, + "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": 4183436, "tid": 4183436, + "ts": 667115434304.575, "dur": 16.854, + "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": 4183436, "tid": 4183436, + "ts": 667115434326.699, "dur": 4.138, + "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": 4183436, "tid": 4183436, + "ts": 667115434329.103, "dur": 0.971, + "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": 4183436, "tid": 4183436, + "ts": 667115434334.793, "dur": 48.796, + "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": 4183436, "tid": 4183436, + "ts": 667115434335.582, "dur": 4.772, + "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": 4183436, "tid": 4183436, + "ts": 667115434336.838, "dur": 2.836, + "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": 4183436, "tid": 4183436, + "ts": 667115434338.629, "dur": 0.907, + "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": 4183436, "tid": 4183436, + "ts": 667115434341.468, "dur": 41.663, + "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": 4183436, "tid": 4183436, + "ts": 667115434342.042, "dur": 40.605, + "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": 4183436, "tid": 4183436, + "ts": 667115434387.419, "dur": 3.835, + "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": 4183436, "tid": 4183436, + "ts": 667115434389.189, "dur": 0.812, + "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": 4183436, "tid": 4183436, + "ts": 667115434396.363, "dur": 1.224, + "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": 4183436, "tid": 4183436, + "ts": 667115434404.432, "dur": 6.297, + "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": 4183436, "tid": 4183436, + "ts": 667115434406.525, "dur": 3.959, + "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": 4183436, "tid": 4183436, + "ts": 667115434486.644, "dur": 349.800, + "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": 4183436, "tid": 4183436, + "ts": 667115434488.413, "dur": 21.200, + "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": 4183436, "tid": 4183436, + "ts": 667115434514.785, "dur": 320.723, + "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": 4183436, "tid": 4183436, + "ts": 667115434516.587, "dur": 0.507, + "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": 4183436, "tid": 4183436, + "ts": 667115434518.575, "dur": 26.446, + "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": 4183436, "tid": 4183436, + "ts": 667115434546.547, "dur": 5.970, + "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": 4183436, "tid": 4183436, + "ts": 667115434548.732, "dur": 3.424, + "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": 4183436, "tid": 4183436, + "ts": 667115434553.585, "dur": 55.014, + "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": 4183436, "tid": 4183436, + "ts": 667115434554.872, "dur": 1.863, + "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": 4183436, "tid": 4183436, + "ts": 667115434584.172, "dur": 24.170, + "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": 4183436, "tid": 4183436, + "ts": 667115434588.452, "dur": 2.631, + "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": 4183436, "tid": 4183436, + "ts": 667115434609.984, "dur": 34.672, + "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": 4183436, "tid": 4183436, + "ts": 667115434646.187, "dur": 51.334, + "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": 4183436, "tid": 4183436, + "ts": 667115434701.732, "dur": 34.519, + "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": 4183436, "tid": 4183436, + "ts": 667115434737.977, "dur": 28.405, + "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": 4183436, "tid": 4183436, + "ts": 667115434768.262, "dur": 26.890, + "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": 4183436, "tid": 4183436, + "ts": 667115434770.050, "dur": 2.015, + "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": 4183436, "tid": 4183436, + "ts": 667115434774.435, "dur": 0.908, + "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": 4183436, "tid": 4183436, + "ts": 667115434797.434, "dur": 17.426, + "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": 4183436, "tid": 4183436, + "ts": 667115434816.740, "dur": 16.911, + "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": 4183436, "tid": 4183436, + "ts": 667115434847.329, "dur": 3.536, + "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": 4183436, "tid": 4183436, + "ts": 667115434865.403, "dur": 7.043, + "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": 4183436, "tid": 4183436, + "ts": 667115434870.135, "dur": 0.700, + "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": 4183436, "tid": 4183436, + "ts": 667115434982.821, "dur": 77.936, + "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": 4183436, "tid": 4183436, + "ts": 667115435068.749, "dur": 7.085, + "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": 4183436, "tid": 4183436, + "ts": 667115435073.272, "dur": 1.047, + "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": 4183436, "tid": 4183436, + "ts": 667115435078.475, "dur": 33.652, + "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": 4183436, "tid": 4183436, + "ts": 667115435119.792, "dur": 8.440, + "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": 4183436, "tid": 4183436, + "ts": 667115435122.407, "dur": 4.773, + "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": 4183436, "tid": 4183436, + "ts": 667115435125.057, "dur": 1.752, + "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": 4183436, "tid": 4183436, + "ts": 667115435132.565, "dur": 62.128, + "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": 4183436, "tid": 4183436, + "ts": 667115435134.198, "dur": 59.613, + "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": 4183436, "tid": 4183436, + "ts": 667115435200.402, "dur": 22.128, + "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": 4183436, "tid": 4183436, + "ts": 667115435231.713, "dur": 6.140, + "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": 4183436, "tid": 4183436, + "ts": 667115435235.160, "dur": 1.285, + "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": 4183436, "tid": 4183436, + "ts": 667115435243.581, "dur": 68.609, + "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": 4183436, "tid": 4183436, + "ts": 667115435245.091, "dur": 6.031, + "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": 4183436, "tid": 4183436, + "ts": 667115435246.393, "dur": 3.941, + "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": 4183436, "tid": 4183436, + "ts": 667115435248.629, "dur": 1.439, + "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": 4183436, "tid": 4183436, + "ts": 667115435252.383, "dur": 59.205, + "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": 4183436, "tid": 4183436, + "ts": 667115435253.585, "dur": 56.933, + "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": 4183436, "tid": 4183436, + "ts": 667115435318.388, "dur": 5.500, + "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": 4183436, "tid": 4183436, + "ts": 667115435321.030, "dur": 1.281, + "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": 4183436, "tid": 4183436, + "ts": 667115435332.708, "dur": 2.162, + "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": 4183436, "tid": 4183436, + "ts": 667115435345.566, "dur": 11.268, + "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": 4183436, "tid": 4183436, + "ts": 667115435348.737, "dur": 7.605, + "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": 4183436, "tid": 4183436, + "ts": 667115435481.005, "dur": 271.879, + "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": 4183436, "tid": 4183436, + "ts": 667115435483.727, "dur": 3.501, + "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": 4183436, "tid": 4183436, + "ts": 667115435489.900, "dur": 262.308, + "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": 4183436, "tid": 4183436, + "ts": 667115435507.638, "dur": 0.586, + "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": 4183436, "tid": 4183436, + "ts": 667115435510.679, "dur": 35.814, + "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": 4183436, "tid": 4183436, + "ts": 667115435548.776, "dur": 3.690, + "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": 4183436, "tid": 4183436, + "ts": 667115435551.056, "dur": 1.123, + "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": 4183436, "tid": 4183436, + "ts": 667115435554.343, "dur": 26.273, + "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": 4183436, "tid": 4183436, + "ts": 667115435555.696, "dur": 2.082, + "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": 4183436, "tid": 4183436, + "ts": 667115435559.275, "dur": 21.029, + "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": 4183436, "tid": 4183436, + "ts": 667115435565.338, "dur": 2.440, + "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": 4183436, "tid": 4183436, + "ts": 667115435582.486, "dur": 21.830, + "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": 4183436, "tid": 4183436, + "ts": 667115435606.017, "dur": 14.991, + "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": 4183436, "tid": 4183436, + "ts": 667115435630.623, "dur": 14.711, + "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": 4183436, "tid": 4183436, + "ts": 667115435646.735, "dur": 48.724, + "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": 4183436, "tid": 4183436, + "ts": 667115435698.527, "dur": 23.350, + "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": 4183436, "tid": 4183436, + "ts": 667115435700.855, "dur": 2.166, + "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": 4183436, "tid": 4183436, + "ts": 667115435705.528, "dur": 1.116, + "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": 4183436, "tid": 4183436, + "ts": 667115435723.914, "dur": 13.965, + "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": 4183436, "tid": 4183436, + "ts": 667115435739.128, "dur": 11.227, + "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": 4183436, "tid": 4183436, + "ts": 667115435762.156, "dur": 3.236, + "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": 4183436, "tid": 4183436, + "ts": 667115435777.034, "dur": 4.575, + "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": 4183436, "tid": 4183436, + "ts": 667115435779.874, "dur": 0.690, + "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": 4183436, "tid": 4183436, + "ts": 667115435863.831, "dur": 58.087, + "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": 4183436, "tid": 4183436, + "ts": 667115435927.335, "dur": 6.750, + "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": 4183436, "tid": 4183436, + "ts": 667115435929.997, "dur": 2.982, + "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": 4183436, "tid": 4183436, + "ts": 667115435935.924, "dur": 25.886, + "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": 4183436, "tid": 4183436, + "ts": 667115435966.860, "dur": 6.152, + "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": 4183436, "tid": 4183436, + "ts": 667115435968.675, "dur": 3.558, + "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": 4183436, "tid": 4183436, + "ts": 667115435970.948, "dur": 1.077, + "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": 4183436, "tid": 4183436, + "ts": 667115435976.098, "dur": 46.802, + "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": 4183436, "tid": 4183436, + "ts": 667115435977.814, "dur": 44.543, + "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": 4183436, "tid": 4183436, + "ts": 667115436027.220, "dur": 15.563, + "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": 4183436, "tid": 4183436, + "ts": 667115436048.886, "dur": 4.651, + "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": 4183436, "tid": 4183436, + "ts": 667115436051.537, "dur": 0.962, + "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": 4183436, "tid": 4183436, + "ts": 667115436058.207, "dur": 50.967, + "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": 4183436, "tid": 4183436, + "ts": 667115436059.073, "dur": 5.069, + "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": 4183436, "tid": 4183436, + "ts": 667115436060.187, "dur": 3.329, + "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": 4183436, "tid": 4183436, + "ts": 667115436062.436, "dur": 0.946, + "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": 4183436, "tid": 4183436, + "ts": 667115436065.007, "dur": 43.786, + "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": 4183436, "tid": 4183436, + "ts": 667115436065.815, "dur": 42.380, + "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": 4183436, "tid": 4183436, + "ts": 667115436113.386, "dur": 4.401, + "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": 4183436, "tid": 4183436, + "ts": 667115436115.567, "dur": 0.795, + "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": 4183436, "tid": 4183436, + "ts": 667115436123.329, "dur": 1.610, + "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": 4183436, "tid": 4183436, + "ts": 667115436133.412, "dur": 7.440, + "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": 4183436, "tid": 4183436, + "ts": 667115436136.008, "dur": 4.562, + "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": 4183436, "tid": 4183436, + "ts": 667115436229.368, "dur": 189.561, + "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": 4183436, "tid": 4183436, + "ts": 667115436231.317, "dur": 4.282, + "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": 4183436, "tid": 4183436, + "ts": 667115436237.619, "dur": 180.719, + "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": 4183436, "tid": 4183436, + "ts": 667115436239.365, "dur": 0.509, + "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": 4183436, "tid": 4183436, + "ts": 667115436241.270, "dur": 20.694, + "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": 4183436, "tid": 4183436, + "ts": 667115436263.520, "dur": 5.819, + "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": 4183436, "tid": 4183436, + "ts": 667115436268.501, "dur": 0.573, + "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": 4183436, "tid": 4183436, + "ts": 667115436270.449, "dur": 23.953, + "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": 4183436, "tid": 4183436, + "ts": 667115436271.977, "dur": 1.509, + "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": 4183436, "tid": 4183436, + "ts": 667115436274.789, "dur": 19.363, + "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": 4183436, "tid": 4183436, + "ts": 667115436277.100, "dur": 2.394, + "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": 4183436, "tid": 4183436, + "ts": 667115436295.998, "dur": 21.006, + "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": 4183436, "tid": 4183436, + "ts": 667115436318.604, "dur": 12.892, + "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": 4183436, "tid": 4183436, + "ts": 667115436334.104, "dur": 15.737, + "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": 4183436, "tid": 4183436, + "ts": 667115436351.439, "dur": 12.796, + "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": 4183436, "tid": 4183436, + "ts": 667115436365.917, "dur": 24.476, + "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": 4183436, "tid": 4183436, + "ts": 667115436370.017, "dur": 1.744, + "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": 4183436, "tid": 4183436, + "ts": 667115436374.259, "dur": 0.740, + "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": 4183436, "tid": 4183436, + "ts": 667115436392.213, "dur": 13.131, + "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": 4183436, "tid": 4183436, + "ts": 667115436406.376, "dur": 11.199, + "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": 4183436, "tid": 4183436, + "ts": 667115436425.028, "dur": 1.752, + "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": 4183436, "tid": 4183436, + "ts": 667115436434.568, "dur": 3.828, + "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": 4183436, "tid": 4183436, + "ts": 667115436437.114, "dur": 0.417, + "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": 4183436, "tid": 4183436, + "ts": 667115436520.345, "dur": 48.942, + "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": 4183436, "tid": 4183436, + "ts": 667115436575.120, "dur": 5.447, + "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": 4183436, "tid": 4183436, + "ts": 667115436578.245, "dur": 0.829, + "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": 4183436, "tid": 4183436, + "ts": 667115436582.384, "dur": 26.019, + "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": 4183436, "tid": 4183436, + "ts": 667115436612.939, "dur": 5.991, + "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": 4183436, "tid": 4183436, + "ts": 667115436614.840, "dur": 3.478, + "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": 4183436, "tid": 4183436, + "ts": 667115436616.910, "dur": 1.200, + "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": 4183436, "tid": 4183436, + "ts": 667115436621.522, "dur": 79.797, + "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": 4183436, "tid": 4183436, + "ts": 667115436622.618, "dur": 77.521, + "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": 4183436, "tid": 4183436, + "ts": 667115436707.295, "dur": 18.582, + "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": 4183436, "tid": 4183436, + "ts": 667115436732.149, "dur": 25.147, + "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": 4183436, "tid": 4183436, + "ts": 667115436734.578, "dur": 22.372, + "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": 4183436, "tid": 4183436, + "ts": 667115436739.962, "dur": 1.068, + "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": 4183436, "tid": 4183436, + "ts": 667115436763.380, "dur": 31.117, + "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": 4183436, "tid": 4183436, + "ts": 667115436765.553, "dur": 28.675, + "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": 4183436, "tid": 4183436, + "ts": 667115436770.397, "dur": 4.065, + "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": 4183436, "tid": 4183436, + "ts": 667115436775.843, "dur": 17.889, + "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": 4183436, "tid": 4183436, + "ts": 667115436810.339, "dur": 5.635, + "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": 4183436, "tid": 4183436, + "ts": 667115436812.774, "dur": 2.968, + "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": 4183436, "tid": 4183436, + "ts": 667115436817.055, "dur": 1.295, + "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": 4183436, "tid": 4183436, + "ts": 667115436817.779, "dur": 0.455, + "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": 4183436, "tid": 4183436, + "ts": 667115436858.915, "dur": 23.229, + "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": 4183436, "tid": 4183436, "ts": 667115436858.915, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183436, "tid": 4183436, + "ts": 667115436888.477, "dur": 6.926, + "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": 4183436, "tid": 4183436, + "ts": 667115436892.564, "dur": 1.308, + "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": 4183436, "tid": 4183436, + "ts": 667115436898.159, "dur": 6.422, + "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": 4183436, "tid": 4183436, + "ts": 667115436902.590, "dur": 0.830, + "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": 4183436, "tid": 4183436, + "ts": 667115436906.003, "dur": 3.078, + "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": 4183436, "tid": 4183436, + "ts": 667115436907.758, "dur": 0.784, + "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": 4183436, "tid": 4183436, + "ts": 667115436914.015, "dur": 6.533, + "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": 4183436, "tid": 4183436, "ts": 667115436914.015, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115436917.923, "dur": 1.112, + "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": 4183436, "tid": 4183436, + "ts": 667115436921.534, "dur": 5.149, + "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": 4183436, "tid": 4183436, "ts": 667115436921.534, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115436925.038, "dur": 0.892, + "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": 4183436, "tid": 4183436, + "ts": 667115436927.702, "dur": 5.903, + "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": 4183436, "tid": 4183436, "ts": 667115436927.702, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115436931.799, "dur": 0.970, + "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": 4183436, "tid": 4183436, + "ts": 667115436934.572, "dur": 4.110, + "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": 4183436, "tid": 4183436, "ts": 667115436934.572, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115436936.992, "dur": 0.937, + "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": 4183436, "tid": 4183436, + "ts": 667115436942.426, "dur": 31.874, + "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": 4183436, "tid": 4183436, + "ts": 667115436944.202, "dur": 29.880, + "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": 4183436, "tid": 4183436, + "ts": 667115436946.461, "dur": 9.331, + "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": 4183436, "tid": 4183436, + "ts": 667115436949.410, "dur": 5.737, + "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": 4183436, "tid": 4183436, + "ts": 667115436956.764, "dur": 16.870, + "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": 4183436, "tid": 4183436, + "ts": 667115437000.690, "dur": 4.935, + "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": 4183436, "tid": 4183436, "ts": 667115437000.690, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115437008.169, "dur": 1.364, + "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": 4183436, "tid": 4183436, + "ts": 667115437041.228, "dur": 22653.064, + "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": 4183436, "tid": 4183436, "ts": 667115437041.228, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 4183436, + "ts": 667115437055.572, "dur": 25.116, + "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": 4183436, "tid": 4183436, + "ts": 667115437056.656, "dur": 23.817, + "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": 4183436, "tid": 4183436, + "ts": 667115437058.277, "dur": 5.838, + "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": 4183436, "tid": 4183436, + "ts": 667115437059.749, "dur": 3.904, + "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": 4183436, "tid": 4183436, + "ts": 667115437064.769, "dur": 15.377, + "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": 4183436, "tid": 4183436, + "ts": 667115437095.973, "dur": 24.847, + "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": 4183436, "tid": 4183436, + "ts": 667115437097.469, "dur": 5.685, + "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": 4183436, "tid": 4183436, + "ts": 667115437099.553, "dur": 3.209, + "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": 4183436, "tid": 4183436, + "ts": 667115437104.400, "dur": 16.204, + "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": 4183436, "tid": 4183436, + "ts": 667115437106.374, "dur": 13.799, + "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": 4183436, "tid": 4183436, + "ts": 667115437124.053, "dur": 24.204, + "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": 4183436, "tid": 4183436, + "ts": 667115437124.779, "dur": 5.202, + "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": 4183436, "tid": 4183436, + "ts": 667115437126.264, "dur": 3.502, + "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": 4183436, "tid": 4183436, + "ts": 667115437131.077, "dur": 16.975, + "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": 4183436, "tid": 4183436, + "ts": 667115437131.584, "dur": 16.026, + "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": 4183436, "tid": 4183436, + "ts": 667115437153.873, "dur": 16.364, + "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": 4183436, "tid": 4183436, + "ts": 667115437155.631, "dur": 2.846, + "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": 4183436, "tid": 4183436, + "ts": 667115437159.154, "dur": 10.812, + "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": 4183436, "tid": 4183436, + "ts": 667115437160.003, "dur": 9.599, + "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": 4183436, "tid": 4183436, + "ts": 667115437175.428, "dur": 20.847, + "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": 4183436, "tid": 4183436, + "ts": 667115437199.031, "dur": 44.555, + "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": 4183436, "tid": 4183436, + "ts": 667115437200.956, "dur": 42.222, + "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": 4183436, "tid": 4183436, + "ts": 667115437205.159, "dur": 0.957, + "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": 4183436, "tid": 4183436, + "ts": 667115437207.629, "dur": 21.682, + "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": 4183436, "tid": 4183436, + "ts": 667115437208.950, "dur": 20.178, + "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": 4183436, "tid": 4183436, + "ts": 667115437213.582, "dur": 2.849, + "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": 4183436, "tid": 4183436, + "ts": 667115437217.286, "dur": 11.580, + "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": 4183436, "tid": 4183436, + "ts": 667115437247.547, "dur": 16454.875, + "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": 4183436, "tid": 4183436, + "ts": 667115437248.804, "dur": 16451.833, + "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": 4183436, "tid": 4183436, + "ts": 667115453717.467, "dur": 8.498, + "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": 4183436, "tid": 4183436, + "ts": 667115453722.855, "dur": 1.161, + "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": 4183436, "tid": 4183436, + "ts": 667115453731.768, "dur": 112.358, + "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": 4183436, "tid": 4183436, + "ts": 667115453733.558, "dur": 7.247, + "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": 4183436, "tid": 4183436, + "ts": 667115453735.892, "dur": 3.938, + "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": 4183436, "tid": 4183436, + "ts": 667115453738.369, "dur": 1.152, + "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": 4183436, "tid": 4183436, + "ts": 667115453742.178, "dur": 101.176, + "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": 4183436, "tid": 4183436, + "ts": 667115453744.184, "dur": 98.158, + "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": 4183436, "tid": 4183436, + "ts": 667115453848.236, "dur": 4.731, + "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": 4183436, "tid": 4183436, + "ts": 667115453850.486, "dur": 0.869, + "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": 4183436, "tid": 4183436, + "ts": 667115453861.805, "dur": 2.789, + "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": 4183436, "tid": 4183436, + "ts": 667115453875.552, "dur": 7.913, + "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": 4183436, "tid": 4183436, + "ts": 667115453878.258, "dur": 4.909, + "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": 4183436, "tid": 4183436, + "ts": 667115454018.845, "dur": 226.524, + "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": 4183436, "tid": 4183436, + "ts": 667115454022.796, "dur": 2.789, + "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": 4183436, "tid": 4183436, + "ts": 667115454030.216, "dur": 214.554, + "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": 4183436, "tid": 4183436, + "ts": 667115454032.369, "dur": 0.468, + "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": 4183436, "tid": 4183436, + "ts": 667115454034.789, "dur": 28.186, + "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": 4183436, "tid": 4183436, + "ts": 667115454065.077, "dur": 5.856, + "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": 4183436, "tid": 4183436, + "ts": 667115454067.601, "dur": 2.939, + "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": 4183436, "tid": 4183436, + "ts": 667115454072.233, "dur": 38.097, + "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": 4183436, "tid": 4183436, + "ts": 667115454086.261, "dur": 1.732, + "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": 4183436, "tid": 4183436, + "ts": 667115454090.157, "dur": 19.916, + "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": 4183436, "tid": 4183436, + "ts": 667115454094.208, "dur": 3.211, + "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": 4183436, "tid": 4183436, + "ts": 667115454112.343, "dur": 23.491, + "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": 4183436, "tid": 4183436, + "ts": 667115454137.724, "dur": 18.483, + "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": 4183436, "tid": 4183436, + "ts": 667115454159.194, "dur": 15.688, + "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": 4183436, "tid": 4183436, + "ts": 667115454176.975, "dur": 14.989, + "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": 4183436, "tid": 4183436, + "ts": 667115454194.134, "dur": 21.243, + "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": 4183436, "tid": 4183436, + "ts": 667115454196.170, "dur": 1.542, + "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": 4183436, "tid": 4183436, + "ts": 667115454200.301, "dur": 1.045, + "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": 4183436, "tid": 4183436, + "ts": 667115454217.075, "dur": 13.978, + "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": 4183436, "tid": 4183436, + "ts": 667115454232.492, "dur": 11.396, + "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": 4183436, "tid": 4183436, + "ts": 667115454251.872, "dur": 2.405, + "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": 4183436, "tid": 4183436, + "ts": 667115454261.459, "dur": 4.917, + "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": 4183436, "tid": 4183436, + "ts": 667115454264.229, "dur": 0.972, + "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": 4183436, "tid": 4183436, + "ts": 667115454344.370, "dur": 59.337, + "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": 4183436, "tid": 4183436, + "ts": 667115454408.949, "dur": 6.653, + "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": 4183436, "tid": 4183436, + "ts": 667115454411.971, "dur": 0.915, + "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": 4183436, "tid": 4183436, + "ts": 667115454417.568, "dur": 26.204, + "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": 4183436, "tid": 4183436, + "ts": 667115454449.351, "dur": 6.868, + "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": 4183436, "tid": 4183436, + "ts": 667115454451.352, "dur": 3.976, + "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": 4183436, "tid": 4183436, + "ts": 667115454453.831, "dur": 1.283, + "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": 4183436, "tid": 4183436, + "ts": 667115454459.205, "dur": 67.170, + "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": 4183436, "tid": 4183436, + "ts": 667115454460.630, "dur": 64.614, + "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": 4183436, "tid": 4183436, + "ts": 667115454532.289, "dur": 17.943, + "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": 4183436, "tid": 4183436, + "ts": 667115454557.713, "dur": 4.558, + "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": 4183436, "tid": 4183436, + "ts": 667115454560.267, "dur": 0.825, + "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": 4183436, "tid": 4183436, + "ts": 667115454567.420, "dur": 55.684, + "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": 4183436, "tid": 4183436, + "ts": 667115454568.876, "dur": 4.944, + "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": 4183436, "tid": 4183436, + "ts": 667115454570.010, "dur": 3.184, + "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": 4183436, "tid": 4183436, + "ts": 667115454572.070, "dur": 0.876, + "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": 4183436, "tid": 4183436, + "ts": 667115454574.765, "dur": 47.825, + "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": 4183436, "tid": 4183436, + "ts": 667115454575.364, "dur": 46.626, + "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": 4183436, "tid": 4183436, + "ts": 667115454627.323, "dur": 3.697, + "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": 4183436, "tid": 4183436, + "ts": 667115454629.079, "dur": 0.749, + "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": 4183436, "tid": 4183436, + "ts": 667115454638.129, "dur": 2.094, + "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": 4183436, "tid": 4183436, + "ts": 667115454649.304, "dur": 45.895, + "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": 4183436, "tid": 4183436, + "ts": 667115454686.927, "dur": 7.728, + "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": 4183436, "tid": 4183436, + "ts": 667115454803.279, "dur": 319.176, + "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": 4183436, "tid": 4183436, + "ts": 667115454805.893, "dur": 2.029, + "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": 4183436, "tid": 4183436, + "ts": 667115454809.395, "dur": 312.566, + "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": 4183436, "tid": 4183436, + "ts": 667115454811.774, "dur": 0.515, + "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": 4183436, "tid": 4183436, + "ts": 667115454813.950, "dur": 26.667, + "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": 4183436, "tid": 4183436, + "ts": 667115454842.548, "dur": 3.452, + "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": 4183436, "tid": 4183436, + "ts": 667115454844.877, "dur": 0.811, + "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": 4183436, "tid": 4183436, + "ts": 667115454847.160, "dur": 25.760, + "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": 4183436, "tid": 4183436, + "ts": 667115454848.363, "dur": 1.657, + "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": 4183436, "tid": 4183436, + "ts": 667115454851.280, "dur": 21.285, + "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": 4183436, "tid": 4183436, + "ts": 667115454856.732, "dur": 2.861, + "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": 4183436, "tid": 4183436, + "ts": 667115454874.896, "dur": 26.455, + "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": 4183436, "tid": 4183436, + "ts": 667115454903.084, "dur": 18.200, + "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": 4183436, "tid": 4183436, + "ts": 667115454924.332, "dur": 36.710, + "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": 4183436, "tid": 4183436, + "ts": 667115454962.508, "dur": 38.312, + "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": 4183436, "tid": 4183436, + "ts": 667115455002.723, "dur": 43.324, + "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": 4183436, "tid": 4183436, + "ts": 667115455004.578, "dur": 1.706, + "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": 4183436, "tid": 4183436, + "ts": 667115455009.123, "dur": 0.888, + "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": 4183436, "tid": 4183436, + "ts": 667115455047.716, "dur": 45.531, + "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": 4183436, "tid": 4183436, + "ts": 667115455094.683, "dur": 26.253, + "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": 4183436, "tid": 4183436, + "ts": 667115455129.175, "dur": 2.836, + "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": 4183436, "tid": 4183436, + "ts": 667115455141.569, "dur": 4.315, + "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": 4183436, "tid": 4183436, + "ts": 667115455144.299, "dur": 0.508, + "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": 4183436, "tid": 4183436, + "ts": 667115455215.006, "dur": 52.146, + "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": 4183436, "tid": 4183436, + "ts": 667115455271.959, "dur": 5.345, + "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": 4183436, "tid": 4183436, + "ts": 667115455274.842, "dur": 1.359, + "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": 4183436, "tid": 4183436, + "ts": 667115455278.681, "dur": 25.538, + "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": 4183436, "tid": 4183436, + "ts": 667115455309.161, "dur": 5.662, + "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": 4183436, "tid": 4183436, + "ts": 667115455310.524, "dur": 3.617, + "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": 4183436, "tid": 4183436, + "ts": 667115455312.640, "dur": 1.285, + "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": 4183436, "tid": 4183436, + "ts": 667115455317.596, "dur": 43.170, + "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": 4183436, "tid": 4183436, + "ts": 667115455319.027, "dur": 41.018, + "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": 4183436, "tid": 4183436, + "ts": 667115455364.452, "dur": 15.085, + "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": 4183436, "tid": 4183436, + "ts": 667115455385.229, "dur": 4.293, + "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": 4183436, "tid": 4183436, + "ts": 667115455387.826, "dur": 0.916, + "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": 4183436, "tid": 4183436, + "ts": 667115455393.882, "dur": 63.010, + "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": 4183436, "tid": 4183436, + "ts": 667115455394.829, "dur": 6.117, + "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": 4183436, "tid": 4183436, + "ts": 667115455395.871, "dur": 4.390, + "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": 4183436, "tid": 4183436, + "ts": 667115455397.456, "dur": 2.618, + "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": 4183436, "tid": 4183436, + "ts": 667115455413.664, "dur": 42.697, + "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": 4183436, "tid": 4183436, + "ts": 667115455415.200, "dur": 40.511, + "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": 4183436, "tid": 4183436, + "ts": 667115455461.592, "dur": 3.906, + "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": 4183436, "tid": 4183436, + "ts": 667115455463.763, "dur": 0.595, + "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": 4183436, "tid": 4183436, + "ts": 667115455471.634, "dur": 1.604, + "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": 4183436, "tid": 4183436, + "ts": 667115455481.260, "dur": 5.687, + "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": 4183436, "tid": 4183436, + "ts": 667115455483.248, "dur": 3.437, + "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": 4183436, "tid": 4183436, + "ts": 667115455597.280, "dur": 229.423, + "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": 4183436, "tid": 4183436, + "ts": 667115455602.270, "dur": 3.006, + "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": 4183436, "tid": 4183436, + "ts": 667115455607.087, "dur": 218.819, + "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": 4183436, "tid": 4183436, + "ts": 667115455608.798, "dur": 0.410, + "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": 4183436, "tid": 4183436, + "ts": 667115455610.561, "dur": 22.075, + "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": 4183436, "tid": 4183436, + "ts": 667115455634.568, "dur": 5.556, + "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": 4183436, "tid": 4183436, + "ts": 667115455638.965, "dur": 0.892, + "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": 4183436, "tid": 4183436, + "ts": 667115455640.971, "dur": 60.315, + "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": 4183436, "tid": 4183436, + "ts": 667115455642.614, "dur": 1.670, + "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": 4183436, "tid": 4183436, + "ts": 667115455646.115, "dur": 54.878, + "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": 4183436, "tid": 4183436, + "ts": 667115455648.839, "dur": 37.028, + "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": 4183436, "tid": 4183436, + "ts": 667115455703.774, "dur": 21.972, + "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": 4183436, "tid": 4183436, + "ts": 667115455727.185, "dur": 17.649, + "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": 4183436, "tid": 4183436, + "ts": 667115455747.920, "dur": 15.016, + "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": 4183436, "tid": 4183436, + "ts": 667115455764.635, "dur": 13.343, + "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": 4183436, "tid": 4183436, + "ts": 667115455780.176, "dur": 20.628, + "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": 4183436, "tid": 4183436, + "ts": 667115455782.289, "dur": 1.812, + "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": 4183436, "tid": 4183436, + "ts": 667115455786.353, "dur": 1.116, + "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": 4183436, "tid": 4183436, + "ts": 667115455802.336, "dur": 10.582, + "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": 4183436, "tid": 4183436, + "ts": 667115455814.208, "dur": 10.497, + "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": 4183436, "tid": 4183436, + "ts": 667115455838.461, "dur": 2.783, + "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": 4183436, "tid": 4183436, + "ts": 667115455851.040, "dur": 4.134, + "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": 4183436, "tid": 4183436, + "ts": 667115455853.805, "dur": 0.455, + "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": 4183436, "tid": 4183436, + "ts": 667115455929.446, "dur": 47.882, + "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": 4183436, "tid": 4183436, + "ts": 667115455982.659, "dur": 4.864, + "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": 4183436, "tid": 4183436, + "ts": 667115455985.428, "dur": 1.006, + "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": 4183436, "tid": 4183436, + "ts": 667115455989.229, "dur": 22.860, + "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": 4183436, "tid": 4183436, + "ts": 667115456016.887, "dur": 8.197, + "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": 4183436, "tid": 4183436, + "ts": 667115456018.613, "dur": 5.614, + "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": 4183436, "tid": 4183436, + "ts": 667115456020.846, "dur": 3.146, + "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": 4183436, "tid": 4183436, + "ts": 667115456028.018, "dur": 41.578, + "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": 4183436, "tid": 4183436, + "ts": 667115456029.656, "dur": 39.291, + "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": 4183436, "tid": 4183436, + "ts": 667115456073.952, "dur": 13.608, + "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": 4183436, "tid": 4183436, + "ts": 667115456093.859, "dur": 4.513, + "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": 4183436, "tid": 4183436, + "ts": 667115456096.636, "dur": 0.908, + "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": 4183436, "tid": 4183436, + "ts": 667115456102.781, "dur": 48.834, + "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": 4183436, "tid": 4183436, + "ts": 667115456104.012, "dur": 4.639, + "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": 4183436, "tid": 4183436, + "ts": 667115456104.851, "dur": 3.208, + "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": 4183436, "tid": 4183436, + "ts": 667115456106.869, "dur": 1.033, + "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": 4183436, "tid": 4183436, + "ts": 667115456109.858, "dur": 41.304, + "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": 4183436, "tid": 4183436, + "ts": 667115456110.756, "dur": 39.877, + "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": 4183436, "tid": 4183436, + "ts": 667115456156.032, "dur": 3.982, + "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": 4183436, "tid": 4183436, + "ts": 667115456157.926, "dur": 0.779, + "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": 4183436, "tid": 4183436, + "ts": 667115456165.691, "dur": 1.510, + "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": 4183436, "tid": 4183436, + "ts": 667115456175.294, "dur": 7.465, + "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": 4183436, "tid": 4183436, + "ts": 667115456178.270, "dur": 4.186, + "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": 4183436, "tid": 4183436, + "ts": 667115456263.953, "dur": 171.428, + "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": 4183436, "tid": 4183436, + "ts": 667115456266.018, "dur": 2.157, + "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": 4183436, "tid": 4183436, + "ts": 667115456272.517, "dur": 162.375, + "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": 4183436, "tid": 4183436, + "ts": 667115456274.144, "dur": 0.323, + "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": 4183436, "tid": 4183436, + "ts": 667115456275.791, "dur": 18.907, + "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": 4183436, "tid": 4183436, + "ts": 667115456296.346, "dur": 5.632, + "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": 4183436, "tid": 4183436, + "ts": 667115456298.493, "dur": 3.215, + "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": 4183436, "tid": 4183436, + "ts": 667115456303.286, "dur": 20.137, + "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": 4183436, "tid": 4183436, + "ts": 667115456305.032, "dur": 1.794, + "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": 4183436, "tid": 4183436, + "ts": 667115456308.231, "dur": 14.881, + "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": 4183436, "tid": 4183436, + "ts": 667115456310.824, "dur": 2.265, + "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": 4183436, "tid": 4183436, + "ts": 667115456325.061, "dur": 18.973, + "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": 4183436, "tid": 4183436, + "ts": 667115456345.356, "dur": 13.308, + "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": 4183436, "tid": 4183436, + "ts": 667115456361.384, "dur": 14.641, + "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": 4183436, "tid": 4183436, + "ts": 667115456377.646, "dur": 12.149, + "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": 4183436, "tid": 4183436, + "ts": 667115456391.783, "dur": 18.112, + "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": 4183436, "tid": 4183436, + "ts": 667115456393.836, "dur": 1.607, + "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": 4183436, "tid": 4183436, + "ts": 667115456397.808, "dur": 0.639, + "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": 4183436, "tid": 4183436, + "ts": 667115456411.439, "dur": 10.889, + "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": 4183436, "tid": 4183436, + "ts": 667115456423.608, "dur": 10.372, + "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": 4183436, "tid": 4183436, + "ts": 667115456441.258, "dur": 1.754, + "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": 4183436, "tid": 4183436, + "ts": 667115456450.693, "dur": 3.362, + "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": 4183436, "tid": 4183436, + "ts": 667115456452.703, "dur": 0.436, + "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": 4183436, "tid": 4183436, + "ts": 667115456537.367, "dur": 48.684, + "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": 4183436, "tid": 4183436, + "ts": 667115456591.293, "dur": 8.419, + "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": 4183436, "tid": 4183436, + "ts": 667115456594.773, "dur": 3.406, + "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": 4183436, "tid": 4183436, + "ts": 667115456601.652, "dur": 22.799, + "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": 4183436, "tid": 4183436, + "ts": 667115456629.280, "dur": 6.124, + "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": 4183436, "tid": 4183436, + "ts": 667115456630.888, "dur": 3.539, + "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": 4183436, "tid": 4183436, + "ts": 667115456633.084, "dur": 1.098, + "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": 4183436, "tid": 4183436, + "ts": 667115456638.295, "dur": 81.378, + "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": 4183436, "tid": 4183436, + "ts": 667115456639.389, "dur": 79.196, + "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": 4183436, "tid": 4183436, + "ts": 667115456725.097, "dur": 16.045, + "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": 4183436, "tid": 4183436, + "ts": 667115456748.150, "dur": 5.150, + "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": 4183436, "tid": 4183436, + "ts": 667115456751.131, "dur": 1.021, + "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": 4183436, "tid": 4183436, + "ts": 667115456757.499, "dur": 51.884, + "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": 4183436, "tid": 4183436, + "ts": 667115456758.703, "dur": 4.969, + "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": 4183436, "tid": 4183436, + "ts": 667115456759.641, "dur": 3.371, + "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": 4183436, "tid": 4183436, + "ts": 667115456761.721, "dur": 1.151, + "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": 4183436, "tid": 4183436, + "ts": 667115456764.317, "dur": 44.622, + "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": 4183436, "tid": 4183436, + "ts": 667115456765.054, "dur": 43.422, + "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": 4183436, "tid": 4183436, + "ts": 667115456813.669, "dur": 4.070, + "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": 4183436, "tid": 4183436, + "ts": 667115456815.610, "dur": 0.846, + "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": 4183436, "tid": 4183436, + "ts": 667115456824.929, "dur": 1.789, + "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": 4183436, "tid": 4183436, + "ts": 667115456834.348, "dur": 6.649, + "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": 4183436, "tid": 4183436, + "ts": 667115456836.770, "dur": 3.970, + "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": 4183436, "tid": 4183436, + "ts": 667115456931.984, "dur": 176.926, + "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": 4183436, "tid": 4183436, + "ts": 667115456934.035, "dur": 4.360, + "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": 4183436, "tid": 4183436, + "ts": 667115456940.223, "dur": 168.245, + "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": 4183436, "tid": 4183436, + "ts": 667115456941.896, "dur": 0.451, + "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": 4183436, "tid": 4183436, + "ts": 667115456943.933, "dur": 20.492, + "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": 4183436, "tid": 4183436, + "ts": 667115456966.315, "dur": 5.616, + "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": 4183436, "tid": 4183436, + "ts": 667115456971.011, "dur": 0.635, + "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": 4183436, "tid": 4183436, + "ts": 667115456973.309, "dur": 20.763, + "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": 4183436, "tid": 4183436, + "ts": 667115456974.545, "dur": 1.177, + "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": 4183436, "tid": 4183436, + "ts": 667115456977.002, "dur": 16.773, + "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": 4183436, "tid": 4183436, + "ts": 667115456979.911, "dur": 2.877, + "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": 4183436, "tid": 4183436, + "ts": 667115456996.350, "dur": 19.014, + "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": 4183436, "tid": 4183436, + "ts": 667115457016.724, "dur": 12.782, + "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": 4183436, "tid": 4183436, + "ts": 667115457032.135, "dur": 13.837, + "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": 4183436, "tid": 4183436, + "ts": 667115457047.348, "dur": 11.660, + "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": 4183436, "tid": 4183436, + "ts": 667115457060.811, "dur": 21.838, + "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": 4183436, "tid": 4183436, + "ts": 667115457065.184, "dur": 1.555, + "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": 4183436, "tid": 4183436, + "ts": 667115457069.244, "dur": 0.764, + "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": 4183436, "tid": 4183436, + "ts": 667115457084.355, "dur": 10.777, + "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": 4183436, "tid": 4183436, + "ts": 667115457096.140, "dur": 10.876, + "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": 4183436, "tid": 4183436, + "ts": 667115457115.030, "dur": 1.822, + "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": 4183436, "tid": 4183436, + "ts": 667115457125.130, "dur": 3.332, + "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": 4183436, "tid": 4183436, + "ts": 667115457127.213, "dur": 0.397, + "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": 4183436, "tid": 4183436, + "ts": 667115457190.443, "dur": 40.187, + "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": 4183436, "tid": 4183436, + "ts": 667115457235.626, "dur": 4.721, + "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": 4183436, "tid": 4183436, + "ts": 667115457238.403, "dur": 1.028, + "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": 4183436, "tid": 4183436, + "ts": 667115457241.827, "dur": 20.558, + "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": 4183436, "tid": 4183436, + "ts": 667115457266.501, "dur": 5.711, + "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": 4183436, "tid": 4183436, + "ts": 667115457267.854, "dur": 3.754, + "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": 4183436, "tid": 4183436, + "ts": 667115457269.834, "dur": 1.594, + "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": 4183436, "tid": 4183436, + "ts": 667115457274.511, "dur": 39.629, + "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": 4183436, "tid": 4183436, + "ts": 667115457275.505, "dur": 37.948, + "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": 4183436, "tid": 4183436, + "ts": 667115457317.468, "dur": 13.305, + "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": 4183436, "tid": 4183436, + "ts": 667115457336.765, "dur": 3.855, + "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": 4183436, "tid": 4183436, + "ts": 667115457338.974, "dur": 0.860, + "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": 4183436, "tid": 4183436, + "ts": 667115457344.481, "dur": 45.938, + "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": 4183436, "tid": 4183436, + "ts": 667115457345.451, "dur": 3.788, + "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": 4183436, "tid": 4183436, + "ts": 667115457346.289, "dur": 2.367, + "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": 4183436, "tid": 4183436, + "ts": 667115457347.827, "dur": 0.692, + "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": 4183436, "tid": 4183436, + "ts": 667115457350.199, "dur": 39.941, + "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": 4183436, "tid": 4183436, + "ts": 667115457350.733, "dur": 38.831, + "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": 4183436, "tid": 4183436, + "ts": 667115457394.433, "dur": 4.083, + "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": 4183436, "tid": 4183436, + "ts": 667115457396.530, "dur": 0.674, + "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": 4183436, "tid": 4183436, + "ts": 667115457403.804, "dur": 1.421, + "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": 4183436, "tid": 4183436, + "ts": 667115457412.128, "dur": 6.438, + "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": 4183436, "tid": 4183436, + "ts": 667115457414.474, "dur": 3.791, + "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": 4183436, "tid": 4183436, + "ts": 667115457515.161, "dur": 232.281, + "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": 4183436, "tid": 4183436, + "ts": 667115457520.223, "dur": 3.397, + "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": 4183436, "tid": 4183436, + "ts": 667115457525.715, "dur": 221.118, + "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": 4183436, "tid": 4183436, + "ts": 667115457527.691, "dur": 0.419, + "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": 4183436, "tid": 4183436, + "ts": 667115457529.330, "dur": 22.793, + "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": 4183436, "tid": 4183436, + "ts": 667115457553.637, "dur": 5.424, + "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": 4183436, "tid": 4183436, + "ts": 667115457558.023, "dur": 0.769, + "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": 4183436, "tid": 4183436, + "ts": 667115457559.864, "dur": 25.408, + "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": 4183436, "tid": 4183436, + "ts": 667115457560.960, "dur": 1.519, + "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": 4183436, "tid": 4183436, + "ts": 667115457564.257, "dur": 20.707, + "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": 4183436, "tid": 4183436, + "ts": 667115457566.928, "dur": 3.106, + "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": 4183436, "tid": 4183436, + "ts": 667115457586.614, "dur": 22.981, + "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": 4183436, "tid": 4183436, + "ts": 667115457611.456, "dur": 13.040, + "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": 4183436, "tid": 4183436, + "ts": 667115457627.302, "dur": 14.721, + "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": 4183436, "tid": 4183436, + "ts": 667115457643.678, "dur": 48.602, + "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": 4183436, "tid": 4183436, + "ts": 667115457695.640, "dur": 22.840, + "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": 4183436, "tid": 4183436, + "ts": 667115457697.529, "dur": 2.103, + "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": 4183436, "tid": 4183436, + "ts": 667115457701.911, "dur": 0.952, + "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": 4183436, "tid": 4183436, + "ts": 667115457720.315, "dur": 12.923, + "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": 4183436, "tid": 4183436, + "ts": 667115457734.551, "dur": 11.156, + "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": 4183436, "tid": 4183436, + "ts": 667115457755.042, "dur": 2.616, + "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": 4183436, "tid": 4183436, + "ts": 667115457766.748, "dur": 3.903, + "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": 4183436, "tid": 4183436, + "ts": 667115457769.336, "dur": 0.330, + "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": 4183436, "tid": 4183436, + "ts": 667115457859.268, "dur": 52.077, + "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": 4183436, "tid": 4183436, + "ts": 667115457916.661, "dur": 4.230, + "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": 4183436, "tid": 4183436, + "ts": 667115457919.252, "dur": 0.598, + "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": 4183436, "tid": 4183436, + "ts": 667115457922.591, "dur": 27.803, + "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": 4183436, "tid": 4183436, + "ts": 667115457955.323, "dur": 7.820, + "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": 4183436, "tid": 4183436, + "ts": 667115457957.016, "dur": 5.410, + "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": 4183436, "tid": 4183436, + "ts": 667115457959.189, "dur": 2.992, + "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": 4183436, "tid": 4183436, + "ts": 667115457965.874, "dur": 67.073, + "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": 4183436, "tid": 4183436, + "ts": 667115457966.810, "dur": 65.353, + "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": 4183436, "tid": 4183436, + "ts": 667115458037.063, "dur": 24.617, + "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": 4183436, "tid": 4183436, + "ts": 667115458067.290, "dur": 4.501, + "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": 4183436, "tid": 4183436, + "ts": 667115458069.965, "dur": 0.993, + "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": 4183436, "tid": 4183436, + "ts": 667115458075.924, "dur": 49.011, + "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": 4183436, "tid": 4183436, + "ts": 667115458077.098, "dur": 4.445, + "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": 4183436, "tid": 4183436, + "ts": 667115458077.970, "dur": 2.996, + "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": 4183436, "tid": 4183436, + "ts": 667115458079.933, "dur": 0.813, + "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": 4183436, "tid": 4183436, + "ts": 667115458082.453, "dur": 42.181, + "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": 4183436, "tid": 4183436, + "ts": 667115458083.237, "dur": 40.682, + "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": 4183436, "tid": 4183436, + "ts": 667115458129.056, "dur": 3.987, + "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": 4183436, "tid": 4183436, + "ts": 667115458130.986, "dur": 0.852, + "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": 4183436, "tid": 4183436, + "ts": 667115458139.081, "dur": 1.300, + "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": 4183436, "tid": 4183436, + "ts": 667115458147.801, "dur": 14.652, + "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": 4183436, "tid": 4183436, + "ts": 667115458155.914, "dur": 6.169, + "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": 4183436, "tid": 4183436, + "ts": 667115458245.145, "dur": 184.100, + "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": 4183436, "tid": 4183436, + "ts": 667115458247.543, "dur": 2.129, + "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": 4183436, "tid": 4183436, + "ts": 667115458251.652, "dur": 177.055, + "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": 4183436, "tid": 4183436, + "ts": 667115458253.440, "dur": 0.408, + "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": 4183436, "tid": 4183436, + "ts": 667115458255.219, "dur": 22.849, + "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": 4183436, "tid": 4183436, + "ts": 667115458279.966, "dur": 3.574, + "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": 4183436, "tid": 4183436, + "ts": 667115458282.296, "dur": 1.009, + "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": 4183436, "tid": 4183436, + "ts": 667115458284.541, "dur": 25.031, + "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": 4183436, "tid": 4183436, + "ts": 667115458286.235, "dur": 1.429, + "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": 4183436, "tid": 4183436, + "ts": 667115458289.421, "dur": 19.831, + "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": 4183436, "tid": 4183436, + "ts": 667115458294.179, "dur": 2.102, + "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": 4183436, "tid": 4183436, + "ts": 667115458311.272, "dur": 19.402, + "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": 4183436, "tid": 4183436, + "ts": 667115458332.005, "dur": 14.973, + "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": 4183436, "tid": 4183436, + "ts": 667115458349.365, "dur": 14.175, + "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": 4183436, "tid": 4183436, + "ts": 667115458365.051, "dur": 13.090, + "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": 4183436, "tid": 4183436, + "ts": 667115458379.766, "dur": 20.617, + "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": 4183436, "tid": 4183436, + "ts": 667115458381.351, "dur": 1.489, + "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": 4183436, "tid": 4183436, + "ts": 667115458385.630, "dur": 1.001, + "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": 4183436, "tid": 4183436, + "ts": 667115458401.773, "dur": 12.850, + "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": 4183436, "tid": 4183436, + "ts": 667115458415.997, "dur": 11.371, + "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": 4183436, "tid": 4183436, + "ts": 667115458434.621, "dur": 1.427, + "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": 4183436, "tid": 4183436, + "ts": 667115458443.844, "dur": 3.673, + "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": 4183436, "tid": 4183436, + "ts": 667115458446.313, "dur": 0.562, + "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": 4183436, "tid": 4183436, + "ts": 667115458531.242, "dur": 46.532, + "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": 4183436, "tid": 4183436, + "ts": 667115458582.767, "dur": 5.825, + "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": 4183436, "tid": 4183436, + "ts": 667115458585.886, "dur": 1.273, + "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": 4183436, "tid": 4183436, + "ts": 667115458589.983, "dur": 23.533, + "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": 4183436, "tid": 4183436, + "ts": 667115458618.219, "dur": 5.413, + "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": 4183436, "tid": 4183436, + "ts": 667115458619.507, "dur": 3.474, + "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": 4183436, "tid": 4183436, + "ts": 667115458621.612, "dur": 1.184, + "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": 4183436, "tid": 4183436, + "ts": 667115458625.892, "dur": 78.133, + "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": 4183436, "tid": 4183436, + "ts": 667115458627.142, "dur": 75.773, + "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": 4183436, "tid": 4183436, + "ts": 667115458709.541, "dur": 16.495, + "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": 4183436, "tid": 4183436, + "ts": 667115458733.209, "dur": 5.138, + "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": 4183436, "tid": 4183436, + "ts": 667115458736.298, "dur": 0.933, + "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": 4183436, "tid": 4183436, + "ts": 667115458742.560, "dur": 55.517, + "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": 4183436, "tid": 4183436, + "ts": 667115458743.780, "dur": 7.193, + "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": 4183436, "tid": 4183436, + "ts": 667115458745.067, "dur": 5.275, + "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": 4183436, "tid": 4183436, + "ts": 667115458747.226, "dur": 2.962, + "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": 4183436, "tid": 4183436, + "ts": 667115458751.906, "dur": 45.704, + "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": 4183436, "tid": 4183436, + "ts": 667115458752.770, "dur": 44.123, + "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": 4183436, "tid": 4183436, + "ts": 667115458802.405, "dur": 4.256, + "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": 4183436, "tid": 4183436, + "ts": 667115458804.924, "dur": 0.628, + "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": 4183436, "tid": 4183436, + "ts": 667115458813.049, "dur": 1.590, + "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": 4183436, "tid": 4183436, + "ts": 667115458849.221, "dur": 10.807, + "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": 4183436, "tid": 4183436, + "ts": 667115458855.451, "dur": 4.287, + "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": 4183436, "tid": 4183436, + "ts": 667115458951.929, "dur": 198.407, + "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": 4183436, "tid": 4183436, + "ts": 667115458956.477, "dur": 2.438, + "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": 4183436, "tid": 4183436, + "ts": 667115458960.323, "dur": 189.232, + "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": 4183436, "tid": 4183436, + "ts": 667115458961.965, "dur": 0.360, + "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": 4183436, "tid": 4183436, + "ts": 667115458963.676, "dur": 21.021, + "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": 4183436, "tid": 4183436, + "ts": 667115458986.299, "dur": 5.343, + "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": 4183436, "tid": 4183436, + "ts": 667115458990.849, "dur": 0.559, + "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": 4183436, "tid": 4183436, + "ts": 667115458992.535, "dur": 20.917, + "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": 4183436, "tid": 4183436, + "ts": 667115458993.740, "dur": 1.527, + "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": 4183436, "tid": 4183436, + "ts": 667115458997.019, "dur": 16.192, + "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": 4183436, "tid": 4183436, + "ts": 667115458999.505, "dur": 2.903, + "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": 4183436, "tid": 4183436, + "ts": 667115459014.912, "dur": 19.724, + "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": 4183436, "tid": 4183436, + "ts": 667115459036.014, "dur": 11.806, + "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": 4183436, "tid": 4183436, + "ts": 667115459050.412, "dur": 15.845, + "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": 4183436, "tid": 4183436, + "ts": 667115459067.925, "dur": 15.997, + "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": 4183436, "tid": 4183436, + "ts": 667115459086.152, "dur": 28.576, + "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": 4183436, "tid": 4183436, + "ts": 667115459091.092, "dur": 2.632, + "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": 4183436, "tid": 4183436, + "ts": 667115459096.944, "dur": 1.060, + "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": 4183436, "tid": 4183436, + "ts": 667115459116.878, "dur": 14.684, + "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": 4183436, "tid": 4183436, + "ts": 667115459133.435, "dur": 13.772, + "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": 4183436, "tid": 4183436, + "ts": 667115459160.787, "dur": 2.797, + "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": 4183436, "tid": 4183436, + "ts": 667115459176.155, "dur": 5.305, + "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": 4183436, "tid": 4183436, + "ts": 667115459179.353, "dur": 0.692, + "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": 4183436, "tid": 4183436, + "ts": 667115459276.277, "dur": 66.977, + "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": 4183436, "tid": 4183436, + "ts": 667115459350.479, "dur": 7.371, + "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": 4183436, "tid": 4183436, + "ts": 667115459354.377, "dur": 1.442, + "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": 4183436, "tid": 4183436, + "ts": 667115459359.957, "dur": 31.375, + "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": 4183436, "tid": 4183436, + "ts": 667115459398.042, "dur": 8.494, + "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": 4183436, "tid": 4183436, + "ts": 667115459400.245, "dur": 5.033, + "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": 4183436, "tid": 4183436, + "ts": 667115459403.223, "dur": 1.721, + "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": 4183436, "tid": 4183436, + "ts": 667115459410.033, "dur": 57.760, + "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": 4183436, "tid": 4183436, + "ts": 667115459412.013, "dur": 54.866, + "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": 4183436, "tid": 4183436, + "ts": 667115459473.266, "dur": 34.206, + "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": 4183436, "tid": 4183436, + "ts": 667115459517.601, "dur": 33.010, + "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": 4183436, "tid": 4183436, + "ts": 667115459520.909, "dur": 28.987, + "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": 4183436, "tid": 4183436, + "ts": 667115459528.277, "dur": 1.543, + "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": 4183436, "tid": 4183436, + "ts": 667115459557.172, "dur": 49.407, + "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": 4183436, "tid": 4183436, + "ts": 667115459565.751, "dur": 40.489, + "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": 4183436, "tid": 4183436, + "ts": 667115459572.313, "dur": 5.196, + "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": 4183436, "tid": 4183436, + "ts": 667115459579.334, "dur": 26.200, + "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": 4183436, "tid": 4183436, + "ts": 667115459623.489, "dur": 6.077, + "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": 4183436, "tid": 4183436, + "ts": 667115459626.156, "dur": 3.110, + "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": 4183436, "tid": 4183436, + "ts": 667115459631.024, "dur": 2.178, + "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": 4183436, "tid": 4183436, + "ts": 667115459632.173, "dur": 0.884, + "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": 4183436, "tid": 4183436, + "ts": 667115459716.779, "dur": 34.933, + "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": 4183436, "tid": 4183436, + "ts": 667115459754.260, "dur": 17.873, + "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": 4183436, "tid": 4183436, "ts": 667115459754.260, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183436, "tid": 4183436, + "ts": 667115459780.874, "dur": 9.386, + "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": 4183436, "tid": 4183436, + "ts": 667115459786.172, "dur": 1.671, + "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": 4183436, "tid": 4183436, + "ts": 667115459793.547, "dur": 9.355, + "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": 4183436, "tid": 4183436, + "ts": 667115459799.597, "dur": 1.553, + "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": 4183436, "tid": 4183436, + "ts": 667115459805.068, "dur": 3.986, + "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": 4183436, "tid": 4183436, + "ts": 667115459807.442, "dur": 0.764, + "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": 4183436, "tid": 4183436, + "ts": 667115459816.110, "dur": 9.230, + "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": 4183436, "tid": 4183436, "ts": 667115459816.110, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115459821.157, "dur": 2.068, + "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": 4183436, "tid": 4183436, + "ts": 667115459827.156, "dur": 6.562, + "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": 4183436, "tid": 4183436, "ts": 667115459827.156, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115459831.769, "dur": 0.827, + "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": 4183436, "tid": 4183436, + "ts": 667115459835.514, "dur": 6.684, + "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": 4183436, "tid": 4183436, "ts": 667115459835.514, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115459840.007, "dur": 1.027, + "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": 4183436, "tid": 4183436, + "ts": 667115459843.835, "dur": 5.996, + "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": 4183436, "tid": 4183436, "ts": 667115459843.835, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115459847.446, "dur": 1.225, + "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": 4183436, "tid": 4183436, + "ts": 667115459854.560, "dur": 45.868, + "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": 4183436, "tid": 4183436, + "ts": 667115459856.794, "dur": 43.344, + "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": 4183436, "tid": 4183436, + "ts": 667115459859.961, "dur": 12.377, + "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": 4183436, "tid": 4183436, + "ts": 667115459863.307, "dur": 8.219, + "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": 4183436, "tid": 4183436, + "ts": 667115459873.747, "dur": 25.756, + "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": 4183436, "tid": 4183436, + "ts": 667115459932.805, "dur": 6.054, + "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": 4183436, "tid": 4183436, "ts": 667115459932.805, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115459942.259, "dur": 1.545, + "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": 4183436, "tid": 4183436, + "ts": 667115459981.542, "dur": 23299.506, + "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": 4183436, "tid": 4183436, "ts": 667115459981.542, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 4183436, + "ts": 667115460001.310, "dur": 35.717, + "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": 4183436, "tid": 4183436, + "ts": 667115460002.657, "dur": 34.092, + "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": 4183436, "tid": 4183436, + "ts": 667115460004.715, "dur": 8.618, + "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": 4183436, "tid": 4183436, + "ts": 667115460007.234, "dur": 5.419, + "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": 4183436, "tid": 4183436, + "ts": 667115460014.562, "dur": 21.675, + "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": 4183436, "tid": 4183436, + "ts": 667115460056.489, "dur": 33.085, + "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": 4183436, "tid": 4183436, + "ts": 667115460058.346, "dur": 8.604, + "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": 4183436, "tid": 4183436, + "ts": 667115460060.969, "dur": 5.443, + "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": 4183436, "tid": 4183436, + "ts": 667115460068.373, "dur": 20.933, + "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": 4183436, "tid": 4183436, + "ts": 667115460070.934, "dur": 17.807, + "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": 4183436, "tid": 4183436, + "ts": 667115460093.954, "dur": 26.800, + "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": 4183436, "tid": 4183436, + "ts": 667115460095.311, "dur": 5.784, + "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": 4183436, "tid": 4183436, + "ts": 667115460097.229, "dur": 3.458, + "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": 4183436, "tid": 4183436, + "ts": 667115460102.109, "dur": 18.341, + "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": 4183436, "tid": 4183436, + "ts": 667115460103.195, "dur": 16.847, + "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": 4183436, "tid": 4183436, + "ts": 667115460126.908, "dur": 18.057, + "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": 4183436, "tid": 4183436, + "ts": 667115460128.789, "dur": 2.504, + "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": 4183436, "tid": 4183436, + "ts": 667115460131.990, "dur": 12.712, + "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": 4183436, "tid": 4183436, + "ts": 667115460132.877, "dur": 11.524, + "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": 4183436, "tid": 4183436, + "ts": 667115460149.634, "dur": 24.608, + "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": 4183436, "tid": 4183436, + "ts": 667115460177.094, "dur": 50.852, + "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": 4183436, "tid": 4183436, + "ts": 667115460179.240, "dur": 48.249, + "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": 4183436, "tid": 4183436, + "ts": 667115460183.804, "dur": 0.905, + "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": 4183436, "tid": 4183436, + "ts": 667115460186.357, "dur": 24.153, + "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": 4183436, "tid": 4183436, + "ts": 667115460187.897, "dur": 22.382, + "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": 4183436, "tid": 4183436, + "ts": 667115460192.765, "dur": 2.931, + "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": 4183436, "tid": 4183436, + "ts": 667115460196.506, "dur": 13.408, + "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": 4183436, "tid": 4183436, + "ts": 667115460231.953, "dur": 17480.529, + "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": 4183436, "tid": 4183436, + "ts": 667115460233.295, "dur": 17477.104, + "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": 4183436, "tid": 4183436, + "ts": 667115477727.883, "dur": 9.076, + "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": 4183436, "tid": 4183436, + "ts": 667115477733.448, "dur": 1.260, + "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": 4183436, "tid": 4183436, + "ts": 667115477743.197, "dur": 110.383, + "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": 4183436, "tid": 4183436, + "ts": 667115477744.652, "dur": 6.985, + "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": 4183436, "tid": 4183436, + "ts": 667115477747.202, "dur": 3.567, + "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": 4183436, "tid": 4183436, + "ts": 667115477749.238, "dur": 1.246, + "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": 4183436, "tid": 4183436, + "ts": 667115477753.138, "dur": 99.506, + "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": 4183436, "tid": 4183436, + "ts": 667115477754.855, "dur": 97.009, + "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": 4183436, "tid": 4183436, + "ts": 667115477857.717, "dur": 4.702, + "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": 4183436, "tid": 4183436, + "ts": 667115477860.022, "dur": 0.767, + "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": 4183436, "tid": 4183436, + "ts": 667115477872.521, "dur": 2.676, + "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": 4183436, "tid": 4183436, + "ts": 667115477885.782, "dur": 8.021, + "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": 4183436, "tid": 4183436, + "ts": 667115477888.642, "dur": 4.859, + "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": 4183436, "tid": 4183436, + "ts": 667115478027.577, "dur": 209.506, + "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": 4183436, "tid": 4183436, + "ts": 667115478030.869, "dur": 2.453, + "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": 4183436, "tid": 4183436, + "ts": 667115478037.864, "dur": 198.652, + "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": 4183436, "tid": 4183436, + "ts": 667115478039.515, "dur": 0.478, + "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": 4183436, "tid": 4183436, + "ts": 667115478041.774, "dur": 27.767, + "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": 4183436, "tid": 4183436, + "ts": 667115478071.455, "dur": 6.205, + "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": 4183436, "tid": 4183436, + "ts": 667115478073.814, "dur": 3.334, + "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": 4183436, "tid": 4183436, + "ts": 667115478078.758, "dur": 25.015, + "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": 4183436, "tid": 4183436, + "ts": 667115478080.100, "dur": 1.524, + "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": 4183436, "tid": 4183436, + "ts": 667115478083.124, "dur": 20.398, + "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": 4183436, "tid": 4183436, + "ts": 667115478086.766, "dur": 2.962, + "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": 4183436, "tid": 4183436, + "ts": 667115478105.730, "dur": 24.163, + "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": 4183436, "tid": 4183436, + "ts": 667115478131.571, "dur": 14.417, + "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": 4183436, "tid": 4183436, + "ts": 667115478148.871, "dur": 17.272, + "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": 4183436, "tid": 4183436, + "ts": 667115478167.742, "dur": 13.922, + "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": 4183436, "tid": 4183436, + "ts": 667115478183.550, "dur": 23.517, + "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": 4183436, "tid": 4183436, + "ts": 667115478185.561, "dur": 1.851, + "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": 4183436, "tid": 4183436, + "ts": 667115478189.979, "dur": 2.698, + "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": 4183436, "tid": 4183436, + "ts": 667115478208.796, "dur": 12.704, + "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": 4183436, "tid": 4183436, + "ts": 667115478222.836, "dur": 12.653, + "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": 4183436, "tid": 4183436, + "ts": 667115478243.770, "dur": 2.210, + "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": 4183436, "tid": 4183436, + "ts": 667115478252.370, "dur": 4.501, + "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": 4183436, "tid": 4183436, + "ts": 667115478255.101, "dur": 0.777, + "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": 4183436, "tid": 4183436, + "ts": 667115478324.769, "dur": 55.376, + "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": 4183436, "tid": 4183436, + "ts": 667115478385.503, "dur": 6.496, + "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": 4183436, "tid": 4183436, + "ts": 667115478388.583, "dur": 0.899, + "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": 4183436, "tid": 4183436, + "ts": 667115478393.572, "dur": 26.547, + "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": 4183436, "tid": 4183436, + "ts": 667115478425.580, "dur": 6.921, + "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": 4183436, "tid": 4183436, + "ts": 667115478427.396, "dur": 4.121, + "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": 4183436, "tid": 4183436, + "ts": 667115478429.709, "dur": 1.557, + "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": 4183436, "tid": 4183436, + "ts": 667115478435.403, "dur": 46.140, + "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": 4183436, "tid": 4183436, + "ts": 667115478436.593, "dur": 44.421, + "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": 4183436, "tid": 4183436, + "ts": 667115478485.730, "dur": 36.289, + "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": 4183436, "tid": 4183436, + "ts": 667115478530.571, "dur": 5.285, + "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": 4183436, "tid": 4183436, + "ts": 667115478533.656, "dur": 1.023, + "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": 4183436, "tid": 4183436, + "ts": 667115478541.036, "dur": 54.067, + "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": 4183436, "tid": 4183436, + "ts": 667115478541.965, "dur": 4.050, + "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": 4183436, "tid": 4183436, + "ts": 667115478542.890, "dur": 2.525, + "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": 4183436, "tid": 4183436, + "ts": 667115478544.449, "dur": 0.805, + "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": 4183436, "tid": 4183436, + "ts": 667115478547.103, "dur": 47.507, + "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": 4183436, "tid": 4183436, + "ts": 667115478547.824, "dur": 46.256, + "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": 4183436, "tid": 4183436, + "ts": 667115478599.394, "dur": 4.422, + "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": 4183436, "tid": 4183436, + "ts": 667115478601.604, "dur": 1.005, + "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": 4183436, "tid": 4183436, + "ts": 667115478610.669, "dur": 1.776, + "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": 4183436, "tid": 4183436, + "ts": 667115478621.347, "dur": 6.427, + "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": 4183436, "tid": 4183436, + "ts": 667115478623.604, "dur": 3.931, + "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": 4183436, "tid": 4183436, + "ts": 667115478768.981, "dur": 249.274, + "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": 4183436, "tid": 4183436, + "ts": 667115478773.925, "dur": 3.382, + "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": 4183436, "tid": 4183436, + "ts": 667115478779.527, "dur": 238.265, + "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": 4183436, "tid": 4183436, + "ts": 667115478781.687, "dur": 0.561, + "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": 4183436, "tid": 4183436, + "ts": 667115478784.010, "dur": 23.187, + "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": 4183436, "tid": 4183436, + "ts": 667115478808.858, "dur": 5.665, + "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": 4183436, "tid": 4183436, + "ts": 667115478813.247, "dur": 0.977, + "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": 4183436, "tid": 4183436, + "ts": 667115478815.732, "dur": 31.027, + "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": 4183436, "tid": 4183436, + "ts": 667115478816.939, "dur": 1.476, + "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": 4183436, "tid": 4183436, + "ts": 667115478829.342, "dur": 17.155, + "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": 4183436, "tid": 4183436, + "ts": 667115478832.882, "dur": 2.707, + "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": 4183436, "tid": 4183436, + "ts": 667115478848.439, "dur": 20.812, + "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": 4183436, "tid": 4183436, + "ts": 667115478870.615, "dur": 17.641, + "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": 4183436, "tid": 4183436, + "ts": 667115478890.719, "dur": 14.514, + "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": 4183436, "tid": 4183436, + "ts": 667115478906.639, "dur": 14.363, + "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": 4183436, "tid": 4183436, + "ts": 667115478922.960, "dur": 22.986, + "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": 4183436, "tid": 4183436, + "ts": 667115478925.012, "dur": 1.635, + "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": 4183436, "tid": 4183436, + "ts": 667115478929.419, "dur": 0.821, + "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": 4183436, "tid": 4183436, + "ts": 667115478947.532, "dur": 24.886, + "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": 4183436, "tid": 4183436, + "ts": 667115478973.803, "dur": 43.020, + "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": 4183436, "tid": 4183436, + "ts": 667115479025.496, "dur": 2.593, + "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": 4183436, "tid": 4183436, + "ts": 667115479037.804, "dur": 3.891, + "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": 4183436, "tid": 4183436, + "ts": 667115479040.303, "dur": 0.544, + "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": 4183436, "tid": 4183436, + "ts": 667115479114.996, "dur": 52.420, + "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": 4183436, "tid": 4183436, + "ts": 667115479171.970, "dur": 5.258, + "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": 4183436, "tid": 4183436, + "ts": 667115479174.971, "dur": 1.052, + "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": 4183436, "tid": 4183436, + "ts": 667115479178.705, "dur": 25.055, + "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": 4183436, "tid": 4183436, + "ts": 667115479208.370, "dur": 6.083, + "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": 4183436, "tid": 4183436, + "ts": 667115479210.091, "dur": 3.623, + "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": 4183436, "tid": 4183436, + "ts": 667115479212.164, "dur": 1.343, + "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": 4183436, "tid": 4183436, + "ts": 667115479217.346, "dur": 45.211, + "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": 4183436, "tid": 4183436, + "ts": 667115479218.749, "dur": 43.134, + "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": 4183436, "tid": 4183436, + "ts": 667115479266.458, "dur": 13.955, + "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": 4183436, "tid": 4183436, + "ts": 667115479286.470, "dur": 3.584, + "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": 4183436, "tid": 4183436, + "ts": 667115479288.563, "dur": 0.691, + "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": 4183436, "tid": 4183436, + "ts": 667115479294.451, "dur": 49.744, + "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": 4183436, "tid": 4183436, + "ts": 667115479295.633, "dur": 4.072, + "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": 4183436, "tid": 4183436, + "ts": 667115479296.670, "dur": 2.387, + "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": 4183436, "tid": 4183436, + "ts": 667115479298.215, "dur": 0.679, + "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": 4183436, "tid": 4183436, + "ts": 667115479300.697, "dur": 43.137, + "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": 4183436, "tid": 4183436, + "ts": 667115479301.398, "dur": 41.874, + "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": 4183436, "tid": 4183436, + "ts": 667115479348.304, "dur": 4.206, + "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": 4183436, "tid": 4183436, + "ts": 667115479350.580, "dur": 0.794, + "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": 4183436, "tid": 4183436, + "ts": 667115479357.934, "dur": 1.638, + "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": 4183436, "tid": 4183436, + "ts": 667115479367.298, "dur": 7.668, + "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": 4183436, "tid": 4183436, + "ts": 667115479369.346, "dur": 5.374, + "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": 4183436, "tid": 4183436, + "ts": 667115479461.332, "dur": 248.429, + "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": 4183436, "tid": 4183436, + "ts": 667115479463.453, "dur": 2.137, + "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": 4183436, "tid": 4183436, + "ts": 667115479467.062, "dur": 242.109, + "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": 4183436, "tid": 4183436, + "ts": 667115479468.755, "dur": 0.320, + "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": 4183436, "tid": 4183436, + "ts": 667115479470.219, "dur": 43.101, + "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": 4183436, "tid": 4183436, + "ts": 667115479516.020, "dur": 3.936, + "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": 4183436, "tid": 4183436, + "ts": 667115479518.642, "dur": 1.038, + "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": 4183436, "tid": 4183436, + "ts": 667115479520.843, "dur": 27.730, + "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": 4183436, "tid": 4183436, + "ts": 667115479522.446, "dur": 2.051, + "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": 4183436, "tid": 4183436, + "ts": 667115479526.393, "dur": 21.857, + "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": 4183436, "tid": 4183436, + "ts": 667115479531.915, "dur": 2.662, + "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": 4183436, "tid": 4183436, + "ts": 667115479550.179, "dur": 20.782, + "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": 4183436, "tid": 4183436, + "ts": 667115479572.208, "dur": 13.165, + "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": 4183436, "tid": 4183436, + "ts": 667115479587.865, "dur": 15.753, + "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": 4183436, "tid": 4183436, + "ts": 667115479605.281, "dur": 12.991, + "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": 4183436, "tid": 4183436, + "ts": 667115479620.238, "dur": 20.907, + "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": 4183436, "tid": 4183436, + "ts": 667115479622.161, "dur": 1.444, + "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": 4183436, "tid": 4183436, + "ts": 667115479625.898, "dur": 0.672, + "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": 4183436, "tid": 4183436, + "ts": 667115479642.723, "dur": 48.444, + "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": 4183436, "tid": 4183436, + "ts": 667115479693.503, "dur": 13.996, + "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": 4183436, "tid": 4183436, + "ts": 667115479718.266, "dur": 2.665, + "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": 4183436, "tid": 4183436, + "ts": 667115479730.890, "dur": 4.549, + "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": 4183436, "tid": 4183436, + "ts": 667115479733.944, "dur": 0.533, + "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": 4183436, "tid": 4183436, + "ts": 667115479805.211, "dur": 50.752, + "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": 4183436, "tid": 4183436, + "ts": 667115479860.660, "dur": 5.370, + "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": 4183436, "tid": 4183436, + "ts": 667115479863.584, "dur": 1.372, + "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": 4183436, "tid": 4183436, + "ts": 667115479867.501, "dur": 23.094, + "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": 4183436, "tid": 4183436, + "ts": 667115479895.110, "dur": 6.101, + "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": 4183436, "tid": 4183436, + "ts": 667115479896.634, "dur": 3.622, + "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": 4183436, "tid": 4183436, + "ts": 667115479899.293, "dur": 0.782, + "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": 4183436, "tid": 4183436, + "ts": 667115479903.662, "dur": 47.657, + "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": 4183436, "tid": 4183436, + "ts": 667115479904.786, "dur": 45.787, + "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": 4183436, "tid": 4183436, + "ts": 667115479955.183, "dur": 17.932, + "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": 4183436, "tid": 4183436, + "ts": 667115479979.357, "dur": 4.424, + "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": 4183436, "tid": 4183436, + "ts": 667115479982.038, "dur": 0.839, + "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": 4183436, "tid": 4183436, + "ts": 667115479987.858, "dur": 50.921, + "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": 4183436, "tid": 4183436, + "ts": 667115479989.064, "dur": 6.361, + "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": 4183436, "tid": 4183436, + "ts": 667115479989.823, "dur": 4.934, + "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": 4183436, "tid": 4183436, + "ts": 667115479991.530, "dur": 3.037, + "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": 4183436, "tid": 4183436, + "ts": 667115479996.038, "dur": 42.422, + "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": 4183436, "tid": 4183436, + "ts": 667115479996.644, "dur": 41.121, + "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": 4183436, "tid": 4183436, + "ts": 667115480042.708, "dur": 3.954, + "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": 4183436, "tid": 4183436, + "ts": 667115480044.757, "dur": 0.815, + "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": 4183436, "tid": 4183436, + "ts": 667115480051.829, "dur": 1.474, + "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": 4183436, "tid": 4183436, + "ts": 667115480061.192, "dur": 6.571, + "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": 4183436, "tid": 4183436, + "ts": 667115480063.749, "dur": 3.769, + "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": 4183436, "tid": 4183436, + "ts": 667115480150.161, "dur": 181.455, + "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": 4183436, "tid": 4183436, + "ts": 667115480153.162, "dur": 2.323, + "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": 4183436, "tid": 4183436, + "ts": 667115480157.050, "dur": 174.033, + "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": 4183436, "tid": 4183436, + "ts": 667115480158.933, "dur": 0.692, + "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": 4183436, "tid": 4183436, + "ts": 667115480163.709, "dur": 20.961, + "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": 4183436, "tid": 4183436, + "ts": 667115480186.256, "dur": 3.427, + "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": 4183436, "tid": 4183436, + "ts": 667115480188.645, "dur": 0.858, + "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": 4183436, "tid": 4183436, + "ts": 667115480190.724, "dur": 22.837, + "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": 4183436, "tid": 4183436, + "ts": 667115480191.664, "dur": 3.249, + "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": 4183436, "tid": 4183436, + "ts": 667115480196.315, "dur": 17.005, + "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": 4183436, "tid": 4183436, + "ts": 667115480198.996, "dur": 2.238, + "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": 4183436, "tid": 4183436, + "ts": 667115480215.290, "dur": 20.578, + "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": 4183436, "tid": 4183436, + "ts": 667115480237.000, "dur": 14.140, + "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": 4183436, "tid": 4183436, + "ts": 667115480253.694, "dur": 13.869, + "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": 4183436, "tid": 4183436, + "ts": 667115480268.818, "dur": 13.081, + "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": 4183436, "tid": 4183436, + "ts": 667115480283.901, "dur": 20.402, + "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": 4183436, "tid": 4183436, + "ts": 667115480285.962, "dur": 1.605, + "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": 4183436, "tid": 4183436, + "ts": 667115480290.001, "dur": 0.611, + "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": 4183436, "tid": 4183436, + "ts": 667115480305.737, "dur": 12.811, + "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": 4183436, "tid": 4183436, + "ts": 667115480319.763, "dur": 10.549, + "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": 4183436, "tid": 4183436, + "ts": 667115480337.322, "dur": 1.699, + "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": 4183436, "tid": 4183436, + "ts": 667115480346.703, "dur": 3.624, + "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": 4183436, "tid": 4183436, + "ts": 667115480349.091, "dur": 0.424, + "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": 4183436, "tid": 4183436, + "ts": 667115480410.918, "dur": 40.027, + "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": 4183436, "tid": 4183436, + "ts": 667115480454.785, "dur": 4.540, + "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": 4183436, "tid": 4183436, + "ts": 667115480457.173, "dur": 1.152, + "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": 4183436, "tid": 4183436, + "ts": 667115480460.672, "dur": 20.848, + "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": 4183436, "tid": 4183436, + "ts": 667115480485.771, "dur": 26.897, + "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": 4183436, "tid": 4183436, + "ts": 667115480487.025, "dur": 24.601, + "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": 4183436, "tid": 4183436, + "ts": 667115480489.071, "dur": 21.827, + "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": 4183436, "tid": 4183436, + "ts": 667115480516.465, "dur": 47.104, + "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": 4183436, "tid": 4183436, + "ts": 667115480517.649, "dur": 45.243, + "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": 4183436, "tid": 4183436, + "ts": 667115480567.167, "dur": 15.949, + "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": 4183436, "tid": 4183436, + "ts": 667115480589.247, "dur": 4.156, + "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": 4183436, "tid": 4183436, + "ts": 667115480591.725, "dur": 0.805, + "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": 4183436, "tid": 4183436, + "ts": 667115480597.302, "dur": 96.468, + "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": 4183436, "tid": 4183436, + "ts": 667115480598.702, "dur": 4.688, + "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": 4183436, "tid": 4183436, + "ts": 667115480599.796, "dur": 3.037, + "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": 4183436, "tid": 4183436, + "ts": 667115480602.081, "dur": 0.623, + "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": 4183436, "tid": 4183436, + "ts": 667115480615.202, "dur": 77.987, + "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": 4183436, "tid": 4183436, + "ts": 667115480615.956, "dur": 75.974, + "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": 4183436, "tid": 4183436, + "ts": 667115480700.336, "dur": 5.365, + "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": 4183436, "tid": 4183436, + "ts": 667115480703.124, "dur": 0.993, + "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": 4183436, "tid": 4183436, + "ts": 667115480712.210, "dur": 2.008, + "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": 4183436, "tid": 4183436, + "ts": 667115480722.694, "dur": 8.190, + "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": 4183436, "tid": 4183436, + "ts": 667115480724.844, "dur": 5.780, + "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": 4183436, "tid": 4183436, + "ts": 667115480822.728, "dur": 187.255, + "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": 4183436, "tid": 4183436, + "ts": 667115480825.014, "dur": 2.248, + "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": 4183436, "tid": 4183436, + "ts": 667115480829.333, "dur": 180.107, + "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": 4183436, "tid": 4183436, + "ts": 667115480830.702, "dur": 0.382, + "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": 4183436, "tid": 4183436, + "ts": 667115480832.459, "dur": 25.171, + "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": 4183436, "tid": 4183436, + "ts": 667115480859.518, "dur": 2.866, + "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": 4183436, "tid": 4183436, + "ts": 667115480861.391, "dur": 0.785, + "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": 4183436, "tid": 4183436, + "ts": 667115480863.356, "dur": 25.379, + "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": 4183436, "tid": 4183436, + "ts": 667115480864.451, "dur": 1.602, + "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": 4183436, "tid": 4183436, + "ts": 667115480867.188, "dur": 21.276, + "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": 4183436, "tid": 4183436, + "ts": 667115480872.096, "dur": 2.364, + "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": 4183436, "tid": 4183436, + "ts": 667115480890.681, "dur": 20.937, + "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": 4183436, "tid": 4183436, + "ts": 667115480912.755, "dur": 13.565, + "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": 4183436, "tid": 4183436, + "ts": 667115480929.072, "dur": 15.244, + "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": 4183436, "tid": 4183436, + "ts": 667115480946.051, "dur": 12.851, + "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": 4183436, "tid": 4183436, + "ts": 667115480960.645, "dur": 20.974, + "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": 4183436, "tid": 4183436, + "ts": 667115480962.444, "dur": 1.653, + "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": 4183436, "tid": 4183436, + "ts": 667115480966.895, "dur": 0.850, + "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": 4183436, "tid": 4183436, + "ts": 667115480983.008, "dur": 12.616, + "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": 4183436, "tid": 4183436, + "ts": 667115480996.976, "dur": 11.626, + "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": 4183436, "tid": 4183436, + "ts": 667115481015.763, "dur": 1.809, + "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": 4183436, "tid": 4183436, + "ts": 667115481025.742, "dur": 3.507, + "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": 4183436, "tid": 4183436, + "ts": 667115481027.896, "dur": 0.444, + "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": 4183436, "tid": 4183436, + "ts": 667115481088.706, "dur": 46.220, + "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": 4183436, "tid": 4183436, + "ts": 667115481139.591, "dur": 4.667, + "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": 4183436, "tid": 4183436, + "ts": 667115481142.129, "dur": 1.202, + "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": 4183436, "tid": 4183436, + "ts": 667115481145.538, "dur": 23.953, + "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": 4183436, "tid": 4183436, + "ts": 667115481173.839, "dur": 4.784, + "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": 4183436, "tid": 4183436, + "ts": 667115481175.177, "dur": 2.789, + "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": 4183436, "tid": 4183436, + "ts": 667115481176.909, "dur": 0.874, + "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": 4183436, "tid": 4183436, + "ts": 667115481180.912, "dur": 39.983, + "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": 4183436, "tid": 4183436, + "ts": 667115481182.249, "dur": 38.130, + "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": 4183436, "tid": 4183436, + "ts": 667115481224.587, "dur": 14.703, + "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": 4183436, "tid": 4183436, + "ts": 667115481244.812, "dur": 3.988, + "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": 4183436, "tid": 4183436, + "ts": 667115481246.962, "dur": 1.011, + "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": 4183436, "tid": 4183436, + "ts": 667115481252.637, "dur": 49.592, + "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": 4183436, "tid": 4183436, + "ts": 667115481253.649, "dur": 6.044, + "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": 4183436, "tid": 4183436, + "ts": 667115481254.306, "dur": 4.812, + "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": 4183436, "tid": 4183436, + "ts": 667115481256.006, "dur": 2.948, + "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": 4183436, "tid": 4183436, + "ts": 667115481260.326, "dur": 41.423, + "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": 4183436, "tid": 4183436, + "ts": 667115481260.842, "dur": 40.232, + "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": 4183436, "tid": 4183436, + "ts": 667115481306.161, "dur": 3.805, + "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": 4183436, "tid": 4183436, + "ts": 667115481307.975, "dur": 0.884, + "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": 4183436, "tid": 4183436, + "ts": 667115481314.980, "dur": 1.367, + "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": 4183436, "tid": 4183436, + "ts": 667115481323.264, "dur": 6.617, + "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": 4183436, "tid": 4183436, + "ts": 667115481325.207, "dur": 4.449, + "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": 4183436, "tid": 4183436, + "ts": 667115481404.824, "dur": 197.327, + "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": 4183436, "tid": 4183436, + "ts": 667115481407.368, "dur": 2.231, + "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": 4183436, "tid": 4183436, + "ts": 667115481410.897, "dur": 190.780, + "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": 4183436, "tid": 4183436, + "ts": 667115481412.343, "dur": 0.325, + "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": 4183436, "tid": 4183436, + "ts": 667115481416.512, "dur": 19.277, + "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": 4183436, "tid": 4183436, + "ts": 667115481437.345, "dur": 3.185, + "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": 4183436, "tid": 4183436, + "ts": 667115481439.311, "dur": 1.031, + "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": 4183436, "tid": 4183436, + "ts": 667115481441.458, "dur": 22.394, + "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": 4183436, "tid": 4183436, + "ts": 667115481442.344, "dur": 3.482, + "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": 4183436, "tid": 4183436, + "ts": 667115481447.286, "dur": 16.290, + "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": 4183436, "tid": 4183436, + "ts": 667115481449.570, "dur": 2.647, + "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": 4183436, "tid": 4183436, + "ts": 667115481465.249, "dur": 17.642, + "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": 4183436, "tid": 4183436, + "ts": 667115481484.329, "dur": 32.086, + "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": 4183436, "tid": 4183436, + "ts": 667115481520.330, "dur": 16.037, + "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": 4183436, "tid": 4183436, + "ts": 667115481537.560, "dur": 12.950, + "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": 4183436, "tid": 4183436, + "ts": 667115481552.303, "dur": 21.762, + "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": 4183436, "tid": 4183436, + "ts": 667115481554.226, "dur": 1.947, + "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": 4183436, "tid": 4183436, + "ts": 667115481558.633, "dur": 1.199, + "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": 4183436, "tid": 4183436, + "ts": 667115481575.447, "dur": 12.436, + "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": 4183436, "tid": 4183436, + "ts": 667115481589.249, "dur": 11.421, + "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": 4183436, "tid": 4183436, + "ts": 667115481608.689, "dur": 2.437, + "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": 4183436, "tid": 4183436, + "ts": 667115481619.074, "dur": 3.535, + "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": 4183436, "tid": 4183436, + "ts": 667115481621.458, "dur": 0.404, + "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": 4183436, "tid": 4183436, + "ts": 667115481729.061, "dur": 49.212, + "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": 4183436, "tid": 4183436, + "ts": 667115481783.446, "dur": 6.000, + "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": 4183436, "tid": 4183436, + "ts": 667115481786.687, "dur": 1.141, + "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": 4183436, "tid": 4183436, + "ts": 667115481790.687, "dur": 23.180, + "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": 4183436, "tid": 4183436, + "ts": 667115481818.417, "dur": 8.210, + "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": 4183436, "tid": 4183436, + "ts": 667115481820.052, "dur": 5.675, + "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": 4183436, "tid": 4183436, + "ts": 667115481822.094, "dur": 3.398, + "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": 4183436, "tid": 4183436, + "ts": 667115481829.047, "dur": 40.992, + "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": 4183436, "tid": 4183436, + "ts": 667115481830.106, "dur": 39.324, + "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": 4183436, "tid": 4183436, + "ts": 667115481873.886, "dur": 16.037, + "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": 4183436, "tid": 4183436, + "ts": 667115481896.049, "dur": 4.182, + "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": 4183436, "tid": 4183436, + "ts": 667115481898.536, "dur": 0.874, + "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": 4183436, "tid": 4183436, + "ts": 667115481904.127, "dur": 66.128, + "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": 4183436, "tid": 4183436, + "ts": 667115481905.398, "dur": 3.924, + "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": 4183436, "tid": 4183436, + "ts": 667115481906.178, "dur": 2.603, + "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": 4183436, "tid": 4183436, + "ts": 667115481907.843, "dur": 0.804, + "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": 4183436, "tid": 4183436, + "ts": 667115481909.889, "dur": 60.040, + "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": 4183436, "tid": 4183436, + "ts": 667115481910.634, "dur": 58.646, + "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": 4183436, "tid": 4183436, + "ts": 667115481974.142, "dur": 4.091, + "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": 4183436, "tid": 4183436, + "ts": 667115481976.165, "dur": 0.840, + "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": 4183436, "tid": 4183436, + "ts": 667115481984.111, "dur": 1.870, + "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": 4183436, "tid": 4183436, + "ts": 667115481993.754, "dur": 5.865, + "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": 4183436, "tid": 4183436, + "ts": 667115481995.556, "dur": 3.809, + "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": 4183436, "tid": 4183436, + "ts": 667115482084.618, "dur": 192.016, + "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": 4183436, "tid": 4183436, + "ts": 667115482086.541, "dur": 2.283, + "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": 4183436, "tid": 4183436, + "ts": 667115482092.791, "dur": 183.429, + "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": 4183436, "tid": 4183436, + "ts": 667115482094.000, "dur": 0.368, + "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": 4183436, "tid": 4183436, + "ts": 667115482095.582, "dur": 23.552, + "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": 4183436, "tid": 4183436, + "ts": 667115482120.774, "dur": 5.445, + "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": 4183436, "tid": 4183436, + "ts": 667115482122.793, "dur": 3.133, + "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": 4183436, "tid": 4183436, + "ts": 667115482127.077, "dur": 21.763, + "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": 4183436, "tid": 4183436, + "ts": 667115482128.517, "dur": 1.767, + "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": 4183436, "tid": 4183436, + "ts": 667115482131.471, "dur": 17.093, + "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": 4183436, "tid": 4183436, + "ts": 667115482134.119, "dur": 2.908, + "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": 4183436, "tid": 4183436, + "ts": 667115482150.656, "dur": 23.481, + "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": 4183436, "tid": 4183436, + "ts": 667115482175.431, "dur": 18.890, + "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": 4183436, "tid": 4183436, + "ts": 667115482196.654, "dur": 15.418, + "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": 4183436, "tid": 4183436, + "ts": 667115482213.469, "dur": 13.447, + "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": 4183436, "tid": 4183436, + "ts": 667115482228.585, "dur": 20.522, + "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": 4183436, "tid": 4183436, + "ts": 667115482230.307, "dur": 1.509, + "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": 4183436, "tid": 4183436, + "ts": 667115482234.096, "dur": 0.956, + "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": 4183436, "tid": 4183436, + "ts": 667115482250.467, "dur": 12.076, + "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": 4183436, "tid": 4183436, + "ts": 667115482263.859, "dur": 11.460, + "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": 4183436, "tid": 4183436, + "ts": 667115482282.565, "dur": 1.475, + "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": 4183436, "tid": 4183436, + "ts": 667115482291.902, "dur": 3.516, + "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": 4183436, "tid": 4183436, + "ts": 667115482294.132, "dur": 0.487, + "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": 4183436, "tid": 4183436, + "ts": 667115482355.507, "dur": 38.435, + "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": 4183436, "tid": 4183436, + "ts": 667115482409.668, "dur": 7.631, + "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": 4183436, "tid": 4183436, + "ts": 667115482412.807, "dur": 3.540, + "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": 4183436, "tid": 4183436, + "ts": 667115482418.616, "dur": 20.379, + "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": 4183436, "tid": 4183436, + "ts": 667115482442.969, "dur": 5.474, + "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": 4183436, "tid": 4183436, + "ts": 667115482444.571, "dur": 3.177, + "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": 4183436, "tid": 4183436, + "ts": 667115482446.663, "dur": 0.918, + "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": 4183436, "tid": 4183436, + "ts": 667115482450.738, "dur": 58.784, + "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": 4183436, "tid": 4183436, + "ts": 667115482451.729, "dur": 56.707, + "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": 4183436, "tid": 4183436, + "ts": 667115482514.837, "dur": 16.064, + "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": 4183436, "tid": 4183436, + "ts": 667115482537.331, "dur": 4.770, + "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": 4183436, "tid": 4183436, + "ts": 667115482540.183, "dur": 0.965, + "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": 4183436, "tid": 4183436, + "ts": 667115482546.293, "dur": 51.455, + "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": 4183436, "tid": 4183436, + "ts": 667115482547.560, "dur": 4.528, + "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": 4183436, "tid": 4183436, + "ts": 667115482548.652, "dur": 2.949, + "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": 4183436, "tid": 4183436, + "ts": 667115482550.406, "dur": 1.077, + "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": 4183436, "tid": 4183436, + "ts": 667115482552.677, "dur": 44.686, + "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": 4183436, "tid": 4183436, + "ts": 667115482553.213, "dur": 43.476, + "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": 4183436, "tid": 4183436, + "ts": 667115482601.987, "dur": 3.735, + "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": 4183436, "tid": 4183436, + "ts": 667115482603.780, "dur": 0.799, + "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": 4183436, "tid": 4183436, + "ts": 667115482611.732, "dur": 1.479, + "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": 4183436, "tid": 4183436, + "ts": 667115482620.750, "dur": 6.993, + "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": 4183436, "tid": 4183436, + "ts": 667115482623.083, "dur": 4.410, + "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": 4183436, "tid": 4183436, + "ts": 667115482754.582, "dur": 182.634, + "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": 4183436, "tid": 4183436, + "ts": 667115482757.477, "dur": 4.918, + "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": 4183436, "tid": 4183436, + "ts": 667115482764.006, "dur": 172.706, + "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": 4183436, "tid": 4183436, + "ts": 667115482766.006, "dur": 0.456, + "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": 4183436, "tid": 4183436, + "ts": 667115482767.894, "dur": 20.841, + "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": 4183436, "tid": 4183436, + "ts": 667115482790.582, "dur": 5.751, + "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": 4183436, "tid": 4183436, + "ts": 667115482795.216, "dur": 0.819, + "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": 4183436, "tid": 4183436, + "ts": 667115482797.509, "dur": 20.555, + "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": 4183436, "tid": 4183436, + "ts": 667115482798.539, "dur": 1.442, + "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": 4183436, "tid": 4183436, + "ts": 667115482801.441, "dur": 16.368, + "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": 4183436, "tid": 4183436, + "ts": 667115482804.669, "dur": 2.319, + "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": 4183436, "tid": 4183436, + "ts": 667115482820.027, "dur": 19.247, + "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": 4183436, "tid": 4183436, + "ts": 667115482840.643, "dur": 12.076, + "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": 4183436, "tid": 4183436, + "ts": 667115482855.593, "dur": 18.459, + "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": 4183436, "tid": 4183436, + "ts": 667115482875.559, "dur": 11.030, + "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": 4183436, "tid": 4183436, + "ts": 667115482888.226, "dur": 21.146, + "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": 4183436, "tid": 4183436, + "ts": 667115482890.202, "dur": 1.576, + "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": 4183436, "tid": 4183436, + "ts": 667115482894.352, "dur": 3.154, + "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": 4183436, "tid": 4183436, + "ts": 667115482910.990, "dur": 10.609, + "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": 4183436, "tid": 4183436, + "ts": 667115482923.064, "dur": 12.613, + "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": 4183436, "tid": 4183436, + "ts": 667115482943.568, "dur": 2.085, + "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": 4183436, "tid": 4183436, + "ts": 667115482954.482, "dur": 3.805, + "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": 4183436, "tid": 4183436, + "ts": 667115482956.968, "dur": 0.506, + "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": 4183436, "tid": 4183436, + "ts": 667115483021.923, "dur": 45.217, + "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": 4183436, "tid": 4183436, + "ts": 667115483071.692, "dur": 5.593, + "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": 4183436, "tid": 4183436, + "ts": 667115483074.803, "dur": 1.465, + "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": 4183436, "tid": 4183436, + "ts": 667115483078.789, "dur": 21.325, + "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": 4183436, "tid": 4183436, + "ts": 667115483104.567, "dur": 6.947, + "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": 4183436, "tid": 4183436, + "ts": 667115483106.301, "dur": 4.511, + "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": 4183436, "tid": 4183436, + "ts": 667115483108.307, "dur": 2.271, + "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": 4183436, "tid": 4183436, + "ts": 667115483114.294, "dur": 41.187, + "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": 4183436, "tid": 4183436, + "ts": 667115483115.370, "dur": 39.355, + "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": 4183436, "tid": 4183436, + "ts": 667115483159.049, "dur": 15.342, + "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": 4183436, "tid": 4183436, + "ts": 667115483180.241, "dur": 23.368, + "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": 4183436, "tid": 4183436, + "ts": 667115483182.431, "dur": 20.818, + "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": 4183436, "tid": 4183436, + "ts": 667115483187.142, "dur": 1.194, + "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": 4183436, "tid": 4183436, + "ts": 667115483208.929, "dur": 27.497, + "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": 4183436, "tid": 4183436, + "ts": 667115483210.884, "dur": 25.329, + "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": 4183436, "tid": 4183436, + "ts": 667115483215.615, "dur": 4.529, + "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": 4183436, "tid": 4183436, + "ts": 667115483221.337, "dur": 14.411, + "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": 4183436, "tid": 4183436, + "ts": 667115483247.157, "dur": 4.970, + "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": 4183436, "tid": 4183436, + "ts": 667115483249.413, "dur": 2.441, + "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": 4183436, "tid": 4183436, + "ts": 667115483253.170, "dur": 1.324, + "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": 4183436, "tid": 4183436, + "ts": 667115483253.910, "dur": 0.517, + "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": 4183436, "tid": 4183436, + "ts": 667115483297.312, "dur": 22.098, + "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": 4183436, "tid": 4183436, + "ts": 667115483321.245, "dur": 14.976, + "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": 4183436, "tid": 4183436, "ts": 667115483321.245, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183436, "tid": 4183436, + "ts": 667115483341.892, "dur": 5.877, + "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": 4183436, "tid": 4183436, + "ts": 667115483345.356, "dur": 1.141, + "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": 4183436, "tid": 4183436, + "ts": 667115483350.478, "dur": 6.580, + "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": 4183436, "tid": 4183436, + "ts": 667115483354.888, "dur": 0.933, + "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": 4183436, "tid": 4183436, + "ts": 667115483358.498, "dur": 3.492, + "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": 4183436, "tid": 4183436, + "ts": 667115483360.533, "dur": 0.883, + "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": 4183436, "tid": 4183436, + "ts": 667115483366.242, "dur": 6.312, + "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": 4183436, "tid": 4183436, "ts": 667115483366.242, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115483370.155, "dur": 1.002, + "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": 4183436, "tid": 4183436, + "ts": 667115483373.695, "dur": 5.302, + "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": 4183436, "tid": 4183436, "ts": 667115483373.695, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115483377.261, "dur": 0.983, + "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": 4183436, "tid": 4183436, + "ts": 667115483379.929, "dur": 5.495, + "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": 4183436, "tid": 4183436, "ts": 667115483379.929, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115483383.821, "dur": 0.724, + "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": 4183436, "tid": 4183436, + "ts": 667115483386.525, "dur": 4.660, + "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": 4183436, "tid": 4183436, "ts": 667115483386.525, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 667115483389.627, "dur": 0.829, + "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": 4183436, "tid": 4183436, + "ts": 667115483394.901, "dur": 29.995, + "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": 4183436, "tid": 4183436, + "ts": 667115483396.449, "dur": 28.257, + "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": 4183436, "tid": 4183436, + "ts": 667115483399.006, "dur": 7.027, + "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": 4183436, "tid": 4183436, + "ts": 667115483401.461, "dur": 4.032, + "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": 4183436, "tid": 4183436, + "ts": 667115483406.735, "dur": 17.457, + "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": 4183436, "tid": 4183436, + "ts": 667115483449.575, "dur": 6.578, + "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": 4183436, "tid": 4183436, "ts": 667115483449.575, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 667115483458.791, "dur": 1.351, + "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": 4183436, "tid": 4183436, + "ts": 667115483514.534, "dur": 24189.949, + "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": 4183436, "tid": 4183436, "ts": 667115483514.534, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 4183436, + "ts": 667115483530.347, "dur": 33.055, + "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": 4183436, "tid": 4183436, + "ts": 667115483531.571, "dur": 31.649, + "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": 4183436, "tid": 4183436, + "ts": 667115483533.124, "dur": 7.786, + "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": 4183436, "tid": 4183436, + "ts": 667115483535.085, "dur": 5.136, + "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": 4183436, "tid": 4183436, + "ts": 667115483541.951, "dur": 20.780, + "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": 4183436, "tid": 4183436, + "ts": 667115483579.608, "dur": 26.272, + "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": 4183436, "tid": 4183436, + "ts": 667115483580.785, "dur": 6.717, + "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": 4183436, "tid": 4183436, + "ts": 667115483582.912, "dur": 4.197, + "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": 4183436, "tid": 4183436, + "ts": 667115483588.770, "dur": 16.872, + "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": 4183436, "tid": 4183436, + "ts": 667115483590.801, "dur": 14.465, + "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": 4183436, "tid": 4183436, + "ts": 667115483642.616, "dur": 61.335, + "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": 4183436, "tid": 4183436, + "ts": 667115483644.096, "dur": 5.300, + "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": 4183436, "tid": 4183436, + "ts": 667115483645.857, "dur": 3.243, + "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": 4183436, "tid": 4183436, + "ts": 667115483649.931, "dur": 53.823, + "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": 4183436, "tid": 4183436, + "ts": 667115483686.047, "dur": 17.039, + "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": 4183436, "tid": 4183436, + "ts": 667115483712.105, "dur": 26.453, + "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": 4183436, "tid": 4183436, + "ts": 667115483716.078, "dur": 3.343, + "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": 4183436, "tid": 4183436, + "ts": 667115483720.038, "dur": 18.269, + "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": 4183436, "tid": 4183436, + "ts": 667115483720.711, "dur": 17.292, + "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": 4183436, "tid": 4183436, + "ts": 667115483743.586, "dur": 22.250, + "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": 4183436, "tid": 4183436, + "ts": 667115483768.998, "dur": 48.077, + "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": 4183436, "tid": 4183436, + "ts": 667115483770.899, "dur": 45.688, + "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": 4183436, "tid": 4183436, + "ts": 667115483775.708, "dur": 0.963, + "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": 4183436, "tid": 4183436, + "ts": 667115483778.010, "dur": 23.972, + "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": 4183436, "tid": 4183436, + "ts": 667115483779.469, "dur": 22.331, + "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": 4183436, "tid": 4183436, + "ts": 667115483783.874, "dur": 2.913, + "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": 4183436, "tid": 4183436, + "ts": 667115483787.562, "dur": 13.887, + "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": 4183436, "tid": 4183436, + "ts": 667115483821.289, "dur": 18200.551, + "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": 4183436, "tid": 4183436, + "ts": 667115483822.542, "dur": 18197.628, + "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": 4183436, "tid": 4183436, + "ts": 667115502037.648, "dur": 9.417, + "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": 4183436, "tid": 4183436, + "ts": 667115502043.099, "dur": 1.578, + "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": 4183436, "tid": 4183436, + "ts": 667115502053.017, "dur": 111.570, + "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": 4183436, "tid": 4183436, + "ts": 667115502054.840, "dur": 7.503, + "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": 4183436, "tid": 4183436, + "ts": 667115502057.335, "dur": 4.193, + "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": 4183436, "tid": 4183436, + "ts": 667115502060.011, "dur": 1.216, + "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": 4183436, "tid": 4183436, + "ts": 667115502063.614, "dur": 100.055, + "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": 4183436, "tid": 4183436, + "ts": 667115502065.758, "dur": 96.970, + "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": 4183436, "tid": 4183436, + "ts": 667115502168.843, "dur": 5.138, + "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": 4183436, "tid": 4183436, + "ts": 667115502171.607, "dur": 0.740, + "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": 4183436, "tid": 4183436, + "ts": 667115502183.687, "dur": 2.980, + "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": 4183436, "tid": 4183436, + "ts": 667115502202.300, "dur": 7.388, + "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": 4183436, "tid": 4183436, + "ts": 667115502204.478, "dur": 4.917, + "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": 4183436, "tid": 4183436, + "ts": 667115502347.818, "dur": 220.051, + "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": 4183436, "tid": 4183436, + "ts": 667115502353.350, "dur": 2.263, + "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": 4183436, "tid": 4183436, + "ts": 667115502357.626, "dur": 209.708, + "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": 4183436, "tid": 4183436, + "ts": 667115502359.742, "dur": 0.419, + "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": 4183436, "tid": 4183436, + "ts": 667115502361.804, "dur": 27.831, + "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": 4183436, "tid": 4183436, + "ts": 667115502391.630, "dur": 6.111, + "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": 4183436, "tid": 4183436, + "ts": 667115502396.696, "dur": 0.766, + "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": 4183436, "tid": 4183436, + "ts": 667115502399.040, "dur": 24.508, + "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": 4183436, "tid": 4183436, + "ts": 667115502400.277, "dur": 1.387, + "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": 4183436, "tid": 4183436, + "ts": 667115502403.633, "dur": 19.588, + "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": 4183436, "tid": 4183436, + "ts": 667115502407.551, "dur": 3.334, + "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": 4183436, "tid": 4183436, + "ts": 667115502425.550, "dur": 24.010, + "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": 4183436, "tid": 4183436, + "ts": 667115502451.317, "dur": 14.890, + "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": 4183436, "tid": 4183436, + "ts": 667115502469.512, "dur": 14.889, + "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": 4183436, "tid": 4183436, + "ts": 667115502485.932, "dur": 28.399, + "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": 4183436, "tid": 4183436, + "ts": 667115502517.512, "dur": 22.775, + "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": 4183436, "tid": 4183436, + "ts": 667115502520.121, "dur": 2.413, + "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": 4183436, "tid": 4183436, + "ts": 667115502525.285, "dur": 0.945, + "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": 4183436, "tid": 4183436, + "ts": 667115502542.077, "dur": 12.068, + "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": 4183436, "tid": 4183436, + "ts": 667115502555.762, "dur": 10.485, + "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": 4183436, "tid": 4183436, + "ts": 667115502576.307, "dur": 3.032, + "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": 4183436, "tid": 4183436, + "ts": 667115502587.595, "dur": 4.783, + "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": 4183436, "tid": 4183436, + "ts": 667115502590.606, "dur": 0.698, + "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": 4183436, "tid": 4183436, + "ts": 667115502706.414, "dur": 64.114, + "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": 4183436, "tid": 4183436, + "ts": 667115502777.271, "dur": 14.003, + "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": 4183436, "tid": 4183436, + "ts": 667115502786.891, "dur": 1.826, + "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": 4183436, "tid": 4183436, + "ts": 667115502793.027, "dur": 25.136, + "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": 4183436, "tid": 4183436, + "ts": 667115502824.789, "dur": 8.483, + "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": 4183436, "tid": 4183436, + "ts": 667115502826.801, "dur": 5.654, + "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": 4183436, "tid": 4183436, + "ts": 667115502829.059, "dur": 3.092, + "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": 4183436, "tid": 4183436, + "ts": 667115502836.329, "dur": 48.215, + "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": 4183436, "tid": 4183436, + "ts": 667115502837.749, "dur": 46.023, + "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": 4183436, "tid": 4183436, + "ts": 667115502889.274, "dur": 16.064, + "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": 4183436, "tid": 4183436, + "ts": 667115502912.568, "dur": 4.646, + "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": 4183436, "tid": 4183436, + "ts": 667115502915.052, "dur": 1.027, + "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": 4183436, "tid": 4183436, + "ts": 667115502921.835, "dur": 52.545, + "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": 4183436, "tid": 4183436, + "ts": 667115502923.170, "dur": 4.473, + "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": 4183436, "tid": 4183436, + "ts": 667115502924.200, "dur": 2.890, + "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": 4183436, "tid": 4183436, + "ts": 667115502926.198, "dur": 0.753, + "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": 4183436, "tid": 4183436, + "ts": 667115502928.157, "dur": 45.796, + "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": 4183436, "tid": 4183436, + "ts": 667115502928.993, "dur": 44.476, + "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": 4183436, "tid": 4183436, + "ts": 667115502978.826, "dur": 4.054, + "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": 4183436, "tid": 4183436, + "ts": 667115502980.740, "dur": 0.699, + "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": 4183436, "tid": 4183436, + "ts": 667115502989.886, "dur": 1.927, + "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": 4183436, "tid": 4183436, + "ts": 667115503000.597, "dur": 7.812, + "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": 4183436, "tid": 4183436, + "ts": 667115503003.079, "dur": 5.046, + "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": 4183436, "tid": 4183436, + "ts": 667115503107.966, "dur": 242.241, + "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": 4183436, "tid": 4183436, + "ts": 667115503110.123, "dur": 2.577, + "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": 4183436, "tid": 4183436, + "ts": 667115503116.437, "dur": 233.274, + "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": 4183436, "tid": 4183436, + "ts": 667115503118.287, "dur": 0.526, + "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": 4183436, "tid": 4183436, + "ts": 667115503120.296, "dur": 20.610, + "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": 4183436, "tid": 4183436, + "ts": 667115503142.836, "dur": 5.561, + "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": 4183436, "tid": 4183436, + "ts": 667115503145.367, "dur": 2.690, + "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": 4183436, "tid": 4183436, + "ts": 667115503149.695, "dur": 21.252, + "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": 4183436, "tid": 4183436, + "ts": 667115503151.333, "dur": 1.305, + "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": 4183436, "tid": 4183436, + "ts": 667115503153.954, "dur": 16.723, + "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": 4183436, "tid": 4183436, + "ts": 667115503156.881, "dur": 2.865, + "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": 4183436, "tid": 4183436, + "ts": 667115503172.549, "dur": 20.730, + "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": 4183436, "tid": 4183436, + "ts": 667115503194.671, "dur": 12.732, + "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": 4183436, "tid": 4183436, + "ts": 667115503210.008, "dur": 14.556, + "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": 4183436, "tid": 4183436, + "ts": 667115503225.972, "dur": 12.956, + "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": 4183436, "tid": 4183436, + "ts": 667115503240.683, "dur": 22.321, + "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": 4183436, "tid": 4183436, + "ts": 667115503243.240, "dur": 1.454, + "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": 4183436, "tid": 4183436, + "ts": 667115503246.756, "dur": 2.763, + "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": 4183436, "tid": 4183436, + "ts": 667115503264.736, "dur": 39.085, + "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": 4183436, "tid": 4183436, + "ts": 667115503305.076, "dur": 43.611, + "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": 4183436, "tid": 4183436, + "ts": 667115503356.331, "dur": 1.870, + "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": 4183436, "tid": 4183436, + "ts": 667115503366.559, "dur": 3.465, + "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": 4183436, "tid": 4183436, + "ts": 667115503368.751, "dur": 0.333, + "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": 4183436, "tid": 4183436, + "ts": 667115503437.918, "dur": 42.174, + "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": 4183436, "tid": 4183436, + "ts": 667115503484.633, "dur": 4.465, + "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": 4183436, "tid": 4183436, + "ts": 667115503487.144, "dur": 0.854, + "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": 4183436, "tid": 4183436, + "ts": 667115503490.446, "dur": 42.724, + "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": 4183436, "tid": 4183436, + "ts": 667115503548.221, "dur": 8.925, + "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": 4183436, "tid": 4183436, + "ts": 667115503550.713, "dur": 5.572, + "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": 4183436, "tid": 4183436, + "ts": 667115503552.826, "dur": 3.240, + "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": 4183436, "tid": 4183436, + "ts": 667115503560.015, "dur": 47.899, + "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": 4183436, "tid": 4183436, + "ts": 667115503561.441, "dur": 45.852, + "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": 4183436, "tid": 4183436, + "ts": 667115503611.791, "dur": 16.276, + "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": 4183436, "tid": 4183436, + "ts": 667115503634.832, "dur": 4.303, + "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": 4183436, "tid": 4183436, + "ts": 667115503637.213, "dur": 1.011, + "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": 4183436, "tid": 4183436, + "ts": 667115503643.384, "dur": 90.270, + "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": 4183436, "tid": 4183436, + "ts": 667115503644.168, "dur": 4.228, + "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": 4183436, "tid": 4183436, + "ts": 667115503645.221, "dur": 2.620, + "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": 4183436, "tid": 4183436, + "ts": 667115503646.808, "dur": 0.883, + "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": 4183436, "tid": 4183436, + "ts": 667115503649.040, "dur": 84.158, + "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": 4183436, "tid": 4183436, + "ts": 667115503649.755, "dur": 82.363, + "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": 4183436, "tid": 4183436, + "ts": 667115503739.905, "dur": 5.035, + "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": 4183436, "tid": 4183436, + "ts": 667115503742.475, "dur": 0.879, + "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": 4183436, "tid": 4183436, + "ts": 667115503751.854, "dur": 1.703, + "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": 4183436, "tid": 4183436, + "ts": 667115503761.484, "dur": 7.454, + "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": 4183436, "tid": 4183436, + "ts": 667115503764.130, "dur": 4.449, + "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": 4183436, "tid": 4183436, + "ts": 667115503865.834, "dur": 186.596, + "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": 4183436, "tid": 4183436, + "ts": 667115503868.180, "dur": 3.107, + "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": 4183436, "tid": 4183436, + "ts": 667115503874.748, "dur": 177.210, + "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": 4183436, "tid": 4183436, + "ts": 667115503876.487, "dur": 0.344, + "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": 4183436, "tid": 4183436, + "ts": 667115503878.433, "dur": 23.480, + "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": 4183436, "tid": 4183436, + "ts": 667115503903.679, "dur": 5.718, + "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": 4183436, "tid": 4183436, + "ts": 667115503906.036, "dur": 3.109, + "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": 4183436, "tid": 4183436, + "ts": 667115503910.492, "dur": 23.418, + "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": 4183436, "tid": 4183436, + "ts": 667115503911.830, "dur": 1.971, + "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": 4183436, "tid": 4183436, + "ts": 667115503915.191, "dur": 18.463, + "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": 4183436, "tid": 4183436, + "ts": 667115503918.050, "dur": 2.675, + "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": 4183436, "tid": 4183436, + "ts": 667115503937.914, "dur": 20.363, + "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": 4183436, "tid": 4183436, + "ts": 667115503959.777, "dur": 16.618, + "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": 4183436, "tid": 4183436, + "ts": 667115503979.384, "dur": 12.879, + "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": 4183436, "tid": 4183436, + "ts": 667115503993.772, "dur": 11.562, + "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": 4183436, "tid": 4183436, + "ts": 667115504007.039, "dur": 19.589, + "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": 4183436, "tid": 4183436, + "ts": 667115504008.959, "dur": 1.602, + "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": 4183436, "tid": 4183436, + "ts": 667115504013.029, "dur": 0.865, + "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": 4183436, "tid": 4183436, + "ts": 667115504028.356, "dur": 10.964, + "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": 4183436, "tid": 4183436, + "ts": 667115504040.303, "dur": 10.462, + "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": 4183436, "tid": 4183436, + "ts": 667115504058.790, "dur": 1.801, + "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": 4183436, "tid": 4183436, + "ts": 667115504070.097, "dur": 3.346, + "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": 4183436, "tid": 4183436, + "ts": 667115504072.254, "dur": 0.357, + "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": 4183436, "tid": 4183436, + "ts": 667115504138.204, "dur": 40.816, + "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": 4183436, "tid": 4183436, + "ts": 667115504183.633, "dur": 5.280, + "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": 4183436, "tid": 4183436, + "ts": 667115504186.502, "dur": 1.202, + "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": 4183436, "tid": 4183436, + "ts": 667115504190.211, "dur": 20.287, + "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": 4183436, "tid": 4183436, + "ts": 667115504214.577, "dur": 5.798, + "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": 4183436, "tid": 4183436, + "ts": 667115504216.182, "dur": 3.500, + "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": 4183436, "tid": 4183436, + "ts": 667115504218.142, "dur": 1.342, + "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": 4183436, "tid": 4183436, + "ts": 667115504223.119, "dur": 43.379, + "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": 4183436, "tid": 4183436, + "ts": 667115504224.804, "dur": 41.146, + "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": 4183436, "tid": 4183436, + "ts": 667115504270.414, "dur": 13.022, + "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": 4183436, "tid": 4183436, + "ts": 667115504288.740, "dur": 4.513, + "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": 4183436, "tid": 4183436, + "ts": 667115504291.489, "dur": 0.759, + "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": 4183436, "tid": 4183436, + "ts": 667115504297.173, "dur": 47.058, + "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": 4183436, "tid": 4183436, + "ts": 667115504298.023, "dur": 4.609, + "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": 4183436, "tid": 4183436, + "ts": 667115504298.856, "dur": 3.199, + "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": 4183436, "tid": 4183436, + "ts": 667115504300.886, "dur": 1.041, + "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": 4183436, "tid": 4183436, + "ts": 667115504303.592, "dur": 40.278, + "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": 4183436, "tid": 4183436, + "ts": 667115504304.516, "dur": 38.838, + "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": 4183436, "tid": 4183436, + "ts": 667115504348.098, "dur": 4.211, + "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": 4183436, "tid": 4183436, + "ts": 667115504350.278, "dur": 0.865, + "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": 4183436, "tid": 4183436, + "ts": 667115504357.543, "dur": 1.433, + "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": 4183436, "tid": 4183436, + "ts": 667115504366.389, "dur": 8.118, + "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": 4183436, "tid": 4183436, + "ts": 667115504368.494, "dur": 5.740, + "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": 4183436, "tid": 4183436, + "ts": 667115504452.414, "dur": 194.677, + "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": 4183436, "tid": 4183436, + "ts": 667115504454.320, "dur": 2.436, + "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": 4183436, "tid": 4183436, + "ts": 667115504458.205, "dur": 188.366, + "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": 4183436, "tid": 4183436, + "ts": 667115504459.770, "dur": 0.272, + "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": 4183436, "tid": 4183436, + "ts": 667115504461.253, "dur": 20.272, + "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": 4183436, "tid": 4183436, + "ts": 667115504483.112, "dur": 3.273, + "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": 4183436, "tid": 4183436, + "ts": 667115504485.232, "dur": 0.984, + "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": 4183436, "tid": 4183436, + "ts": 667115504487.327, "dur": 45.445, + "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": 4183436, "tid": 4183436, + "ts": 667115504488.580, "dur": 19.931, + "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": 4183436, "tid": 4183436, + "ts": 667115504510.675, "dur": 21.845, + "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": 4183436, "tid": 4183436, + "ts": 667115504516.418, "dur": 3.484, + "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": 4183436, "tid": 4183436, + "ts": 667115504534.173, "dur": 22.050, + "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": 4183436, "tid": 4183436, + "ts": 667115504557.786, "dur": 12.596, + "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": 4183436, "tid": 4183436, + "ts": 667115504573.088, "dur": 14.360, + "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": 4183436, "tid": 4183436, + "ts": 667115504588.820, "dur": 11.521, + "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": 4183436, "tid": 4183436, + "ts": 667115504601.914, "dur": 19.360, + "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": 4183436, "tid": 4183436, + "ts": 667115504603.925, "dur": 1.715, + "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": 4183436, "tid": 4183436, + "ts": 667115504608.122, "dur": 1.062, + "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": 4183436, "tid": 4183436, + "ts": 667115504623.012, "dur": 10.407, + "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": 4183436, "tid": 4183436, + "ts": 667115504634.437, "dur": 10.721, + "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": 4183436, "tid": 4183436, + "ts": 667115504689.100, "dur": 2.768, + "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": 4183436, "tid": 4183436, + "ts": 667115504702.621, "dur": 4.123, + "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": 4183436, "tid": 4183436, + "ts": 667115504705.136, "dur": 0.673, + "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": 4183436, "tid": 4183436, + "ts": 667115504777.857, "dur": 48.190, + "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": 4183436, "tid": 4183436, + "ts": 667115504830.481, "dur": 5.650, + "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": 4183436, "tid": 4183436, + "ts": 667115504833.546, "dur": 1.337, + "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": 4183436, "tid": 4183436, + "ts": 667115504837.448, "dur": 22.007, + "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": 4183436, "tid": 4183436, + "ts": 667115504864.007, "dur": 6.352, + "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": 4183436, "tid": 4183436, + "ts": 667115504865.988, "dur": 3.487, + "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": 4183436, "tid": 4183436, + "ts": 667115504868.217, "dur": 1.006, + "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": 4183436, "tid": 4183436, + "ts": 667115504873.000, "dur": 41.333, + "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": 4183436, "tid": 4183436, + "ts": 667115504874.608, "dur": 39.038, + "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": 4183436, "tid": 4183436, + "ts": 667115504918.632, "dur": 14.581, + "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": 4183436, "tid": 4183436, + "ts": 667115504939.405, "dur": 4.541, + "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": 4183436, "tid": 4183436, + "ts": 667115504942.009, "dur": 1.082, + "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": 4183436, "tid": 4183436, + "ts": 667115504948.055, "dur": 51.435, + "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": 4183436, "tid": 4183436, + "ts": 667115504949.098, "dur": 6.984, + "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": 4183436, "tid": 4183436, + "ts": 667115504950.067, "dur": 5.444, + "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": 4183436, "tid": 4183436, + "ts": 667115504951.759, "dur": 3.574, + "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": 4183436, "tid": 4183436, + "ts": 667115504956.706, "dur": 42.347, + "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": 4183436, "tid": 4183436, + "ts": 667115504957.702, "dur": 40.570, + "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": 4183436, "tid": 4183436, + "ts": 667115505003.648, "dur": 4.483, + "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": 4183436, "tid": 4183436, + "ts": 667115505005.909, "dur": 1.146, + "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": 4183436, "tid": 4183436, + "ts": 667115505014.029, "dur": 1.478, + "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": 4183436, "tid": 4183436, + "ts": 667115505022.814, "dur": 6.236, + "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": 4183436, "tid": 4183436, + "ts": 667115505024.943, "dur": 3.863, + "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": 4183436, "tid": 4183436, + "ts": 667115505118.391, "dur": 171.896, + "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": 4183436, "tid": 4183436, + "ts": 667115505120.780, "dur": 2.116, + "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": 4183436, "tid": 4183436, + "ts": 667115505124.106, "dur": 165.741, + "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": 4183436, "tid": 4183436, + "ts": 667115505125.716, "dur": 0.486, + "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": 4183436, "tid": 4183436, + "ts": 667115505129.909, "dur": 24.292, + "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": 4183436, "tid": 4183436, + "ts": 667115505155.887, "dur": 3.521, + "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": 4183436, "tid": 4183436, + "ts": 667115505158.141, "dur": 0.876, + "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": 4183436, "tid": 4183436, + "ts": 667115505160.396, "dur": 21.835, + "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": 4183436, "tid": 4183436, + "ts": 667115505161.476, "dur": 3.394, + "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": 4183436, "tid": 4183436, + "ts": 667115505166.108, "dur": 15.878, + "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": 4183436, "tid": 4183436, + "ts": 667115505168.977, "dur": 2.804, + "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": 4183436, "tid": 4183436, + "ts": 667115505183.747, "dur": 18.739, + "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": 4183436, "tid": 4183436, + "ts": 667115505204.018, "dur": 12.879, + "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": 4183436, "tid": 4183436, + "ts": 667115505219.444, "dur": 12.467, + "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": 4183436, "tid": 4183436, + "ts": 667115505233.527, "dur": 11.302, + "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": 4183436, "tid": 4183436, + "ts": 667115505246.530, "dur": 17.976, + "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": 4183436, "tid": 4183436, + "ts": 667115505248.469, "dur": 1.431, + "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": 4183436, "tid": 4183436, + "ts": 667115505252.456, "dur": 0.754, + "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": 4183436, "tid": 4183436, + "ts": 667115505266.039, "dur": 11.303, + "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": 4183436, "tid": 4183436, + "ts": 667115505278.617, "dur": 10.205, + "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": 4183436, "tid": 4183436, + "ts": 667115505296.070, "dur": 1.776, + "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": 4183436, "tid": 4183436, + "ts": 667115505307.070, "dur": 3.395, + "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": 4183436, "tid": 4183436, + "ts": 667115505309.301, "dur": 0.459, + "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": 4183436, "tid": 4183436, + "ts": 667115505372.548, "dur": 38.816, + "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": 4183436, "tid": 4183436, + "ts": 667115505415.896, "dur": 5.029, + "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": 4183436, "tid": 4183436, + "ts": 667115505418.280, "dur": 1.395, + "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": 4183436, "tid": 4183436, + "ts": 667115505422.196, "dur": 22.172, + "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": 4183436, "tid": 4183436, + "ts": 667115505448.559, "dur": 7.209, + "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": 4183436, "tid": 4183436, + "ts": 667115505450.017, "dur": 5.099, + "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": 4183436, "tid": 4183436, + "ts": 667115505451.997, "dur": 2.922, + "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": 4183436, "tid": 4183436, + "ts": 667115505457.871, "dur": 59.967, + "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": 4183436, "tid": 4183436, + "ts": 667115505458.979, "dur": 57.921, + "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": 4183436, "tid": 4183436, + "ts": 667115505522.949, "dur": 16.394, + "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": 4183436, "tid": 4183436, + "ts": 667115505546.106, "dur": 4.799, + "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": 4183436, "tid": 4183436, + "ts": 667115505548.598, "dur": 1.143, + "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": 4183436, "tid": 4183436, + "ts": 667115505554.942, "dur": 51.353, + "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": 4183436, "tid": 4183436, + "ts": 667115505555.767, "dur": 4.524, + "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": 4183436, "tid": 4183436, + "ts": 667115505556.978, "dur": 2.726, + "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": 4183436, "tid": 4183436, + "ts": 667115505558.608, "dur": 0.805, + "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": 4183436, "tid": 4183436, + "ts": 667115505561.096, "dur": 44.814, + "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": 4183436, "tid": 4183436, + "ts": 667115505562.016, "dur": 43.302, + "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": 4183436, "tid": 4183436, + "ts": 667115505610.574, "dur": 4.224, + "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": 4183436, "tid": 4183436, + "ts": 667115505612.581, "dur": 1.050, + "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": 4183436, "tid": 4183436, + "ts": 667115505620.437, "dur": 1.559, + "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": 4183436, "tid": 4183436, + "ts": 667115505629.479, "dur": 7.253, + "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": 4183436, "tid": 4183436, + "ts": 667115505631.688, "dur": 4.736, + "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": 4183436, "tid": 4183436, + "ts": 667115505763.794, "dur": 196.482, + "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": 4183436, "tid": 4183436, + "ts": 667115505766.444, "dur": 3.131, + "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": 4183436, "tid": 4183436, + "ts": 667115505773.919, "dur": 185.822, + "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": 4183436, "tid": 4183436, + "ts": 667115505775.407, "dur": 0.407, + "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": 4183436, "tid": 4183436, + "ts": 667115505777.003, "dur": 23.992, + "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": 4183436, "tid": 4183436, + "ts": 667115505802.583, "dur": 5.251, + "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": 4183436, "tid": 4183436, + "ts": 667115505804.315, "dur": 3.169, + "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": 4183436, "tid": 4183436, + "ts": 667115505808.731, "dur": 22.503, + "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": 4183436, "tid": 4183436, + "ts": 667115505809.996, "dur": 1.608, + "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": 4183436, "tid": 4183436, + "ts": 667115505812.764, "dur": 18.230, + "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": 4183436, "tid": 4183436, + "ts": 667115505815.350, "dur": 2.637, + "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": 4183436, "tid": 4183436, + "ts": 667115505832.682, "dur": 21.008, + "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": 4183436, "tid": 4183436, + "ts": 667115505855.059, "dur": 13.740, + "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": 4183436, "tid": 4183436, + "ts": 667115505871.639, "dur": 15.802, + "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": 4183436, "tid": 4183436, + "ts": 667115505888.683, "dur": 13.113, + "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": 4183436, "tid": 4183436, + "ts": 667115505903.607, "dur": 26.064, + "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": 4183436, "tid": 4183436, + "ts": 667115505905.912, "dur": 1.577, + "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": 4183436, "tid": 4183436, + "ts": 667115505909.788, "dur": 3.098, + "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": 4183436, "tid": 4183436, + "ts": 667115505931.645, "dur": 13.258, + "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": 4183436, "tid": 4183436, + "ts": 667115505946.249, "dur": 12.031, + "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": 4183436, "tid": 4183436, + "ts": 667115505967.007, "dur": 2.477, + "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": 4183436, "tid": 4183436, + "ts": 667115505993.010, "dur": 4.026, + "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": 4183436, "tid": 4183436, + "ts": 667115505995.588, "dur": 0.538, + "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": 4183436, "tid": 4183436, + "ts": 667115506059.446, "dur": 47.616, + "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": 4183436, "tid": 4183436, + "ts": 667115506112.162, "dur": 5.057, + "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": 4183436, "tid": 4183436, + "ts": 667115506115.044, "dur": 0.975, + "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": 4183436, "tid": 4183436, + "ts": 667115506118.566, "dur": 22.957, + "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": 4183436, "tid": 4183436, + "ts": 667115506145.769, "dur": 8.014, + "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": 4183436, "tid": 4183436, + "ts": 667115506147.329, "dur": 5.783, + "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": 4183436, "tid": 4183436, + "ts": 667115506149.599, "dur": 3.311, + "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": 4183436, "tid": 4183436, + "ts": 667115506156.084, "dur": 51.358, + "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": 4183436, "tid": 4183436, + "ts": 667115506157.749, "dur": 48.812, + "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": 4183436, "tid": 4183436, + "ts": 667115506211.050, "dur": 38.631, + "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": 4183436, "tid": 4183436, + "ts": 667115506255.098, "dur": 3.840, + "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": 4183436, "tid": 4183436, + "ts": 667115506257.052, "dur": 0.939, + "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": 4183436, "tid": 4183436, + "ts": 667115506262.764, "dur": 77.855, + "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": 4183436, "tid": 4183436, + "ts": 667115506263.478, "dur": 4.403, + "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": 4183436, "tid": 4183436, + "ts": 667115506264.858, "dur": 2.456, + "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": 4183436, "tid": 4183436, + "ts": 667115506266.391, "dur": 0.787, + "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": 4183436, "tid": 4183436, + "ts": 667115506268.516, "dur": 71.645, + "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": 4183436, "tid": 4183436, + "ts": 667115506269.632, "dur": 69.995, + "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": 4183436, "tid": 4183436, + "ts": 667115506344.684, "dur": 3.893, + "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": 4183436, "tid": 4183436, + "ts": 667115506346.680, "dur": 0.720, + "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": 4183436, "tid": 4183436, + "ts": 667115506353.616, "dur": 1.384, + "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": 4183436, "tid": 4183436, + "ts": 667115506362.453, "dur": 6.339, + "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": 4183436, "tid": 4183436, + "ts": 667115506364.575, "dur": 3.967, + "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": 4183436, "tid": 4183436, + "ts": 667115506447.310, "dur": 201.370, + "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": 4183436, "tid": 4183436, + "ts": 667115506449.358, "dur": 1.921, + "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": 4183436, "tid": 4183436, + "ts": 667115506454.859, "dur": 193.272, + "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": 4183436, "tid": 4183436, + "ts": 667115506456.340, "dur": 0.328, + "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": 4183436, "tid": 4183436, + "ts": 667115506457.933, "dur": 20.366, + "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": 4183436, "tid": 4183436, + "ts": 667115506479.837, "dur": 5.115, + "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": 4183436, "tid": 4183436, + "ts": 667115506481.785, "dur": 2.978, + "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": 4183436, "tid": 4183436, + "ts": 667115506485.908, "dur": 41.822, + "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": 4183436, "tid": 4183436, + "ts": 667115506487.008, "dur": 1.391, + "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": 4183436, "tid": 4183436, + "ts": 667115506489.544, "dur": 37.881, + "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": 4183436, "tid": 4183436, + "ts": 667115506510.409, "dur": 3.125, + "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": 4183436, "tid": 4183436, + "ts": 667115506529.317, "dur": 21.012, + "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": 4183436, "tid": 4183436, + "ts": 667115506551.569, "dur": 14.367, + "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": 4183436, "tid": 4183436, + "ts": 667115506568.636, "dur": 14.192, + "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": 4183436, "tid": 4183436, + "ts": 667115506584.476, "dur": 12.838, + "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": 4183436, "tid": 4183436, + "ts": 667115506598.945, "dur": 21.561, + "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": 4183436, "tid": 4183436, + "ts": 667115506601.049, "dur": 1.312, + "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": 4183436, "tid": 4183436, + "ts": 667115506604.848, "dur": 1.530, + "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": 4183436, "tid": 4183436, + "ts": 667115506622.006, "dur": 13.166, + "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": 4183436, "tid": 4183436, + "ts": 667115506636.326, "dur": 10.925, + "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": 4183436, "tid": 4183436, + "ts": 667115506691.567, "dur": 2.894, + "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": 4183436, "tid": 4183436, + "ts": 667115506704.761, "dur": 3.992, + "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": 4183436, "tid": 4183436, + "ts": 667115506707.228, "dur": 0.586, + "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": 4183436, "tid": 4183436, + "ts": 667115506780.813, "dur": 47.831, + "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": 4183436, "tid": 4183436, + "ts": 667115506833.404, "dur": 7.330, + "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": 4183436, "tid": 4183436, + "ts": 667115506836.268, "dur": 3.216, + "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": 4183436, "tid": 4183436, + "ts": 667115506841.910, "dur": 21.549, + "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": 4183436, "tid": 4183436, + "ts": 667115506868.133, "dur": 6.375, + "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": 4183436, "tid": 4183436, + "ts": 667115506869.475, "dur": 4.146, + "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": 4183436, "tid": 4183436, + "ts": 667115506871.863, "dur": 1.269, + "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": 4183436, "tid": 4183436, + "ts": 667115506876.923, "dur": 39.679, + "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": 4183436, "tid": 4183436, + "ts": 667115506878.340, "dur": 37.554, + "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": 4183436, "tid": 4183436, + "ts": 667115506920.536, "dur": 13.423, + "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": 4183436, "tid": 4183436, + "ts": 667115506939.580, "dur": 4.534, + "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": 4183436, "tid": 4183436, + "ts": 667115506942.253, "dur": 0.977, + "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": 4183436, "tid": 4183436, + "ts": 667115506947.935, "dur": 46.241, + "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": 4183436, "tid": 4183436, + "ts": 667115506949.307, "dur": 4.531, + "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": 4183436, "tid": 4183436, + "ts": 667115506950.285, "dur": 2.963, + "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": 4183436, "tid": 4183436, + "ts": 667115506951.976, "dur": 0.949, + "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": 4183436, "tid": 4183436, + "ts": 667115506954.354, "dur": 39.454, + "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": 4183436, "tid": 4183436, + "ts": 667115506955.054, "dur": 38.125, + "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": 4183436, "tid": 4183436, + "ts": 667115506998.493, "dur": 3.914, + "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": 4183436, "tid": 4183436, + "ts": 667115507000.485, "dur": 0.764, + "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": 4183436, "tid": 4183436, + "ts": 667115507007.695, "dur": 1.395, + "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": 4183436, "tid": 4183436, + "ts": 667115507016.508, "dur": 6.920, + "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": 4183436, "tid": 4183436, + "ts": 667115507018.916, "dur": 4.234, + "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": 4183436, "tid": 4183436, + "ts": 667115507099.059, "dur": 171.625, + "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": 4183436, "tid": 4183436, + "ts": 667115507101.575, "dur": 4.507, + "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": 4183436, "tid": 4183436, + "ts": 667115507107.233, "dur": 163.004, + "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": 4183436, "tid": 4183436, + "ts": 667115507109.161, "dur": 0.548, + "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": 4183436, "tid": 4183436, + "ts": 667115507111.002, "dur": 17.887, + "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": 4183436, "tid": 4183436, + "ts": 667115507130.448, "dur": 5.789, + "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": 4183436, "tid": 4183436, + "ts": 667115507135.144, "dur": 0.861, + "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": 4183436, "tid": 4183436, + "ts": 667115507137.283, "dur": 20.407, + "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": 4183436, "tid": 4183436, + "ts": 667115507138.309, "dur": 1.768, + "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": 4183436, "tid": 4183436, + "ts": 667115507141.326, "dur": 16.136, + "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": 4183436, "tid": 4183436, + "ts": 667115507144.029, "dur": 3.021, + "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": 4183436, "tid": 4183436, + "ts": 667115507159.338, "dur": 19.326, + "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": 4183436, "tid": 4183436, + "ts": 667115507179.908, "dur": 13.769, + "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": 4183436, "tid": 4183436, + "ts": 667115507196.502, "dur": 13.844, + "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": 4183436, "tid": 4183436, + "ts": 667115507211.774, "dur": 11.061, + "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": 4183436, "tid": 4183436, + "ts": 667115507224.539, "dur": 20.865, + "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": 4183436, "tid": 4183436, + "ts": 667115507228.459, "dur": 1.631, + "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": 4183436, "tid": 4183436, + "ts": 667115507232.496, "dur": 1.094, + "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": 4183436, "tid": 4183436, + "ts": 667115507246.643, "dur": 10.525, + "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": 4183436, "tid": 4183436, + "ts": 667115507258.359, "dur": 10.712, + "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": 4183436, "tid": 4183436, + "ts": 667115507276.758, "dur": 1.464, + "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": 4183436, "tid": 4183436, + "ts": 667115507285.878, "dur": 3.789, + "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": 4183436, "tid": 4183436, + "ts": 667115507288.216, "dur": 0.636, + "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": 4183436, "tid": 4183436, + "ts": 667115507349.623, "dur": 39.622, + "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": 4183436, "tid": 4183436, + "ts": 667115507393.647, "dur": 13.351, + "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": 4183436, "tid": 4183436, + "ts": 667115507404.756, "dur": 1.078, + "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": 4183436, "tid": 4183436, + "ts": 667115507408.411, "dur": 21.185, + "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": 4183436, "tid": 4183436, + "ts": 667115507433.801, "dur": 8.474, + "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": 4183436, "tid": 4183436, + "ts": 667115507435.200, "dur": 6.316, + "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": 4183436, "tid": 4183436, + "ts": 667115507437.449, "dur": 3.700, + "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": 4183436, "tid": 4183436, + "ts": 667115507445.390, "dur": 69.316, + "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": 4183436, "tid": 4183436, + "ts": 667115507447.285, "dur": 66.210, + "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": 4183436, "tid": 4183436, + "ts": 667115507521.968, "dur": 21.342, + "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": 4183436, "tid": 4183436, + "ts": 667115507552.564, "dur": 34.019, + "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": 4183436, "tid": 4183436, + "ts": 667115507556.297, "dur": 29.681, + "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": 4183436, "tid": 4183436, + "ts": 667115507563.887, "dur": 2.155, + "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": 4183436, "tid": 4183436, + "ts": 667115507594.023, "dur": 29.393, + "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": 4183436, "tid": 4183436, + "ts": 667115507596.580, "dur": 26.621, + "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": 4183436, "tid": 4183436, + "ts": 667115507602.380, "dur": 5.054, + "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": 4183436, "tid": 4183436, + "ts": 667115507608.836, "dur": 13.863, + "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": 4183436, "tid": 4183436, + "ts": 667115507637.472, "dur": 5.514, + "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": 4183436, "tid": 4183436, + "ts": 667115507640.142, "dur": 2.617, + "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": 4183436, "tid": 4183436, + "ts": 667115507644.121, "dur": 1.544, + "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": 4183436, "tid": 4183436, + "ts": 667115507644.940, "dur": 0.660, + "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": 4183436, "tid": 4183436, + "ts": 667115507726.127, "dur": 26.401, + "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": 4183436, "tid": 4183436, + "ts": 667115507754.355, "dur": 12.545, + "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": 4183436, "tid": 4183436, "ts": 667115507754.355, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 4183436, "tid": 4183436, + "ts": 667115507875.030, "dur": 38.636, + "args": { + "External id": 229777,"Record function id": 0, "Ev Idx": 8576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 4183436, "tid": 4183436, + "ts": 667115508012.531, "dur": 32.022, + "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": 4183436, "tid": 4183436, "ts": 667115508012.531, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 4183436, "tid": 4183436, + "ts": 667115508097.479, "dur": 27.912, + "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": 4183436, "tid": 4183436, + "ts": 667115508099.327, "dur": 8.318, + "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": 4183436, "tid": 4183436, + "ts": 667115508102.987, "dur": 4.080, + "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": 4183436, "tid": 4183436, + "ts": 667115508109.318, "dur": 15.706, + "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": 4183436, "tid": 4183436, + "ts": 667115955538.802, "dur": 59.965, + "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": 4183436, "tid": 4183436, + "ts": 667115955696.994, "dur": 27.556, + "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": 4183436, "tid": 4183436, + "ts": 667115955734.387, "dur": 21.250, + "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": 4183436, "tid": 4183436, + "ts": 667115956111.790, "dur": 21.017, + "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": 4183436, "tid": 4183436, + "ts": 667115956138.086, "dur": 12.400, + "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": 4183436, "tid": 4183436, + "ts": 667115957391.276, "dur": 2327.697, + "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": 4183436, "tid": 4183436, + "ts": 667115957869.771, "dur": 606.473, + "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": 4183436, "tid": 4183436, + "ts": 667115957886.566, "dur": 65.500, + "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": 4183436, "tid": 4183436, + "ts": 667115957893.166, "dur": 11.137, + "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": 4183436, "tid": 4183436, + "ts": 667115957906.924, "dur": 44.843, + "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": 4183436, "tid": 4183436, + "ts": 667115957908.753, "dur": 42.485, + "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": 4183436, "tid": 4183436, + "ts": 667115959750.042, "dur": 3.364, + "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": 4183436, "tid": 4183436, + "ts": 667115959755.860, "dur": 0.552, + "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": 4183436, "tid": 4183436, + "ts": 667115959757.654, "dur": 0.472, + "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": 4183436, "tid": 4183436, + "ts": 667115959759.210, "dur": 0.567, + "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": 4183436, "tid": 4183436, + "ts": 667115959760.939, "dur": 3.839, + "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": 4183436, "tid": 4183436, + "ts": 667115959766.061, "dur": 0.263, + "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": 4183436, "tid": 4183436, + "ts": 667115959767.259, "dur": 0.435, + "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": 4183436, "tid": 4183436, + "ts": 667115959769.881, "dur": 0.420, + "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": 4183436, "tid": 4183436, + "ts": 667115959771.386, "dur": 0.393, + "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": 4183436, "tid": 4183436, + "ts": 667115959773.119, "dur": 0.478, + "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": 4183436, "tid": 4183436, + "ts": 667115959774.446, "dur": 0.369, + "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": 4183436, "tid": 4183436, + "ts": 667115959775.771, "dur": 0.459, + "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": 4183436, "tid": 4183436, + "ts": 667115959777.271, "dur": 0.419, + "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": 4183436, "tid": 4183436, + "ts": 667115959778.491, "dur": 0.205, + "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": 4183436, "tid": 4183436, + "ts": 667115959779.396, "dur": 0.241, + "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": 4183436, "tid": 4183436, + "ts": 667115959781.665, "dur": 0.193, + "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": 4183436, "tid": 4183436, + "ts": 667115959782.648, "dur": 0.218, + "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": 4183436, "tid": 4183436, + "ts": 667115959783.864, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115959785.175, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115959786.095, "dur": 0.231, + "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": 4183436, "tid": 4183436, + "ts": 667115959787.301, "dur": 0.191, + "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": 4183436, "tid": 4183436, + "ts": 667115959788.197, "dur": 0.381, + "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": 4183436, "tid": 4183436, + "ts": 667115959789.485, "dur": 0.192, + "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": 4183436, "tid": 4183436, + "ts": 667115959791.564, "dur": 0.234, + "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": 4183436, "tid": 4183436, + "ts": 667115959792.592, "dur": 0.400, + "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": 4183436, "tid": 4183436, + "ts": 667115959794.034, "dur": 0.260, + "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": 4183436, "tid": 4183436, + "ts": 667115959795.252, "dur": 0.405, + "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": 4183436, "tid": 4183436, + "ts": 667115959796.617, "dur": 0.414, + "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": 4183436, "tid": 4183436, + "ts": 667115959798.000, "dur": 0.430, + "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": 4183436, "tid": 4183436, + "ts": 667115959799.216, "dur": 0.398, + "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": 4183436, "tid": 4183436, + "ts": 667115959800.376, "dur": 0.214, + "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": 4183436, "tid": 4183436, + "ts": 667115959802.375, "dur": 0.205, + "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": 4183436, "tid": 4183436, + "ts": 667115959803.512, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959804.919, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959805.851, "dur": 0.368, + "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": 4183436, "tid": 4183436, + "ts": 667115959806.961, "dur": 0.595, + "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": 4183436, "tid": 4183436, + "ts": 667115959808.611, "dur": 0.199, + "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": 4183436, "tid": 4183436, + "ts": 667115959809.578, "dur": 0.206, + "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": 4183436, "tid": 4183436, + "ts": 667115959810.820, "dur": 0.199, + "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": 4183436, "tid": 4183436, + "ts": 667115959812.924, "dur": 0.205, + "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": 4183436, "tid": 4183436, + "ts": 667115959814.054, "dur": 0.223, + "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": 4183436, "tid": 4183436, + "ts": 667115959815.197, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959816.105, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959817.128, "dur": 0.232, + "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": 4183436, "tid": 4183436, + "ts": 667115959818.304, "dur": 0.446, + "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": 4183436, "tid": 4183436, + "ts": 667115959819.450, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959823.668, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115959827.112, "dur": 0.217, + "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": 4183436, "tid": 4183436, + "ts": 667115959828.228, "dur": 0.203, + "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": 4183436, "tid": 4183436, + "ts": 667115959829.320, "dur": 0.207, + "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": 4183436, "tid": 4183436, + "ts": 667115959830.410, "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": 4183436, "tid": 4183436, + "ts": 667115959831.336, "dur": 0.204, + "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": 4183436, "tid": 4183436, + "ts": 667115959832.404, "dur": 0.209, + "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": 4183436, "tid": 4183436, + "ts": 667115959833.603, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115959834.591, "dur": 0.486, + "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": 4183436, "tid": 4183436, + "ts": 667115959837.270, "dur": 0.194, + "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": 4183436, "tid": 4183436, + "ts": 667115959838.272, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115959839.169, "dur": 0.374, + "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": 4183436, "tid": 4183436, + "ts": 667115959840.281, "dur": 0.360, + "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": 4183436, "tid": 4183436, + "ts": 667115959841.363, "dur": 0.400, + "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": 4183436, "tid": 4183436, + "ts": 667115959842.568, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115959843.487, "dur": 0.391, + "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": 4183436, "tid": 4183436, + "ts": 667115959844.621, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959846.722, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115959847.677, "dur": 0.199, + "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": 4183436, "tid": 4183436, + "ts": 667115959848.897, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959849.877, "dur": 0.192, + "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": 4183436, "tid": 4183436, + "ts": 667115959850.825, "dur": 0.191, + "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": 4183436, "tid": 4183436, + "ts": 667115959851.768, "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": 4183436, "tid": 4183436, + "ts": 667115959852.690, "dur": 0.218, + "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": 4183436, "tid": 4183436, + "ts": 667115959853.609, "dur": 0.234, + "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": 4183436, "tid": 4183436, + "ts": 667115959856.112, "dur": 0.203, + "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": 4183436, "tid": 4183436, + "ts": 667115959857.112, "dur": 0.192, + "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": 4183436, "tid": 4183436, + "ts": 667115959858.010, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959858.916, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115959860.111, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959861.193, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959863.159, "dur": 0.193, + "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": 4183436, "tid": 4183436, + "ts": 667115959864.232, "dur": 0.190, + "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": 4183436, "tid": 4183436, + "ts": 667115959866.097, "dur": 0.263, + "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": 4183436, "tid": 4183436, + "ts": 667115959867.223, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959868.136, "dur": 0.203, + "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": 4183436, "tid": 4183436, + "ts": 667115959869.501, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959870.488, "dur": 0.408, + "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": 4183436, "tid": 4183436, + "ts": 667115959872.015, "dur": 0.281, + "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": 4183436, "tid": 4183436, + "ts": 667115959873.020, "dur": 0.433, + "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": 4183436, "tid": 4183436, + "ts": 667115959874.239, "dur": 0.403, + "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": 4183436, "tid": 4183436, + "ts": 667115959876.278, "dur": 0.225, + "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": 4183436, "tid": 4183436, + "ts": 667115959877.254, "dur": 0.215, + "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": 4183436, "tid": 4183436, + "ts": 667115959881.759, "dur": 0.209, + "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": 4183436, "tid": 4183436, + "ts": 667115959882.801, "dur": 0.377, + "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": 4183436, "tid": 4183436, + "ts": 667115959883.903, "dur": 0.191, + "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": 4183436, "tid": 4183436, + "ts": 667115959884.942, "dur": 0.203, + "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": 4183436, "tid": 4183436, + "ts": 667115959887.292, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959888.276, "dur": 0.210, + "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": 4183436, "tid": 4183436, + "ts": 667115959914.421, "dur": 0.223, + "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": 4183436, "tid": 4183436, + "ts": 667115959915.603, "dur": 0.204, + "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": 4183436, "tid": 4183436, + "ts": 667115959916.625, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959917.597, "dur": 0.193, + "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": 4183436, "tid": 4183436, + "ts": 667115959918.499, "dur": 0.198, + "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": 4183436, "tid": 4183436, + "ts": 667115959919.485, "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": 4183436, "tid": 4183436, + "ts": 667115959920.475, "dur": 0.195, + "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": 4183436, "tid": 4183436, + "ts": 667115959921.435, "dur": 0.208, + "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": 4183436, "tid": 4183436, + "ts": 667115959923.732, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959924.792, "dur": 0.213, + "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": 4183436, "tid": 4183436, + "ts": 667115959925.859, "dur": 0.193, + "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": 4183436, "tid": 4183436, + "ts": 667115959926.767, "dur": 0.203, + "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": 4183436, "tid": 4183436, + "ts": 667115959927.686, "dur": 0.203, + "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": 4183436, "tid": 4183436, + "ts": 667115959928.824, "dur": 0.207, + "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": 4183436, "tid": 4183436, + "ts": 667115959933.452, "dur": 0.235, + "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": 4183436, "tid": 4183436, + "ts": 667115959934.549, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959940.370, "dur": 0.195, + "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": 4183436, "tid": 4183436, + "ts": 667115959941.318, "dur": 0.197, + "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": 4183436, "tid": 4183436, + "ts": 667115959942.349, "dur": 0.229, + "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": 4183436, "tid": 4183436, + "ts": 667115959943.298, "dur": 0.190, + "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": 4183436, "tid": 4183436, + "ts": 667115959944.282, "dur": 0.233, + "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": 4183436, "tid": 4183436, + "ts": 667115959945.330, "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": 4183436, "tid": 4183436, + "ts": 667115959946.308, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959951.122, "dur": 0.220, + "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": 4183436, "tid": 4183436, + "ts": 667115959953.224, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115959954.245, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959955.204, "dur": 0.216, + "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": 4183436, "tid": 4183436, + "ts": 667115959956.163, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115959957.137, "dur": 0.199, + "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": 4183436, "tid": 4183436, + "ts": 667115959958.087, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115959959.055, "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": 4183436, "tid": 4183436, + "ts": 667115959960.108, "dur": 0.222, + "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": 4183436, "tid": 4183436, + "ts": 667115959962.184, "dur": 0.196, + "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": 4183436, "tid": 4183436, + "ts": 667115959963.184, "dur": 0.206, + "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": 4183436, "tid": 4183436, + "ts": 667115959964.640, "dur": 0.234, + "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": 4183436, "tid": 4183436, + "ts": 667115959965.652, "dur": 0.225, + "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": 4183436, "tid": 4183436, + "ts": 667115959966.719, "dur": 0.204, + "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": 4183436, "tid": 4183436, + "ts": 667115959967.671, "dur": 0.207, + "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": 4183436, "tid": 4183436, + "ts": 667115959968.697, "dur": 0.196, + "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": 4183436, "tid": 4183436, + "ts": 667115959969.703, "dur": 0.206, + "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": 4183436, "tid": 4183436, + "ts": 667115959972.453, "dur": 0.197, + "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": 4183436, "tid": 4183436, + "ts": 667115959973.411, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115959974.335, "dur": 0.195, + "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": 4183436, "tid": 4183436, + "ts": 667115959975.297, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115959976.216, "dur": 0.197, + "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": 4183436, "tid": 4183436, + "ts": 667115959977.134, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959978.060, "dur": 0.223, + "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": 4183436, "tid": 4183436, + "ts": 667115959979.006, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115959981.349, "dur": 0.198, + "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": 4183436, "tid": 4183436, + "ts": 667115959982.318, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959983.338, "dur": 0.197, + "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": 4183436, "tid": 4183436, + "ts": 667115959984.263, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959985.192, "dur": 0.196, + "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": 4183436, "tid": 4183436, + "ts": 667115959986.131, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115959987.432, "dur": 0.191, + "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": 4183436, "tid": 4183436, + "ts": 667115959988.415, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115959990.585, "dur": 0.197, + "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": 4183436, "tid": 4183436, + "ts": 667115959991.525, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115959992.559, "dur": 0.258, + "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": 4183436, "tid": 4183436, + "ts": 667115959993.605, "dur": 0.204, + "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": 4183436, "tid": 4183436, + "ts": 667115959994.644, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115959998.972, "dur": 0.239, + "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": 4183436, "tid": 4183436, + "ts": 667115959999.972, "dur": 0.198, + "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": 4183436, "tid": 4183436, + "ts": 667115960000.958, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115960003.580, "dur": 0.195, + "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": 4183436, "tid": 4183436, + "ts": 667115960004.585, "dur": 0.204, + "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": 4183436, "tid": 4183436, + "ts": 667115960006.947, "dur": 0.213, + "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": 4183436, "tid": 4183436, + "ts": 667115960007.896, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115960008.886, "dur": 0.196, + "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": 4183436, "tid": 4183436, + "ts": 667115960009.855, "dur": 0.196, + "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": 4183436, "tid": 4183436, + "ts": 667115960010.785, "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": 4183436, "tid": 4183436, + "ts": 667115960011.807, "dur": 0.234, + "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": 4183436, "tid": 4183436, + "ts": 667115960013.535, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115960014.501, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115960015.427, "dur": 0.212, + "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": 4183436, "tid": 4183436, + "ts": 667115960016.360, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115960017.273, "dur": 0.188, + "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": 4183436, "tid": 4183436, + "ts": 667115960018.227, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115960019.463, "dur": 0.199, + "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": 4183436, "tid": 4183436, + "ts": 667115960020.473, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115960022.468, "dur": 0.199, + "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": 4183436, "tid": 4183436, + "ts": 667115960023.546, "dur": 0.192, + "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": 4183436, "tid": 4183436, + "ts": 667115960024.507, "dur": 0.198, + "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": 4183436, "tid": 4183436, + "ts": 667115960025.435, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115960026.364, "dur": 0.197, + "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": 4183436, "tid": 4183436, + "ts": 667115960027.332, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115960028.265, "dur": 0.196, + "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": 4183436, "tid": 4183436, + "ts": 667115960029.222, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115960031.582, "dur": 0.192, + "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": 4183436, "tid": 4183436, + "ts": 667115960032.505, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115960033.468, "dur": 0.187, + "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": 4183436, "tid": 4183436, + "ts": 667115960034.369, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115960035.348, "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": 4183436, "tid": 4183436, + "ts": 667115960036.254, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115960037.227, "dur": 0.195, + "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": 4183436, "tid": 4183436, + "ts": 667115960038.159, "dur": 0.203, + "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": 4183436, "tid": 4183436, + "ts": 667115960039.820, "dur": 0.197, + "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": 4183436, "tid": 4183436, + "ts": 667115960040.825, "dur": 0.209, + "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": 4183436, "tid": 4183436, + "ts": 667115960041.911, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115960042.819, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115960043.967, "dur": 0.190, + "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": 4183436, "tid": 4183436, + "ts": 667115960044.895, "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": 4183436, "tid": 4183436, + "ts": 667115960045.860, "dur": 0.189, + "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": 4183436, "tid": 4183436, + "ts": 667115960046.784, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115960049.229, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115960050.225, "dur": 0.195, + "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": 4183436, "tid": 4183436, + "ts": 667115960051.767, "dur": 0.217, + "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": 4183436, "tid": 4183436, + "ts": 667115960052.736, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115960064.083, "dur": 0.228, + "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": 4183436, "tid": 4183436, + "ts": 667115960065.186, "dur": 0.193, + "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": 4183436, "tid": 4183436, + "ts": 667115960066.261, "dur": 0.196, + "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": 4183436, "tid": 4183436, + "ts": 667115960067.217, "dur": 0.200, + "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": 4183436, "tid": 4183436, + "ts": 667115960069.084, "dur": 0.198, + "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": 4183436, "tid": 4183436, + "ts": 667115960069.999, "dur": 0.203, + "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": 4183436, "tid": 4183436, + "ts": 667115960070.919, "dur": 0.192, + "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": 4183436, "tid": 4183436, + "ts": 667115960071.843, "dur": 0.201, + "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": 4183436, "tid": 4183436, + "ts": 667115960072.760, "dur": 0.197, + "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": 4183436, "tid": 4183436, + "ts": 667115960073.665, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115960074.715, "dur": 0.190, + "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": 4183436, "tid": 4183436, + "ts": 667115960075.608, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115960077.978, "dur": 0.197, + "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": 4183436, "tid": 4183436, + "ts": 667115960078.939, "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": 4183436, "tid": 4183436, + "ts": 667115960079.874, "dur": 0.197, + "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": 4183436, "tid": 4183436, + "ts": 667115960080.774, "dur": 0.203, + "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": 4183436, "tid": 4183436, + "ts": 667115960125.281, "dur": 1138.989, + "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": 4183436, "tid": 4183436, + "ts": 667115960477.544, "dur": 721.902, + "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": 4183436, "tid": 4183436, + "ts": 667115960483.377, "dur": 7.034, + "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": 4183436, "tid": 4183436, + "ts": 667115960487.049, "dur": 2.940, + "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": 4183436, "tid": 4183436, + "ts": 667115960490.939, "dur": 16.561, + "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": 4183436, "tid": 4183436, + "ts": 667115960491.561, "dur": 15.243, + "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": 4183436, "tid": 4183436, + "ts": 667115960508.633, "dur": 3.375, + "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": 4183436, "tid": 4183436, + "ts": 667115960511.444, "dur": 0.490, + "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": 4183436, "tid": 4183436, + "ts": 667115960512.339, "dur": 1.280, + "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": 4183436, "tid": 4183436, + "ts": 667115960512.752, "dur": 0.803, + "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": 4183436, "tid": 4183436, + "ts": 667115960514.613, "dur": 4.914, + "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": 4183436, "tid": 4183436, + "ts": 667115960518.828, "dur": 0.629, + "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": 4183436, "tid": 4183436, + "ts": 667115960519.809, "dur": 1.149, + "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": 4183436, "tid": 4183436, + "ts": 667115960520.219, "dur": 0.676, + "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": 4183436, "tid": 4183436, + "ts": 667115960521.211, "dur": 1.008, + "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": 4183436, "tid": 4183436, + "ts": 667115960521.627, "dur": 0.525, + "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": 4183436, "tid": 4183436, + "ts": 667115960522.469, "dur": 4.295, + "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": 4183436, "tid": 4183436, + "ts": 667115960526.178, "dur": 0.520, + "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": 4183436, "tid": 4183436, + "ts": 667115960527.189, "dur": 1.206, + "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": 4183436, "tid": 4183436, + "ts": 667115960527.611, "dur": 0.717, + "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": 4183436, "tid": 4183436, + "ts": 667115960528.656, "dur": 2.957, + "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": 4183436, "tid": 4183436, + "ts": 667115960529.070, "dur": 2.452, + "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": 4183436, "tid": 4183436, + "ts": 667115960531.858, "dur": 2.699, + "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": 4183436, "tid": 4183436, + "ts": 667115960533.954, "dur": 0.537, + "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": 4183436, "tid": 4183436, + "ts": 667115960534.790, "dur": 1.127, + "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": 4183436, "tid": 4183436, + "ts": 667115960535.163, "dur": 0.689, + "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": 4183436, "tid": 4183436, + "ts": 667115960537.228, "dur": 5.111, + "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": 4183436, "tid": 4183436, + "ts": 667115960541.515, "dur": 0.754, + "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": 4183436, "tid": 4183436, + "ts": 667115960542.600, "dur": 1.287, + "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": 4183436, "tid": 4183436, + "ts": 667115960542.967, "dur": 0.850, + "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": 4183436, "tid": 4183436, + "ts": 667115960544.137, "dur": 1.208, + "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": 4183436, "tid": 4183436, + "ts": 667115960544.528, "dur": 0.753, + "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": 4183436, "tid": 4183436, + "ts": 667115960545.684, "dur": 3.739, + "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": 4183436, "tid": 4183436, + "ts": 667115960548.803, "dur": 0.561, + "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": 4183436, "tid": 4183436, + "ts": 667115960549.683, "dur": 1.269, + "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": 4183436, "tid": 4183436, + "ts": 667115960550.065, "dur": 0.821, + "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": 4183436, "tid": 4183436, + "ts": 667115960551.183, "dur": 2.603, + "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": 4183436, "tid": 4183436, + "ts": 667115960551.585, "dur": 2.131, + "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": 4183436, "tid": 4183436, + "ts": 667115960554.022, "dur": 3.021, + "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": 4183436, "tid": 4183436, + "ts": 667115960555.975, "dur": 1.006, + "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": 4183436, "tid": 4183436, + "ts": 667115960557.276, "dur": 1.068, + "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": 4183436, "tid": 4183436, + "ts": 667115960557.647, "dur": 0.632, + "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": 4183436, "tid": 4183436, + "ts": 667115960560.021, "dur": 4.688, + "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": 4183436, "tid": 4183436, + "ts": 667115960563.901, "dur": 0.742, + "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": 4183436, "tid": 4183436, + "ts": 667115960564.969, "dur": 1.540, + "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": 4183436, "tid": 4183436, + "ts": 667115960565.621, "dur": 0.823, + "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": 4183436, "tid": 4183436, + "ts": 667115960566.737, "dur": 1.435, + "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": 4183436, "tid": 4183436, + "ts": 667115960567.151, "dur": 0.954, + "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": 4183436, "tid": 4183436, + "ts": 667115960568.401, "dur": 3.255, + "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": 4183436, "tid": 4183436, + "ts": 667115960571.083, "dur": 0.506, + "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": 4183436, "tid": 4183436, + "ts": 667115960571.911, "dur": 1.234, + "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": 4183436, "tid": 4183436, + "ts": 667115960572.270, "dur": 0.806, + "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": 4183436, "tid": 4183436, + "ts": 667115960573.378, "dur": 2.645, + "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": 4183436, "tid": 4183436, + "ts": 667115960573.816, "dur": 2.043, + "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": 4183436, "tid": 4183436, + "ts": 667115960576.262, "dur": 2.294, + "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": 4183436, "tid": 4183436, + "ts": 667115960577.890, "dur": 0.602, + "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": 4183436, "tid": 4183436, + "ts": 667115960578.970, "dur": 1.120, + "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": 4183436, "tid": 4183436, + "ts": 667115960579.359, "dur": 0.663, + "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": 4183436, "tid": 4183436, + "ts": 667115960581.175, "dur": 4.219, + "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": 4183436, "tid": 4183436, + "ts": 667115960584.682, "dur": 0.645, + "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": 4183436, "tid": 4183436, + "ts": 667115960585.671, "dur": 1.375, + "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": 4183436, "tid": 4183436, + "ts": 667115960586.116, "dur": 0.868, + "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": 4183436, "tid": 4183436, + "ts": 667115960587.472, "dur": 1.341, + "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": 4183436, "tid": 4183436, + "ts": 667115960587.859, "dur": 0.887, + "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": 4183436, "tid": 4183436, + "ts": 667115960589.043, "dur": 3.110, + "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": 4183436, "tid": 4183436, + "ts": 667115960591.570, "dur": 0.518, + "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": 4183436, "tid": 4183436, + "ts": 667115960592.382, "dur": 1.017, + "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": 4183436, "tid": 4183436, + "ts": 667115960592.791, "dur": 0.541, + "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": 4183436, "tid": 4183436, + "ts": 667115960593.629, "dur": 2.553, + "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": 4183436, "tid": 4183436, + "ts": 667115960594.005, "dur": 2.107, + "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": 4183436, "tid": 4183436, + "ts": 667115960596.467, "dur": 2.656, + "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": 4183436, "tid": 4183436, + "ts": 667115960598.088, "dur": 0.969, + "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": 4183436, "tid": 4183436, + "ts": 667115960599.354, "dur": 1.222, + "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": 4183436, "tid": 4183436, + "ts": 667115960599.723, "dur": 0.787, + "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": 4183436, "tid": 4183436, + "ts": 667115960601.323, "dur": 4.662, + "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": 4183436, "tid": 4183436, + "ts": 667115960605.229, "dur": 0.686, + "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": 4183436, "tid": 4183436, + "ts": 667115960606.234, "dur": 1.446, + "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": 4183436, "tid": 4183436, + "ts": 667115960606.636, "dur": 0.982, + "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": 4183436, "tid": 4183436, + "ts": 667115960607.912, "dur": 1.231, + "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": 4183436, "tid": 4183436, + "ts": 667115960608.305, "dur": 0.771, + "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": 4183436, "tid": 4183436, + "ts": 667115960609.374, "dur": 4.260, + "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": 4183436, "tid": 4183436, + "ts": 667115960612.671, "dur": 0.896, + "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": 4183436, "tid": 4183436, + "ts": 667115960613.901, "dur": 1.213, + "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": 4183436, "tid": 4183436, + "ts": 667115960614.267, "dur": 0.780, + "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": 4183436, "tid": 4183436, + "ts": 667115960615.371, "dur": 3.017, + "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": 4183436, "tid": 4183436, + "ts": 667115960615.740, "dur": 2.581, + "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": 4183436, "tid": 4183436, + "ts": 667115960618.623, "dur": 1.476, + "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": 4183436, "tid": 4183436, + "ts": 667115960619.333, "dur": 0.703, + "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": 4183436, "tid": 4183436, + "ts": 667115960620.343, "dur": 1.553, + "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": 4183436, "tid": 4183436, + "ts": 667115960620.760, "dur": 1.075, + "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": 4183436, "tid": 4183436, + "ts": 667115960622.485, "dur": 3.360, + "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": 4183436, "tid": 4183436, + "ts": 667115960625.125, "dur": 0.655, + "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": 4183436, "tid": 4183436, + "ts": 667115960626.124, "dur": 1.176, + "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": 4183436, "tid": 4183436, + "ts": 667115960626.500, "dur": 0.733, + "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": 4183436, "tid": 4183436, + "ts": 667115960627.533, "dur": 1.121, + "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": 4183436, "tid": 4183436, + "ts": 667115960627.893, "dur": 0.699, + "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": 4183436, "tid": 4183436, + "ts": 667115960628.920, "dur": 3.921, + "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": 4183436, "tid": 4183436, + "ts": 667115960631.954, "dur": 0.819, + "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": 4183436, "tid": 4183436, + "ts": 667115960633.069, "dur": 1.466, + "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": 4183436, "tid": 4183436, + "ts": 667115960633.480, "dur": 0.985, + "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": 4183436, "tid": 4183436, + "ts": 667115960634.764, "dur": 2.750, + "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": 4183436, "tid": 4183436, + "ts": 667115960635.173, "dur": 2.266, + "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": 4183436, "tid": 4183436, + "ts": 667115960637.747, "dur": 1.146, + "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": 4183436, "tid": 4183436, + "ts": 667115960638.184, "dur": 0.640, + "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": 4183436, "tid": 4183436, + "ts": 667115960639.122, "dur": 1.650, + "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": 4183436, "tid": 4183436, + "ts": 667115960639.479, "dur": 1.230, + "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": 4183436, "tid": 4183436, + "ts": 667115960641.152, "dur": 3.693, + "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": 4183436, "tid": 4183436, + "ts": 667115960643.986, "dur": 0.796, + "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": 4183436, "tid": 4183436, + "ts": 667115960645.122, "dur": 1.000, + "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": 4183436, "tid": 4183436, + "ts": 667115960645.508, "dur": 0.539, + "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": 4183436, "tid": 4183436, + "ts": 667115960646.359, "dur": 1.440, + "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": 4183436, "tid": 4183436, + "ts": 667115960646.725, "dur": 1.011, + "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": 4183436, "tid": 4183436, + "ts": 667115960648.035, "dur": 30.539, + "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": 4183436, "tid": 4183436, + "ts": 667115960650.285, "dur": 27.285, + "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": 4183436, "tid": 4183436, + "ts": 667115960679.744, "dur": 1.913, + "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": 4183436, "tid": 4183436, + "ts": 667115960680.703, "dur": 0.780, + "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": 4183436, "tid": 4183436, + "ts": 667115960681.956, "dur": 2.562, + "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": 4183436, "tid": 4183436, + "ts": 667115960682.338, "dur": 2.113, + "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": 4183436, "tid": 4183436, + "ts": 667115960684.870, "dur": 1.407, + "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": 4183436, "tid": 4183436, + "ts": 667115960685.619, "dur": 0.595, + "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": 4183436, "tid": 4183436, + "ts": 667115960686.625, "dur": 1.361, + "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": 4183436, "tid": 4183436, + "ts": 667115960687.007, "dur": 0.916, + "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": 4183436, "tid": 4183436, + "ts": 667115960688.322, "dur": 3.165, + "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": 4183436, "tid": 4183436, + "ts": 667115960690.875, "dur": 0.541, + "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": 4183436, "tid": 4183436, + "ts": 667115960691.787, "dur": 1.167, + "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": 4183436, "tid": 4183436, + "ts": 667115960692.156, "dur": 0.732, + "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": 4183436, "tid": 4183436, + "ts": 667115960693.219, "dur": 1.161, + "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": 4183436, "tid": 4183436, + "ts": 667115960693.578, "dur": 0.736, + "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": 4183436, "tid": 4183436, + "ts": 667115960694.823, "dur": 3.722, + "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": 4183436, "tid": 4183436, + "ts": 667115960697.257, "dur": 1.038, + "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": 4183436, "tid": 4183436, + "ts": 667115960698.816, "dur": 1.008, + "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": 4183436, "tid": 4183436, + "ts": 667115960699.184, "dur": 0.567, + "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": 4183436, "tid": 4183436, + "ts": 667115960700.072, "dur": 2.578, + "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": 4183436, "tid": 4183436, + "ts": 667115960700.434, "dur": 2.148, + "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": 4183436, "tid": 4183436, + "ts": 667115960702.916, "dur": 1.300, + "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": 4183436, "tid": 4183436, + "ts": 667115960703.460, "dur": 0.688, + "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": 4183436, "tid": 4183436, + "ts": 667115960704.603, "dur": 1.166, + "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": 4183436, "tid": 4183436, + "ts": 667115960704.955, "dur": 0.747, + "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": 4183436, "tid": 4183436, + "ts": 667115960706.058, "dur": 3.273, + "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": 4183436, "tid": 4183436, + "ts": 667115960708.534, "dur": 0.715, + "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": 4183436, "tid": 4183436, + "ts": 667115960709.637, "dur": 1.359, + "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": 4183436, "tid": 4183436, + "ts": 667115960709.989, "dur": 0.945, + "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": 4183436, "tid": 4183436, + "ts": 667115960711.275, "dur": 1.232, + "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": 4183436, "tid": 4183436, + "ts": 667115960711.674, "dur": 0.767, + "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": 4183436, "tid": 4183436, + "ts": 667115960712.771, "dur": 3.789, + "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": 4183436, "tid": 4183436, + "ts": 667115960715.460, "dur": 0.824, + "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": 4183436, "tid": 4183436, + "ts": 667115960716.809, "dur": 1.147, + "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": 4183436, "tid": 4183436, + "ts": 667115960717.173, "dur": 0.719, + "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": 4183436, "tid": 4183436, + "ts": 667115960718.209, "dur": 3.020, + "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": 4183436, "tid": 4183436, + "ts": 667115960718.572, "dur": 2.586, + "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": 4183436, "tid": 4183436, + "ts": 667115960721.540, "dur": 1.268, + "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": 4183436, "tid": 4183436, + "ts": 667115960722.198, "dur": 0.544, + "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": 4183436, "tid": 4183436, + "ts": 667115960723.087, "dur": 1.203, + "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": 4183436, "tid": 4183436, + "ts": 667115960723.456, "dur": 0.768, + "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": 4183436, "tid": 4183436, + "ts": 667115960724.542, "dur": 2.960, + "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": 4183436, "tid": 4183436, + "ts": 667115960727.014, "dur": 0.423, + "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": 4183436, "tid": 4183436, + "ts": 667115960727.885, "dur": 1.159, + "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": 4183436, "tid": 4183436, + "ts": 667115960728.264, "dur": 0.715, + "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": 4183436, "tid": 4183436, + "ts": 667115960729.284, "dur": 1.477, + "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": 4183436, "tid": 4183436, + "ts": 667115960729.636, "dur": 1.059, + "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": 4183436, "tid": 4183436, + "ts": 667115960731.014, "dur": 3.273, + "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": 4183436, "tid": 4183436, + "ts": 667115960733.561, "dur": 0.659, + "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": 4183436, "tid": 4183436, + "ts": 667115960734.531, "dur": 0.996, + "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": 4183436, "tid": 4183436, + "ts": 667115960734.879, "dur": 0.586, + "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": 4183436, "tid": 4183436, + "ts": 667115960735.953, "dur": 2.705, + "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": 4183436, "tid": 4183436, + "ts": 667115960736.327, "dur": 2.263, + "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": 4183436, "tid": 4183436, + "ts": 667115960738.913, "dur": 1.667, + "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": 4183436, "tid": 4183436, + "ts": 667115960739.493, "dur": 1.028, + "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": 4183436, "tid": 4183436, + "ts": 667115960740.827, "dur": 1.327, + "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": 4183436, "tid": 4183436, + "ts": 667115960741.176, "dur": 0.911, + "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": 4183436, "tid": 4183436, + "ts": 667115960742.396, "dur": 3.563, + "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": 4183436, "tid": 4183436, + "ts": 667115960745.164, "dur": 0.727, + "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": 4183436, "tid": 4183436, + "ts": 667115960746.284, "dur": 1.310, + "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": 4183436, "tid": 4183436, + "ts": 667115960746.729, "dur": 0.611, + "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": 4183436, "tid": 4183436, + "ts": 667115960747.838, "dur": 1.264, + "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": 4183436, "tid": 4183436, + "ts": 667115960748.202, "dur": 0.836, + "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": 4183436, "tid": 4183436, + "ts": 667115960749.346, "dur": 2.895, + "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": 4183436, "tid": 4183436, + "ts": 667115960751.752, "dur": 0.422, + "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": 4183436, "tid": 4183436, + "ts": 667115960752.482, "dur": 1.248, + "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": 4183436, "tid": 4183436, + "ts": 667115960752.846, "dur": 0.818, + "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": 4183436, "tid": 4183436, + "ts": 667115960753.972, "dur": 2.643, + "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": 4183436, "tid": 4183436, + "ts": 667115960754.320, "dur": 2.226, + "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": 4183436, "tid": 4183436, + "ts": 667115960757.074, "dur": 1.335, + "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": 4183436, "tid": 4183436, + "ts": 667115960757.778, "dur": 0.571, + "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": 4183436, "tid": 4183436, + "ts": 667115960758.729, "dur": 1.182, + "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": 4183436, "tid": 4183436, + "ts": 667115960759.089, "dur": 0.660, + "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": 4183436, "tid": 4183436, + "ts": 667115960760.200, "dur": 3.182, + "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": 4183436, "tid": 4183436, + "ts": 667115960762.649, "dur": 0.668, + "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": 4183436, "tid": 4183436, + "ts": 667115960763.645, "dur": 1.448, + "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": 4183436, "tid": 4183436, + "ts": 667115960764.211, "dur": 0.821, + "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": 4183436, "tid": 4183436, + "ts": 667115960765.382, "dur": 1.253, + "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": 4183436, "tid": 4183436, + "ts": 667115960765.773, "dur": 0.798, + "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": 4183436, "tid": 4183436, + "ts": 667115960766.916, "dur": 3.024, + "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": 4183436, "tid": 4183436, + "ts": 667115960769.299, "dur": 0.581, + "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": 4183436, "tid": 4183436, + "ts": 667115960770.185, "dur": 1.025, + "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": 4183436, "tid": 4183436, + "ts": 667115960770.560, "dur": 0.487, + "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": 4183436, "tid": 4183436, + "ts": 667115960771.478, "dur": 2.375, + "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": 4183436, "tid": 4183436, + "ts": 667115960771.845, "dur": 1.934, + "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": 4183436, "tid": 4183436, + "ts": 667115960774.146, "dur": 1.672, + "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": 4183436, "tid": 4183436, + "ts": 667115960774.759, "dur": 0.999, + "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": 4183436, "tid": 4183436, + "ts": 667115960776.143, "dur": 1.352, + "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": 4183436, "tid": 4183436, + "ts": 667115960776.719, "dur": 0.707, + "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": 4183436, "tid": 4183436, + "ts": 667115960777.740, "dur": 3.955, + "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": 4183436, "tid": 4183436, + "ts": 667115960780.910, "dur": 0.719, + "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": 4183436, "tid": 4183436, + "ts": 667115960781.993, "dur": 0.878, + "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": 4183436, "tid": 4183436, + "ts": 667115960782.379, "dur": 0.425, + "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": 4183436, "tid": 4183436, + "ts": 667115960783.190, "dur": 1.221, + "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": 4183436, "tid": 4183436, + "ts": 667115960783.554, "dur": 0.788, + "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": 4183436, "tid": 4183436, + "ts": 667115960784.657, "dur": 2.761, + "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": 4183436, "tid": 4183436, + "ts": 667115960786.793, "dur": 0.560, + "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": 4183436, "tid": 4183436, + "ts": 667115960787.659, "dur": 1.119, + "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": 4183436, "tid": 4183436, + "ts": 667115960788.013, "dur": 0.605, + "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": 4183436, "tid": 4183436, + "ts": 667115960789.044, "dur": 2.680, + "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": 4183436, "tid": 4183436, + "ts": 667115960789.406, "dur": 2.245, + "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": 4183436, "tid": 4183436, + "ts": 667115960791.986, "dur": 1.817, + "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": 4183436, "tid": 4183436, + "ts": 667115960792.910, "dur": 0.829, + "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": 4183436, "tid": 4183436, + "ts": 667115960794.079, "dur": 1.269, + "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": 4183436, "tid": 4183436, + "ts": 667115960794.478, "dur": 0.799, + "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": 4183436, "tid": 4183436, + "ts": 667115960795.633, "dur": 3.919, + "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": 4183436, "tid": 4183436, + "ts": 667115960798.577, "dur": 0.907, + "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": 4183436, "tid": 4183436, + "ts": 667115960799.836, "dur": 1.058, + "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": 4183436, "tid": 4183436, + "ts": 667115960800.238, "dur": 0.591, + "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": 4183436, "tid": 4183436, + "ts": 667115960801.144, "dur": 1.194, + "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": 4183436, "tid": 4183436, + "ts": 667115960801.531, "dur": 0.741, + "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": 4183436, "tid": 4183436, + "ts": 667115960802.611, "dur": 3.234, + "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": 4183436, "tid": 4183436, + "ts": 667115960805.184, "dur": 0.594, + "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": 4183436, "tid": 4183436, + "ts": 667115960806.086, "dur": 1.365, + "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": 4183436, "tid": 4183436, + "ts": 667115960806.464, "dur": 0.921, + "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": 4183436, "tid": 4183436, + "ts": 667115960807.727, "dur": 2.787, + "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": 4183436, "tid": 4183436, + "ts": 667115960808.093, "dur": 2.347, + "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": 4183436, "tid": 4183436, + "ts": 667115960810.764, "dur": 1.356, + "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": 4183436, "tid": 4183436, + "ts": 667115960811.466, "dur": 0.498, + "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": 4183436, "tid": 4183436, + "ts": 667115960812.362, "dur": 1.461, + "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": 4183436, "tid": 4183436, + "ts": 667115960812.731, "dur": 1.027, + "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": 4183436, "tid": 4183436, + "ts": 667115960814.067, "dur": 3.442, + "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": 4183436, "tid": 4183436, + "ts": 667115960816.945, "dur": 0.495, + "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": 4183436, "tid": 4183436, + "ts": 667115960817.804, "dur": 1.095, + "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": 4183436, "tid": 4183436, + "ts": 667115960818.166, "dur": 0.668, + "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": 4183436, "tid": 4183436, + "ts": 667115960819.252, "dur": 1.133, + "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": 4183436, "tid": 4183436, + "ts": 667115960819.625, "dur": 0.698, + "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": 4183436, "tid": 4183436, + "ts": 667115960820.681, "dur": 3.498, + "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": 4183436, "tid": 4183436, + "ts": 667115960823.230, "dur": 0.889, + "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": 4183436, "tid": 4183436, + "ts": 667115960824.449, "dur": 1.353, + "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": 4183436, "tid": 4183436, + "ts": 667115960824.811, "dur": 0.751, + "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": 4183436, "tid": 4183436, + "ts": 667115960826.065, "dur": 2.559, + "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": 4183436, "tid": 4183436, + "ts": 667115960826.449, "dur": 2.105, + "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": 4183436, "tid": 4183436, + "ts": 667115960828.884, "dur": 1.543, + "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": 4183436, "tid": 4183436, + "ts": 667115960829.537, "dur": 0.827, + "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": 4183436, "tid": 4183436, + "ts": 667115960830.733, "dur": 1.096, + "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": 4183436, "tid": 4183436, + "ts": 667115960831.111, "dur": 0.652, + "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": 4183436, "tid": 4183436, + "ts": 667115960832.112, "dur": 3.945, + "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": 4183436, "tid": 4183436, + "ts": 667115960835.173, "dur": 0.817, + "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": 4183436, "tid": 4183436, + "ts": 667115960836.390, "dur": 0.843, + "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": 4183436, "tid": 4183436, + "ts": 667115960836.757, "dur": 0.409, + "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": 4183436, "tid": 4183436, + "ts": 667115960837.529, "dur": 1.046, + "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": 4183436, "tid": 4183436, + "ts": 667115960837.892, "dur": 0.617, + "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": 4183436, "tid": 4183436, + "ts": 667115960838.842, "dur": 3.008, + "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": 4183436, "tid": 4183436, + "ts": 667115960841.269, "dur": 0.514, + "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": 4183436, "tid": 4183436, + "ts": 667115960842.130, "dur": 1.176, + "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": 4183436, "tid": 4183436, + "ts": 667115960842.542, "dur": 0.700, + "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": 4183436, "tid": 4183436, + "ts": 667115960843.548, "dur": 3.028, + "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": 4183436, "tid": 4183436, + "ts": 667115960843.897, "dur": 2.412, + "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": 4183436, "tid": 4183436, + "ts": 667115960846.899, "dur": 1.509, + "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": 4183436, "tid": 4183436, + "ts": 667115960847.550, "dur": 0.789, + "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": 4183436, "tid": 4183436, + "ts": 667115960848.686, "dur": 1.175, + "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": 4183436, "tid": 4183436, + "ts": 667115960849.073, "dur": 0.550, + "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": 4183436, "tid": 4183436, + "ts": 667115960850.154, "dur": 3.384, + "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": 4183436, "tid": 4183436, + "ts": 667115960852.830, "dur": 0.641, + "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": 4183436, "tid": 4183436, + "ts": 667115960853.804, "dur": 1.120, + "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": 4183436, "tid": 4183436, + "ts": 667115960854.173, "dur": 0.600, + "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": 4183436, "tid": 4183436, + "ts": 667115960855.166, "dur": 1.123, + "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": 4183436, "tid": 4183436, + "ts": 667115960855.517, "dur": 0.705, + "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": 4183436, "tid": 4183436, + "ts": 667115960856.542, "dur": 4.237, + "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": 4183436, "tid": 4183436, + "ts": 667115960860.144, "dur": 0.566, + "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": 4183436, "tid": 4183436, + "ts": 667115960861.078, "dur": 1.041, + "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": 4183436, "tid": 4183436, + "ts": 667115960861.445, "dur": 0.610, + "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": 4183436, "tid": 4183436, + "ts": 667115960862.389, "dur": 2.598, + "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": 4183436, "tid": 4183436, + "ts": 667115960862.776, "dur": 1.939, + "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": 4183436, "tid": 4183436, + "ts": 667115960865.270, "dur": 1.329, + "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": 4183436, "tid": 4183436, + "ts": 667115960865.817, "dur": 0.722, + "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": 4183436, "tid": 4183436, + "ts": 667115960866.965, "dur": 1.254, + "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": 4183436, "tid": 4183436, + "ts": 667115960867.329, "dur": 0.824, + "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": 4183436, "tid": 4183436, + "ts": 667115960868.474, "dur": 3.591, + "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": 4183436, "tid": 4183436, + "ts": 667115960871.435, "dur": 0.558, + "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": 4183436, "tid": 4183436, + "ts": 667115960872.448, "dur": 1.405, + "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": 4183436, "tid": 4183436, + "ts": 667115960872.802, "dur": 0.981, + "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": 4183436, "tid": 4183436, + "ts": 667115960874.127, "dur": 1.141, + "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": 4183436, "tid": 4183436, + "ts": 667115960874.499, "dur": 0.703, + "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": 4183436, "tid": 4183436, + "ts": 667115960875.513, "dur": 3.108, + "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": 4183436, "tid": 4183436, + "ts": 667115960877.867, "dur": 0.688, + "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": 4183436, "tid": 4183436, + "ts": 667115960878.966, "dur": 1.262, + "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": 4183436, "tid": 4183436, + "ts": 667115960879.525, "dur": 0.635, + "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": 4183436, "tid": 4183436, + "ts": 667115960880.557, "dur": 2.935, + "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": 4183436, "tid": 4183436, + "ts": 667115960881.041, "dur": 2.282, + "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": 4183436, "tid": 4183436, + "ts": 667115960883.808, "dur": 1.100, + "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": 4183436, "tid": 4183436, + "ts": 667115960884.268, "dur": 0.571, + "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": 4183436, "tid": 4183436, + "ts": 667115960885.428, "dur": 1.149, + "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": 4183436, "tid": 4183436, + "ts": 667115960885.871, "dur": 0.642, + "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": 4183436, "tid": 4183436, + "ts": 667115960886.848, "dur": 3.274, + "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": 4183436, "tid": 4183436, + "ts": 667115960889.267, "dur": 0.787, + "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": 4183436, "tid": 4183436, + "ts": 667115960890.454, "dur": 1.501, + "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": 4183436, "tid": 4183436, + "ts": 667115960890.901, "dur": 0.992, + "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": 4183436, "tid": 4183436, + "ts": 667115960892.248, "dur": 1.226, + "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": 4183436, "tid": 4183436, + "ts": 667115960892.673, "dur": 0.737, + "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": 4183436, "tid": 4183436, + "ts": 667115960893.762, "dur": 3.130, + "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": 4183436, "tid": 4183436, + "ts": 667115960896.240, "dur": 0.581, + "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": 4183436, "tid": 4183436, + "ts": 667115960897.182, "dur": 1.335, + "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": 4183436, "tid": 4183436, + "ts": 667115960897.653, "dur": 0.797, + "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": 4183436, "tid": 4183436, + "ts": 667115960898.796, "dur": 2.874, + "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": 4183436, "tid": 4183436, + "ts": 667115960899.266, "dur": 2.152, + "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": 4183436, "tid": 4183436, + "ts": 667115960901.979, "dur": 1.338, + "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": 4183436, "tid": 4183436, + "ts": 667115960902.461, "dur": 0.794, + "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": 4183436, "tid": 4183436, + "ts": 667115960903.643, "dur": 1.316, + "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": 4183436, "tid": 4183436, + "ts": 667115960904.175, "dur": 0.715, + "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": 4183436, "tid": 4183436, + "ts": 667115960905.260, "dur": 3.130, + "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": 4183436, "tid": 4183436, + "ts": 667115960907.734, "dur": 0.591, + "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": 4183436, "tid": 4183436, + "ts": 667115960908.677, "dur": 1.079, + "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": 4183436, "tid": 4183436, + "ts": 667115960909.100, "dur": 0.477, + "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": 4183436, "tid": 4183436, + "ts": 667115960910.028, "dur": 1.238, + "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": 4183436, "tid": 4183436, + "ts": 667115960910.536, "dur": 0.666, + "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": 4183436, "tid": 4183436, + "ts": 667115960911.534, "dur": 2.956, + "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": 4183436, "tid": 4183436, + "ts": 667115960913.746, "dur": 0.579, + "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": 4183436, "tid": 4183436, + "ts": 667115960914.795, "dur": 1.203, + "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": 4183436, "tid": 4183436, + "ts": 667115960915.210, "dur": 0.724, + "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": 4183436, "tid": 4183436, + "ts": 667115960916.263, "dur": 2.230, + "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": 4183436, "tid": 4183436, + "ts": 667115960916.712, "dur": 1.711, + "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": 4183436, "tid": 4183436, + "ts": 667115960918.757, "dur": 1.197, + "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": 4183436, "tid": 4183436, + "ts": 667115960919.159, "dur": 0.735, + "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": 4183436, "tid": 4183436, + "ts": 667115960920.383, "dur": 1.441, + "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": 4183436, "tid": 4183436, + "ts": 667115960920.805, "dur": 0.860, + "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": 4183436, "tid": 4183436, + "ts": 667115960922.086, "dur": 2.753, + "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": 4183436, "tid": 4183436, + "ts": 667115960924.243, "dur": 0.525, + "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": 4183436, "tid": 4183436, + "ts": 667115960925.135, "dur": 1.493, + "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": 4183436, "tid": 4183436, + "ts": 667115960925.641, "dur": 0.921, + "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": 4183436, "tid": 4183436, + "ts": 667115960926.891, "dur": 1.255, + "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": 4183436, "tid": 4183436, + "ts": 667115960927.337, "dur": 0.746, + "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": 4183436, "tid": 4183436, + "ts": 667115960928.439, "dur": 3.202, + "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": 4183436, "tid": 4183436, + "ts": 667115960930.695, "dur": 0.881, + "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": 4183436, "tid": 4183436, + "ts": 667115960931.956, "dur": 1.783, + "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": 4183436, "tid": 4183436, + "ts": 667115960932.368, "dur": 1.093, + "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": 4183436, "tid": 4183436, + "ts": 667115960934.012, "dur": 2.614, + "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": 4183436, "tid": 4183436, + "ts": 667115960934.447, "dur": 2.114, + "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": 4183436, "tid": 4183436, + "ts": 667115960936.939, "dur": 1.264, + "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": 4183436, "tid": 4183436, + "ts": 667115960937.433, "dur": 0.706, + "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": 4183436, "tid": 4183436, + "ts": 667115960938.483, "dur": 1.049, + "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": 4183436, "tid": 4183436, + "ts": 667115960938.909, "dur": 0.556, + "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": 4183436, "tid": 4183436, + "ts": 667115960939.805, "dur": 3.086, + "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": 4183436, "tid": 4183436, + "ts": 667115960942.262, "dur": 0.568, + "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": 4183436, "tid": 4183436, + "ts": 667115960943.181, "dur": 1.104, + "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": 4183436, "tid": 4183436, + "ts": 667115960943.608, "dur": 0.508, + "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": 4183436, "tid": 4183436, + "ts": 667115960944.576, "dur": 1.201, + "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": 4183436, "tid": 4183436, + "ts": 667115960944.992, "dur": 0.720, + "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": 4183436, "tid": 4183436, + "ts": 667115960946.072, "dur": 2.991, + "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": 4183436, "tid": 4183436, + "ts": 667115960948.321, "dur": 0.678, + "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": 4183436, "tid": 4183436, + "ts": 667115960949.376, "dur": 1.522, + "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": 4183436, "tid": 4183436, + "ts": 667115960949.796, "dur": 1.036, + "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": 4183436, "tid": 4183436, + "ts": 667115960951.162, "dur": 3.018, + "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": 4183436, "tid": 4183436, + "ts": 667115960951.552, "dur": 2.451, + "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": 4183436, "tid": 4183436, + "ts": 667115960954.445, "dur": 1.712, + "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": 4183436, "tid": 4183436, + "ts": 667115960954.868, "dur": 1.129, + "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": 4183436, "tid": 4183436, + "ts": 667115960956.442, "dur": 1.519, + "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": 4183436, "tid": 4183436, + "ts": 667115960956.856, "dur": 1.040, + "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": 4183436, "tid": 4183436, + "ts": 667115960958.230, "dur": 2.682, + "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": 4183436, "tid": 4183436, + "ts": 667115960960.515, "dur": 0.335, + "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": 4183436, "tid": 4183436, + "ts": 667115960961.191, "dur": 0.931, + "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": 4183436, "tid": 4183436, + "ts": 667115960961.592, "dur": 0.465, + "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": 4183436, "tid": 4183436, + "ts": 667115960962.384, "dur": 0.861, + "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": 4183436, "tid": 4183436, + "ts": 667115960962.784, "dur": 0.300, + "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": 4183436, "tid": 4183436, + "ts": 667115960963.508, "dur": 3.074, + "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": 4183436, "tid": 4183436, + "ts": 667115960966.000, "dur": 0.518, + "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": 4183436, "tid": 4183436, + "ts": 667115960966.850, "dur": 0.828, + "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": 4183436, "tid": 4183436, + "ts": 667115960967.263, "dur": 0.353, + "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": 4183436, "tid": 4183436, + "ts": 667115960967.951, "dur": 2.463, + "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": 4183436, "tid": 4183436, + "ts": 667115960968.353, "dur": 1.992, + "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": 4183436, "tid": 4183436, + "ts": 667115960970.678, "dur": 0.758, + "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": 4183436, "tid": 4183436, + "ts": 667115960971.110, "dur": 0.263, + "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": 4183436, "tid": 4183436, + "ts": 667115960971.995, "dur": 1.180, + "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": 4183436, "tid": 4183436, + "ts": 667115960972.456, "dur": 0.556, + "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": 4183436, "tid": 4183436, + "ts": 667115960973.443, "dur": 2.700, + "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": 4183436, "tid": 4183436, + "ts": 667115960975.685, "dur": 0.396, + "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": 4183436, "tid": 4183436, + "ts": 667115960976.423, "dur": 1.173, + "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": 4183436, "tid": 4183436, + "ts": 667115960976.818, "dur": 0.712, + "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": 4183436, "tid": 4183436, + "ts": 667115960978.103, "dur": 1.502, + "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": 4183436, "tid": 4183436, + "ts": 667115960978.551, "dur": 0.983, + "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": 4183436, "tid": 4183436, + "ts": 667115960979.885, "dur": 3.427, + "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": 4183436, "tid": 4183436, + "ts": 667115960982.058, "dur": 0.982, + "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": 4183436, "tid": 4183436, + "ts": 667115960983.588, "dur": 1.220, + "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": 4183436, "tid": 4183436, + "ts": 667115960984.000, "dur": 0.745, + "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": 4183436, "tid": 4183436, + "ts": 667115961002.613, "dur": 3.335, + "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": 4183436, "tid": 4183436, + "ts": 667115961003.301, "dur": 2.485, + "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": 4183436, "tid": 4183436, + "ts": 667115961006.292, "dur": 1.003, + "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": 4183436, "tid": 4183436, + "ts": 667115961006.875, "dur": 0.355, + "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": 4183436, "tid": 4183436, + "ts": 667115961007.584, "dur": 1.125, + "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": 4183436, "tid": 4183436, + "ts": 667115961007.986, "dur": 0.659, + "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": 4183436, "tid": 4183436, + "ts": 667115961009.048, "dur": 2.769, + "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": 4183436, "tid": 4183436, + "ts": 667115961011.282, "dur": 0.474, + "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": 4183436, "tid": 4183436, + "ts": 667115961012.137, "dur": 0.818, + "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": 4183436, "tid": 4183436, + "ts": 667115961012.542, "dur": 0.348, + "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": 4183436, "tid": 4183436, + "ts": 667115961013.232, "dur": 0.923, + "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": 4183436, "tid": 4183436, + "ts": 667115961013.648, "dur": 0.444, + "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": 4183436, "tid": 4183436, + "ts": 667115961014.428, "dur": 2.798, + "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": 4183436, "tid": 4183436, + "ts": 667115961016.727, "dur": 0.433, + "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": 4183436, "tid": 4183436, + "ts": 667115961017.594, "dur": 1.214, + "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": 4183436, "tid": 4183436, + "ts": 667115961018.169, "dur": 0.572, + "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": 4183436, "tid": 4183436, + "ts": 667115961019.073, "dur": 3.051, + "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": 4183436, "tid": 4183436, + "ts": 667115961020.055, "dur": 1.998, + "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": 4183436, "tid": 4183436, + "ts": 667115961022.402, "dur": 1.741, + "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": 4183436, "tid": 4183436, + "ts": 667115961023.581, "dur": 0.403, + "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": 4183436, "tid": 4183436, + "ts": 667115961024.398, "dur": 1.470, + "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": 4183436, "tid": 4183436, + "ts": 667115961025.069, "dur": 0.735, + "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": 4183436, "tid": 4183436, + "ts": 667115961026.141, "dur": 3.832, + "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": 4183436, "tid": 4183436, + "ts": 667115961029.254, "dur": 0.648, + "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": 4183436, "tid": 4183436, + "ts": 667115961030.228, "dur": 1.746, + "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": 4183436, "tid": 4183436, + "ts": 667115961031.135, "dur": 0.777, + "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": 4183436, "tid": 4183436, + "ts": 667115961032.241, "dur": 7.446, + "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": 4183436, "tid": 4183436, + "ts": 667115961037.487, "dur": 2.120, + "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": 4183436, "tid": 4183436, + "ts": 667115961039.991, "dur": 1.694, + "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": 4183436, "tid": 4183436, + "ts": 667115961041.009, "dur": 0.612, + "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": 4183436, "tid": 4183436, + "ts": 667115961041.975, "dur": 1.848, + "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": 4183436, "tid": 4183436, + "ts": 667115961042.567, "dur": 1.095, + "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": 4183436, "tid": 4183436, + "ts": 667115961044.098, "dur": 3.755, + "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": 4183436, "tid": 4183436, + "ts": 667115961047.169, "dur": 0.620, + "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": 4183436, "tid": 4183436, + "ts": 667115961048.136, "dur": 1.831, + "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": 4183436, "tid": 4183436, + "ts": 667115961049.069, "dur": 0.628, + "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": 4183436, "tid": 4183436, + "ts": 667115961050.250, "dur": 1.728, + "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": 4183436, "tid": 4183436, + "ts": 667115961051.351, "dur": 0.557, + "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": 4183436, "tid": 4183436, + "ts": 667115961052.283, "dur": 3.143, + "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": 4183436, "tid": 4183436, + "ts": 667115961054.723, "dur": 0.635, + "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": 4183436, "tid": 4183436, + "ts": 667115961055.679, "dur": 1.206, + "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": 4183436, "tid": 4183436, + "ts": 667115961056.325, "dur": 0.494, + "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": 4183436, "tid": 4183436, + "ts": 667115961057.137, "dur": 2.808, + "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": 4183436, "tid": 4183436, + "ts": 667115961057.846, "dur": 2.031, + "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": 4183436, "tid": 4183436, + "ts": 667115961060.199, "dur": 1.437, + "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": 4183436, "tid": 4183436, + "ts": 667115961060.896, "dur": 0.579, + "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": 4183436, "tid": 4183436, + "ts": 667115961062.068, "dur": 1.231, + "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": 4183436, "tid": 4183436, + "ts": 667115961062.686, "dur": 0.544, + "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": 4183436, "tid": 4183436, + "ts": 667115961063.587, "dur": 3.656, + "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": 4183436, "tid": 4183436, + "ts": 667115961066.752, "dur": 0.426, + "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": 4183436, "tid": 4183436, + "ts": 667115961067.612, "dur": 1.794, + "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": 4183436, "tid": 4183436, + "ts": 667115961068.796, "dur": 0.549, + "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": 4183436, "tid": 4183436, + "ts": 667115961087.724, "dur": 103.411, + "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": 4183436, "tid": 4183436, + "ts": 667115961277.122, "dur": 121.719, + "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": 4183436, "tid": 4183436, + "ts": 667115961335.770, "dur": 44.531, + "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": 4183436, "tid": 4183436, + "ts": 667115961349.933, "dur": 0.868, + "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": 4183436, "tid": 4183436, + "ts": 667115961720.533, "dur": 871.800, + "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": 4183436, "tid": 4183436, + "ts": 667115961773.350, "dur": 52.555, + "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": 4183436, "tid": 4183436, + "ts": 667115961777.955, "dur": 1.628, + "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": 4183436, "tid": 4183436, + "ts": 667115961781.322, "dur": 0.623, + "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": 4183436, "tid": 4183436, + "ts": 667115961851.003, "dur": 441.014, + "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": 4183436, "tid": 4183436, + "ts": 667115961854.791, "dur": 42.217, + "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": 4183436, "tid": 4183436, + "ts": 667115961857.557, "dur": 8.738, + "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": 4183436, "tid": 4183436, + "ts": 667115961861.546, "dur": 3.890, + "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": 4183436, "tid": 4183436, + "ts": 667115961867.722, "dur": 28.815, + "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": 4183436, "tid": 4183436, + "ts": 667115961906.597, "dur": 382.207, + "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": 4183436, "tid": 4183436, + "ts": 667115961933.365, "dur": 349.624, + "args": { + "External id": 235075,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[[]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 4183436, "tid": 4183436, + "ts": 667115961949.538, "dur": 328.291, + "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": 4183436, "tid": 4183436, + "ts": 667115962350.668, "dur": 204.163, + "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": 4183436, "tid": 4183436, + "ts": 667115962433.009, "dur": 26.263, + "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": 4183436, "tid": 4183436, + "ts": 667115962446.308, "dur": 4.362, + "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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 4183436, "tid": 4183436, + "ts": 667115962487.667, "dur": 60.273, + "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": 4183436, "tid": 4183436, + "ts": 667115962489.972, "dur": 0.788, + "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": 4183436, "tid": 4183436, + "ts": 667115962510.898, "dur": 0.709, + "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": 4183436, "tid": 4183436, + "ts": 667115962608.707, "dur": 20.846, + "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": 4183436, "tid": 4183436, + "ts": 667115962618.753, "dur": 7.820, + "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": 4183436, "tid": 4183436, + "ts": 667115962621.113, "dur": 5.262, + "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": 4183436, "tid": 4183436, + "ts": 667115963011.897, "dur": 38.315, + "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": 4183436, "tid": 4183436, + "ts": 667115963060.573, "dur": 20.834, + "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": 4183436, "tid": 4183436, + "ts": 667115963088.719, "dur": 21.933, + "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": 4183436, "tid": 4183436, + "ts": 667115963123.141, "dur": 24.129, + "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": 4183436, "tid": 4183436, + "ts": 667115963127.127, "dur": 0.528, + "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": 4183436, "tid": 4183436, + "ts": 667115963163.408, "dur": 0.531, + "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": 4183436, "tid": 4183436, + "ts": 667115963256.785, "dur": 547.452, + "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": 4183436, "tid": 4183436, + "ts": 667115963708.894, "dur": 65.660, + "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": 4183436, "tid": 4183436, + "ts": 667115963845.243, "dur": 25.439, + "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": 4183436, "tid": 4183436, + "ts": 667115963848.686, "dur": 21.434, + "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": 4183436, "tid": 4183436, + "ts": 667115963873.778, "dur": 590.403, + "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": 4183436, "tid": 4183436, + "ts": 667115963875.146, "dur": 588.757, + "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": 4183436, "tid": 4183436, + "ts": 667115963876.929, "dur": 586.111, + "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": 4183436, "tid": 4183436, + "ts": 667115964470.642, "dur": 75.717, + "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": 4183436, "tid": 4183436, + "ts": 667115964473.484, "dur": 47.713, + "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": 4183436, "tid": 4183436, + "ts": 667115964478.715, "dur": 3.030, + "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": 4183436, "tid": 4183436, + "ts": 667115964485.285, "dur": 35.574, + "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": 4183436, "tid": 4183436, + "ts": 667115964490.022, "dur": 14.652, + "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": 4183436, "tid": 4183436, + "ts": 667115964523.766, "dur": 21.736, + "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": 4183436, "tid": 4183436, + "ts": 667115964549.294, "dur": 37.961, + "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": 4183436, "tid": 4183436, + "ts": 667115964550.387, "dur": 36.722, + "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": 4183436, "tid": 4183436, + "ts": 667115964551.400, "dur": 35.410, + "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": 4183436, "tid": 4183436, + "ts": 667115964619.048, "dur": 4337.966, + "args": { + "External id": 235108,"Record function id": 0, "Ev Idx": 9299 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 4183436, "tid": 4183436, + "ts": 667115964679.352, "dur": 4256.180, + "args": { + "External id": 235109,"Record function id": 0, "Ev Idx": 9300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 4183436, "tid": 4183436, + "ts": 667115965624.762, "dur": 262.246, + "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": 4183436, "tid": 4183436, + "ts": 667115965640.976, "dur": 1.133, + "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": 4183436, "tid": 4183436, + "ts": 667115965643.128, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965643.634, "dur": 0.146, + "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": 4183436, "tid": 4183436, + "ts": 667115965644.189, "dur": 0.208, + "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": 4183436, "tid": 4183436, + "ts": 667115965644.897, "dur": 0.221, + "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": 4183436, "tid": 4183436, + "ts": 667115965645.668, "dur": 0.347, + "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": 4183436, "tid": 4183436, + "ts": 667115965646.596, "dur": 0.098, + "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": 4183436, "tid": 4183436, + "ts": 667115965647.102, "dur": 0.194, + "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": 4183436, "tid": 4183436, + "ts": 667115965647.634, "dur": 0.057, + "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": 4183436, "tid": 4183436, + "ts": 667115965648.130, "dur": 0.053, + "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": 4183436, "tid": 4183436, + "ts": 667115965648.508, "dur": 0.091, + "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": 4183436, "tid": 4183436, + "ts": 667115965648.978, "dur": 0.185, + "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": 4183436, "tid": 4183436, + "ts": 667115965649.484, "dur": 0.063, + "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": 4183436, "tid": 4183436, + "ts": 667115965649.972, "dur": 0.064, + "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": 4183436, "tid": 4183436, + "ts": 667115965679.876, "dur": 0.643, + "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": 4183436, "tid": 4183436, + "ts": 667115965682.485, "dur": 0.094, + "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": 4183436, "tid": 4183436, + "ts": 667115965683.271, "dur": 0.078, + "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": 4183436, "tid": 4183436, + "ts": 667115965684.270, "dur": 0.095, + "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": 4183436, "tid": 4183436, + "ts": 667115965685.014, "dur": 0.072, + "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": 4183436, "tid": 4183436, + "ts": 667115965685.700, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965686.464, "dur": 0.084, + "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": 4183436, "tid": 4183436, + "ts": 667115965687.204, "dur": 0.282, + "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": 4183436, "tid": 4183436, + "ts": 667115965688.191, "dur": 0.089, + "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": 4183436, "tid": 4183436, + "ts": 667115965688.988, "dur": 0.086, + "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": 4183436, "tid": 4183436, + "ts": 667115965689.637, "dur": 0.071, + "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": 4183436, "tid": 4183436, + "ts": 667115965690.403, "dur": 0.068, + "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": 4183436, "tid": 4183436, + "ts": 667115965691.140, "dur": 0.093, + "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": 4183436, "tid": 4183436, + "ts": 667115965692.087, "dur": 0.101, + "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": 4183436, "tid": 4183436, + "ts": 667115965692.854, "dur": 0.194, + "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": 4183436, "tid": 4183436, + "ts": 667115965693.732, "dur": 0.098, + "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": 4183436, "tid": 4183436, + "ts": 667115965694.485, "dur": 0.115, + "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": 4183436, "tid": 4183436, + "ts": 667115965695.290, "dur": 0.095, + "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": 4183436, "tid": 4183436, + "ts": 667115965696.079, "dur": 0.094, + "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": 4183436, "tid": 4183436, + "ts": 667115965696.771, "dur": 0.077, + "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": 4183436, "tid": 4183436, + "ts": 667115965697.524, "dur": 0.088, + "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": 4183436, "tid": 4183436, + "ts": 667115965698.302, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965699.083, "dur": 0.211, + "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": 4183436, "tid": 4183436, + "ts": 667115965699.862, "dur": 0.086, + "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": 4183436, "tid": 4183436, + "ts": 667115965700.725, "dur": 0.215, + "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": 4183436, "tid": 4183436, + "ts": 667115965701.594, "dur": 0.191, + "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": 4183436, "tid": 4183436, + "ts": 667115965702.518, "dur": 0.083, + "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": 4183436, "tid": 4183436, + "ts": 667115965703.344, "dur": 0.185, + "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": 4183436, "tid": 4183436, + "ts": 667115965704.170, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115965705.005, "dur": 0.079, + "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": 4183436, "tid": 4183436, + "ts": 667115965705.848, "dur": 0.084, + "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": 4183436, "tid": 4183436, + "ts": 667115965706.600, "dur": 0.086, + "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": 4183436, "tid": 4183436, + "ts": 667115965707.383, "dur": 0.089, + "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": 4183436, "tid": 4183436, + "ts": 667115965708.144, "dur": 0.093, + "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": 4183436, "tid": 4183436, + "ts": 667115965708.941, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965709.690, "dur": 0.082, + "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": 4183436, "tid": 4183436, + "ts": 667115965710.411, "dur": 0.280, + "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": 4183436, "tid": 4183436, + "ts": 667115965711.377, "dur": 0.095, + "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": 4183436, "tid": 4183436, + "ts": 667115965712.152, "dur": 0.204, + "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": 4183436, "tid": 4183436, + "ts": 667115965713.053, "dur": 0.222, + "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": 4183436, "tid": 4183436, + "ts": 667115965713.905, "dur": 0.219, + "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": 4183436, "tid": 4183436, + "ts": 667115965714.770, "dur": 0.095, + "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": 4183436, "tid": 4183436, + "ts": 667115965715.451, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965716.227, "dur": 0.096, + "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": 4183436, "tid": 4183436, + "ts": 667115965716.942, "dur": 0.094, + "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": 4183436, "tid": 4183436, + "ts": 667115965717.704, "dur": 0.124, + "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": 4183436, "tid": 4183436, + "ts": 667115965718.564, "dur": 0.207, + "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": 4183436, "tid": 4183436, + "ts": 667115965719.510, "dur": 0.118, + "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": 4183436, "tid": 4183436, + "ts": 667115965720.203, "dur": 0.078, + "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": 4183436, "tid": 4183436, + "ts": 667115965720.982, "dur": 0.085, + "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": 4183436, "tid": 4183436, + "ts": 667115965721.737, "dur": 0.086, + "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": 4183436, "tid": 4183436, + "ts": 667115965722.654, "dur": 0.089, + "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": 4183436, "tid": 4183436, + "ts": 667115965723.356, "dur": 0.189, + "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": 4183436, "tid": 4183436, + "ts": 667115965724.196, "dur": 0.172, + "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": 4183436, "tid": 4183436, + "ts": 667115965725.039, "dur": 0.233, + "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": 4183436, "tid": 4183436, + "ts": 667115965725.969, "dur": 0.097, + "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": 4183436, "tid": 4183436, + "ts": 667115965726.763, "dur": 0.198, + "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": 4183436, "tid": 4183436, + "ts": 667115965727.569, "dur": 0.203, + "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": 4183436, "tid": 4183436, + "ts": 667115965728.457, "dur": 0.068, + "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": 4183436, "tid": 4183436, + "ts": 667115965729.174, "dur": 0.094, + "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": 4183436, "tid": 4183436, + "ts": 667115965729.990, "dur": 0.187, + "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": 4183436, "tid": 4183436, + "ts": 667115965731.029, "dur": 0.228, + "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": 4183436, "tid": 4183436, + "ts": 667115965731.954, "dur": 0.093, + "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": 4183436, "tid": 4183436, + "ts": 667115965732.777, "dur": 0.195, + "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": 4183436, "tid": 4183436, + "ts": 667115965733.725, "dur": 0.205, + "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": 4183436, "tid": 4183436, + "ts": 667115965734.644, "dur": 0.202, + "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": 4183436, "tid": 4183436, + "ts": 667115965735.606, "dur": 0.086, + "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": 4183436, "tid": 4183436, + "ts": 667115965736.421, "dur": 0.089, + "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": 4183436, "tid": 4183436, + "ts": 667115965737.193, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965737.960, "dur": 0.079, + "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": 4183436, "tid": 4183436, + "ts": 667115965738.833, "dur": 0.089, + "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": 4183436, "tid": 4183436, + "ts": 667115965739.705, "dur": 0.089, + "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": 4183436, "tid": 4183436, + "ts": 667115965740.483, "dur": 0.094, + "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": 4183436, "tid": 4183436, + "ts": 667115965741.183, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965741.910, "dur": 0.084, + "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": 4183436, "tid": 4183436, + "ts": 667115965742.652, "dur": 0.093, + "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": 4183436, "tid": 4183436, + "ts": 667115965743.452, "dur": 0.196, + "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": 4183436, "tid": 4183436, + "ts": 667115965744.341, "dur": 0.212, + "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": 4183436, "tid": 4183436, + "ts": 667115965745.216, "dur": 0.083, + "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": 4183436, "tid": 4183436, + "ts": 667115965745.920, "dur": 0.088, + "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": 4183436, "tid": 4183436, + "ts": 667115965746.572, "dur": 0.100, + "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": 4183436, "tid": 4183436, + "ts": 667115965747.310, "dur": 0.098, + "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": 4183436, "tid": 4183436, + "ts": 667115965748.068, "dur": 0.081, + "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": 4183436, "tid": 4183436, + "ts": 667115965748.799, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965749.529, "dur": 0.114, + "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": 4183436, "tid": 4183436, + "ts": 667115965750.276, "dur": 0.207, + "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": 4183436, "tid": 4183436, + "ts": 667115965751.177, "dur": 0.107, + "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": 4183436, "tid": 4183436, + "ts": 667115965752.501, "dur": 0.152, + "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": 4183436, "tid": 4183436, + "ts": 667115965753.368, "dur": 0.097, + "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": 4183436, "tid": 4183436, + "ts": 667115965754.169, "dur": 0.223, + "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": 4183436, "tid": 4183436, + "ts": 667115965755.011, "dur": 0.092, + "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": 4183436, "tid": 4183436, + "ts": 667115965755.967, "dur": 0.098, + "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": 4183436, "tid": 4183436, + "ts": 667115965756.633, "dur": 0.082, + "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": 4183436, "tid": 4183436, + "ts": 667115965757.356, "dur": 0.077, + "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": 4183436, "tid": 4183436, + "ts": 667115965758.069, "dur": 0.100, + "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": 4183436, "tid": 4183436, + "ts": 667115965758.874, "dur": 0.095, + "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": 4183436, "tid": 4183436, + "ts": 667115965759.642, "dur": 0.094, + "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": 4183436, "tid": 4183436, + "ts": 667115965760.421, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965761.197, "dur": 0.092, + "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": 4183436, "tid": 4183436, + "ts": 667115965762.039, "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": 4183436, "tid": 4183436, + "ts": 667115965762.835, "dur": 0.106, + "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": 4183436, "tid": 4183436, + "ts": 667115965763.632, "dur": 0.089, + "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": 4183436, "tid": 4183436, + "ts": 667115965764.388, "dur": 0.097, + "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": 4183436, "tid": 4183436, + "ts": 667115965765.105, "dur": 0.083, + "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": 4183436, "tid": 4183436, + "ts": 667115965765.863, "dur": 0.093, + "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": 4183436, "tid": 4183436, + "ts": 667115965766.681, "dur": 0.183, + "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": 4183436, "tid": 4183436, + "ts": 667115965767.499, "dur": 0.086, + "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": 4183436, "tid": 4183436, + "ts": 667115965768.136, "dur": 0.077, + "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": 4183436, "tid": 4183436, + "ts": 667115965769.489, "dur": 0.143, + "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": 4183436, "tid": 4183436, + "ts": 667115965770.329, "dur": 0.134, + "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": 4183436, "tid": 4183436, + "ts": 667115965770.843, "dur": 0.186, + "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": 4183436, "tid": 4183436, + "ts": 667115965771.325, "dur": 0.097, + "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": 4183436, "tid": 4183436, + "ts": 667115965771.781, "dur": 0.048, + "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": 4183436, "tid": 4183436, + "ts": 667115965772.190, "dur": 0.062, + "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": 4183436, "tid": 4183436, + "ts": 667115965772.646, "dur": 0.062, + "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": 4183436, "tid": 4183436, + "ts": 667115965773.063, "dur": 0.075, + "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": 4183436, "tid": 4183436, + "ts": 667115965773.536, "dur": 0.066, + "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": 4183436, "tid": 4183436, + "ts": 667115965773.960, "dur": 0.059, + "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": 4183436, "tid": 4183436, + "ts": 667115965774.600, "dur": 0.068, + "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": 4183436, "tid": 4183436, + "ts": 667115965775.088, "dur": 0.064, + "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": 4183436, "tid": 4183436, + "ts": 667115965775.468, "dur": 0.068, + "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": 4183436, "tid": 4183436, + "ts": 667115965775.952, "dur": 0.065, + "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": 4183436, "tid": 4183436, + "ts": 667115965776.428, "dur": 0.066, + "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": 4183436, "tid": 4183436, + "ts": 667115965776.809, "dur": 0.065, + "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": 4183436, "tid": 4183436, + "ts": 667115965777.134, "dur": 0.067, + "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": 4183436, "tid": 4183436, + "ts": 667115965777.582, "dur": 0.067, + "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": 4183436, "tid": 4183436, + "ts": 667115965777.957, "dur": 0.068, + "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": 4183436, "tid": 4183436, + "ts": 667115965778.361, "dur": 0.091, + "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": 4183436, "tid": 4183436, + "ts": 667115965778.812, "dur": 0.102, + "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": 4183436, "tid": 4183436, + "ts": 667115965779.252, "dur": 0.090, + "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": 4183436, "tid": 4183436, + "ts": 667115965779.723, "dur": 0.060, + "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": 4183436, "tid": 4183436, + "ts": 667115965780.204, "dur": 0.077, + "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": 4183436, "tid": 4183436, + "ts": 667115965780.710, "dur": 0.052, + "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": 4183436, "tid": 4183436, + "ts": 667115965781.046, "dur": 0.075, + "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": 4183436, "tid": 4183436, + "ts": 667115965781.455, "dur": 0.198, + "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": 4183436, "tid": 4183436, + "ts": 667115965782.063, "dur": 0.052, + "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": 4183436, "tid": 4183436, + "ts": 667115965782.490, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965782.941, "dur": 0.087, + "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": 4183436, "tid": 4183436, + "ts": 667115965783.363, "dur": 0.067, + "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": 4183436, "tid": 4183436, + "ts": 667115965783.785, "dur": 0.066, + "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": 4183436, "tid": 4183436, + "ts": 667115965784.266, "dur": 0.068, + "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": 4183436, "tid": 4183436, + "ts": 667115965784.679, "dur": 0.067, + "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": 4183436, "tid": 4183436, + "ts": 667115965785.027, "dur": 0.071, + "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": 4183436, "tid": 4183436, + "ts": 667115965785.550, "dur": 0.068, + "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": 4183436, "tid": 4183436, + "ts": 667115965785.957, "dur": 0.068, + "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": 4183436, "tid": 4183436, + "ts": 667115965786.408, "dur": 0.061, + "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": 4183436, "tid": 4183436, + "ts": 667115965786.816, "dur": 0.063, + "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": 4183436, "tid": 4183436, + "ts": 667115965787.248, "dur": 0.062, + "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": 4183436, "tid": 4183436, + "ts": 667115965787.665, "dur": 0.055, + "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": 4183436, "tid": 4183436, + "ts": 667115965788.235, "dur": 0.061, + "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": 4183436, "tid": 4183436, + "ts": 667115965788.588, "dur": 0.054, + "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": 4183436, "tid": 4183436, + "ts": 667115965789.056, "dur": 0.072, + "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": 4183436, "tid": 4183436, + "ts": 667115965789.382, "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": 4183436, "tid": 4183436, + "ts": 667115965789.995, "dur": 0.070, + "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": 4183436, "tid": 4183436, + "ts": 667115965790.308, "dur": 0.064, + "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": 4183436, "tid": 4183436, + "ts": 667115965791.136, "dur": 0.063, + "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": 4183436, "tid": 4183436, + "ts": 667115965791.450, "dur": 0.053, + "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": 4183436, "tid": 4183436, + "ts": 667115965792.449, "dur": 0.232, + "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": 4183436, "tid": 4183436, + "ts": 667115965793.034, "dur": 0.093, + "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": 4183436, "tid": 4183436, + "ts": 667115965793.781, "dur": 0.086, + "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": 4183436, "tid": 4183436, + "ts": 667115965794.212, "dur": 0.090, + "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": 4183436, "tid": 4183436, + "ts": 667115965794.758, "dur": 0.183, + "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": 4183436, "tid": 4183436, + "ts": 667115965795.276, "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": 4183436, "tid": 4183436, + "ts": 667115965795.950, "dur": 0.064, + "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": 4183436, "tid": 4183436, + "ts": 667115965796.260, "dur": 0.051, + "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": 4183436, "tid": 4183436, + "ts": 667115965796.854, "dur": 0.065, + "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": 4183436, "tid": 4183436, + "ts": 667115965797.189, "dur": 0.054, + "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": 4183436, "tid": 4183436, + "ts": 667115965797.677, "dur": 0.068, + "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": 4183436, "tid": 4183436, + "ts": 667115965797.984, "dur": 0.055, + "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": 4183436, "tid": 4183436, + "ts": 667115965798.603, "dur": 0.064, + "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": 4183436, "tid": 4183436, + "ts": 667115965798.907, "dur": 0.059, + "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": 4183436, "tid": 4183436, + "ts": 667115965799.647, "dur": 0.063, + "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": 4183436, "tid": 4183436, + "ts": 667115965799.950, "dur": 0.054, + "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": 4183436, "tid": 4183436, + "ts": 667115965800.528, "dur": 0.054, + "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": 4183436, "tid": 4183436, + "ts": 667115965800.819, "dur": 0.051, + "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": 4183436, "tid": 4183436, + "ts": 667115965801.349, "dur": 0.063, + "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": 4183436, "tid": 4183436, + "ts": 667115965801.656, "dur": 0.051, + "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": 4183436, "tid": 4183436, + "ts": 667115965802.200, "dur": 0.061, + "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": 4183436, "tid": 4183436, + "ts": 667115965802.514, "dur": 0.051, + "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": 4183436, "tid": 4183436, + "ts": 667115965803.160, "dur": 0.064, + "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": 4183436, "tid": 4183436, + "ts": 667115965803.472, "dur": 0.050, + "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": 4183436, "tid": 4183436, + "ts": 667115965804.464, "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": 4183436, "tid": 4183436, + "ts": 667115965804.767, "dur": 0.054, + "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": 4183436, "tid": 4183436, + "ts": 667115965805.284, "dur": 0.066, + "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": 4183436, "tid": 4183436, + "ts": 667115965805.605, "dur": 0.051, + "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": 4183436, "tid": 4183436, + "ts": 667115965806.234, "dur": 0.065, + "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": 4183436, "tid": 4183436, + "ts": 667115965806.550, "dur": 0.051, + "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": 4183436, "tid": 4183436, + "ts": 667115965807.170, "dur": 0.054, + "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": 4183436, "tid": 4183436, + "ts": 667115965807.475, "dur": 0.053, + "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": 4183436, "tid": 4183436, + "ts": 667115965808.249, "dur": 0.065, + "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": 4183436, "tid": 4183436, + "ts": 667115965808.569, "dur": 0.051, + "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": 4183436, "tid": 4183436, + "ts": 667115965809.105, "dur": 0.063, + "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": 4183436, "tid": 4183436, + "ts": 667115965809.421, "dur": 0.052, + "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": 4183436, "tid": 4183436, + "ts": 667115965810.027, "dur": 0.061, + "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": 4183436, "tid": 4183436, + "ts": 667115965810.343, "dur": 0.047, + "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": 4183436, "tid": 4183436, + "ts": 667115965810.934, "dur": 0.066, + "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": 4183436, "tid": 4183436, + "ts": 667115965811.251, "dur": 0.051, + "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": 4183436, "tid": 4183436, + "ts": 667115965811.776, "dur": 0.067, + "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": 4183436, "tid": 4183436, + "ts": 667115965812.099, "dur": 0.053, + "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": 4183436, "tid": 4183436, + "ts": 667115965812.692, "dur": 0.052, + "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": 4183436, "tid": 4183436, + "ts": 667115965813.000, "dur": 0.045, + "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": 4183436, "tid": 4183436, + "ts": 667115965813.431, "dur": 0.068, + "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": 4183436, "tid": 4183436, + "ts": 667115965813.887, "dur": 0.058, + "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": 4183436, "tid": 4183436, + "ts": 667115965814.386, "dur": 0.066, + "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": 4183436, "tid": 4183436, + "ts": 667115965814.838, "dur": 0.064, + "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": 4183436, "tid": 4183436, + "ts": 667115966275.737, "dur": 2581.443, + "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": 4183436, "tid": 4183436, + "ts": 667115968510.275, "dur": 227.261, + "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": 667115182767.140, "pid": 4183436, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 667115182767.140, "pid": 4183436, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 667115182767.140, "pid": 4183436, "tid": 0, + "args": { + "sort_index": 4183436 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 667115182767.140, "pid": 4183436, "tid": 31338, + "args": { + "name": "thread 31338 (pt_autograd_0)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 667115182767.140, "pid": 4183436, "tid": 31338, + "args": { + "sort_index": 31338 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 667115182767.140, "pid": 4183436, "tid": 4183436, + "args": { + "name": "thread 4183436 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 667115182767.140, "pid": 4183436, "tid": 4183436, + "args": { + "sort_index": 4183436 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 667115182767.140, "pid": 4183436, "tid": 31338, + "args": { + "name": "thread 31338 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 667115182767.140, "pid": 4183436, "tid": 31338, + "args": { + "sort_index": 31338 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 667115182699.229, "dur": 786516.778, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 667115182699.229, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 667115182699.229 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 667116012287.098 + } + ], + "traceName": "exp/mtp.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine/profile_trace/iteration_12288/rank0_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file