diff --git "a/profile_trace/iteration_39936/rank0_trace.json" "b/profile_trace/iteration_39936/rank0_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_39936/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": "C869550602AE47448ECAC8B4E9649134", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924372534.027, "dur": 179.616, + "args": { + "External id": 760833,"Record function id": 0, "Sequence number": 8962174, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924372572.422, "dur": 129.801, + "args": { + "External id": 760834,"Sequence number": 8962174, "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": 688924372572.422, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 4183436, "tid": 31338, + "ts": 688924372582.020, "dur": 117.623, + "args": { + "External id": 760835,"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": 688924372728.716, "dur": 284.369, + "args": { + "External id": 760836,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 4183436, "tid": 31338, + "ts": 688924372809.222, "dur": 109.959, + "args": { + "External id": 760837,"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": 688924372850.278, "dur": 56.292, + "args": { + "External id": 760838,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924372925.185, "dur": 1.621, + "args": { + "External id": 760839,"Sequence number": 8962173, "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": 688924372925.185, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183436, "tid": 31338, + "ts": 688924372931.458, "dur": 73.911, + "args": { + "External id": 760840,"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": 688924372951.497, "dur": 53.333, + "args": { + "External id": 760841,"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": 688924372963.669, "dur": 3.444, + "args": { + "External id": 760842,"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": 688924373024.918, "dur": 16719.065, + "args": { + "External id": 760843,"Record function id": 0, "Sequence number": 8962171, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924373027.323, "dur": 16705.552, + "args": { + "External id": 760844,"Sequence number": 8962171, "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": 688924373027.323, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924373074.573, "dur": 5.194, + "args": { + "External id": 760845,"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": 688924373086.147, "dur": 16508.438, + "args": { + "External id": 760846,"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": 688924373088.582, "dur": 16505.597, + "args": { + "External id": 760847,"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": 688924373094.233, "dur": 7.013, + "args": { + "External id": 760848,"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": 688924373103.629, "dur": 16489.658, + "args": { + "External id": 760849,"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": 688924389599.519, "dur": 0.488, + "args": { + "External id": 760850,"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": 688924389602.653, "dur": 3.362, + "args": { + "External id": 760851,"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": 688924389604.534, "dur": 1.222, + "args": { + "External id": 760852,"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": 688924389611.938, "dur": 29.529, + "args": { + "External id": 760853,"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": 688924389649.427, "dur": 73.064, + "args": { + "External id": 760854,"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": 688924389673.506, "dur": 48.732, + "args": { + "External id": 760855,"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": 688924389676.228, "dur": 45.513, + "args": { + "External id": 760856,"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": 688924389756.612, "dur": 20.633, + "args": { + "External id": 760857,"Record function id": 0, "Sequence number": 8962170, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924389758.617, "dur": 14.693, + "args": { + "External id": 760858,"Sequence number": 8962170, "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": 688924389758.617, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924389762.711, "dur": 10.352, + "args": { + "External id": 760859,"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": 688924389766.418, "dur": 6.476, + "args": { + "External id": 760860,"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": 688924389781.587, "dur": 113.306, + "args": { + "External id": 760861,"Record function id": 0, "Sequence number": 8962169, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924389782.323, "dur": 102.357, + "args": { + "External id": 760862,"Sequence number": 8962169, "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": 688924389782.323, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924389797.936, "dur": 86.178, + "args": { + "External id": 760863,"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": 688924389804.020, "dur": 39.467, + "args": { + "External id": 760864,"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": 688924389808.471, "dur": 8.734, + "args": { + "External id": 760865,"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": 688924389819.627, "dur": 23.571, + "args": { + "External id": 760866,"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": 688924389823.473, "dur": 19.280, + "args": { + "External id": 760867,"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": 688924389848.223, "dur": 4.403, + "args": { + "External id": 760868,"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": 688924389850.814, "dur": 1.377, + "args": { + "External id": 760869,"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": 688924389853.927, "dur": 29.340, + "args": { + "External id": 760870,"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": 688924389901.398, "dur": 60.125, + "args": { + "External id": 760871,"Record function id": 0, "Sequence number": 8962168, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924389902.471, "dur": 54.780, + "args": { + "External id": 760872,"Sequence number": 8962168, "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": 688924389902.471, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183436, "tid": 31338, + "ts": 688924389905.523, "dur": 51.492, + "args": { + "External id": 760873,"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": 688924389907.662, "dur": 21.719, + "args": { + "External id": 760874,"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": 688924389910.369, "dur": 2.882, + "args": { + "External id": 760875,"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": 688924389913.793, "dur": 15.303, + "args": { + "External id": 760876,"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": 688924389916.749, "dur": 11.923, + "args": { + "External id": 760877,"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": 688924389933.498, "dur": 5.980, + "args": { + "External id": 760878,"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": 688924389937.328, "dur": 1.519, + "args": { + "External id": 760879,"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": 688924389939.987, "dur": 16.454, + "args": { + "External id": 760880,"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": 688924389966.024, "dur": 99.864, + "args": { + "External id": 760881,"Record function id": 0, "Sequence number": 8962167, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924389967.167, "dur": 93.435, + "args": { + "External id": 760882,"Sequence number": 8962167, "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": 688924389967.167, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924389969.040, "dur": 91.241, + "args": { + "External id": 760883,"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": 688924389974.139, "dur": 16.278, + "args": { + "External id": 760884,"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": 688924389974.871, "dur": 2.270, + "args": { + "External id": 760885,"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": 688924389977.931, "dur": 12.208, + "args": { + "External id": 760886,"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": 688924389978.884, "dur": 10.900, + "args": { + "External id": 760887,"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": 688924389993.337, "dur": 4.362, + "args": { + "External id": 760888,"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": 688924389994.640, "dur": 2.854, + "args": { + "External id": 760889,"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": 688924389998.314, "dur": 61.198, + "args": { + "External id": 760890,"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": 688924390071.228, "dur": 65.735, + "args": { + "External id": 760891,"Record function id": 0, "Sequence number": 8962166, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924390072.003, "dur": 60.651, + "args": { + "External id": 760892,"Sequence number": 8962166, "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": 688924390072.003, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924390073.313, "dur": 59.041, + "args": { + "External id": 760893,"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": 688924390074.377, "dur": 16.551, + "args": { + "External id": 760894,"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": 688924390076.994, "dur": 2.097, + "args": { + "External id": 760895,"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": 688924390079.723, "dur": 10.958, + "args": { + "External id": 760896,"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": 688924390080.381, "dur": 9.946, + "args": { + "External id": 760897,"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": 688924390091.723, "dur": 4.077, + "args": { + "External id": 760898,"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": 688924390095.000, "dur": 0.652, + "args": { + "External id": 760899,"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": 688924390098.066, "dur": 33.729, + "args": { + "External id": 760900,"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": 688924390141.396, "dur": 37.194, + "args": { + "External id": 760901,"Record function id": 0, "Sequence number": 8962165, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924390142.533, "dur": 0.843, + "args": { + "External id": 760902,"Sequence number": 8962165, "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": 688924390142.533, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183436, "tid": 31338, + "ts": 688924390146.430, "dur": 27.426, + "args": { + "External id": 760903,"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": 688924390148.307, "dur": 25.030, + "args": { + "External id": 760904,"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": 688924390152.991, "dur": 2.928, + "args": { + "External id": 760905,"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": 688924390183.463, "dur": 1091.434, + "args": { + "External id": 760906,"Record function id": 0, "Sequence number": 8962163, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924390184.729, "dur": 1055.953, + "args": { + "External id": 760907,"Sequence number": 8962163, "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": 688924390184.729, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924390222.045, "dur": 2.406, + "args": { + "External id": 760908,"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": 688924390226.788, "dur": 929.345, + "args": { + "External id": 760909,"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": 688924390228.445, "dur": 927.389, + "args": { + "External id": 760910,"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": 688924390230.883, "dur": 4.001, + "args": { + "External id": 760911,"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": 688924390235.861, "dur": 918.684, + "args": { + "External id": 760912,"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": 688924391159.222, "dur": 0.331, + "args": { + "External id": 760913,"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": 688924391160.895, "dur": 4.098, + "args": { + "External id": 760914,"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": 688924391163.864, "dur": 0.918, + "args": { + "External id": 760915,"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": 688924391168.581, "dur": 20.790, + "args": { + "External id": 760916,"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": 688924391194.261, "dur": 39.595, + "args": { + "External id": 760917,"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": 688924391195.279, "dur": 38.370, + "args": { + "External id": 760918,"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": 688924391196.261, "dur": 36.976, + "args": { + "External id": 760919,"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": 688924391252.177, "dur": 18.261, + "args": { + "External id": 760920,"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": 688924391282.104, "dur": 15.584, + "args": { + "External id": 760921,"Record function id": 0, "Sequence number": 8962162, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924391283.490, "dur": 10.934, + "args": { + "External id": 760922,"Sequence number": 8962162, "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": 688924391283.490, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924391288.020, "dur": 6.215, + "args": { + "External id": 760923,"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": 688924391290.928, "dur": 3.145, + "args": { + "External id": 760924,"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": 688924391301.464, "dur": 58.971, + "args": { + "External id": 760925,"Record function id": 0, "Sequence number": 8962161, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924391302.277, "dur": 52.304, + "args": { + "External id": 760926,"Sequence number": 8962161, "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": 688924391302.277, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924391303.877, "dur": 50.381, + "args": { + "External id": 760927,"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": 688924391305.731, "dur": 23.524, + "args": { + "External id": 760928,"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": 688924391309.104, "dur": 4.919, + "args": { + "External id": 760929,"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": 688924391314.990, "dur": 13.935, + "args": { + "External id": 760930,"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": 688924391316.337, "dur": 12.175, + "args": { + "External id": 760931,"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": 688924391330.421, "dur": 2.549, + "args": { + "External id": 760932,"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": 688924391331.898, "dur": 0.834, + "args": { + "External id": 760933,"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": 688924391333.904, "dur": 19.527, + "args": { + "External id": 760934,"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": 688924391366.911, "dur": 53.998, + "args": { + "External id": 760935,"Record function id": 0, "Sequence number": 8962160, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924391368.035, "dur": 49.994, + "args": { + "External id": 760936,"Sequence number": 8962160, "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": 688924391368.035, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183436, "tid": 31338, + "ts": 688924391372.421, "dur": 45.374, + "args": { + "External id": 760937,"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": 688924391374.186, "dur": 17.825, + "args": { + "External id": 760938,"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": 688924391375.124, "dur": 2.217, + "args": { + "External id": 760939,"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": 688924391378.398, "dur": 13.369, + "args": { + "External id": 760940,"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": 688924391379.430, "dur": 11.997, + "args": { + "External id": 760941,"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": 688924391393.115, "dur": 5.752, + "args": { + "External id": 760942,"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": 688924391397.532, "dur": 0.808, + "args": { + "External id": 760943,"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": 688924391399.347, "dur": 17.931, + "args": { + "External id": 760944,"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": 688924391424.651, "dur": 90.673, + "args": { + "External id": 760945,"Record function id": 0, "Sequence number": 8962159, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924391425.755, "dur": 85.600, + "args": { + "External id": 760946,"Sequence number": 8962159, "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": 688924391425.755, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924391428.551, "dur": 82.539, + "args": { + "External id": 760947,"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": 688924391429.353, "dur": 17.301, + "args": { + "External id": 760948,"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": 688924391430.151, "dur": 2.299, + "args": { + "External id": 760949,"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": 688924391433.151, "dur": 13.210, + "args": { + "External id": 760950,"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": 688924391434.150, "dur": 11.863, + "args": { + "External id": 760951,"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": 688924391447.687, "dur": 3.585, + "args": { + "External id": 760952,"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": 688924391450.569, "dur": 0.551, + "args": { + "External id": 760953,"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": 688924391452.071, "dur": 58.260, + "args": { + "External id": 760954,"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": 688924391521.104, "dur": 73.450, + "args": { + "External id": 760955,"Record function id": 0, "Sequence number": 8962158, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924391521.949, "dur": 57.412, + "args": { + "External id": 760956,"Sequence number": 8962158, "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": 688924391521.949, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924391525.828, "dur": 53.326, + "args": { + "External id": 760957,"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": 688924391526.656, "dur": 14.175, + "args": { + "External id": 760958,"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": 688924391527.384, "dur": 1.650, + "args": { + "External id": 760959,"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": 688924391529.644, "dur": 10.942, + "args": { + "External id": 760960,"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": 688924391530.168, "dur": 10.048, + "args": { + "External id": 760961,"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": 688924391541.470, "dur": 2.038, + "args": { + "External id": 760962,"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": 688924391542.741, "dur": 0.653, + "args": { + "External id": 760963,"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": 688924391543.950, "dur": 34.664, + "args": { + "External id": 760964,"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": 688924391582.503, "dur": 10.909, + "args": { + "External id": 760965,"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": 688924391598.661, "dur": 36.491, + "args": { + "External id": 760966,"Record function id": 0, "Sequence number": 8962157, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924391601.771, "dur": 0.579, + "args": { + "External id": 760967,"Sequence number": 8962157, "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": 688924391601.771, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183436, "tid": 31338, + "ts": 688924391604.957, "dur": 25.852, + "args": { + "External id": 760968,"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": 688924391606.457, "dur": 23.904, + "args": { + "External id": 760969,"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": 688924391613.843, "dur": 0.716, + "args": { + "External id": 760970,"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": 688924391640.257, "dur": 1485.383, + "args": { + "External id": 760971,"Record function id": 0, "Sequence number": 8962155, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924391643.716, "dur": 1455.452, + "args": { + "External id": 760972,"Sequence number": 8962155, "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": 688924391643.716, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924391701.826, "dur": 2.373, + "args": { + "External id": 760973,"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": 688924391706.616, "dur": 1308.449, + "args": { + "External id": 760974,"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": 688924391707.808, "dur": 1307.048, + "args": { + "External id": 760975,"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": 688924391709.731, "dur": 3.775, + "args": { + "External id": 760976,"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": 688924391714.338, "dur": 1299.518, + "args": { + "External id": 760977,"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": 688924393017.803, "dur": 0.288, + "args": { + "External id": 760978,"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": 688924393019.100, "dur": 2.002, + "args": { + "External id": 760979,"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": 688924393020.177, "dur": 0.806, + "args": { + "External id": 760980,"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": 688924393024.783, "dur": 19.252, + "args": { + "External id": 760981,"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": 688924393050.888, "dur": 42.260, + "args": { + "External id": 760982,"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": 688924393051.666, "dur": 41.293, + "args": { + "External id": 760983,"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": 688924393054.587, "dur": 38.051, + "args": { + "External id": 760984,"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": 688924393106.917, "dur": 15.019, + "args": { + "External id": 760985,"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": 688924393135.740, "dur": 10.856, + "args": { + "External id": 760986,"Record function id": 0, "Sequence number": 8962154, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924393137.225, "dur": 6.385, + "args": { + "External id": 760987,"Sequence number": 8962154, "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": 688924393137.225, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924393139.662, "dur": 3.747, + "args": { + "External id": 760988,"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": 688924393140.672, "dur": 2.621, + "args": { + "External id": 760989,"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": 688924393149.903, "dur": 62.904, + "args": { + "External id": 760990,"Record function id": 0, "Sequence number": 8962153, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924393151.093, "dur": 57.131, + "args": { + "External id": 760991,"Sequence number": 8962153, "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": 688924393151.093, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924393152.926, "dur": 55.036, + "args": { + "External id": 760992,"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": 688924393158.756, "dur": 20.194, + "args": { + "External id": 760993,"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": 688924393159.755, "dur": 2.357, + "args": { + "External id": 760994,"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": 688924393163.112, "dur": 15.549, + "args": { + "External id": 760995,"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": 688924393164.234, "dur": 13.975, + "args": { + "External id": 760996,"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": 688924393180.095, "dur": 4.519, + "args": { + "External id": 760997,"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": 688924393183.583, "dur": 0.790, + "args": { + "External id": 760998,"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": 688924393185.225, "dur": 22.007, + "args": { + "External id": 760999,"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": 688924393216.686, "dur": 54.461, + "args": { + "External id": 761000,"Record function id": 0, "Sequence number": 8962152, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924393217.967, "dur": 49.403, + "args": { + "External id": 761001,"Sequence number": 8962152, "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": 688924393217.967, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183436, "tid": 31338, + "ts": 688924393219.403, "dur": 47.735, + "args": { + "External id": 761002,"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": 688924393220.683, "dur": 18.458, + "args": { + "External id": 761003,"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": 688924393223.669, "dur": 2.489, + "args": { + "External id": 761004,"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": 688924393226.749, "dur": 12.146, + "args": { + "External id": 761005,"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": 688924393227.566, "dur": 10.958, + "args": { + "External id": 761006,"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": 688924393240.080, "dur": 8.233, + "args": { + "External id": 761007,"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": 688924393244.720, "dur": 3.124, + "args": { + "External id": 761008,"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": 688924393249.141, "dur": 17.488, + "args": { + "External id": 761009,"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": 688924393274.768, "dur": 68.316, + "args": { + "External id": 761010,"Record function id": 0, "Sequence number": 8962151, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924393276.005, "dur": 63.643, + "args": { + "External id": 761011,"Sequence number": 8962151, "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": 688924393276.005, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924393277.430, "dur": 61.993, + "args": { + "External id": 761012,"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": 688924393278.341, "dur": 16.368, + "args": { + "External id": 761013,"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": 688924393280.867, "dur": 2.528, + "args": { + "External id": 761014,"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": 688924393284.042, "dur": 10.420, + "args": { + "External id": 761015,"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": 688924393284.536, "dur": 9.550, + "args": { + "External id": 761016,"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": 688924393295.536, "dur": 4.557, + "args": { + "External id": 761017,"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": 688924393299.087, "dur": 0.842, + "args": { + "External id": 761018,"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": 688924393300.622, "dur": 38.116, + "args": { + "External id": 761019,"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": 688924393346.679, "dur": 77.319, + "args": { + "External id": 761020,"Record function id": 0, "Sequence number": 8962150, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924393347.476, "dur": 61.996, + "args": { + "External id": 761021,"Sequence number": 8962150, "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": 688924393347.476, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924393351.341, "dur": 57.911, + "args": { + "External id": 761022,"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": 688924393352.043, "dur": 17.718, + "args": { + "External id": 761023,"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": 688924393354.233, "dur": 1.943, + "args": { + "External id": 761024,"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": 688924393356.729, "dur": 12.759, + "args": { + "External id": 761025,"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": 688924393357.249, "dur": 11.919, + "args": { + "External id": 761026,"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": 688924393370.610, "dur": 2.031, + "args": { + "External id": 761027,"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": 688924393371.650, "dur": 0.862, + "args": { + "External id": 761028,"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": 688924393373.340, "dur": 35.283, + "args": { + "External id": 761029,"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": 688924393412.428, "dur": 10.449, + "args": { + "External id": 761030,"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": 688924393427.589, "dur": 28.709, + "args": { + "External id": 761031,"Record function id": 0, "Sequence number": 8962149, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924393428.535, "dur": 1.001, + "args": { + "External id": 761032,"Sequence number": 8962149, "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": 688924393428.535, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183436, "tid": 31338, + "ts": 688924393431.196, "dur": 20.030, + "args": { + "External id": 761033,"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": 688924393434.257, "dur": 16.567, + "args": { + "External id": 761034,"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": 688924393437.834, "dur": 0.524, + "args": { + "External id": 761035,"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": 688924393460.769, "dur": 1510.340, + "args": { + "External id": 761036,"Record function id": 0, "Sequence number": 8962148, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924393472.160, "dur": 1472.547, + "args": { + "External id": 761037,"Sequence number": 8962148, "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": 688924393472.160, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924393494.835, "dur": 1.827, + "args": { + "External id": 761038,"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": 688924393498.234, "dur": 1370.153, + "args": { + "External id": 761039,"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": 688924393499.176, "dur": 1368.925, + "args": { + "External id": 761040,"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": 688924393501.117, "dur": 2.949, + "args": { + "External id": 761041,"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": 688924393504.660, "dur": 1362.572, + "args": { + "External id": 761042,"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": 688924394872.856, "dur": 0.313, + "args": { + "External id": 761043,"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": 688924394874.203, "dur": 2.039, + "args": { + "External id": 761044,"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": 688924394875.321, "dur": 0.798, + "args": { + "External id": 761045,"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": 688924394879.788, "dur": 19.291, + "args": { + "External id": 761046,"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": 688924394903.073, "dur": 35.730, + "args": { + "External id": 761047,"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": 688924394903.789, "dur": 34.846, + "args": { + "External id": 761048,"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": 688924394904.866, "dur": 33.532, + "args": { + "External id": 761049,"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": 688924394955.129, "dur": 12.132, + "args": { + "External id": 761050,"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": 688924394981.702, "dur": 11.892, + "args": { + "External id": 761051,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924394984.120, "dur": 8.002, + "args": { + "External id": 761052,"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": 688924394987.072, "dur": 4.033, + "args": { + "External id": 761053,"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": 688924394987.889, "dur": 3.107, + "args": { + "External id": 761054,"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": 688924394997.360, "dur": 10.036, + "args": { + "External id": 761055,"Record function id": 0, "Sequence number": 8962147, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924394998.389, "dur": 5.963, + "args": { + "External id": 761056,"Sequence number": 8962147, "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": 688924394998.389, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924395001.089, "dur": 3.069, + "args": { + "External id": 761057,"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": 688924395001.947, "dur": 2.079, + "args": { + "External id": 761058,"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": 688924395010.896, "dur": 58.945, + "args": { + "External id": 761059,"Record function id": 0, "Sequence number": 8962146, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924395011.934, "dur": 52.083, + "args": { + "External id": 761060,"Sequence number": 8962146, "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": 688924395011.934, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924395015.469, "dur": 48.275, + "args": { + "External id": 761061,"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": 688924395019.363, "dur": 19.058, + "args": { + "External id": 761062,"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": 688924395020.684, "dur": 2.747, + "args": { + "External id": 761063,"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": 688924395024.222, "dur": 13.929, + "args": { + "External id": 761064,"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": 688924395025.134, "dur": 12.437, + "args": { + "External id": 761065,"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": 688924395039.679, "dur": 4.512, + "args": { + "External id": 761066,"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": 688924395043.121, "dur": 0.862, + "args": { + "External id": 761067,"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": 688924395044.884, "dur": 18.160, + "args": { + "External id": 761068,"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": 688924395075.762, "dur": 53.659, + "args": { + "External id": 761069,"Record function id": 0, "Sequence number": 8962145, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924395076.752, "dur": 49.138, + "args": { + "External id": 761070,"Sequence number": 8962145, "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": 688924395076.752, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183436, "tid": 31338, + "ts": 688924395078.387, "dur": 47.265, + "args": { + "External id": 761071,"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": 688924395079.642, "dur": 19.899, + "args": { + "External id": 761072,"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": 688924395083.823, "dur": 2.224, + "args": { + "External id": 761073,"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": 688924395086.695, "dur": 12.588, + "args": { + "External id": 761074,"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": 688924395087.309, "dur": 11.573, + "args": { + "External id": 761075,"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": 688924395100.637, "dur": 5.920, + "args": { + "External id": 761076,"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": 688924395105.463, "dur": 0.706, + "args": { + "External id": 761077,"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": 688924395107.106, "dur": 18.047, + "args": { + "External id": 761078,"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": 688924395133.345, "dur": 69.397, + "args": { + "External id": 761079,"Record function id": 0, "Sequence number": 8962144, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924395134.426, "dur": 65.773, + "args": { + "External id": 761080,"Sequence number": 8962144, "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": 688924395134.426, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924395135.783, "dur": 64.179, + "args": { + "External id": 761081,"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": 688924395136.676, "dur": 18.269, + "args": { + "External id": 761082,"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": 688924395141.284, "dur": 1.674, + "args": { + "External id": 761083,"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": 688924395143.530, "dur": 11.175, + "args": { + "External id": 761084,"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": 688924395144.450, "dur": 9.859, + "args": { + "External id": 761085,"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": 688924395155.772, "dur": 3.541, + "args": { + "External id": 761086,"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": 688924395156.720, "dur": 2.457, + "args": { + "External id": 761087,"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": 688924395160.010, "dur": 39.258, + "args": { + "External id": 761088,"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": 688924395206.790, "dur": 98.396, + "args": { + "External id": 761089,"Record function id": 0, "Sequence number": 8962143, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924395207.582, "dur": 81.636, + "args": { + "External id": 761090,"Sequence number": 8962143, "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": 688924395207.582, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183436, "tid": 31338, + "ts": 688924395209.167, "dur": 79.747, + "args": { + "External id": 761091,"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": 688924395209.971, "dur": 38.363, + "args": { + "External id": 761092,"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": 688924395214.180, "dur": 1.584, + "args": { + "External id": 761093,"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": 688924395235.083, "dur": 12.975, + "args": { + "External id": 761094,"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": 688924395237.917, "dur": 9.747, + "args": { + "External id": 761095,"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": 688924395249.079, "dur": 3.557, + "args": { + "External id": 761096,"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": 688924395251.794, "dur": 0.677, + "args": { + "External id": 761097,"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": 688924395253.102, "dur": 35.106, + "args": { + "External id": 761098,"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": 688924395292.553, "dur": 10.858, + "args": { + "External id": 761099,"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": 688924395310.965, "dur": 399.760, + "args": { + "External id": 761100,"Record function id": 0, "Sequence number": 8962142, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924395312.233, "dur": 337.880, + "args": { + "External id": 761101,"Sequence number": 8962142, "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": 688924395312.233, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183436, "tid": 31338, + "ts": 688924395488.768, "dur": 41.969, + "args": { + "External id": 761102,"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": 688924395563.057, "dur": 25.240, + "args": { + "External id": 761103,"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": 688924395609.033, "dur": 17.550, + "args": { + "External id": 761104,"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": 688924395723.163, "dur": 14.138, + "args": { + "External id": 761105,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924395725.884, "dur": 10.393, + "args": { + "External id": 761106,"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": 688924395728.796, "dur": 6.600, + "args": { + "External id": 761107,"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": 688924395731.799, "dur": 3.416, + "args": { + "External id": 761108,"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": 688924395743.045, "dur": 36.416, + "args": { + "External id": 761109,"Record function id": 0, "Sequence number": 8962141, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924395743.920, "dur": 23.494, + "args": { + "External id": 761110,"Sequence number": 8962141, "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": 688924395743.920, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183436, "tid": 31338, + "ts": 688924395746.005, "dur": 7.796, + "args": { + "External id": 761111,"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": 688924395750.845, "dur": 1.511, + "args": { + "External id": 761112,"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": 688924395754.383, "dur": 4.546, + "args": { + "External id": 761113,"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": 688924395757.581, "dur": 0.592, + "args": { + "External id": 761114,"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": 688924395759.307, "dur": 2.290, + "args": { + "External id": 761115,"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": 688924395760.260, "dur": 0.525, + "args": { + "External id": 761116,"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": 688924395762.231, "dur": 4.488, + "args": { + "External id": 761117,"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": 688924395765.384, "dur": 0.488, + "args": { + "External id": 761118,"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": 688924395783.094, "dur": 19.597, + "args": { + "External id": 761119,"Record function id": 0, "Sequence number": 8962140, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924395783.929, "dur": 1.296, + "args": { + "External id": 761120,"Sequence number": 8962140, "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": 688924395783.929, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924395809.348, "dur": 498.270, + "args": { + "External id": 761121,"Record function id": 0, "Sequence number": 8962139, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924395810.849, "dur": 481.482, + "args": { + "External id": 761122,"Sequence number": 8962139, "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": 688924395810.849, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924395853.154, "dur": 11.870, + "args": { + "External id": 761123,"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": 688924395860.537, "dur": 4.185, + "args": { + "External id": 761124,"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": 688924395870.270, "dur": 10.467, + "args": { + "External id": 761125,"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": 688924395873.388, "dur": 6.389, + "args": { + "External id": 761126,"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": 688924395876.774, "dur": 2.784, + "args": { + "External id": 761127,"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": 688924395885.757, "dur": 126.400, + "args": { + "External id": 761128,"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": 688924395887.138, "dur": 3.110, + "args": { + "External id": 761129,"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": 688924395887.840, "dur": 1.535, + "args": { + "External id": 761130,"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": 688924395888.948, "dur": 0.331, + "args": { + "External id": 761131,"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": 688924395892.933, "dur": 118.496, + "args": { + "External id": 761132,"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": 688924395895.413, "dur": 114.879, + "args": { + "External id": 761133,"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": 688924396020.267, "dur": 6.280, + "args": { + "External id": 761134,"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": 688924396023.917, "dur": 2.509, + "args": { + "External id": 761135,"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": 688924396063.835, "dur": 6.046, + "args": { + "External id": 761136,"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": 688924396070.915, "dur": 2.058, + "args": { + "External id": 761137,"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": 688924396073.602, "dur": 1.766, + "args": { + "External id": 761138,"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": 688924396115.122, "dur": 2.250, + "args": { + "External id": 761139,"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": 688924396115.832, "dur": 1.389, + "args": { + "External id": 761140,"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": 688924396143.083, "dur": 128.290, + "args": { + "External id": 761141,"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": 688924396151.190, "dur": 7.485, + "args": { + "External id": 761142,"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": 688924396153.980, "dur": 2.309, + "args": { + "External id": 761143,"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": 688924396162.852, "dur": 5.883, + "args": { + "External id": 761144,"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": 688924396167.463, "dur": 0.522, + "args": { + "External id": 761145,"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": 688924396170.530, "dur": 3.733, + "args": { + "External id": 761146,"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": 688924396173.399, "dur": 0.488, + "args": { + "External id": 761147,"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": 688924396175.115, "dur": 3.903, + "args": { + "External id": 761148,"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": 688924396178.268, "dur": 0.434, + "args": { + "External id": 761149,"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": 688924396184.397, "dur": 4.000, + "args": { + "External id": 761150,"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": 688924396187.567, "dur": 0.535, + "args": { + "External id": 761151,"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": 688924396189.081, "dur": 7.286, + "args": { + "External id": 761152,"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": 688924396194.277, "dur": 1.907, + "args": { + "External id": 761153,"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": 688924396197.138, "dur": 1.537, + "args": { + "External id": 761154,"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": 688924396198.081, "dur": 0.314, + "args": { + "External id": 761155,"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": 688924396201.479, "dur": 2.002, + "args": { + "External id": 761156,"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": 688924396202.094, "dur": 1.283, + "args": { + "External id": 761157,"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": 688924396205.251, "dur": 53.741, + "args": { + "External id": 761158,"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": 688924396260.522, "dur": 1.192, + "args": { + "External id": 761159,"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": 688924396262.336, "dur": 4.911, + "args": { + "External id": 761160,"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": 688924396265.795, "dur": 0.620, + "args": { + "External id": 761161,"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": 688924396269.427, "dur": 0.968, + "args": { + "External id": 761162,"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": 688924396318.109, "dur": 9.204, + "args": { + "External id": 761163,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924396319.928, "dur": 6.469, + "args": { + "External id": 761164,"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": 688924396322.008, "dur": 3.473, + "args": { + "External id": 761165,"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": 688924396323.111, "dur": 2.267, + "args": { + "External id": 761166,"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": 688924396331.281, "dur": 9.489, + "args": { + "External id": 761167,"Record function id": 0, "Sequence number": 8962138, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924396332.357, "dur": 5.667, + "args": { + "External id": 761168,"Sequence number": 8962138, "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": 688924396332.357, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924396334.242, "dur": 3.608, + "args": { + "External id": 761169,"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": 688924396336.987, "dur": 0.767, + "args": { + "External id": 761170,"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": 688924396344.531, "dur": 123.622, + "args": { + "External id": 761171,"Record function id": 0, "Sequence number": 8962137, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924396347.589, "dur": 111.354, + "args": { + "External id": 761172,"Sequence number": 8962137, "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": 688924396347.589, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924396352.749, "dur": 4.364, + "args": { + "External id": 761173,"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": 688924396354.049, "dur": 2.463, + "args": { + "External id": 761174,"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": 688924396355.395, "dur": 0.954, + "args": { + "External id": 761175,"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": 688924396358.330, "dur": 38.652, + "args": { + "External id": 761176,"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": 688924396398.162, "dur": 5.129, + "args": { + "External id": 761177,"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": 688924396398.870, "dur": 3.846, + "args": { + "External id": 761178,"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": 688924396401.859, "dur": 0.714, + "args": { + "External id": 761179,"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": 688924396404.954, "dur": 6.438, + "args": { + "External id": 761180,"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": 688924396406.105, "dur": 4.752, + "args": { + "External id": 761181,"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": 688924396408.466, "dur": 2.328, + "args": { + "External id": 761182,"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": 688924396412.470, "dur": 45.537, + "args": { + "External id": 761183,"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": 688924396472.834, "dur": 8.858, + "args": { + "External id": 761184,"Record function id": 0, "Sequence number": 8962136, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924396474.229, "dur": 5.384, + "args": { + "External id": 761185,"Sequence number": 8962136, "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": 688924396474.229, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924396475.788, "dur": 3.653, + "args": { + "External id": 761186,"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": 688924396478.273, "dur": 1.020, + "args": { + "External id": 761187,"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": 688924396485.297, "dur": 8.632, + "args": { + "External id": 761188,"Record function id": 0, "Sequence number": 8962135, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924396486.391, "dur": 4.219, + "args": { + "External id": 761189,"Sequence number": 8962135, "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": 688924396486.391, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924396487.334, "dur": 3.060, + "args": { + "External id": 761190,"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": 688924396488.035, "dur": 1.858, + "args": { + "External id": 761191,"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": 688924396489.120, "dur": 0.639, + "args": { + "External id": 761192,"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": 688924396499.915, "dur": 5.064, + "args": { + "External id": 761193,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924396501.200, "dur": 3.259, + "args": { + "External id": 761194,"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": 688924396502.086, "dur": 1.866, + "args": { + "External id": 761195,"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": 688924396502.589, "dur": 1.291, + "args": { + "External id": 761196,"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": 688924396508.019, "dur": 7.854, + "args": { + "External id": 761197,"Record function id": 0, "Sequence number": 8962134, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924396508.937, "dur": 4.241, + "args": { + "External id": 761198,"Sequence number": 8962134, "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": 688924396508.937, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924396511.430, "dur": 1.596, + "args": { + "External id": 761199,"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": 688924396511.959, "dur": 0.934, + "args": { + "External id": 761200,"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": 688924396519.042, "dur": 97.855, + "args": { + "External id": 761201,"Record function id": 0, "Sequence number": 8962133, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924396519.926, "dur": 86.901, + "args": { + "External id": 761202,"Sequence number": 8962133, "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": 688924396519.926, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924396522.677, "dur": 4.925, + "args": { + "External id": 761203,"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": 688924396523.326, "dur": 3.866, + "args": { + "External id": 761204,"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": 688924396526.571, "dur": 0.489, + "args": { + "External id": 761205,"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": 688924396528.447, "dur": 27.955, + "args": { + "External id": 761206,"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": 688924396557.282, "dur": 6.569, + "args": { + "External id": 761207,"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": 688924396557.894, "dur": 5.458, + "args": { + "External id": 761208,"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": 688924396560.564, "dur": 2.632, + "args": { + "External id": 761209,"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": 688924396565.400, "dur": 4.257, + "args": { + "External id": 761210,"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": 688924396566.022, "dur": 3.041, + "args": { + "External id": 761211,"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": 688924396568.451, "dur": 0.503, + "args": { + "External id": 761212,"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": 688924396570.138, "dur": 36.035, + "args": { + "External id": 761213,"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": 688924396623.504, "dur": 74.829, + "args": { + "External id": 761214,"Record function id": 0, "Sequence number": 8962132, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924396624.491, "dur": 4.786, + "args": { + "External id": 761215,"Sequence number": 8962132, "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": 688924396624.491, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924396625.706, "dur": 3.434, + "args": { + "External id": 761216,"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": 688924396627.804, "dur": 1.198, + "args": { + "External id": 761217,"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": 688924396633.391, "dur": 60.749, + "args": { + "External id": 761218,"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": 688924396704.852, "dur": 11.846, + "args": { + "External id": 761219,"Record function id": 0, "Sequence number": 8962131, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924396706.280, "dur": 7.174, + "args": { + "External id": 761220,"Sequence number": 8962131, "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": 688924396706.280, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924396709.144, "dur": 4.083, + "args": { + "External id": 761221,"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": 688924396710.388, "dur": 2.134, + "args": { + "External id": 761222,"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": 688924396711.792, "dur": 0.574, + "args": { + "External id": 761223,"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": 688924396720.873, "dur": 6.454, + "args": { + "External id": 761224,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924396722.502, "dur": 4.295, + "args": { + "External id": 761225,"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": 688924396724.097, "dur": 2.300, + "args": { + "External id": 761226,"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": 688924396724.796, "dur": 1.505, + "args": { + "External id": 761227,"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": 688924396731.741, "dur": 493.880, + "args": { + "External id": 761228,"Record function id": 0, "Sequence number": 8962130, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924396733.002, "dur": 474.852, + "args": { + "External id": 761229,"Sequence number": 8962130, "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": 688924396733.002, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 31338, + "ts": 688924396760.636, "dur": 57.191, + "args": { + "External id": 761230,"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": 688924396762.220, "dur": 55.382, + "args": { + "External id": 761231,"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": 688924396767.489, "dur": 6.038, + "args": { + "External id": 761232,"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": 688924396769.820, "dur": 3.224, + "args": { + "External id": 761233,"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": 688924396775.010, "dur": 41.736, + "args": { + "External id": 761234,"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": 688924396835.451, "dur": 4.562, + "args": { + "External id": 761235,"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": 688924396836.026, "dur": 3.894, + "args": { + "External id": 761236,"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": 688924396844.482, "dur": 1.624, + "args": { + "External id": 761237,"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": 688924396845.112, "dur": 0.863, + "args": { + "External id": 761238,"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": 688924396861.648, "dur": 2.889, + "args": { + "External id": 761239,"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": 688924396880.877, "dur": 3.305, + "args": { + "External id": 761240,"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": 688924397093.557, "dur": 2.372, + "args": { + "External id": 761241,"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": 688924397100.582, "dur": 35.368, + "args": { + "External id": 761242,"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": 688924397110.721, "dur": 1.054, + "args": { + "External id": 761243,"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": 688924397142.065, "dur": 30.370, + "args": { + "External id": 761244,"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": 688924397143.802, "dur": 28.422, + "args": { + "External id": 761245,"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": 688924397147.414, "dur": 4.103, + "args": { + "External id": 761246,"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": 688924397155.713, "dur": 16.075, + "args": { + "External id": 761247,"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": 688924397177.078, "dur": 2.270, + "args": { + "External id": 761248,"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": 688924397178.237, "dur": 0.966, + "args": { + "External id": 761249,"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": 688924397185.927, "dur": 6.781, + "args": { + "External id": 761250,"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": 688924397189.352, "dur": 3.243, + "args": { + "External id": 761251,"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": 688924397194.734, "dur": 1.597, + "args": { + "External id": 761252,"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": 688924397195.590, "dur": 0.650, + "args": { + "External id": 761253,"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": 688924397238.106, "dur": 8.535, + "args": { + "External id": 761254,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924397239.928, "dur": 6.057, + "args": { + "External id": 761255,"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": 688924397241.790, "dur": 3.448, + "args": { + "External id": 761256,"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": 688924397243.029, "dur": 2.143, + "args": { + "External id": 761257,"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": 688924397250.383, "dur": 10.699, + "args": { + "External id": 761258,"Record function id": 0, "Sequence number": 8962129, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924397251.355, "dur": 5.662, + "args": { + "External id": 761259,"Sequence number": 8962129, "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": 688924397251.355, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924397252.828, "dur": 4.002, + "args": { + "External id": 761260,"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": 688924397255.614, "dur": 1.075, + "args": { + "External id": 761261,"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": 688924397266.627, "dur": 144.297, + "args": { + "External id": 761262,"Record function id": 0, "Sequence number": 8962128, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924397267.498, "dur": 136.221, + "args": { + "External id": 761263,"Sequence number": 8962128, "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": 688924397267.498, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924397271.780, "dur": 4.498, + "args": { + "External id": 761264,"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": 688924397273.216, "dur": 2.432, + "args": { + "External id": 761265,"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": 688924397274.712, "dur": 0.753, + "args": { + "External id": 761266,"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": 688924397277.730, "dur": 74.818, + "args": { + "External id": 761267,"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": 688924397354.002, "dur": 7.407, + "args": { + "External id": 761268,"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": 688924397356.951, "dur": 3.847, + "args": { + "External id": 761269,"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": 688924397358.007, "dur": 2.589, + "args": { + "External id": 761270,"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": 688924397363.127, "dur": 4.800, + "args": { + "External id": 761271,"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": 688924397364.403, "dur": 3.046, + "args": { + "External id": 761272,"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": 688924397366.988, "dur": 0.387, + "args": { + "External id": 761273,"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": 688924397368.708, "dur": 34.398, + "args": { + "External id": 761274,"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": 688924397415.619, "dur": 11.212, + "args": { + "External id": 761275,"Record function id": 0, "Sequence number": 8962127, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924397416.804, "dur": 7.214, + "args": { + "External id": 761276,"Sequence number": 8962127, "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": 688924397416.804, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924397420.257, "dur": 3.614, + "args": { + "External id": 761277,"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": 688924397420.754, "dur": 2.958, + "args": { + "External id": 761278,"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": 688924397430.421, "dur": 7.543, + "args": { + "External id": 761279,"Record function id": 0, "Sequence number": 8962126, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924397431.344, "dur": 3.820, + "args": { + "External id": 761280,"Sequence number": 8962126, "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": 688924397431.344, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924397432.351, "dur": 2.597, + "args": { + "External id": 761281,"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": 688924397432.957, "dur": 1.514, + "args": { + "External id": 761282,"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": 688924397433.807, "dur": 0.546, + "args": { + "External id": 761283,"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": 688924397443.720, "dur": 6.999, + "args": { + "External id": 761284,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924397445.216, "dur": 5.072, + "args": { + "External id": 761285,"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": 688924397446.285, "dur": 3.518, + "args": { + "External id": 761286,"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": 688924397448.801, "dur": 0.891, + "args": { + "External id": 761287,"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": 688924397453.996, "dur": 7.838, + "args": { + "External id": 761288,"Record function id": 0, "Sequence number": 8962125, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924397454.938, "dur": 4.203, + "args": { + "External id": 761289,"Sequence number": 8962125, "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": 688924397454.938, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924397456.550, "dur": 2.452, + "args": { + "External id": 761290,"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": 688924397457.516, "dur": 1.351, + "args": { + "External id": 761291,"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": 688924397466.397, "dur": 416.210, + "args": { + "External id": 761292,"Record function id": 0, "Sequence number": 8962124, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183436, "tid": 31338, + "ts": 688924397467.928, "dur": 389.494, + "args": { + "External id": 761293,"Sequence number": 8962124, "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": 688924397467.928, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 31338, + "ts": 688924397486.220, "dur": 10.493, + "args": { + "External id": 761294,"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": 688924397493.007, "dur": 3.303, + "args": { + "External id": 761295,"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": 688924397498.979, "dur": 3.500, + "args": { + "External id": 761296,"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": 688924397500.190, "dur": 2.102, + "args": { + "External id": 761297,"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": 688924397503.812, "dur": 6.698, + "args": { + "External id": 761298,"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": 688924397506.914, "dur": 3.408, + "args": { + "External id": 761299,"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": 688924397554.436, "dur": 271.807, + "args": { + "External id": 761300,"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": 688924397698.895, "dur": 6.085, + "args": { + "External id": 761301,"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": 688924397708.425, "dur": 4.022, + "args": { + "External id": 761302,"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": 688924397842.268, "dur": 5.125, + "args": { + "External id": 761303,"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": 688924397850.703, "dur": 0.674, + "args": { + "External id": 761304,"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": 688924397853.817, "dur": 0.537, + "args": { + "External id": 761305,"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": 688924397893.813, "dur": 247.682, + "args": { + "External id": 761306,"Record function id": 0, "Sequence number": 8962123, "Fwd thread id": 1, "Ev Idx": 473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924397895.525, "dur": 238.261, + "args": { + "External id": 761307,"Sequence number": 8962123, "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": 688924397895.525, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 688924397920.162, "dur": 45.221, + "args": { + "External id": 761308,"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": 688924397925.264, "dur": 3.833, + "args": { + "External id": 761309,"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": 688924397930.625, "dur": 34.103, + "args": { + "External id": 761310,"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": 688924397978.186, "dur": 3.815, + "args": { + "External id": 761311,"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": 688924397979.401, "dur": 2.254, + "args": { + "External id": 761312,"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": 688924398148.505, "dur": 154.301, + "args": { + "External id": 761313,"Record function id": 0, "Sequence number": 8962122, "Fwd thread id": 1, "Ev Idx": 480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924398150.142, "dur": 144.987, + "args": { + "External id": 761314,"Sequence number": 8962122, "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": 688924398150.142, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 688924398162.079, "dur": 29.551, + "args": { + "External id": 761315,"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": 688924398164.020, "dur": 2.568, + "args": { + "External id": 761316,"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": 688924398167.586, "dur": 23.376, + "args": { + "External id": 761317,"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": 688924398199.826, "dur": 5.314, + "args": { + "External id": 761318,"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": 688924398201.297, "dur": 3.541, + "args": { + "External id": 761319,"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": 688924398308.807, "dur": 14.906, + "args": { + "External id": 761320,"Record function id": 0, "Sequence number": 8962121, "Fwd thread id": 1, "Ev Idx": 487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398310.491, "dur": 10.430, + "args": { + "External id": 761321,"Sequence number": 8962121, "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": 688924398310.491, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924398312.768, "dur": 7.871, + "args": { + "External id": 761322,"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": 688924398314.268, "dur": 6.177, + "args": { + "External id": 761323,"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": 688924398327.201, "dur": 9.262, + "args": { + "External id": 761324,"Record function id": 0, "Sequence number": 8962120, "Fwd thread id": 1, "Ev Idx": 491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398328.614, "dur": 4.850, + "args": { + "External id": 761325,"Sequence number": 8962120, "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": 688924398328.614, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924398331.651, "dur": 1.673, + "args": { + "External id": 761326,"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": 688924398332.284, "dur": 0.932, + "args": { + "External id": 761327,"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": 688924398339.651, "dur": 9.157, + "args": { + "External id": 761328,"Record function id": 0, "Sequence number": 8962119, "Fwd thread id": 1, "Ev Idx": 495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398343.018, "dur": 3.118, + "args": { + "External id": 761329,"Sequence number": 8962119, "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": 688924398343.018, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924398344.608, "dur": 1.388, + "args": { + "External id": 761330,"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": 688924398345.113, "dur": 0.801, + "args": { + "External id": 761331,"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": 688924398352.264, "dur": 8.834, + "args": { + "External id": 761332,"Record function id": 0, "Sequence number": 8962118, "Fwd thread id": 1, "Ev Idx": 499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398355.091, "dur": 3.101, + "args": { + "External id": 761333,"Sequence number": 8962118, "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": 688924398355.091, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924398356.345, "dur": 1.711, + "args": { + "External id": 761334,"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": 688924398356.848, "dur": 1.108, + "args": { + "External id": 761335,"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": 688924398364.383, "dur": 226.902, + "args": { + "External id": 761336,"Record function id": 0, "Sequence number": 8962117, "Fwd thread id": 1, "Ev Idx": 503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398365.358, "dur": 216.129, + "args": { + "External id": 761337,"Sequence number": 8962117, "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": 688924398365.358, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924398372.061, "dur": 6.247, + "args": { + "External id": 761338,"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": 688924398374.135, "dur": 3.579, + "args": { + "External id": 761339,"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": 688924398375.940, "dur": 1.522, + "args": { + "External id": 761340,"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": 688924398379.662, "dur": 80.934, + "args": { + "External id": 761341,"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": 688924398461.873, "dur": 6.526, + "args": { + "External id": 761342,"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": 688924398462.703, "dur": 5.002, + "args": { + "External id": 761343,"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": 688924398466.246, "dur": 1.269, + "args": { + "External id": 761344,"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": 688924398528.806, "dur": 5.477, + "args": { + "External id": 761345,"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": 688924398530.331, "dur": 3.170, + "args": { + "External id": 761346,"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": 688924398532.900, "dur": 0.521, + "args": { + "External id": 761347,"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": 688924398534.998, "dur": 45.669, + "args": { + "External id": 761348,"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": 688924398597.009, "dur": 6.116, + "args": { + "External id": 761349,"Record function id": 0, "Sequence number": 8962116, "Fwd thread id": 1, "Ev Idx": 516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398597.919, "dur": 3.377, + "args": { + "External id": 761350,"Sequence number": 8962116, "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": 688924398597.919, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924398599.400, "dur": 1.736, + "args": { + "External id": 761351,"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": 688924398599.938, "dur": 1.098, + "args": { + "External id": 761352,"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": 688924398606.598, "dur": 10.464, + "args": { + "External id": 761353,"Record function id": 0, "Sequence number": 8962115, "Fwd thread id": 1, "Ev Idx": 520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398609.432, "dur": 5.683, + "args": { + "External id": 761354,"Sequence number": 8962115, "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": 688924398609.432, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924398610.231, "dur": 4.660, + "args": { + "External id": 761355,"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": 688924398610.887, "dur": 3.533, + "args": { + "External id": 761356,"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": 688924398613.772, "dur": 0.545, + "args": { + "External id": 761357,"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": 688924398622.640, "dur": 8.525, + "args": { + "External id": 761358,"Record function id": 0, "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924398624.299, "dur": 6.139, + "args": { + "External id": 761359,"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": 688924398626.518, "dur": 3.528, + "args": { + "External id": 761360,"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": 688924398627.483, "dur": 2.463, + "args": { + "External id": 761361,"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": 688924398636.395, "dur": 9.455, + "args": { + "External id": 761362,"Record function id": 0, "Sequence number": 8962114, "Fwd thread id": 1, "Ev Idx": 529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398637.890, "dur": 5.381, + "args": { + "External id": 761363,"Sequence number": 8962114, "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": 688924398637.890, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924398639.598, "dur": 3.524, + "args": { + "External id": 761364,"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": 688924398642.128, "dur": 0.838, + "args": { + "External id": 761365,"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": 688924398648.909, "dur": 173.372, + "args": { + "External id": 761366,"Record function id": 0, "Sequence number": 8962113, "Fwd thread id": 1, "Ev Idx": 533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398649.778, "dur": 163.693, + "args": { + "External id": 761367,"Sequence number": 8962113, "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": 688924398649.778, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924398652.243, "dur": 55.820, + "args": { + "External id": 761368,"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": 688924398652.692, "dur": 54.340, + "args": { + "External id": 761369,"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": 688924398705.639, "dur": 0.901, + "args": { + "External id": 761370,"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": 688924398711.460, "dur": 42.920, + "args": { + "External id": 761371,"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": 688924398755.492, "dur": 3.022, + "args": { + "External id": 761372,"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": 688924398756.081, "dur": 1.934, + "args": { + "External id": 761373,"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": 688924398757.246, "dur": 0.659, + "args": { + "External id": 761374,"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": 688924398760.290, "dur": 4.263, + "args": { + "External id": 761375,"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": 688924398760.915, "dur": 3.016, + "args": { + "External id": 761376,"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": 688924398761.609, "dur": 2.240, + "args": { + "External id": 761377,"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": 688924398767.285, "dur": 44.939, + "args": { + "External id": 761378,"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": 688924398829.436, "dur": 36.942, + "args": { + "External id": 761379,"Record function id": 0, "Sequence number": 8962112, "Fwd thread id": 1, "Ev Idx": 546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398830.605, "dur": 5.920, + "args": { + "External id": 761380,"Sequence number": 8962112, "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": 688924398830.605, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924398833.997, "dur": 2.382, + "args": { + "External id": 761381,"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": 688924398834.717, "dur": 1.555, + "args": { + "External id": 761382,"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": 688924398839.597, "dur": 24.697, + "args": { + "External id": 761383,"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": 688924398870.258, "dur": 8.533, + "args": { + "External id": 761384,"Record function id": 0, "Sequence number": 8962111, "Fwd thread id": 1, "Ev Idx": 551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398871.389, "dur": 5.402, + "args": { + "External id": 761385,"Sequence number": 8962111, "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": 688924398871.389, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924398872.158, "dur": 4.452, + "args": { + "External id": 761386,"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": 688924398874.608, "dur": 1.460, + "args": { + "External id": 761387,"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": 688924398875.462, "dur": 0.493, + "args": { + "External id": 761388,"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": 688924398882.872, "dur": 5.552, + "args": { + "External id": 761389,"Record function id": 0, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924398884.129, "dur": 3.785, + "args": { + "External id": 761390,"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": 688924398885.291, "dur": 2.105, + "args": { + "External id": 761391,"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": 688924398885.796, "dur": 1.462, + "args": { + "External id": 761392,"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": 688924398891.631, "dur": 8.291, + "args": { + "External id": 761393,"Record function id": 0, "Sequence number": 8962110, "Fwd thread id": 1, "Ev Idx": 560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398894.293, "dur": 2.993, + "args": { + "External id": 761394,"Sequence number": 8962110, "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": 688924398894.293, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924398895.440, "dur": 1.702, + "args": { + "External id": 761395,"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": 688924398895.964, "dur": 1.079, + "args": { + "External id": 761396,"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": 688924398905.022, "dur": 96.097, + "args": { + "External id": 761397,"Record function id": 0, "Sequence number": 8962109, "Fwd thread id": 1, "Ev Idx": 564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924398905.955, "dur": 85.239, + "args": { + "External id": 761398,"Sequence number": 8962109, "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": 688924398905.955, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924398908.753, "dur": 2.096, + "args": { + "External id": 761399,"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": 688924398909.246, "dur": 1.157, + "args": { + "External id": 761400,"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": 688924398909.838, "dur": 0.451, + "args": { + "External id": 761401,"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": 688924398911.435, "dur": 37.887, + "args": { + "External id": 761402,"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": 688924398950.539, "dur": 4.251, + "args": { + "External id": 761403,"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": 688924398952.884, "dur": 1.454, + "args": { + "External id": 761404,"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": 688924398953.768, "dur": 0.467, + "args": { + "External id": 761405,"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": 688924398955.995, "dur": 3.753, + "args": { + "External id": 761406,"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": 688924398956.821, "dur": 2.581, + "args": { + "External id": 761407,"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": 688924398958.942, "dur": 0.352, + "args": { + "External id": 761408,"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": 688924398960.216, "dur": 30.340, + "args": { + "External id": 761409,"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": 688924399005.321, "dur": 25.040, + "args": { + "External id": 761410,"Record function id": 0, "Sequence number": 8962108, "Fwd thread id": 1, "Ev Idx": 577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924399008.311, "dur": 2.990, + "args": { + "External id": 761411,"Sequence number": 8962108, "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": 688924399008.311, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924399009.703, "dur": 1.440, + "args": { + "External id": 761412,"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": 688924399010.114, "dur": 0.925, + "args": { + "External id": 761413,"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": 688924399013.398, "dur": 14.727, + "args": { + "External id": 761414,"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": 688924399034.039, "dur": 11.881, + "args": { + "External id": 761415,"Record function id": 0, "Sequence number": 8962107, "Fwd thread id": 1, "Ev Idx": 582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924399034.875, "dur": 8.670, + "args": { + "External id": 761416,"Sequence number": 8962107, "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": 688924399034.875, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924399035.797, "dur": 7.523, + "args": { + "External id": 761417,"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": 688924399037.990, "dur": 4.837, + "args": { + "External id": 761418,"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": 688924399042.128, "dur": 0.537, + "args": { + "External id": 761419,"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": 688924399049.686, "dur": 4.727, + "args": { + "External id": 761420,"Record function id": 0, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924399051.014, "dur": 2.970, + "args": { + "External id": 761421,"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": 688924399051.952, "dur": 1.540, + "args": { + "External id": 761422,"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": 688924399052.303, "dur": 1.095, + "args": { + "External id": 761423,"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": 688924399059.014, "dur": 376.915, + "args": { + "External id": 761424,"Record function id": 0, "Sequence number": 8962106, "Fwd thread id": 1, "Ev Idx": 591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924399060.091, "dur": 340.404, + "args": { + "External id": 761425,"Sequence number": 8962106, "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": 688924399060.091, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924399097.447, "dur": 1.904, + "args": { + "External id": 761426,"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": 688924399098.010, "dur": 1.182, + "args": { + "External id": 761427,"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": 688924399113.680, "dur": 5.823, + "args": { + "External id": 761428,"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": 688924399132.537, "dur": 4.072, + "args": { + "External id": 761429,"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": 688924399300.283, "dur": 1.885, + "args": { + "External id": 761430,"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": 688924399306.721, "dur": 34.953, + "args": { + "External id": 761431,"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": 688924399317.805, "dur": 0.980, + "args": { + "External id": 761432,"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": 688924399347.383, "dur": 28.079, + "args": { + "External id": 761433,"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": 688924399348.963, "dur": 26.294, + "args": { + "External id": 761434,"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": 688924399352.537, "dur": 3.768, + "args": { + "External id": 761435,"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": 688924399358.179, "dur": 16.622, + "args": { + "External id": 761436,"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": 688924399379.234, "dur": 3.907, + "args": { + "External id": 761437,"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": 688924399381.840, "dur": 1.187, + "args": { + "External id": 761438,"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": 688924399389.455, "dur": 3.618, + "args": { + "External id": 761439,"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": 688924399391.952, "dur": 1.028, + "args": { + "External id": 761440,"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": 688924399411.959, "dur": 17.381, + "args": { + "External id": 761441,"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": 688924399445.529, "dur": 7.192, + "args": { + "External id": 761442,"Record function id": 0, "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924399447.186, "dur": 4.953, + "args": { + "External id": 761443,"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": 688924399448.704, "dur": 2.435, + "args": { + "External id": 761444,"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": 688924399449.602, "dur": 1.434, + "args": { + "External id": 761445,"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": 688924399458.336, "dur": 7.429, + "args": { + "External id": 761446,"Record function id": 0, "Sequence number": 8962105, "Fwd thread id": 1, "Ev Idx": 613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924399459.967, "dur": 1.089, + "args": { + "External id": 761447,"Sequence number": 8962105, "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": 688924399459.967, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924399469.648, "dur": 486.143, + "args": { + "External id": 761448,"Record function id": 0, "Sequence number": 8962104, "Fwd thread id": 1, "Ev Idx": 615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924399470.683, "dur": 470.926, + "args": { + "External id": 761449,"Sequence number": 8962104, "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": 688924399470.683, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924399500.691, "dur": 7.530, + "args": { + "External id": 761450,"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": 688924399504.937, "dur": 2.991, + "args": { + "External id": 761451,"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": 688924399511.523, "dur": 8.178, + "args": { + "External id": 761452,"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": 688924399512.959, "dur": 6.111, + "args": { + "External id": 761453,"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": 688924399516.184, "dur": 2.743, + "args": { + "External id": 761454,"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": 688924399524.912, "dur": 92.046, + "args": { + "External id": 761455,"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": 688924399525.567, "dur": 2.129, + "args": { + "External id": 761456,"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": 688924399525.999, "dur": 1.239, + "args": { + "External id": 761457,"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": 688924399526.615, "dur": 0.526, + "args": { + "External id": 761458,"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": 688924399528.830, "dur": 87.694, + "args": { + "External id": 761459,"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": 688924399530.297, "dur": 85.393, + "args": { + "External id": 761460,"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": 688924399620.527, "dur": 4.395, + "args": { + "External id": 761461,"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": 688924399623.641, "dur": 1.159, + "args": { + "External id": 761462,"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": 688924399699.977, "dur": 6.961, + "args": { + "External id": 761463,"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": 688924399708.357, "dur": 2.095, + "args": { + "External id": 761464,"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": 688924399711.211, "dur": 1.579, + "args": { + "External id": 761465,"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": 688924399751.028, "dur": 2.841, + "args": { + "External id": 761466,"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": 688924399751.868, "dur": 1.804, + "args": { + "External id": 761467,"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": 688924399776.250, "dur": 144.209, + "args": { + "External id": 761468,"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": 688924399781.374, "dur": 26.314, + "args": { + "External id": 761469,"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": 688924399803.287, "dur": 2.997, + "args": { + "External id": 761470,"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": 688924399809.367, "dur": 7.658, + "args": { + "External id": 761471,"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": 688924399815.772, "dur": 0.615, + "args": { + "External id": 761472,"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": 688924399818.547, "dur": 3.205, + "args": { + "External id": 761473,"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": 688924399820.883, "dur": 0.531, + "args": { + "External id": 761474,"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": 688924399822.216, "dur": 2.110, + "args": { + "External id": 761475,"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": 688924399823.293, "dur": 0.379, + "args": { + "External id": 761476,"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": 688924399829.911, "dur": 1.727, + "args": { + "External id": 761477,"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": 688924399830.825, "dur": 0.522, + "args": { + "External id": 761478,"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": 688924399835.669, "dur": 5.819, + "args": { + "External id": 761479,"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": 688924399839.036, "dur": 2.271, + "args": { + "External id": 761480,"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": 688924399842.263, "dur": 2.827, + "args": { + "External id": 761481,"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": 688924399844.400, "dur": 0.443, + "args": { + "External id": 761482,"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": 688924399846.047, "dur": 4.963, + "args": { + "External id": 761483,"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": 688924399847.939, "dur": 2.955, + "args": { + "External id": 761484,"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": 688924399852.490, "dur": 56.320, + "args": { + "External id": 761485,"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": 688924399910.547, "dur": 1.285, + "args": { + "External id": 761486,"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": 688924399912.404, "dur": 3.651, + "args": { + "External id": 761487,"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": 688924399915.015, "dur": 0.477, + "args": { + "External id": 761488,"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": 688924399918.536, "dur": 0.957, + "args": { + "External id": 761489,"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": 688924399968.328, "dur": 8.673, + "args": { + "External id": 761490,"Record function id": 0, "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924399970.246, "dur": 6.058, + "args": { + "External id": 761491,"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": 688924399972.595, "dur": 3.035, + "args": { + "External id": 761492,"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": 688924399973.541, "dur": 1.974, + "args": { + "External id": 761493,"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": 688924399980.940, "dur": 7.132, + "args": { + "External id": 761494,"Record function id": 0, "Sequence number": 8962103, "Fwd thread id": 1, "Ev Idx": 661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924399981.968, "dur": 3.276, + "args": { + "External id": 761495,"Sequence number": 8962103, "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": 688924399981.968, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924399983.414, "dur": 1.634, + "args": { + "External id": 761496,"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": 688924399984.101, "dur": 0.813, + "args": { + "External id": 761497,"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": 688924399991.672, "dur": 107.311, + "args": { + "External id": 761498,"Record function id": 0, "Sequence number": 8962102, "Fwd thread id": 1, "Ev Idx": 665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924399992.716, "dur": 98.193, + "args": { + "External id": 761499,"Sequence number": 8962102, "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": 688924399992.716, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924399999.093, "dur": 4.151, + "args": { + "External id": 761500,"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": 688924400000.461, "dur": 2.182, + "args": { + "External id": 761501,"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": 688924400001.653, "dur": 0.848, + "args": { + "External id": 761502,"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": 688924400004.600, "dur": 34.309, + "args": { + "External id": 761503,"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": 688924400040.074, "dur": 6.357, + "args": { + "External id": 761504,"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": 688924400040.645, "dur": 5.051, + "args": { + "External id": 761505,"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": 688924400044.922, "dur": 0.614, + "args": { + "External id": 761506,"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": 688924400047.892, "dur": 4.364, + "args": { + "External id": 761507,"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": 688924400048.765, "dur": 2.924, + "args": { + "External id": 761508,"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": 688924400049.398, "dur": 2.228, + "args": { + "External id": 761509,"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": 688924400052.673, "dur": 37.392, + "args": { + "External id": 761510,"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": 688924400103.859, "dur": 7.108, + "args": { + "External id": 761511,"Record function id": 0, "Sequence number": 8962101, "Fwd thread id": 1, "Ev Idx": 678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924400104.812, "dur": 4.577, + "args": { + "External id": 761512,"Sequence number": 8962101, "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": 688924400104.812, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924400106.218, "dur": 2.998, + "args": { + "External id": 761513,"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": 688924400107.888, "dur": 1.198, + "args": { + "External id": 761514,"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": 688924400114.269, "dur": 9.264, + "args": { + "External id": 761515,"Record function id": 0, "Sequence number": 8962100, "Fwd thread id": 1, "Ev Idx": 682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924400117.192, "dur": 3.849, + "args": { + "External id": 761516,"Sequence number": 8962100, "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": 688924400117.192, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924400118.120, "dur": 2.711, + "args": { + "External id": 761517,"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": 688924400118.933, "dur": 1.443, + "args": { + "External id": 761518,"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": 688924400119.763, "dur": 0.466, + "args": { + "External id": 761519,"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": 688924400127.195, "dur": 5.018, + "args": { + "External id": 761520,"Record function id": 0, "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924400128.345, "dur": 3.419, + "args": { + "External id": 761521,"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": 688924400129.237, "dur": 2.240, + "args": { + "External id": 761522,"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": 688924400130.061, "dur": 1.335, + "args": { + "External id": 761523,"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": 688924400135.304, "dur": 10.058, + "args": { + "External id": 761524,"Record function id": 0, "Sequence number": 8962099, "Fwd thread id": 1, "Ev Idx": 691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924400136.258, "dur": 5.754, + "args": { + "External id": 761525,"Sequence number": 8962099, "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": 688924400136.258, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924400138.470, "dur": 3.389, + "args": { + "External id": 761526,"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": 688924400141.103, "dur": 0.620, + "args": { + "External id": 761527,"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": 688924400148.545, "dur": 108.288, + "args": { + "External id": 761528,"Record function id": 0, "Sequence number": 8962098, "Fwd thread id": 1, "Ev Idx": 695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924400149.529, "dur": 97.795, + "args": { + "External id": 761529,"Sequence number": 8962098, "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": 688924400149.529, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924400152.025, "dur": 16.782, + "args": { + "External id": 761530,"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": 688924400152.530, "dur": 15.692, + "args": { + "External id": 761531,"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": 688924400167.300, "dur": 0.597, + "args": { + "External id": 761532,"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": 688924400171.573, "dur": 28.253, + "args": { + "External id": 761533,"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": 688924400201.089, "dur": 5.919, + "args": { + "External id": 761534,"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": 688924400201.582, "dur": 4.844, + "args": { + "External id": 761535,"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": 688924400202.480, "dur": 3.793, + "args": { + "External id": 761536,"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": 688924400208.119, "dur": 6.431, + "args": { + "External id": 761537,"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": 688924400208.894, "dur": 5.214, + "args": { + "External id": 761538,"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": 688924400213.428, "dur": 0.614, + "args": { + "External id": 761539,"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": 688924400214.957, "dur": 31.813, + "args": { + "External id": 761540,"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": 688924400261.474, "dur": 29.683, + "args": { + "External id": 761541,"Record function id": 0, "Sequence number": 8962097, "Fwd thread id": 1, "Ev Idx": 708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924400262.665, "dur": 2.663, + "args": { + "External id": 761542,"Sequence number": 8962097, "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": 688924400262.665, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924400263.737, "dur": 1.439, + "args": { + "External id": 761543,"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": 688924400264.185, "dur": 0.879, + "args": { + "External id": 761544,"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": 688924400267.908, "dur": 20.596, + "args": { + "External id": 761545,"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": 688924400294.996, "dur": 11.407, + "args": { + "External id": 761546,"Record function id": 0, "Sequence number": 8962096, "Fwd thread id": 1, "Ev Idx": 713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924400296.111, "dur": 7.600, + "args": { + "External id": 761547,"Sequence number": 8962096, "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": 688924400296.111, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924400297.146, "dur": 6.323, + "args": { + "External id": 761548,"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": 688924400297.966, "dur": 5.032, + "args": { + "External id": 761549,"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": 688924400302.360, "dur": 0.513, + "args": { + "External id": 761550,"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": 688924400310.263, "dur": 4.750, + "args": { + "External id": 761551,"Record function id": 0, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924400311.499, "dur": 3.037, + "args": { + "External id": 761552,"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": 688924400312.549, "dur": 1.616, + "args": { + "External id": 761553,"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": 688924400313.007, "dur": 1.085, + "args": { + "External id": 761554,"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": 688924400320.484, "dur": 460.379, + "args": { + "External id": 761555,"Record function id": 0, "Sequence number": 8962095, "Fwd thread id": 1, "Ev Idx": 722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924400321.545, "dur": 423.397, + "args": { + "External id": 761556,"Sequence number": 8962095, "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": 688924400321.545, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 31338, + "ts": 688924400344.450, "dur": 32.018, + "args": { + "External id": 761557,"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": 688924400345.683, "dur": 30.598, + "args": { + "External id": 761558,"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": 688924400348.141, "dur": 5.132, + "args": { + "External id": 761559,"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": 688924400350.372, "dur": 2.419, + "args": { + "External id": 761560,"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": 688924400354.587, "dur": 21.215, + "args": { + "External id": 761561,"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": 688924400389.011, "dur": 5.062, + "args": { + "External id": 761562,"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": 688924400391.413, "dur": 2.501, + "args": { + "External id": 761563,"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": 688924400397.941, "dur": 1.421, + "args": { + "External id": 761564,"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": 688924400398.555, "dur": 0.716, + "args": { + "External id": 761565,"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": 688924400411.470, "dur": 2.048, + "args": { + "External id": 761566,"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": 688924400424.156, "dur": 2.566, + "args": { + "External id": 761567,"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": 688924400593.313, "dur": 2.186, + "args": { + "External id": 761568,"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": 688924400600.744, "dur": 29.103, + "args": { + "External id": 761569,"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": 688924400608.128, "dur": 0.769, + "args": { + "External id": 761570,"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": 688924400634.938, "dur": 71.862, + "args": { + "External id": 761571,"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": 688924400636.587, "dur": 70.011, + "args": { + "External id": 761572,"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": 688924400641.778, "dur": 3.993, + "args": { + "External id": 761573,"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": 688924400647.138, "dur": 58.419, + "args": { + "External id": 761574,"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": 688924400713.418, "dur": 5.113, + "args": { + "External id": 761575,"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": 688924400716.581, "dur": 1.814, + "args": { + "External id": 761576,"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": 688924400725.915, "dur": 4.225, + "args": { + "External id": 761577,"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": 688924400726.665, "dur": 3.323, + "args": { + "External id": 761578,"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": 688924400731.997, "dur": 3.081, + "args": { + "External id": 761579,"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": 688924400733.770, "dur": 1.228, + "args": { + "External id": 761580,"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": 688924400761.488, "dur": 17.894, + "args": { + "External id": 761581,"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": 688924400810.741, "dur": 12.673, + "args": { + "External id": 761582,"Record function id": 0, "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924400813.354, "dur": 9.167, + "args": { + "External id": 761583,"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": 688924400815.345, "dur": 5.878, + "args": { + "External id": 761584,"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": 688924400818.330, "dur": 2.677, + "args": { + "External id": 761585,"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": 688924400827.122, "dur": 8.647, + "args": { + "External id": 761586,"Record function id": 0, "Sequence number": 8962094, "Fwd thread id": 1, "Ev Idx": 753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924400828.179, "dur": 4.225, + "args": { + "External id": 761587,"Sequence number": 8962094, "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": 688924400828.179, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924400830.029, "dur": 2.137, + "args": { + "External id": 761588,"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": 688924400830.477, "dur": 1.484, + "args": { + "External id": 761589,"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": 688924400839.111, "dur": 141.135, + "args": { + "External id": 761590,"Record function id": 0, "Sequence number": 8962093, "Fwd thread id": 1, "Ev Idx": 757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924400840.080, "dur": 131.999, + "args": { + "External id": 761591,"Sequence number": 8962093, "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": 688924400840.080, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924400844.384, "dur": 7.223, + "args": { + "External id": 761592,"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": 688924400848.138, "dur": 2.760, + "args": { + "External id": 761593,"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": 688924400849.725, "dur": 0.970, + "args": { + "External id": 761594,"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": 688924400852.859, "dur": 69.947, + "args": { + "External id": 761595,"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": 688924400924.228, "dur": 6.196, + "args": { + "External id": 761596,"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": 688924400925.039, "dur": 4.800, + "args": { + "External id": 761597,"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": 688924400927.655, "dur": 2.002, + "args": { + "External id": 761598,"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": 688924400933.802, "dur": 2.591, + "args": { + "External id": 761599,"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": 688924400934.683, "dur": 1.154, + "args": { + "External id": 761600,"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": 688924400935.354, "dur": 0.392, + "args": { + "External id": 761601,"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": 688924400936.787, "dur": 34.547, + "args": { + "External id": 761602,"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": 688924400985.060, "dur": 11.120, + "args": { + "External id": 761603,"Record function id": 0, "Sequence number": 8962092, "Fwd thread id": 1, "Ev Idx": 770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924400986.183, "dur": 7.165, + "args": { + "External id": 761604,"Sequence number": 8962092, "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": 688924400986.183, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924400987.424, "dur": 5.757, + "args": { + "External id": 761605,"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": 688924400989.695, "dur": 3.364, + "args": { + "External id": 761606,"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": 688924401001.795, "dur": 8.148, + "args": { + "External id": 761607,"Record function id": 0, "Sequence number": 8962091, "Fwd thread id": 1, "Ev Idx": 774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924401004.446, "dur": 4.078, + "args": { + "External id": 761608,"Sequence number": 8962091, "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": 688924401004.446, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924401005.324, "dur": 2.983, + "args": { + "External id": 761609,"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": 688924401006.275, "dur": 1.575, + "args": { + "External id": 761610,"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": 688924401007.130, "dur": 0.556, + "args": { + "External id": 761611,"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": 688924401013.664, "dur": 4.603, + "args": { + "External id": 761612,"Record function id": 0, "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924401014.797, "dur": 2.973, + "args": { + "External id": 761613,"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": 688924401015.513, "dur": 1.957, + "args": { + "External id": 761614,"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": 688924401016.106, "dur": 1.284, + "args": { + "External id": 761615,"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": 688924401021.185, "dur": 8.465, + "args": { + "External id": 761616,"Record function id": 0, "Sequence number": 8962090, "Fwd thread id": 1, "Ev Idx": 783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924401022.137, "dur": 5.578, + "args": { + "External id": 761617,"Sequence number": 8962090, "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": 688924401022.137, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924401025.790, "dur": 1.779, + "args": { + "External id": 761618,"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": 688924401026.208, "dur": 1.235, + "args": { + "External id": 761619,"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": 688924401034.788, "dur": 288.889, + "args": { + "External id": 761620,"Record function id": 0, "Sequence number": 8962089, "Fwd thread id": 1, "Ev Idx": 787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183436, "tid": 31338, + "ts": 688924401035.872, "dur": 266.269, + "args": { + "External id": 761621,"Sequence number": 8962089, "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": 688924401035.872, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 31338, + "ts": 688924401052.945, "dur": 5.953, + "args": { + "External id": 761622,"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": 688924401055.101, "dur": 3.408, + "args": { + "External id": 761623,"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": 688924401061.062, "dur": 3.657, + "args": { + "External id": 761624,"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": 688924401062.621, "dur": 1.906, + "args": { + "External id": 761625,"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": 688924401066.256, "dur": 3.960, + "args": { + "External id": 761626,"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": 688924401066.955, "dur": 3.077, + "args": { + "External id": 761627,"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": 688924401097.319, "dur": 179.991, + "args": { + "External id": 761628,"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": 688924401181.194, "dur": 3.493, + "args": { + "External id": 761629,"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": 688924401186.180, "dur": 3.980, + "args": { + "External id": 761630,"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": 688924401289.660, "dur": 3.293, + "args": { + "External id": 761631,"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": 688924401295.724, "dur": 0.684, + "args": { + "External id": 761632,"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": 688924401298.402, "dur": 0.639, + "args": { + "External id": 761633,"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": 688924401330.695, "dur": 226.508, + "args": { + "External id": 761634,"Record function id": 0, "Sequence number": 8962088, "Fwd thread id": 1, "Ev Idx": 801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924401332.095, "dur": 218.041, + "args": { + "External id": 761635,"Sequence number": 8962088, "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": 688924401332.095, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 688924401351.622, "dur": 42.633, + "args": { + "External id": 761636,"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": 688924401354.238, "dur": 2.448, + "args": { + "External id": 761637,"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": 688924401357.998, "dur": 35.524, + "args": { + "External id": 761638,"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": 688924401403.805, "dur": 5.273, + "args": { + "External id": 761639,"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": 688924401406.773, "dur": 1.956, + "args": { + "External id": 761640,"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": 688924401563.501, "dur": 205.005, + "args": { + "External id": 761641,"Record function id": 0, "Sequence number": 8962087, "Fwd thread id": 1, "Ev Idx": 808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924401565.228, "dur": 195.316, + "args": { + "External id": 761642,"Sequence number": 8962087, "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": 688924401565.228, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 688924401576.175, "dur": 27.799, + "args": { + "External id": 761643,"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": 688924401577.954, "dur": 2.860, + "args": { + "External id": 761644,"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": 688924401581.805, "dur": 21.714, + "args": { + "External id": 761645,"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": 688924401610.603, "dur": 7.209, + "args": { + "External id": 761646,"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": 688924401614.853, "dur": 2.612, + "args": { + "External id": 761647,"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": 688924401777.794, "dur": 33.583, + "args": { + "External id": 761648,"Record function id": 0, "Sequence number": 8962086, "Fwd thread id": 1, "Ev Idx": 815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924401779.139, "dur": 27.552, + "args": { + "External id": 761649,"Sequence number": 8962086, "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": 688924401779.139, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924401781.601, "dur": 24.760, + "args": { + "External id": 761650,"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": 688924401784.244, "dur": 21.611, + "args": { + "External id": 761651,"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": 688924401817.244, "dur": 7.466, + "args": { + "External id": 761652,"Record function id": 0, "Sequence number": 8962085, "Fwd thread id": 1, "Ev Idx": 819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924401818.439, "dur": 3.911, + "args": { + "External id": 761653,"Sequence number": 8962085, "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": 688924401818.439, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924401820.044, "dur": 2.166, + "args": { + "External id": 761654,"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": 688924401820.890, "dur": 1.162, + "args": { + "External id": 761655,"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": 688924401829.986, "dur": 7.031, + "args": { + "External id": 761656,"Record function id": 0, "Sequence number": 8962084, "Fwd thread id": 1, "Ev Idx": 823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924401831.103, "dur": 3.472, + "args": { + "External id": 761657,"Sequence number": 8962084, "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": 688924401831.103, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924401832.663, "dur": 1.771, + "args": { + "External id": 761658,"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": 688924401833.270, "dur": 1.027, + "args": { + "External id": 761659,"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": 688924401840.200, "dur": 10.041, + "args": { + "External id": 761660,"Record function id": 0, "Sequence number": 8962083, "Fwd thread id": 1, "Ev Idx": 827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924401841.976, "dur": 5.005, + "args": { + "External id": 761661,"Sequence number": 8962083, "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": 688924401841.976, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924401843.388, "dur": 3.453, + "args": { + "External id": 761662,"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": 688924401845.970, "dur": 0.773, + "args": { + "External id": 761663,"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": 688924401853.569, "dur": 160.557, + "args": { + "External id": 761664,"Record function id": 0, "Sequence number": 8962082, "Fwd thread id": 1, "Ev Idx": 831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924401854.487, "dur": 149.619, + "args": { + "External id": 761665,"Sequence number": 8962082, "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": 688924401854.487, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924401858.854, "dur": 6.999, + "args": { + "External id": 761666,"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": 688924401860.812, "dur": 4.465, + "args": { + "External id": 761667,"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": 688924401863.512, "dur": 1.500, + "args": { + "External id": 761668,"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": 688924401868.982, "dur": 81.981, + "args": { + "External id": 761669,"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": 688924401952.477, "dur": 5.281, + "args": { + "External id": 761670,"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": 688924401953.209, "dur": 3.456, + "args": { + "External id": 761671,"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": 688924401955.165, "dur": 1.291, + "args": { + "External id": 761672,"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": 688924401959.692, "dur": 5.861, + "args": { + "External id": 761673,"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": 688924401961.172, "dur": 3.850, + "args": { + "External id": 761674,"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": 688924401964.645, "dur": 0.311, + "args": { + "External id": 761675,"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": 688924401966.297, "dur": 37.012, + "args": { + "External id": 761676,"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": 688924402018.784, "dur": 7.677, + "args": { + "External id": 761677,"Record function id": 0, "Sequence number": 8962081, "Fwd thread id": 1, "Ev Idx": 844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402019.801, "dur": 5.007, + "args": { + "External id": 761678,"Sequence number": 8962081, "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": 688924402019.801, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924402021.591, "dur": 3.080, + "args": { + "External id": 761679,"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": 688924402023.492, "dur": 1.027, + "args": { + "External id": 761680,"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": 688924402029.873, "dur": 9.377, + "args": { + "External id": 761681,"Record function id": 0, "Sequence number": 8962080, "Fwd thread id": 1, "Ev Idx": 848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402030.886, "dur": 6.508, + "args": { + "External id": 761682,"Sequence number": 8962080, "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": 688924402030.886, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924402031.970, "dur": 5.223, + "args": { + "External id": 761683,"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": 688924402032.607, "dur": 4.085, + "args": { + "External id": 761684,"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": 688924402035.905, "dur": 0.695, + "args": { + "External id": 761685,"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": 688924402044.949, "dur": 9.037, + "args": { + "External id": 761686,"Record function id": 0, "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924402046.940, "dur": 6.325, + "args": { + "External id": 761687,"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": 688924402049.386, "dur": 3.493, + "args": { + "External id": 761688,"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": 688924402050.419, "dur": 2.359, + "args": { + "External id": 761689,"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": 688924402057.485, "dur": 6.914, + "args": { + "External id": 761690,"Record function id": 0, "Sequence number": 8962079, "Fwd thread id": 1, "Ev Idx": 857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402059.013, "dur": 3.365, + "args": { + "External id": 761691,"Sequence number": 8962079, "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": 688924402059.013, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924402060.520, "dur": 1.702, + "args": { + "External id": 761692,"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": 688924402061.372, "dur": 0.755, + "args": { + "External id": 761693,"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": 688924402067.886, "dur": 95.054, + "args": { + "External id": 761694,"Record function id": 0, "Sequence number": 8962078, "Fwd thread id": 1, "Ev Idx": 861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402068.764, "dur": 86.776, + "args": { + "External id": 761695,"Sequence number": 8962078, "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": 688924402068.764, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924402073.363, "dur": 3.029, + "args": { + "External id": 761696,"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": 688924402073.946, "dur": 1.996, + "args": { + "External id": 761697,"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": 688924402075.130, "dur": 0.701, + "args": { + "External id": 761698,"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": 688924402076.951, "dur": 33.571, + "args": { + "External id": 761699,"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": 688924402111.875, "dur": 4.152, + "args": { + "External id": 761700,"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": 688924402112.405, "dur": 3.093, + "args": { + "External id": 761701,"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": 688924402114.503, "dur": 0.868, + "args": { + "External id": 761702,"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": 688924402118.964, "dur": 5.429, + "args": { + "External id": 761703,"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": 688924402120.061, "dur": 3.909, + "args": { + "External id": 761704,"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": 688924402121.485, "dur": 2.405, + "args": { + "External id": 761705,"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": 688924402124.795, "dur": 30.189, + "args": { + "External id": 761706,"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": 688924402167.345, "dur": 35.026, + "args": { + "External id": 761707,"Record function id": 0, "Sequence number": 8962077, "Fwd thread id": 1, "Ev Idx": 874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402168.484, "dur": 4.549, + "args": { + "External id": 761708,"Sequence number": 8962077, "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": 688924402168.484, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924402170.587, "dur": 2.309, + "args": { + "External id": 761709,"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": 688924402171.655, "dur": 1.098, + "args": { + "External id": 761710,"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": 688924402175.818, "dur": 22.857, + "args": { + "External id": 761711,"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": 688924402206.140, "dur": 8.942, + "args": { + "External id": 761712,"Record function id": 0, "Sequence number": 8962076, "Fwd thread id": 1, "Ev Idx": 879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402207.001, "dur": 5.047, + "args": { + "External id": 761713,"Sequence number": 8962076, "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": 688924402207.001, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924402208.273, "dur": 3.552, + "args": { + "External id": 761714,"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": 688924402209.029, "dur": 2.289, + "args": { + "External id": 761715,"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": 688924402210.709, "dur": 0.482, + "args": { + "External id": 761716,"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": 688924402219.086, "dur": 7.182, + "args": { + "External id": 761717,"Record function id": 0, "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924402221.129, "dur": 4.593, + "args": { + "External id": 761718,"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": 688924402222.105, "dur": 3.210, + "args": { + "External id": 761719,"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": 688924402224.151, "dur": 1.054, + "args": { + "External id": 761720,"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": 688924402229.702, "dur": 6.780, + "args": { + "External id": 761721,"Record function id": 0, "Sequence number": 8962075, "Fwd thread id": 1, "Ev Idx": 888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402231.105, "dur": 3.279, + "args": { + "External id": 761722,"Sequence number": 8962075, "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": 688924402231.105, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924402232.452, "dur": 1.785, + "args": { + "External id": 761723,"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": 688924402233.279, "dur": 0.850, + "args": { + "External id": 761724,"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": 688924402241.569, "dur": 100.495, + "args": { + "External id": 761725,"Record function id": 0, "Sequence number": 8962074, "Fwd thread id": 1, "Ev Idx": 892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402242.430, "dur": 89.668, + "args": { + "External id": 761726,"Sequence number": 8962074, "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": 688924402242.430, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924402245.246, "dur": 4.979, + "args": { + "External id": 761727,"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": 688924402245.753, "dur": 3.991, + "args": { + "External id": 761728,"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": 688924402249.186, "dur": 0.441, + "args": { + "External id": 761729,"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": 688924402250.799, "dur": 36.241, + "args": { + "External id": 761730,"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": 688924402288.150, "dur": 4.004, + "args": { + "External id": 761731,"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": 688924402288.769, "dur": 2.816, + "args": { + "External id": 761732,"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": 688924402290.396, "dur": 1.085, + "args": { + "External id": 761733,"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": 688924402293.312, "dur": 7.747, + "args": { + "External id": 761734,"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": 688924402298.293, "dur": 2.134, + "args": { + "External id": 761735,"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": 688924402300.049, "dur": 0.309, + "args": { + "External id": 761736,"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": 688924402301.619, "dur": 29.844, + "args": { + "External id": 761737,"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": 688924402346.427, "dur": 25.264, + "args": { + "External id": 761738,"Record function id": 0, "Sequence number": 8962073, "Fwd thread id": 1, "Ev Idx": 905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402347.450, "dur": 3.711, + "args": { + "External id": 761739,"Sequence number": 8962073, "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": 688924402347.450, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924402348.921, "dur": 2.098, + "args": { + "External id": 761740,"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": 688924402349.869, "dur": 1.024, + "args": { + "External id": 761741,"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": 688924402353.376, "dur": 16.239, + "args": { + "External id": 761742,"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": 688924402375.369, "dur": 9.434, + "args": { + "External id": 761743,"Record function id": 0, "Sequence number": 8962072, "Fwd thread id": 1, "Ev Idx": 910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402378.175, "dur": 4.692, + "args": { + "External id": 761744,"Sequence number": 8962072, "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": 688924402378.175, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924402379.241, "dur": 3.440, + "args": { + "External id": 761745,"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": 688924402379.994, "dur": 2.206, + "args": { + "External id": 761746,"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": 688924402381.548, "dur": 0.502, + "args": { + "External id": 761747,"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": 688924402389.043, "dur": 5.093, + "args": { + "External id": 761748,"Record function id": 0, "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924402390.651, "dur": 2.969, + "args": { + "External id": 761749,"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": 688924402391.714, "dur": 1.435, + "args": { + "External id": 761750,"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": 688924402392.171, "dur": 0.890, + "args": { + "External id": 761751,"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": 688924402398.533, "dur": 411.801, + "args": { + "External id": 761752,"Record function id": 0, "Sequence number": 8962071, "Fwd thread id": 1, "Ev Idx": 919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924402400.353, "dur": 358.453, + "args": { + "External id": 761753,"Sequence number": 8962071, "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": 688924402400.353, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924402430.385, "dur": 3.099, + "args": { + "External id": 761754,"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": 688924402432.364, "dur": 1.022, + "args": { + "External id": 761755,"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": 688924402446.865, "dur": 4.768, + "args": { + "External id": 761756,"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": 688924402460.220, "dur": 3.037, + "args": { + "External id": 761757,"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": 688924402608.151, "dur": 1.725, + "args": { + "External id": 761758,"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": 688924402614.174, "dur": 31.607, + "args": { + "External id": 761759,"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": 688924402624.341, "dur": 0.638, + "args": { + "External id": 761760,"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": 688924402694.976, "dur": 36.504, + "args": { + "External id": 761761,"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": 688924402697.587, "dur": 33.699, + "args": { + "External id": 761762,"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": 688924402704.068, "dur": 6.645, + "args": { + "External id": 761763,"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": 688924402712.419, "dur": 18.230, + "args": { + "External id": 761764,"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": 688924402737.497, "dur": 3.546, + "args": { + "External id": 761765,"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": 688924402739.094, "dur": 1.844, + "args": { + "External id": 761766,"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": 688924402748.954, "dur": 2.544, + "args": { + "External id": 761767,"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": 688924402750.303, "dur": 1.089, + "args": { + "External id": 761768,"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": 688924402772.373, "dur": 31.823, + "args": { + "External id": 761769,"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": 688924402825.072, "dur": 10.264, + "args": { + "External id": 761770,"Record function id": 0, "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924402827.543, "dur": 7.036, + "args": { + "External id": 761771,"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": 688924402830.041, "dur": 3.470, + "args": { + "External id": 761772,"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": 688924402830.988, "dur": 2.409, + "args": { + "External id": 761773,"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": 688924402839.344, "dur": 6.479, + "args": { + "External id": 761774,"Record function id": 0, "Sequence number": 8962070, "Fwd thread id": 1, "Ev Idx": 941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924402840.858, "dur": 1.645, + "args": { + "External id": 761775,"Sequence number": 8962070, "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": 688924402840.858, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924402850.252, "dur": 405.028, + "args": { + "External id": 761776,"Record function id": 0, "Sequence number": 8962069, "Fwd thread id": 1, "Ev Idx": 943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924402851.882, "dur": 391.311, + "args": { + "External id": 761777,"Sequence number": 8962069, "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": 688924402851.882, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924402884.903, "dur": 9.533, + "args": { + "External id": 761778,"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": 688924402890.572, "dur": 3.568, + "args": { + "External id": 761779,"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": 688924402897.969, "dur": 5.950, + "args": { + "External id": 761780,"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": 688924402899.526, "dur": 3.626, + "args": { + "External id": 761781,"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": 688924402901.943, "dur": 1.012, + "args": { + "External id": 761782,"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": 688924402907.544, "dur": 93.838, + "args": { + "External id": 761783,"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": 688924402908.376, "dur": 7.507, + "args": { + "External id": 761784,"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": 688924402911.264, "dur": 4.021, + "args": { + "External id": 761785,"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": 688924402912.798, "dur": 2.398, + "args": { + "External id": 761786,"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": 688924402917.327, "dur": 83.575, + "args": { + "External id": 761787,"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": 688924402918.618, "dur": 81.335, + "args": { + "External id": 761788,"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": 688924403004.768, "dur": 3.223, + "args": { + "External id": 761789,"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": 688924403006.350, "dur": 1.508, + "args": { + "External id": 761790,"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": 688924403041.363, "dur": 5.498, + "args": { + "External id": 761791,"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": 688924403048.319, "dur": 2.162, + "args": { + "External id": 761792,"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": 688924403051.598, "dur": 1.899, + "args": { + "External id": 761793,"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": 688924403083.485, "dur": 2.625, + "args": { + "External id": 761794,"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": 688924403084.787, "dur": 1.180, + "args": { + "External id": 761795,"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": 688924403109.681, "dur": 115.119, + "args": { + "External id": 761796,"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": 688924403114.697, "dur": 5.810, + "args": { + "External id": 761797,"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": 688924403118.459, "dur": 0.918, + "args": { + "External id": 761798,"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": 688924403122.151, "dur": 8.674, + "args": { + "External id": 761799,"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": 688924403127.540, "dur": 2.277, + "args": { + "External id": 761800,"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": 688924403132.132, "dur": 2.659, + "args": { + "External id": 761801,"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": 688924403134.051, "dur": 0.406, + "args": { + "External id": 761802,"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": 688924403135.754, "dur": 3.391, + "args": { + "External id": 761803,"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": 688924403138.052, "dur": 0.505, + "args": { + "External id": 761804,"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": 688924403142.742, "dur": 3.610, + "args": { + "External id": 761805,"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": 688924403145.403, "dur": 0.649, + "args": { + "External id": 761806,"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": 688924403147.536, "dur": 6.442, + "args": { + "External id": 761807,"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": 688924403151.855, "dur": 1.930, + "args": { + "External id": 761808,"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": 688924403155.106, "dur": 2.733, + "args": { + "External id": 761809,"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": 688924403156.915, "dur": 0.607, + "args": { + "External id": 761810,"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": 688924403160.661, "dur": 4.601, + "args": { + "External id": 761811,"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": 688924403161.790, "dur": 3.385, + "args": { + "External id": 761812,"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": 688924403166.402, "dur": 45.213, + "args": { + "External id": 761813,"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": 688924403213.340, "dur": 3.004, + "args": { + "External id": 761814,"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": 688924403217.278, "dur": 3.204, + "args": { + "External id": 761815,"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": 688924403219.378, "dur": 0.543, + "args": { + "External id": 761816,"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": 688924403223.129, "dur": 0.713, + "args": { + "External id": 761817,"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": 688924403264.069, "dur": 8.780, + "args": { + "External id": 761818,"Record function id": 0, "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924403266.318, "dur": 5.737, + "args": { + "External id": 761819,"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": 688924403268.131, "dur": 3.104, + "args": { + "External id": 761820,"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": 688924403269.088, "dur": 2.045, + "args": { + "External id": 761821,"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": 688924403276.888, "dur": 8.889, + "args": { + "External id": 761822,"Record function id": 0, "Sequence number": 8962068, "Fwd thread id": 1, "Ev Idx": 989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924403278.298, "dur": 3.710, + "args": { + "External id": 761823,"Sequence number": 8962068, "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": 688924403278.298, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924403279.885, "dur": 1.948, + "args": { + "External id": 761824,"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": 688924403280.928, "dur": 0.774, + "args": { + "External id": 761825,"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": 688924403289.540, "dur": 105.747, + "args": { + "External id": 761826,"Record function id": 0, "Sequence number": 8962067, "Fwd thread id": 1, "Ev Idx": 993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924403290.551, "dur": 96.879, + "args": { + "External id": 761827,"Sequence number": 8962067, "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": 688924403290.551, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924403294.833, "dur": 5.708, + "args": { + "External id": 761828,"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": 688924403295.980, "dur": 3.964, + "args": { + "External id": 761829,"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": 688924403299.079, "dur": 0.674, + "args": { + "External id": 761830,"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": 688924403301.456, "dur": 34.528, + "args": { + "External id": 761831,"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": 688924403336.867, "dur": 4.526, + "args": { + "External id": 761832,"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": 688924403337.616, "dur": 2.882, + "args": { + "External id": 761833,"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": 688924403339.530, "dur": 0.785, + "args": { + "External id": 761834,"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": 688924403343.197, "dur": 6.264, + "args": { + "External id": 761835,"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": 688924403346.643, "dur": 2.256, + "args": { + "External id": 761836,"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": 688924403348.380, "dur": 0.455, + "args": { + "External id": 761837,"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": 688924403349.986, "dur": 36.591, + "args": { + "External id": 761838,"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": 688924403399.935, "dur": 7.304, + "args": { + "External id": 761839,"Record function id": 0, "Sequence number": 8962066, "Fwd thread id": 1, "Ev Idx": 1006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924403401.000, "dur": 4.460, + "args": { + "External id": 761840,"Sequence number": 8962066, "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": 688924403401.000, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924403402.862, "dur": 2.447, + "args": { + "External id": 761841,"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": 688924403403.994, "dur": 1.173, + "args": { + "External id": 761842,"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": 688924403411.152, "dur": 10.030, + "args": { + "External id": 761843,"Record function id": 0, "Sequence number": 8962065, "Fwd thread id": 1, "Ev Idx": 1010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924403411.954, "dur": 6.838, + "args": { + "External id": 761844,"Sequence number": 8962065, "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": 688924403411.954, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924403412.751, "dur": 5.838, + "args": { + "External id": 761845,"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": 688924403415.721, "dur": 2.363, + "args": { + "External id": 761846,"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": 688924403417.337, "dur": 0.662, + "args": { + "External id": 761847,"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": 688924403424.898, "dur": 5.172, + "args": { + "External id": 761848,"Record function id": 0, "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924403426.684, "dur": 2.880, + "args": { + "External id": 761849,"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": 688924403427.643, "dur": 1.605, + "args": { + "External id": 761850,"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": 688924403428.191, "dur": 0.987, + "args": { + "External id": 761851,"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": 688924403435.198, "dur": 7.179, + "args": { + "External id": 761852,"Record function id": 0, "Sequence number": 8962064, "Fwd thread id": 1, "Ev Idx": 1019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924403436.744, "dur": 3.174, + "args": { + "External id": 761853,"Sequence number": 8962064, "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": 688924403436.744, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924403438.147, "dur": 1.604, + "args": { + "External id": 761854,"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": 688924403439.023, "dur": 0.601, + "args": { + "External id": 761855,"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": 688924403447.277, "dur": 170.702, + "args": { + "External id": 761856,"Record function id": 0, "Sequence number": 8962063, "Fwd thread id": 1, "Ev Idx": 1023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924403524.040, "dur": 85.083, + "args": { + "External id": 761857,"Sequence number": 8962063, "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": 688924403524.040, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924403526.929, "dur": 3.824, + "args": { + "External id": 761858,"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": 688924403527.440, "dur": 2.754, + "args": { + "External id": 761859,"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": 688924403529.532, "dur": 0.525, + "args": { + "External id": 761860,"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": 688924403531.271, "dur": 28.883, + "args": { + "External id": 761861,"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": 688924403562.803, "dur": 4.989, + "args": { + "External id": 761862,"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": 688924403563.235, "dur": 4.035, + "args": { + "External id": 761863,"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": 688924403564.811, "dur": 2.311, + "args": { + "External id": 761864,"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": 688924403569.243, "dur": 5.103, + "args": { + "External id": 761865,"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": 688924403570.322, "dur": 3.494, + "args": { + "External id": 761866,"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": 688924403571.588, "dur": 2.165, + "args": { + "External id": 761867,"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": 688924403576.718, "dur": 31.788, + "args": { + "External id": 761868,"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": 688924403622.743, "dur": 29.699, + "args": { + "External id": 761869,"Record function id": 0, "Sequence number": 8962062, "Fwd thread id": 1, "Ev Idx": 1036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924403623.723, "dur": 3.841, + "args": { + "External id": 761870,"Sequence number": 8962062, "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": 688924403623.723, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924403625.264, "dur": 2.153, + "args": { + "External id": 761871,"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": 688924403626.245, "dur": 1.076, + "args": { + "External id": 761872,"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": 688924403630.547, "dur": 18.951, + "args": { + "External id": 761873,"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": 688924403706.519, "dur": 12.586, + "args": { + "External id": 761874,"Record function id": 0, "Sequence number": 8962061, "Fwd thread id": 1, "Ev Idx": 1041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924403708.305, "dur": 7.964, + "args": { + "External id": 761875,"Sequence number": 8962061, "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": 688924403708.305, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924403709.488, "dur": 6.577, + "args": { + "External id": 761876,"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": 688924403710.505, "dur": 4.836, + "args": { + "External id": 761877,"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": 688924403714.305, "dur": 0.775, + "args": { + "External id": 761878,"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": 688924403723.749, "dur": 5.943, + "args": { + "External id": 761879,"Record function id": 0, "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924403725.411, "dur": 3.773, + "args": { + "External id": 761880,"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": 688924403726.646, "dur": 2.090, + "args": { + "External id": 761881,"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": 688924403727.220, "dur": 1.438, + "args": { + "External id": 761882,"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": 688924403734.074, "dur": 443.927, + "args": { + "External id": 761883,"Record function id": 0, "Sequence number": 8962060, "Fwd thread id": 1, "Ev Idx": 1050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924403735.718, "dur": 406.960, + "args": { + "External id": 761884,"Sequence number": 8962060, "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": 688924403735.718, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 31338, + "ts": 688924403761.749, "dur": 50.940, + "args": { + "External id": 761885,"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": 688924403763.190, "dur": 49.261, + "args": { + "External id": 761886,"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": 688924403766.140, "dur": 6.801, + "args": { + "External id": 761887,"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": 688924403768.815, "dur": 3.640, + "args": { + "External id": 761888,"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": 688924403774.355, "dur": 37.273, + "args": { + "External id": 761889,"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": 688924403826.790, "dur": 3.578, + "args": { + "External id": 761890,"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": 688924403828.072, "dur": 2.165, + "args": { + "External id": 761891,"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": 688924403836.730, "dur": 3.441, + "args": { + "External id": 761892,"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": 688924403837.369, "dur": 2.696, + "args": { + "External id": 761893,"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": 688924403852.816, "dur": 3.025, + "args": { + "External id": 761894,"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": 688924403867.079, "dur": 3.032, + "args": { + "External id": 761895,"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": 688924404033.731, "dur": 2.873, + "args": { + "External id": 761896,"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": 688924404041.373, "dur": 33.861, + "args": { + "External id": 761897,"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": 688924404053.819, "dur": 0.619, + "args": { + "External id": 761898,"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": 688924404081.168, "dur": 28.315, + "args": { + "External id": 761899,"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": 688924404083.047, "dur": 26.178, + "args": { + "External id": 761900,"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": 688924404087.580, "dur": 5.061, + "args": { + "External id": 761901,"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": 688924404094.160, "dur": 14.530, + "args": { + "External id": 761902,"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": 688924404113.940, "dur": 2.597, + "args": { + "External id": 761903,"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": 688924404115.115, "dur": 1.279, + "args": { + "External id": 761904,"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": 688924404124.834, "dur": 2.818, + "args": { + "External id": 761905,"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": 688924404126.312, "dur": 1.236, + "args": { + "External id": 761906,"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": 688924404129.999, "dur": 3.722, + "args": { + "External id": 761907,"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": 688924404131.058, "dur": 2.533, + "args": { + "External id": 761908,"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": 688924404159.065, "dur": 17.372, + "args": { + "External id": 761909,"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": 688924404190.730, "dur": 10.848, + "args": { + "External id": 761910,"Record function id": 0, "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924404193.214, "dur": 7.708, + "args": { + "External id": 761911,"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": 688924404195.120, "dur": 4.956, + "args": { + "External id": 761912,"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": 688924404198.157, "dur": 1.787, + "args": { + "External id": 761913,"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": 688924404205.918, "dur": 8.295, + "args": { + "External id": 761914,"Record function id": 0, "Sequence number": 8962059, "Fwd thread id": 1, "Ev Idx": 1081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924404207.415, "dur": 4.140, + "args": { + "External id": 761915,"Sequence number": 8962059, "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": 688924404207.415, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924404209.104, "dur": 2.215, + "args": { + "External id": 761916,"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": 688924404210.064, "dur": 1.117, + "args": { + "External id": 761917,"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": 688924404217.792, "dur": 160.928, + "args": { + "External id": 761918,"Record function id": 0, "Sequence number": 8962058, "Fwd thread id": 1, "Ev Idx": 1085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924404218.805, "dur": 152.297, + "args": { + "External id": 761919,"Sequence number": 8962058, "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": 688924404218.805, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924404223.931, "dur": 7.240, + "args": { + "External id": 761920,"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": 688924404225.544, "dur": 4.999, + "args": { + "External id": 761921,"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": 688924404229.405, "dur": 0.964, + "args": { + "External id": 761922,"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": 688924404232.439, "dur": 70.357, + "args": { + "External id": 761923,"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": 688924404304.066, "dur": 6.541, + "args": { + "External id": 761924,"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": 688924404304.795, "dur": 5.257, + "args": { + "External id": 761925,"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": 688924404306.612, "dur": 3.249, + "args": { + "External id": 761926,"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": 688924404312.317, "dur": 5.706, + "args": { + "External id": 761927,"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": 688924404315.457, "dur": 2.050, + "args": { + "External id": 761928,"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": 688924404316.931, "dur": 0.514, + "args": { + "External id": 761929,"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": 688924404318.784, "dur": 51.483, + "args": { + "External id": 761930,"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": 688924404383.661, "dur": 9.571, + "args": { + "External id": 761931,"Record function id": 0, "Sequence number": 8962057, "Fwd thread id": 1, "Ev Idx": 1098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924404384.822, "dur": 6.214, + "args": { + "External id": 761932,"Sequence number": 8962057, "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": 688924404384.822, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924404386.463, "dur": 4.417, + "args": { + "External id": 761933,"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": 688924404387.336, "dur": 3.414, + "args": { + "External id": 761934,"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": 688924404396.640, "dur": 11.254, + "args": { + "External id": 761935,"Record function id": 0, "Sequence number": 8962056, "Fwd thread id": 1, "Ev Idx": 1102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924404397.599, "dur": 7.784, + "args": { + "External id": 761936,"Sequence number": 8962056, "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": 688924404397.599, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924404398.757, "dur": 6.415, + "args": { + "External id": 761937,"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": 688924404401.737, "dur": 2.897, + "args": { + "External id": 761938,"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": 688924404403.626, "dur": 0.868, + "args": { + "External id": 761939,"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": 688924404411.787, "dur": 6.164, + "args": { + "External id": 761940,"Record function id": 0, "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924404413.585, "dur": 3.888, + "args": { + "External id": 761941,"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": 688924404415.043, "dur": 2.183, + "args": { + "External id": 761942,"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": 688924404415.923, "dur": 1.207, + "args": { + "External id": 761943,"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": 688924404423.124, "dur": 6.483, + "args": { + "External id": 761944,"Record function id": 0, "Sequence number": 8962055, "Fwd thread id": 1, "Ev Idx": 1111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924404423.960, "dur": 3.447, + "args": { + "External id": 761945,"Sequence number": 8962055, "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": 688924404423.960, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924404425.474, "dur": 1.778, + "args": { + "External id": 761946,"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": 688924404426.027, "dur": 1.093, + "args": { + "External id": 761947,"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": 688924404434.350, "dur": 387.921, + "args": { + "External id": 761948,"Record function id": 0, "Sequence number": 8962054, "Fwd thread id": 1, "Ev Idx": 1115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183436, "tid": 31338, + "ts": 688924404435.878, "dur": 344.243, + "args": { + "External id": 761949,"Sequence number": 8962054, "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": 688924404435.878, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 31338, + "ts": 688924404452.609, "dur": 6.479, + "args": { + "External id": 761950,"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": 688924404455.616, "dur": 3.103, + "args": { + "External id": 761951,"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": 688924404461.240, "dur": 5.523, + "args": { + "External id": 761952,"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": 688924404462.942, "dur": 3.486, + "args": { + "External id": 761953,"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": 688924404504.235, "dur": 6.257, + "args": { + "External id": 761954,"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": 688924404507.778, "dur": 2.441, + "args": { + "External id": 761955,"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": 688924404537.838, "dur": 213.499, + "args": { + "External id": 761956,"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": 688924404612.989, "dur": 5.531, + "args": { + "External id": 761957,"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": 688924404620.322, "dur": 4.149, + "args": { + "External id": 761958,"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": 688924404765.715, "dur": 4.493, + "args": { + "External id": 761959,"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": 688924404773.383, "dur": 0.830, + "args": { + "External id": 761960,"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": 688924404776.337, "dur": 0.847, + "args": { + "External id": 761961,"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": 688924404834.786, "dur": 233.705, + "args": { + "External id": 761962,"Record function id": 0, "Sequence number": 8962053, "Fwd thread id": 1, "Ev Idx": 1129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924404836.619, "dur": 224.532, + "args": { + "External id": 761963,"Sequence number": 8962053, "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": 688924404836.619, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 688924404858.974, "dur": 46.942, + "args": { + "External id": 761964,"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": 688924404862.403, "dur": 4.374, + "args": { + "External id": 761965,"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": 688924404868.211, "dur": 37.076, + "args": { + "External id": 761966,"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": 688924404915.728, "dur": 6.691, + "args": { + "External id": 761967,"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": 688924404917.887, "dur": 4.208, + "args": { + "External id": 761968,"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": 688924405075.904, "dur": 148.881, + "args": { + "External id": 761969,"Record function id": 0, "Sequence number": 8962052, "Fwd thread id": 1, "Ev Idx": 1136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924405078.025, "dur": 139.774, + "args": { + "External id": 761970,"Sequence number": 8962052, "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": 688924405078.025, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 688924405089.630, "dur": 34.704, + "args": { + "External id": 761971,"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": 688924405092.418, "dur": 2.590, + "args": { + "External id": 761972,"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": 688924405099.928, "dur": 23.987, + "args": { + "External id": 761973,"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": 688924405131.288, "dur": 4.456, + "args": { + "External id": 761974,"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": 688924405133.545, "dur": 1.932, + "args": { + "External id": 761975,"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": 688924405230.800, "dur": 16.336, + "args": { + "External id": 761976,"Record function id": 0, "Sequence number": 8962051, "Fwd thread id": 1, "Ev Idx": 1143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405232.255, "dur": 11.969, + "args": { + "External id": 761977,"Sequence number": 8962051, "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": 688924405232.255, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924405235.118, "dur": 8.852, + "args": { + "External id": 761978,"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": 688924405236.723, "dur": 7.077, + "args": { + "External id": 761979,"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": 688924405250.700, "dur": 9.194, + "args": { + "External id": 761980,"Record function id": 0, "Sequence number": 8962050, "Fwd thread id": 1, "Ev Idx": 1147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405253.491, "dur": 4.028, + "args": { + "External id": 761981,"Sequence number": 8962050, "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": 688924405253.491, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924405255.169, "dur": 2.213, + "args": { + "External id": 761982,"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": 688924405256.540, "dur": 0.709, + "args": { + "External id": 761983,"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": 688924405262.904, "dur": 7.476, + "args": { + "External id": 761984,"Record function id": 0, "Sequence number": 8962049, "Fwd thread id": 1, "Ev Idx": 1151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405264.109, "dur": 3.735, + "args": { + "External id": 761985,"Sequence number": 8962049, "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": 688924405264.109, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924405265.555, "dur": 2.156, + "args": { + "External id": 761986,"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": 688924405266.512, "dur": 1.095, + "args": { + "External id": 761987,"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": 688924405273.792, "dur": 8.523, + "args": { + "External id": 761988,"Record function id": 0, "Sequence number": 8962048, "Fwd thread id": 1, "Ev Idx": 1155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405275.011, "dur": 4.922, + "args": { + "External id": 761989,"Sequence number": 8962048, "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": 688924405275.011, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924405276.311, "dur": 3.479, + "args": { + "External id": 761990,"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": 688924405278.872, "dur": 0.822, + "args": { + "External id": 761991,"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": 688924405285.572, "dur": 155.226, + "args": { + "External id": 761992,"Record function id": 0, "Sequence number": 8962047, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405286.471, "dur": 145.787, + "args": { + "External id": 761993,"Sequence number": 8962047, "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": 688924405286.471, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924405291.100, "dur": 6.920, + "args": { + "External id": 761994,"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": 688924405293.205, "dur": 4.150, + "args": { + "External id": 761995,"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": 688924405295.638, "dur": 1.450, + "args": { + "External id": 761996,"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": 688924405299.785, "dur": 76.941, + "args": { + "External id": 761997,"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": 688924405380.032, "dur": 5.048, + "args": { + "External id": 761998,"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": 688924405380.670, "dur": 3.741, + "args": { + "External id": 761999,"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": 688924405382.457, "dur": 1.779, + "args": { + "External id": 762000,"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": 688924405386.939, "dur": 3.912, + "args": { + "External id": 762001,"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": 688924405388.167, "dur": 2.193, + "args": { + "External id": 762002,"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": 688924405389.814, "dur": 0.479, + "args": { + "External id": 762003,"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": 688924405393.546, "dur": 37.802, + "args": { + "External id": 762004,"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": 688924405447.183, "dur": 6.801, + "args": { + "External id": 762005,"Record function id": 0, "Sequence number": 8962046, "Fwd thread id": 1, "Ev Idx": 1172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405448.190, "dur": 4.158, + "args": { + "External id": 762006,"Sequence number": 8962046, "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": 688924405448.190, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924405449.843, "dur": 2.367, + "args": { + "External id": 762007,"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": 688924405450.891, "dur": 1.178, + "args": { + "External id": 762008,"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": 688924405457.565, "dur": 10.513, + "args": { + "External id": 762009,"Record function id": 0, "Sequence number": 8962045, "Fwd thread id": 1, "Ev Idx": 1176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405458.542, "dur": 6.830, + "args": { + "External id": 762010,"Sequence number": 8962045, "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": 688924405458.542, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924405459.726, "dur": 5.410, + "args": { + "External id": 762011,"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": 688924405460.335, "dur": 4.224, + "args": { + "External id": 762012,"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": 688924405463.874, "dur": 0.599, + "args": { + "External id": 762013,"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": 688924405473.777, "dur": 9.615, + "args": { + "External id": 762014,"Record function id": 0, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924405475.725, "dur": 6.986, + "args": { + "External id": 762015,"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": 688924405478.284, "dur": 4.043, + "args": { + "External id": 762016,"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": 688924405479.537, "dur": 2.692, + "args": { + "External id": 762017,"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": 688924405486.782, "dur": 7.847, + "args": { + "External id": 762018,"Record function id": 0, "Sequence number": 8962044, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405488.658, "dur": 3.884, + "args": { + "External id": 762019,"Sequence number": 8962044, "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": 688924405488.658, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924405490.588, "dur": 1.824, + "args": { + "External id": 762020,"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": 688924405491.555, "dur": 0.766, + "args": { + "External id": 762021,"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": 688924405497.925, "dur": 98.081, + "args": { + "External id": 762022,"Record function id": 0, "Sequence number": 8962043, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405499.078, "dur": 89.909, + "args": { + "External id": 762023,"Sequence number": 8962043, "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": 688924405499.078, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924405504.606, "dur": 3.756, + "args": { + "External id": 762024,"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": 688924405505.528, "dur": 2.341, + "args": { + "External id": 762025,"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": 688924405507.204, "dur": 0.550, + "args": { + "External id": 762026,"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": 688924405508.964, "dur": 33.972, + "args": { + "External id": 762027,"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": 688924405544.085, "dur": 4.215, + "args": { + "External id": 762028,"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": 688924405544.833, "dur": 2.936, + "args": { + "External id": 762029,"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": 688924405546.820, "dur": 0.843, + "args": { + "External id": 762030,"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": 688924405551.170, "dur": 5.695, + "args": { + "External id": 762031,"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": 688924405552.449, "dur": 3.745, + "args": { + "External id": 762032,"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": 688924405553.937, "dur": 2.192, + "args": { + "External id": 762033,"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": 688924405557.529, "dur": 30.777, + "args": { + "External id": 762034,"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": 688924405600.144, "dur": 33.607, + "args": { + "External id": 762035,"Record function id": 0, "Sequence number": 8962042, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405601.320, "dur": 6.310, + "args": { + "External id": 762036,"Sequence number": 8962042, "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": 688924405601.320, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924405602.994, "dur": 4.485, + "args": { + "External id": 762037,"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": 688924405606.104, "dur": 1.231, + "args": { + "External id": 762038,"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": 688924405610.894, "dur": 20.362, + "args": { + "External id": 762039,"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": 688924405637.645, "dur": 7.960, + "args": { + "External id": 762040,"Record function id": 0, "Sequence number": 8962041, "Fwd thread id": 1, "Ev Idx": 1207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405638.590, "dur": 4.917, + "args": { + "External id": 762041,"Sequence number": 8962041, "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": 688924405638.590, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924405639.537, "dur": 3.783, + "args": { + "External id": 762042,"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": 688924405640.338, "dur": 2.477, + "args": { + "External id": 762043,"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": 688924405642.001, "dur": 0.671, + "args": { + "External id": 762044,"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": 688924405649.465, "dur": 60.203, + "args": { + "External id": 762045,"Record function id": 0, "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924405651.045, "dur": 57.391, + "args": { + "External id": 762046,"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": 688924405652.249, "dur": 55.558, + "args": { + "External id": 762047,"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": 688924405705.096, "dur": 2.348, + "args": { + "External id": 762048,"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": 688924405714.936, "dur": 11.278, + "args": { + "External id": 762049,"Record function id": 0, "Sequence number": 8962040, "Fwd thread id": 1, "Ev Idx": 1216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405716.669, "dur": 6.126, + "args": { + "External id": 762050,"Sequence number": 8962040, "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": 688924405716.669, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924405718.451, "dur": 4.176, + "args": { + "External id": 762051,"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": 688924405721.183, "dur": 1.353, + "args": { + "External id": 762052,"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": 688924405729.413, "dur": 129.244, + "args": { + "External id": 762053,"Record function id": 0, "Sequence number": 8962039, "Fwd thread id": 1, "Ev Idx": 1220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405730.270, "dur": 118.331, + "args": { + "External id": 762054,"Sequence number": 8962039, "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": 688924405730.270, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924405736.144, "dur": 3.825, + "args": { + "External id": 762055,"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": 688924405736.863, "dur": 2.668, + "args": { + "External id": 762056,"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": 688924405738.984, "dur": 0.429, + "args": { + "External id": 762057,"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": 688924405740.594, "dur": 41.727, + "args": { + "External id": 762058,"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": 688924405783.611, "dur": 20.712, + "args": { + "External id": 762059,"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": 688924405784.197, "dur": 19.235, + "args": { + "External id": 762060,"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": 688924405800.611, "dur": 2.388, + "args": { + "External id": 762061,"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": 688924405805.995, "dur": 4.143, + "args": { + "External id": 762062,"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": 688924405807.499, "dur": 2.167, + "args": { + "External id": 762063,"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": 688924405809.133, "dur": 0.438, + "args": { + "External id": 762064,"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": 688924405810.749, "dur": 37.235, + "args": { + "External id": 762065,"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": 688924405864.638, "dur": 29.775, + "args": { + "External id": 762066,"Record function id": 0, "Sequence number": 8962038, "Fwd thread id": 1, "Ev Idx": 1233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405865.832, "dur": 7.481, + "args": { + "External id": 762067,"Sequence number": 8962038, "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": 688924405865.832, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924405868.116, "dur": 5.052, + "args": { + "External id": 762068,"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": 688924405871.663, "dur": 1.377, + "args": { + "External id": 762069,"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": 688924405876.131, "dur": 16.039, + "args": { + "External id": 762070,"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": 688924405898.333, "dur": 8.382, + "args": { + "External id": 762071,"Record function id": 0, "Sequence number": 8962037, "Fwd thread id": 1, "Ev Idx": 1238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924405899.390, "dur": 5.270, + "args": { + "External id": 762072,"Sequence number": 8962037, "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": 688924405899.390, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924405900.332, "dur": 4.129, + "args": { + "External id": 762073,"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": 688924405901.314, "dur": 2.644, + "args": { + "External id": 762074,"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": 688924405903.433, "dur": 0.373, + "args": { + "External id": 762075,"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": 688924405911.113, "dur": 6.468, + "args": { + "External id": 762076,"Record function id": 0, "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924405913.038, "dur": 3.980, + "args": { + "External id": 762077,"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": 688924405914.285, "dur": 2.389, + "args": { + "External id": 762078,"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": 688924405915.098, "dur": 1.463, + "args": { + "External id": 762079,"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": 688924405924.198, "dur": 350.666, + "args": { + "External id": 762080,"Record function id": 0, "Sequence number": 8962036, "Fwd thread id": 1, "Ev Idx": 1247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924405926.021, "dur": 319.042, + "args": { + "External id": 762081,"Sequence number": 8962036, "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": 688924405926.021, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924405960.789, "dur": 2.310, + "args": { + "External id": 762082,"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": 688924405961.821, "dur": 1.121, + "args": { + "External id": 762083,"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": 688924405977.454, "dur": 6.027, + "args": { + "External id": 762084,"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": 688924405992.834, "dur": 3.520, + "args": { + "External id": 762085,"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": 688924406143.592, "dur": 2.256, + "args": { + "External id": 762086,"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": 688924406150.221, "dur": 32.773, + "args": { + "External id": 762087,"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": 688924406159.425, "dur": 0.860, + "args": { + "External id": 762088,"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": 688924406188.672, "dur": 32.800, + "args": { + "External id": 762089,"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": 688924406192.799, "dur": 28.479, + "args": { + "External id": 762090,"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": 688924406197.385, "dur": 4.325, + "args": { + "External id": 762091,"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": 688924406203.169, "dur": 17.637, + "args": { + "External id": 762092,"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": 688924406225.464, "dur": 2.869, + "args": { + "External id": 762093,"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": 688924406227.095, "dur": 1.137, + "args": { + "External id": 762094,"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": 688924406234.410, "dur": 4.189, + "args": { + "External id": 762095,"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": 688924406237.395, "dur": 1.109, + "args": { + "External id": 762096,"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": 688924406254.418, "dur": 15.889, + "args": { + "External id": 762097,"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": 688924406285.218, "dur": 7.709, + "args": { + "External id": 762098,"Record function id": 0, "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924406287.329, "dur": 4.912, + "args": { + "External id": 762099,"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": 688924406288.960, "dur": 2.312, + "args": { + "External id": 762100,"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": 688924406289.705, "dur": 1.467, + "args": { + "External id": 762101,"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": 688924406296.828, "dur": 7.081, + "args": { + "External id": 762102,"Record function id": 0, "Sequence number": 8962035, "Fwd thread id": 1, "Ev Idx": 1269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924406298.313, "dur": 1.098, + "args": { + "External id": 762103,"Sequence number": 8962035, "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": 688924406298.313, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924406307.930, "dur": 439.075, + "args": { + "External id": 762104,"Record function id": 0, "Sequence number": 8962034, "Fwd thread id": 1, "Ev Idx": 1271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924406309.609, "dur": 421.910, + "args": { + "External id": 762105,"Sequence number": 8962034, "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": 688924406309.609, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924406341.122, "dur": 8.453, + "args": { + "External id": 762106,"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": 688924406346.213, "dur": 3.042, + "args": { + "External id": 762107,"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": 688924406352.453, "dur": 5.950, + "args": { + "External id": 762108,"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": 688924406354.069, "dur": 3.525, + "args": { + "External id": 762109,"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": 688924406356.392, "dur": 1.004, + "args": { + "External id": 762110,"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": 688924406361.949, "dur": 84.403, + "args": { + "External id": 762111,"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": 688924406364.615, "dur": 5.583, + "args": { + "External id": 762112,"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": 688924406365.271, "dur": 4.432, + "args": { + "External id": 762113,"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": 688924406367.146, "dur": 2.480, + "args": { + "External id": 762114,"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": 688924406371.548, "dur": 74.325, + "args": { + "External id": 762115,"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": 688924406372.795, "dur": 72.334, + "args": { + "External id": 762116,"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": 688924406449.896, "dur": 2.753, + "args": { + "External id": 762117,"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": 688924406451.136, "dur": 1.409, + "args": { + "External id": 762118,"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": 688924406483.942, "dur": 5.296, + "args": { + "External id": 762119,"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": 688924406490.568, "dur": 2.214, + "args": { + "External id": 762120,"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": 688924406494.210, "dur": 2.017, + "args": { + "External id": 762121,"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": 688924406527.227, "dur": 2.640, + "args": { + "External id": 762122,"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": 688924406528.265, "dur": 1.448, + "args": { + "External id": 762123,"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": 688924406551.372, "dur": 159.775, + "args": { + "External id": 762124,"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": 688924406556.461, "dur": 7.103, + "args": { + "External id": 762125,"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": 688924406560.409, "dur": 2.331, + "args": { + "External id": 762126,"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": 688924406564.937, "dur": 6.549, + "args": { + "External id": 762127,"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": 688924406568.317, "dur": 2.330, + "args": { + "External id": 762128,"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": 688924406573.007, "dur": 2.804, + "args": { + "External id": 762129,"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": 688924406575.051, "dur": 0.417, + "args": { + "External id": 762130,"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": 688924406576.760, "dur": 3.145, + "args": { + "External id": 762131,"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": 688924406578.645, "dur": 0.728, + "args": { + "External id": 762132,"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": 688924406583.760, "dur": 3.164, + "args": { + "External id": 762133,"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": 688924406585.955, "dur": 0.637, + "args": { + "External id": 762134,"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": 688924406588.032, "dur": 6.261, + "args": { + "External id": 762135,"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": 688924406592.016, "dur": 2.075, + "args": { + "External id": 762136,"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": 688924406597.626, "dur": 2.940, + "args": { + "External id": 762137,"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": 688924406599.611, "dur": 0.685, + "args": { + "External id": 762138,"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": 688924406601.599, "dur": 4.289, + "args": { + "External id": 762139,"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": 688924406602.652, "dur": 3.159, + "args": { + "External id": 762140,"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": 688924406607.218, "dur": 44.477, + "args": { + "External id": 762141,"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": 688924406653.896, "dur": 45.708, + "args": { + "External id": 762142,"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": 688924406701.903, "dur": 4.252, + "args": { + "External id": 762143,"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": 688924406704.760, "dur": 0.735, + "args": { + "External id": 762144,"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": 688924406709.017, "dur": 1.124, + "args": { + "External id": 762145,"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": 688924406759.323, "dur": 9.942, + "args": { + "External id": 762146,"Record function id": 0, "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924406762.057, "dur": 6.570, + "args": { + "External id": 762147,"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": 688924406764.668, "dur": 3.067, + "args": { + "External id": 762148,"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": 688924406765.508, "dur": 2.129, + "args": { + "External id": 762149,"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": 688924406773.727, "dur": 8.858, + "args": { + "External id": 762150,"Record function id": 0, "Sequence number": 8962033, "Fwd thread id": 1, "Ev Idx": 1317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924406774.969, "dur": 4.198, + "args": { + "External id": 762151,"Sequence number": 8962033, "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": 688924406774.969, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924406776.628, "dur": 2.334, + "args": { + "External id": 762152,"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": 688924406777.601, "dur": 1.235, + "args": { + "External id": 762153,"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": 688924406802.246, "dur": 123.032, + "args": { + "External id": 762154,"Record function id": 0, "Sequence number": 8962032, "Fwd thread id": 1, "Ev Idx": 1321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924406803.915, "dur": 112.773, + "args": { + "External id": 762155,"Sequence number": 8962032, "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": 688924406803.915, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924406810.231, "dur": 6.244, + "args": { + "External id": 762156,"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": 688924406812.032, "dur": 3.637, + "args": { + "External id": 762157,"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": 688924406814.142, "dur": 1.169, + "args": { + "External id": 762158,"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": 688924406817.852, "dur": 42.512, + "args": { + "External id": 762159,"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": 688924406862.075, "dur": 5.775, + "args": { + "External id": 762160,"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": 688924406862.579, "dur": 4.623, + "args": { + "External id": 762161,"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": 688924406865.959, "dur": 1.072, + "args": { + "External id": 762162,"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": 688924406869.889, "dur": 4.392, + "args": { + "External id": 762163,"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": 688924406871.548, "dur": 2.153, + "args": { + "External id": 762164,"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": 688924406873.044, "dur": 0.555, + "args": { + "External id": 762165,"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": 688924406874.915, "dur": 40.897, + "args": { + "External id": 762166,"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": 688924406930.808, "dur": 9.200, + "args": { + "External id": 762167,"Record function id": 0, "Sequence number": 8962031, "Fwd thread id": 1, "Ev Idx": 1334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924406932.004, "dur": 6.533, + "args": { + "External id": 762168,"Sequence number": 8962031, "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": 688924406932.004, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924406934.084, "dur": 4.306, + "args": { + "External id": 762169,"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": 688924406937.173, "dur": 1.124, + "args": { + "External id": 762170,"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": 688924406943.556, "dur": 8.463, + "args": { + "External id": 762171,"Record function id": 0, "Sequence number": 8962030, "Fwd thread id": 1, "Ev Idx": 1338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924406944.825, "dur": 5.129, + "args": { + "External id": 762172,"Sequence number": 8962030, "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": 688924406944.825, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924406945.971, "dur": 3.770, + "args": { + "External id": 762173,"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": 688924406946.798, "dur": 2.472, + "args": { + "External id": 762174,"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": 688924406948.587, "dur": 0.596, + "args": { + "External id": 762175,"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": 688924406956.620, "dur": 6.343, + "args": { + "External id": 762176,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924406958.509, "dur": 3.963, + "args": { + "External id": 762177,"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": 688924406959.631, "dur": 2.207, + "args": { + "External id": 762178,"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": 688924406960.424, "dur": 1.324, + "args": { + "External id": 762179,"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": 688924406966.463, "dur": 10.118, + "args": { + "External id": 762180,"Record function id": 0, "Sequence number": 8962029, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924406967.819, "dur": 6.255, + "args": { + "External id": 762181,"Sequence number": 8962029, "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": 688924406967.819, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924406971.778, "dur": 2.147, + "args": { + "External id": 762182,"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": 688924406973.017, "dur": 0.768, + "args": { + "External id": 762183,"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": 688924406979.578, "dur": 92.877, + "args": { + "External id": 762184,"Record function id": 0, "Sequence number": 8962028, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924406980.628, "dur": 83.239, + "args": { + "External id": 762185,"Sequence number": 8962028, "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": 688924406980.628, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924406984.207, "dur": 5.139, + "args": { + "External id": 762186,"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": 688924406984.994, "dur": 3.889, + "args": { + "External id": 762187,"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": 688924406988.042, "dur": 0.705, + "args": { + "External id": 762188,"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": 688924406989.945, "dur": 28.046, + "args": { + "External id": 762189,"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": 688924407019.168, "dur": 3.899, + "args": { + "External id": 762190,"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": 688924407020.094, "dur": 2.447, + "args": { + "External id": 762191,"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": 688924407021.717, "dur": 0.681, + "args": { + "External id": 762192,"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": 688924407024.330, "dur": 7.297, + "args": { + "External id": 762193,"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": 688924407025.844, "dur": 5.267, + "args": { + "External id": 762194,"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": 688924407028.523, "dur": 2.490, + "args": { + "External id": 762195,"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": 688924407032.031, "dur": 30.913, + "args": { + "External id": 762196,"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": 688924407078.767, "dur": 32.599, + "args": { + "External id": 762197,"Record function id": 0, "Sequence number": 8962027, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924407080.027, "dur": 3.968, + "args": { + "External id": 762198,"Sequence number": 8962027, "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": 688924407080.027, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924407081.796, "dur": 2.047, + "args": { + "External id": 762199,"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": 688924407082.666, "dur": 1.046, + "args": { + "External id": 762200,"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": 688924407086.797, "dur": 21.104, + "args": { + "External id": 762201,"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": 688924407115.067, "dur": 9.344, + "args": { + "External id": 762202,"Record function id": 0, "Sequence number": 8962026, "Fwd thread id": 1, "Ev Idx": 1369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924407116.076, "dur": 6.382, + "args": { + "External id": 762203,"Sequence number": 8962026, "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": 688924407116.076, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924407117.018, "dur": 5.241, + "args": { + "External id": 762204,"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": 688924407118.059, "dur": 3.728, + "args": { + "External id": 762205,"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": 688924407120.965, "dur": 0.716, + "args": { + "External id": 762206,"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": 688924407128.399, "dur": 5.126, + "args": { + "External id": 762207,"Record function id": 0, "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924407129.740, "dur": 3.297, + "args": { + "External id": 762208,"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": 688924407130.902, "dur": 1.769, + "args": { + "External id": 762209,"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": 688924407131.357, "dur": 1.227, + "args": { + "External id": 762210,"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": 688924407137.711, "dur": 406.882, + "args": { + "External id": 762211,"Record function id": 0, "Sequence number": 8962025, "Fwd thread id": 1, "Ev Idx": 1378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924407142.522, "dur": 366.764, + "args": { + "External id": 762212,"Sequence number": 8962025, "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": 688924407142.522, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 31338, + "ts": 688924407165.566, "dur": 34.000, + "args": { + "External id": 762213,"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": 688924407167.008, "dur": 32.305, + "args": { + "External id": 762214,"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": 688924407170.115, "dur": 5.736, + "args": { + "External id": 762215,"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": 688924407172.696, "dur": 2.738, + "args": { + "External id": 762216,"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": 688924407177.184, "dur": 21.556, + "args": { + "External id": 762217,"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": 688924407212.648, "dur": 2.453, + "args": { + "External id": 762218,"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": 688924407213.739, "dur": 1.253, + "args": { + "External id": 762219,"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": 688924407219.265, "dur": 3.403, + "args": { + "External id": 762220,"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": 688924407220.184, "dur": 2.386, + "args": { + "External id": 762221,"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": 688924407236.271, "dur": 2.854, + "args": { + "External id": 762222,"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": 688924407250.129, "dur": 4.424, + "args": { + "External id": 762223,"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": 688924407406.114, "dur": 3.578, + "args": { + "External id": 762224,"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": 688924407414.276, "dur": 28.023, + "args": { + "External id": 762225,"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": 688924407422.578, "dur": 0.712, + "args": { + "External id": 762226,"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": 688924407447.861, "dur": 31.427, + "args": { + "External id": 762227,"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": 688924407449.822, "dur": 29.268, + "args": { + "External id": 762228,"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": 688924407454.383, "dur": 4.429, + "args": { + "External id": 762229,"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": 688924407462.229, "dur": 16.367, + "args": { + "External id": 762230,"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": 688924407482.906, "dur": 2.693, + "args": { + "External id": 762231,"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": 688924407484.201, "dur": 1.256, + "args": { + "External id": 762232,"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": 688924407492.339, "dur": 2.666, + "args": { + "External id": 762233,"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": 688924407493.749, "dur": 1.132, + "args": { + "External id": 762234,"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": 688924407497.262, "dur": 3.786, + "args": { + "External id": 762235,"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": 688924407498.232, "dur": 2.727, + "args": { + "External id": 762236,"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": 688924407527.393, "dur": 15.812, + "args": { + "External id": 762237,"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": 688924407554.396, "dur": 7.358, + "args": { + "External id": 762238,"Record function id": 0, "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924407556.629, "dur": 4.482, + "args": { + "External id": 762239,"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": 688924407558.116, "dur": 2.340, + "args": { + "External id": 762240,"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": 688924407558.837, "dur": 1.529, + "args": { + "External id": 762241,"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": 688924407565.731, "dur": 8.137, + "args": { + "External id": 762242,"Record function id": 0, "Sequence number": 8962024, "Fwd thread id": 1, "Ev Idx": 1409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924407567.044, "dur": 4.197, + "args": { + "External id": 762243,"Sequence number": 8962024, "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": 688924407567.044, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924407568.658, "dur": 2.353, + "args": { + "External id": 762244,"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": 688924407569.906, "dur": 0.955, + "args": { + "External id": 762245,"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": 688924407579.021, "dur": 182.961, + "args": { + "External id": 762246,"Record function id": 0, "Sequence number": 8962023, "Fwd thread id": 1, "Ev Idx": 1413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924407579.891, "dur": 171.930, + "args": { + "External id": 762247,"Sequence number": 8962023, "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": 688924407579.891, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924407583.687, "dur": 4.707, + "args": { + "External id": 762248,"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": 688924407584.953, "dur": 2.818, + "args": { + "External id": 762249,"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": 688924407586.742, "dur": 0.850, + "args": { + "External id": 762250,"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": 688924407589.394, "dur": 58.462, + "args": { + "External id": 762251,"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": 688924407649.310, "dur": 51.724, + "args": { + "External id": 762252,"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": 688924407651.753, "dur": 48.129, + "args": { + "External id": 762253,"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": 688924407696.147, "dur": 3.184, + "args": { + "External id": 762254,"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": 688924407703.402, "dur": 4.450, + "args": { + "External id": 762255,"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": 688924407704.874, "dur": 2.386, + "args": { + "External id": 762256,"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": 688924407706.643, "dur": 0.553, + "args": { + "External id": 762257,"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": 688924407708.735, "dur": 42.342, + "args": { + "External id": 762258,"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": 688924407768.822, "dur": 12.910, + "args": { + "External id": 762259,"Record function id": 0, "Sequence number": 8962022, "Fwd thread id": 1, "Ev Idx": 1426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924407769.961, "dur": 8.942, + "args": { + "External id": 762260,"Sequence number": 8962022, "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": 688924407769.961, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924407773.982, "dur": 4.749, + "args": { + "External id": 762261,"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": 688924407775.398, "dur": 3.218, + "args": { + "External id": 762262,"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": 688924407785.463, "dur": 24.530, + "args": { + "External id": 762263,"Record function id": 0, "Sequence number": 8962021, "Fwd thread id": 1, "Ev Idx": 1430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924407800.937, "dur": 6.652, + "args": { + "External id": 762264,"Sequence number": 8962021, "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": 688924407800.937, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924407802.115, "dur": 5.243, + "args": { + "External id": 762265,"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": 688924407803.353, "dur": 3.274, + "args": { + "External id": 762266,"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": 688924407805.591, "dur": 0.768, + "args": { + "External id": 762267,"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": 688924407815.718, "dur": 10.233, + "args": { + "External id": 762268,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924407818.678, "dur": 6.717, + "args": { + "External id": 762269,"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": 688924407820.322, "dur": 4.732, + "args": { + "External id": 762270,"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": 688924407823.377, "dur": 1.569, + "args": { + "External id": 762271,"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": 688924407828.984, "dur": 7.852, + "args": { + "External id": 762272,"Record function id": 0, "Sequence number": 8962020, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924407829.856, "dur": 4.750, + "args": { + "External id": 762273,"Sequence number": 8962020, "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": 688924407829.856, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924407831.822, "dur": 2.639, + "args": { + "External id": 762274,"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": 688924407832.770, "dur": 1.553, + "args": { + "External id": 762275,"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": 688924407841.627, "dur": 293.516, + "args": { + "External id": 762276,"Record function id": 0, "Sequence number": 8962019, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183436, "tid": 31338, + "ts": 688924407843.522, "dur": 271.177, + "args": { + "External id": 762277,"Sequence number": 8962019, "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": 688924407843.522, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 31338, + "ts": 688924407862.235, "dur": 8.574, + "args": { + "External id": 762278,"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": 688924407865.616, "dur": 4.700, + "args": { + "External id": 762279,"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": 688924407872.804, "dur": 3.603, + "args": { + "External id": 762280,"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": 688924407874.455, "dur": 1.772, + "args": { + "External id": 762281,"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": 688924407878.080, "dur": 4.501, + "args": { + "External id": 762282,"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": 688924407880.548, "dur": 1.841, + "args": { + "External id": 762283,"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": 688924407908.824, "dur": 180.423, + "args": { + "External id": 762284,"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": 688924407988.667, "dur": 4.440, + "args": { + "External id": 762285,"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": 688924407994.977, "dur": 3.883, + "args": { + "External id": 762286,"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": 688924408101.579, "dur": 3.427, + "args": { + "External id": 762287,"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": 688924408107.906, "dur": 0.922, + "args": { + "External id": 762288,"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": 688924408110.816, "dur": 0.932, + "args": { + "External id": 762289,"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": 688924408142.976, "dur": 223.335, + "args": { + "External id": 762290,"Record function id": 0, "Sequence number": 8962018, "Fwd thread id": 1, "Ev Idx": 1457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924408144.733, "dur": 214.891, + "args": { + "External id": 762291,"Sequence number": 8962018, "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": 688924408144.733, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 688924408163.619, "dur": 47.777, + "args": { + "External id": 762292,"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": 688924408166.748, "dur": 2.752, + "args": { + "External id": 762293,"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": 688924408170.972, "dur": 39.867, + "args": { + "External id": 762294,"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": 688924408220.752, "dur": 4.705, + "args": { + "External id": 762295,"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": 688924408222.768, "dur": 2.416, + "args": { + "External id": 762296,"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": 688924408372.917, "dur": 142.317, + "args": { + "External id": 762297,"Record function id": 0, "Sequence number": 8962017, "Fwd thread id": 1, "Ev Idx": 1464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924408374.820, "dur": 134.254, + "args": { + "External id": 762298,"Sequence number": 8962017, "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": 688924408374.820, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183436, "tid": 31338, + "ts": 688924408385.597, "dur": 31.987, + "args": { + "External id": 762299,"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": 688924408388.258, "dur": 2.709, + "args": { + "External id": 762300,"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": 688924408392.007, "dur": 25.084, + "args": { + "External id": 762301,"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": 688924408424.072, "dur": 4.809, + "args": { + "External id": 762302,"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": 688924408426.346, "dur": 2.257, + "args": { + "External id": 762303,"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": 688924408521.435, "dur": 15.528, + "args": { + "External id": 762304,"Record function id": 0, "Sequence number": 8962016, "Fwd thread id": 1, "Ev Idx": 1471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924408522.573, "dur": 11.933, + "args": { + "External id": 762305,"Sequence number": 8962016, "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": 688924408522.573, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924408527.151, "dur": 7.126, + "args": { + "External id": 762306,"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": 688924408528.721, "dur": 5.383, + "args": { + "External id": 762307,"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": 688924408540.243, "dur": 7.293, + "args": { + "External id": 762308,"Record function id": 0, "Sequence number": 8962015, "Fwd thread id": 1, "Ev Idx": 1475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924408541.338, "dur": 3.569, + "args": { + "External id": 762309,"Sequence number": 8962015, "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": 688924408541.338, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924408542.690, "dur": 2.074, + "args": { + "External id": 762310,"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": 688924408543.807, "dur": 0.856, + "args": { + "External id": 762311,"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": 688924408550.483, "dur": 6.400, + "args": { + "External id": 762312,"Record function id": 0, "Sequence number": 8962014, "Fwd thread id": 1, "Ev Idx": 1479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924408551.529, "dur": 3.620, + "args": { + "External id": 762313,"Sequence number": 8962014, "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": 688924408551.529, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924408552.994, "dur": 2.017, + "args": { + "External id": 762314,"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": 688924408554.036, "dur": 0.848, + "args": { + "External id": 762315,"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": 688924408560.467, "dur": 8.894, + "args": { + "External id": 762316,"Record function id": 0, "Sequence number": 8962013, "Fwd thread id": 1, "Ev Idx": 1483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924408561.774, "dur": 4.742, + "args": { + "External id": 762317,"Sequence number": 8962013, "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": 688924408561.774, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924408564.695, "dur": 1.680, + "args": { + "External id": 762318,"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": 688924408565.509, "dur": 0.775, + "args": { + "External id": 762319,"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": 688924408572.625, "dur": 208.127, + "args": { + "External id": 762320,"Record function id": 0, "Sequence number": 8962012, "Fwd thread id": 1, "Ev Idx": 1487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924408573.646, "dur": 197.595, + "args": { + "External id": 762321,"Sequence number": 8962012, "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": 688924408573.646, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924408578.264, "dur": 8.665, + "args": { + "External id": 762322,"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": 688924408580.119, "dur": 6.181, + "args": { + "External id": 762323,"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": 688924408584.447, "dur": 1.602, + "args": { + "External id": 762324,"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": 688924408588.367, "dur": 116.374, + "args": { + "External id": 762325,"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": 688924408707.429, "dur": 6.383, + "args": { + "External id": 762326,"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": 688924408708.657, "dur": 4.022, + "args": { + "External id": 762327,"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": 688924408710.882, "dur": 1.588, + "args": { + "External id": 762328,"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": 688924408715.694, "dur": 6.293, + "args": { + "External id": 762329,"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": 688924408717.433, "dur": 3.972, + "args": { + "External id": 762330,"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": 688924408720.521, "dur": 0.779, + "args": { + "External id": 762331,"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": 688924408722.672, "dur": 47.821, + "args": { + "External id": 762332,"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": 688924408804.905, "dur": 10.862, + "args": { + "External id": 762333,"Record function id": 0, "Sequence number": 8962011, "Fwd thread id": 1, "Ev Idx": 1500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924408806.745, "dur": 6.762, + "args": { + "External id": 762334,"Sequence number": 8962011, "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": 688924408806.745, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924408809.403, "dur": 3.936, + "args": { + "External id": 762335,"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": 688924408811.241, "dur": 1.910, + "args": { + "External id": 762336,"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": 688924408819.671, "dur": 10.337, + "args": { + "External id": 762337,"Record function id": 0, "Sequence number": 8962010, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924408820.911, "dur": 6.736, + "args": { + "External id": 762338,"Sequence number": 8962010, "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": 688924408820.911, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924408821.863, "dur": 5.571, + "args": { + "External id": 762339,"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": 688924408824.353, "dur": 2.529, + "args": { + "External id": 762340,"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": 688924408826.052, "dur": 0.717, + "args": { + "External id": 762341,"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": 688924408835.665, "dur": 9.620, + "args": { + "External id": 762342,"Record function id": 0, "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924408837.646, "dur": 6.977, + "args": { + "External id": 762343,"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": 688924408840.146, "dur": 4.090, + "args": { + "External id": 762344,"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": 688924408841.579, "dur": 2.578, + "args": { + "External id": 762345,"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": 688924408849.177, "dur": 7.699, + "args": { + "External id": 762346,"Record function id": 0, "Sequence number": 8962009, "Fwd thread id": 1, "Ev Idx": 1513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924408850.931, "dur": 3.658, + "args": { + "External id": 762347,"Sequence number": 8962009, "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": 688924408850.931, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924408852.494, "dur": 1.929, + "args": { + "External id": 762348,"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": 688924408853.416, "dur": 0.921, + "args": { + "External id": 762349,"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": 688924408862.050, "dur": 105.665, + "args": { + "External id": 762350,"Record function id": 0, "Sequence number": 8962008, "Fwd thread id": 1, "Ev Idx": 1517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924408863.149, "dur": 97.639, + "args": { + "External id": 762351,"Sequence number": 8962008, "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": 688924408863.149, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924408866.432, "dur": 3.529, + "args": { + "External id": 762352,"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": 688924408867.211, "dur": 2.283, + "args": { + "External id": 762353,"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": 688924408868.622, "dur": 0.750, + "args": { + "External id": 762354,"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": 688924408870.557, "dur": 41.475, + "args": { + "External id": 762355,"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": 688924408913.590, "dur": 6.681, + "args": { + "External id": 762356,"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": 688924408914.501, "dur": 5.224, + "args": { + "External id": 762357,"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": 688924408918.263, "dur": 1.363, + "args": { + "External id": 762358,"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": 688924408921.421, "dur": 5.880, + "args": { + "External id": 762359,"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": 688924408922.966, "dur": 3.770, + "args": { + "External id": 762360,"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": 688924408924.592, "dur": 2.067, + "args": { + "External id": 762361,"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": 688924408928.029, "dur": 32.029, + "args": { + "External id": 762362,"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": 688924408973.936, "dur": 51.769, + "args": { + "External id": 762363,"Record function id": 0, "Sequence number": 8962007, "Fwd thread id": 1, "Ev Idx": 1530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924408975.166, "dur": 20.444, + "args": { + "External id": 762364,"Sequence number": 8962007, "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": 688924408975.166, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924408978.530, "dur": 16.896, + "args": { + "External id": 762365,"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": 688924408993.900, "dur": 1.379, + "args": { + "External id": 762366,"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": 688924408998.786, "dur": 24.253, + "args": { + "External id": 762367,"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": 688924409029.781, "dur": 77.466, + "args": { + "External id": 762368,"Record function id": 0, "Sequence number": 8962006, "Fwd thread id": 1, "Ev Idx": 1535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924409098.362, "dur": 7.091, + "args": { + "External id": 762369,"Sequence number": 8962006, "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": 688924409098.362, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924409099.433, "dur": 5.805, + "args": { + "External id": 762370,"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": 688924409100.355, "dur": 4.331, + "args": { + "External id": 762371,"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": 688924409104.007, "dur": 0.551, + "args": { + "External id": 762372,"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": 688924409111.905, "dur": 5.799, + "args": { + "External id": 762373,"Record function id": 0, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924409113.733, "dur": 3.400, + "args": { + "External id": 762374,"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": 688924409114.873, "dur": 1.770, + "args": { + "External id": 762375,"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": 688924409115.294, "dur": 1.248, + "args": { + "External id": 762376,"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": 688924409120.893, "dur": 7.821, + "args": { + "External id": 762377,"Record function id": 0, "Sequence number": 8962005, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924409122.271, "dur": 3.432, + "args": { + "External id": 762378,"Sequence number": 8962005, "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": 688924409122.271, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924409123.416, "dur": 2.137, + "args": { + "External id": 762379,"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": 688924409124.573, "dur": 0.878, + "args": { + "External id": 762380,"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": 688924409132.172, "dur": 101.086, + "args": { + "External id": 762381,"Record function id": 0, "Sequence number": 8962004, "Fwd thread id": 1, "Ev Idx": 1548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924409133.056, "dur": 91.603, + "args": { + "External id": 762382,"Sequence number": 8962004, "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": 688924409133.056, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924409137.715, "dur": 2.849, + "args": { + "External id": 762383,"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": 688924409138.117, "dur": 2.011, + "args": { + "External id": 762384,"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": 688924409139.488, "dur": 0.531, + "args": { + "External id": 762385,"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": 688924409141.297, "dur": 40.068, + "args": { + "External id": 762386,"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": 688924409182.580, "dur": 4.813, + "args": { + "External id": 762387,"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": 688924409183.131, "dur": 3.743, + "args": { + "External id": 762388,"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": 688924409186.199, "dur": 0.569, + "args": { + "External id": 762389,"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": 688924409189.161, "dur": 3.731, + "args": { + "External id": 762390,"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": 688924409190.137, "dur": 2.094, + "args": { + "External id": 762391,"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": 688924409191.653, "dur": 0.513, + "args": { + "External id": 762392,"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": 688924409193.302, "dur": 30.686, + "args": { + "External id": 762393,"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": 688924409237.764, "dur": 25.625, + "args": { + "External id": 762394,"Record function id": 0, "Sequence number": 8962003, "Fwd thread id": 1, "Ev Idx": 1561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924409238.810, "dur": 3.813, + "args": { + "External id": 762395,"Sequence number": 8962003, "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": 688924409238.810, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924409240.285, "dur": 2.180, + "args": { + "External id": 762396,"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": 688924409241.067, "dur": 1.271, + "args": { + "External id": 762397,"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": 688924409244.932, "dur": 15.808, + "args": { + "External id": 762398,"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": 688924409267.011, "dur": 8.997, + "args": { + "External id": 762399,"Record function id": 0, "Sequence number": 8962002, "Fwd thread id": 1, "Ev Idx": 1566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183436, "tid": 31338, + "ts": 688924409269.676, "dur": 4.293, + "args": { + "External id": 762400,"Sequence number": 8962002, "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": 688924409269.676, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183436, "tid": 31338, + "ts": 688924409270.594, "dur": 3.174, + "args": { + "External id": 762401,"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": 688924409271.232, "dur": 2.016, + "args": { + "External id": 762402,"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": 688924409272.685, "dur": 0.443, + "args": { + "External id": 762403,"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": 688924409279.780, "dur": 4.864, + "args": { + "External id": 762404,"Record function id": 0, "Ev Idx": 1571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924409281.412, "dur": 2.713, + "args": { + "External id": 762405,"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": 688924409282.274, "dur": 1.553, + "args": { + "External id": 762406,"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": 688924409282.641, "dur": 1.074, + "args": { + "External id": 762407,"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": 688924409288.930, "dur": 356.710, + "args": { + "External id": 762408,"Record function id": 0, "Sequence number": 8962001, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924409290.601, "dur": 320.388, + "args": { + "External id": 762409,"Sequence number": 8962001, "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": 688924409290.601, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 31338, + "ts": 688924409326.344, "dur": 4.127, + "args": { + "External id": 762410,"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": 688924409329.363, "dur": 0.977, + "args": { + "External id": 762411,"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": 688924409344.363, "dur": 5.748, + "args": { + "External id": 762412,"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": 688924409359.893, "dur": 3.818, + "args": { + "External id": 762413,"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": 688924409512.197, "dur": 1.783, + "args": { + "External id": 762414,"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": 688924409518.672, "dur": 34.203, + "args": { + "External id": 762415,"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": 688924409528.936, "dur": 0.748, + "args": { + "External id": 762416,"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": 688924409558.417, "dur": 31.103, + "args": { + "External id": 762417,"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": 688924409561.782, "dur": 27.538, + "args": { + "External id": 762418,"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": 688924409566.361, "dur": 3.714, + "args": { + "External id": 762419,"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": 688924409571.725, "dur": 17.090, + "args": { + "External id": 762420,"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": 688924409593.355, "dur": 2.469, + "args": { + "External id": 762421,"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": 688924409594.467, "dur": 1.213, + "args": { + "External id": 762422,"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": 688924409602.095, "dur": 2.124, + "args": { + "External id": 762423,"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": 688924409603.163, "dur": 0.950, + "args": { + "External id": 762424,"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": 688924409626.048, "dur": 15.147, + "args": { + "External id": 762425,"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": 688924409695.751, "dur": 11.517, + "args": { + "External id": 762426,"Record function id": 0, "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924409699.169, "dur": 7.112, + "args": { + "External id": 762427,"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": 688924409701.525, "dur": 3.130, + "args": { + "External id": 762428,"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": 688924409702.394, "dur": 1.973, + "args": { + "External id": 762429,"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": 688924409713.487, "dur": 2805.958, + "args": { + "External id": 762430,"Record function id": 0, "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 4183436, "tid": 31338, + "ts": 688924409748.702, "dur": 1131.544, + "args": { + "External id": 762431,"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": 688924409776.089, "dur": 1093.779, + "args": { + "External id": 762432,"Record function id": 0, "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 4183436, "tid": 31338, + "ts": 688924409809.835, "dur": 1043.080, + "args": { + "External id": 762433,"Record function id": 0, "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924409902.704, "dur": 10.038, + "args": { + "External id": 762434,"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": 688924409929.893, "dur": 36.421, + "args": { + "External id": 762435,"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": 688924409934.981, "dur": 1.303, + "args": { + "External id": 762436,"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": 688924409938.320, "dur": 2.730, + "args": { + "External id": 762437,"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": 688924409944.283, "dur": 0.349, + "args": { + "External id": 762438,"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": 688924409946.124, "dur": 0.766, + "args": { + "External id": 762439,"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": 688924409948.516, "dur": 0.582, + "args": { + "External id": 762440,"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": 688924409952.483, "dur": 0.415, + "args": { + "External id": 762441,"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": 688924409954.841, "dur": 0.438, + "args": { + "External id": 762442,"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": 688924409956.649, "dur": 1.772, + "args": { + "External id": 762443,"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": 688924409959.821, "dur": 0.544, + "args": { + "External id": 762444,"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": 688924409992.108, "dur": 37.657, + "args": { + "External id": 762445,"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": 688924410074.728, "dur": 116.527, + "args": { + "External id": 762446,"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": 688924410086.543, "dur": 6.233, + "args": { + "External id": 762447,"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": 688924410098.445, "dur": 12.482, + "args": { + "External id": 762448,"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": 688924410104.356, "dur": 6.215, + "args": { + "External id": 762449,"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": 688924410108.440, "dur": 0.785, + "args": { + "External id": 762450,"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": 688924410118.172, "dur": 31.298, + "args": { + "External id": 762451,"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": 688924410120.213, "dur": 0.414, + "args": { + "External id": 762452,"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": 688924410122.950, "dur": 1.966, + "args": { + "External id": 762453,"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": 688924410126.406, "dur": 0.700, + "args": { + "External id": 762454,"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": 688924410128.482, "dur": 0.582, + "args": { + "External id": 762455,"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": 688924410132.176, "dur": 0.422, + "args": { + "External id": 762456,"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": 688924410134.177, "dur": 0.540, + "args": { + "External id": 762457,"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": 688924410135.984, "dur": 1.982, + "args": { + "External id": 762458,"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": 688924410141.113, "dur": 0.408, + "args": { + "External id": 762459,"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": 688924410142.602, "dur": 0.631, + "args": { + "External id": 762460,"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": 688924410160.557, "dur": 22.447, + "args": { + "External id": 762461,"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": 688924410254.383, "dur": 466.298, + "args": { + "External id": 762462,"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": 688924410288.240, "dur": 426.163, + "args": { + "External id": 762463,"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": 688924410299.705, "dur": 407.204, + "args": { + "External id": 762464,"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": 688924410747.878, "dur": 2.833, + "args": { + "External id": 762465,"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": 688924410889.755, "dur": 1604.169, + "args": { + "External id": 762466,"Sequence number": 8962000, "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": 688924410889.755, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924411022.665, "dur": 109.555, + "args": { + "External id": 762467,"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": 688924411175.111, "dur": 40.630, + "args": { + "External id": 762468,"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": 688924411235.209, "dur": 41.230, + "args": { + "External id": 762469,"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": 688924411285.932, "dur": 26.400, + "args": { + "External id": 762470,"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": 688924411318.375, "dur": 31.525, + "args": { + "External id": 762471,"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": 688924411361.939, "dur": 19.792, + "args": { + "External id": 762472,"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": 688924411389.408, "dur": 30.123, + "args": { + "External id": 762473,"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": 688924411445.086, "dur": 23.446, + "args": { + "External id": 762474,"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": 688924411492.675, "dur": 29.785, + "args": { + "External id": 762475,"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": 688924411549.962, "dur": 18.734, + "args": { + "External id": 762476,"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": 688924411583.354, "dur": 13.642, + "args": { + "External id": 762477,"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": 688924411610.768, "dur": 34.089, + "args": { + "External id": 762478,"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": 688924411648.130, "dur": 69.962, + "args": { + "External id": 762479,"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": 688924411751.343, "dur": 201.846, + "args": { + "External id": 762480,"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": 688924411855.049, "dur": 6.315, + "args": { + "External id": 762481,"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": 688924411863.652, "dur": 5.446, + "args": { + "External id": 762482,"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": 688924411993.407, "dur": 25.760, + "args": { + "External id": 762483,"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": 688924412031.489, "dur": 13.854, + "args": { + "External id": 762484,"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": 688924412055.203, "dur": 50.900, + "args": { + "External id": 762485,"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": 688924412112.149, "dur": 30.467, + "args": { + "External id": 762486,"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": 688924412149.631, "dur": 30.084, + "args": { + "External id": 762487,"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": 688924412186.104, "dur": 27.591, + "args": { + "External id": 762488,"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": 688924412219.421, "dur": 26.017, + "args": { + "External id": 762489,"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": 688924412252.961, "dur": 27.148, + "args": { + "External id": 762490,"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": 688924412300.536, "dur": 22.158, + "args": { + "External id": 762491,"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": 688924412341.883, "dur": 24.045, + "args": { + "External id": 762492,"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": 688924412383.327, "dur": 19.318, + "args": { + "External id": 762493,"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": 688924412418.873, "dur": 12.548, + "args": { + "External id": 762494,"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": 688924412450.211, "dur": 14.898, + "args": { + "External id": 762495,"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": 688924412541.375, "dur": 13.896, + "args": { + "External id": 762496,"Record function id": 0, "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924412544.471, "dur": 9.942, + "args": { + "External id": 762497,"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": 688924412548.241, "dur": 5.328, + "args": { + "External id": 762498,"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": 688924412549.735, "dur": 3.735, + "args": { + "External id": 762499,"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": 688924412559.280, "dur": 5.345, + "args": { + "External id": 762500,"Record function id": 0, "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924412560.912, "dur": 3.237, + "args": { + "External id": 762501,"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": 688924412561.970, "dur": 1.622, + "args": { + "External id": 762502,"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": 688924412562.524, "dur": 0.948, + "args": { + "External id": 762503,"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": 688924412567.897, "dur": 4.585, + "args": { + "External id": 762504,"Record function id": 0, "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924412569.299, "dur": 2.758, + "args": { + "External id": 762505,"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": 688924412570.083, "dur": 1.436, + "args": { + "External id": 762506,"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": 688924412570.768, "dur": 0.674, + "args": { + "External id": 762507,"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": 688924412575.656, "dur": 6.212, + "args": { + "External id": 762508,"Record function id": 0, "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924412577.260, "dur": 4.185, + "args": { + "External id": 762509,"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": 688924412577.979, "dur": 2.920, + "args": { + "External id": 762510,"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": 688924412578.472, "dur": 2.357, + "args": { + "External id": 762511,"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": 688924412584.970, "dur": 6.965, + "args": { + "External id": 762512,"Record function id": 0, "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924412586.599, "dur": 4.914, + "args": { + "External id": 762513,"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": 688924412587.378, "dur": 3.523, + "args": { + "External id": 762514,"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": 688924412589.580, "dur": 1.207, + "args": { + "External id": 762515,"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": 688924412595.139, "dur": 4.641, + "args": { + "External id": 762516,"Record function id": 0, "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924412596.693, "dur": 2.671, + "args": { + "External id": 762517,"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": 688924412597.488, "dur": 1.272, + "args": { + "External id": 762518,"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": 688924412597.775, "dur": 0.894, + "args": { + "External id": 762519,"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": 688924412602.961, "dur": 4.555, + "args": { + "External id": 762520,"Record function id": 0, "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924412604.386, "dur": 2.688, + "args": { + "External id": 762521,"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": 688924412605.173, "dur": 1.254, + "args": { + "External id": 762522,"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": 688924412605.469, "dur": 0.884, + "args": { + "External id": 762523,"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": 688924412610.600, "dur": 4.272, + "args": { + "External id": 762524,"Record function id": 0, "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924412612.139, "dur": 2.325, + "args": { + "External id": 762525,"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": 688924412612.760, "dur": 1.059, + "args": { + "External id": 762526,"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": 688924412613.095, "dur": 0.647, + "args": { + "External id": 762527,"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": 688924412619.865, "dur": 5.726, + "args": { + "External id": 762528,"Record function id": 0, "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924412621.136, "dur": 4.058, + "args": { + "External id": 762529,"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": 688924412621.912, "dur": 2.659, + "args": { + "External id": 762530,"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": 688924412623.756, "dur": 0.724, + "args": { + "External id": 762531,"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": 688924412630.366, "dur": 57778.411, + "args": { + "External id": 762532,"Record function id": 0, "Sequence number": 8961999, "Fwd thread id": 1, "Ev Idx": 1699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924412631.691, "dur": 57768.798, + "args": { + "External id": 762533,"Sequence number": 8961999, "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": 688924412631.691, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 4183436, "tid": 31338, + "ts": 688924412703.689, "dur": 44.354, + "args": { + "External id": 762534,"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": 688924412756.978, "dur": 106.295, + "args": { + "External id": 762535,"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": 688924412871.192, "dur": 57521.450, + "args": { + "External id": 762536,"Record function id": 0, "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924412927.747, "dur": 9.446, + "args": { + "External id": 762537,"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": 688924412948.185, "dur": 5.577, + "args": { + "External id": 762538,"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": 688924412971.926, "dur": 56624.661, + "args": { + "External id": 762539,"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": 688924412985.992, "dur": 56601.900, + "args": { + "External id": 762540,"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": 688924413065.409, "dur": 8.173, + "args": { + "External id": 762541,"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": 688924413080.175, "dur": 56470.035, + "args": { + "External id": 762542,"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": 688924413082.759, "dur": 56466.798, + "args": { + "External id": 762543,"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": 688924413090.127, "dur": 6.442, + "args": { + "External id": 762544,"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": 688924413098.300, "dur": 56447.205, + "args": { + "External id": 762545,"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": 688924469716.997, "dur": 10.245, + "args": { + "External id": 762546,"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": 688924469720.191, "dur": 6.564, + "args": { + "External id": 762547,"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": 688924469762.283, "dur": 311.092, + "args": { + "External id": 762548,"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": 688924469803.491, "dur": 264.701, + "args": { + "External id": 762549,"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": 688924469817.167, "dur": 246.315, + "args": { + "External id": 762550,"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": 688924470096.500, "dur": 2.420, + "args": { + "External id": 762551,"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": 688924470159.534, "dur": 6.424, + "args": { + "External id": 762552,"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": 688924470219.371, "dur": 1.212, + "args": { + "External id": 762553,"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": 688924470238.958, "dur": 1.333, + "args": { + "External id": 762554,"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": 688924470255.450, "dur": 1.225, + "args": { + "External id": 762555,"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": 688924470269.619, "dur": 0.765, + "args": { + "External id": 762556,"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": 688924470282.749, "dur": 0.768, + "args": { + "External id": 762557,"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": 688924470295.077, "dur": 1.327, + "args": { + "External id": 762558,"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": 688924470313.250, "dur": 2.469, + "args": { + "External id": 762559,"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": 688924470327.612, "dur": 1.016, + "args": { + "External id": 762560,"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": 688924470422.962, "dur": 2877.485, + "args": { + "External id": 762561,"Record function id": 0, "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 4183436, "tid": 31338, + "ts": 688924470443.769, "dur": 1111.059, + "args": { + "External id": 762562,"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": 688924470460.740, "dur": 405.296, + "args": { + "External id": 762563,"Record function id": 0, "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924470549.232, "dur": 4.190, + "args": { + "External id": 762564,"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": 688924470557.311, "dur": 1.074, + "args": { + "External id": 762565,"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": 688924470560.250, "dur": 1.202, + "args": { + "External id": 762566,"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": 688924470563.372, "dur": 2.583, + "args": { + "External id": 762567,"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": 688924470569.635, "dur": 1.061, + "args": { + "External id": 762568,"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": 688924470572.383, "dur": 1.071, + "args": { + "External id": 762569,"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": 688924470575.283, "dur": 2.404, + "args": { + "External id": 762570,"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": 688924470579.578, "dur": 1.021, + "args": { + "External id": 762571,"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": 688924470584.139, "dur": 1.226, + "args": { + "External id": 762572,"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": 688924470587.061, "dur": 4.180, + "args": { + "External id": 762573,"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": 688924470608.583, "dur": 221.700, + "args": { + "External id": 762574,"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": 688924470626.197, "dur": 198.475, + "args": { + "External id": 762575,"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": 688924470697.149, "dur": 14.120, + "args": { + "External id": 762576,"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": 688924470714.695, "dur": 68.223, + "args": { + "External id": 762577,"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": 688924470717.042, "dur": 65.538, + "args": { + "External id": 762578,"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": 688924470721.229, "dur": 8.314, + "args": { + "External id": 762579,"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": 688924470733.445, "dur": 48.564, + "args": { + "External id": 762580,"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": 688924470966.368, "dur": 579.978, + "args": { + "External id": 762581,"Record function id": 0, "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 4183436, "tid": 31338, + "ts": 688924470986.237, "dur": 547.527, + "args": { + "External id": 762582,"Record function id": 0, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924471049.960, "dur": 5.523, + "args": { + "External id": 762583,"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": 688924471071.828, "dur": 37.219, + "args": { + "External id": 762584,"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": 688924471077.028, "dur": 1.665, + "args": { + "External id": 762585,"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": 688924471080.737, "dur": 0.616, + "args": { + "External id": 762586,"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": 688924471083.243, "dur": 0.493, + "args": { + "External id": 762587,"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": 688924471086.666, "dur": 0.613, + "args": { + "External id": 762588,"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": 688924471089.006, "dur": 0.484, + "args": { + "External id": 762589,"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": 688924471091.206, "dur": 2.128, + "args": { + "External id": 762590,"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": 688924471094.975, "dur": 2.272, + "args": { + "External id": 762591,"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": 688924471098.644, "dur": 0.528, + "args": { + "External id": 762592,"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": 688924471102.452, "dur": 0.502, + "args": { + "External id": 762593,"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": 688924471123.249, "dur": 32.576, + "args": { + "External id": 762594,"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": 688924471188.719, "dur": 108.929, + "args": { + "External id": 762595,"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": 688924471198.540, "dur": 4.967, + "args": { + "External id": 762596,"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": 688924471208.491, "dur": 10.227, + "args": { + "External id": 762597,"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": 688924471212.386, "dur": 5.960, + "args": { + "External id": 762598,"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": 688924471216.380, "dur": 0.549, + "args": { + "External id": 762599,"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": 688924471225.230, "dur": 33.697, + "args": { + "External id": 762600,"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": 688924471227.413, "dur": 0.252, + "args": { + "External id": 762601,"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": 688924471229.493, "dur": 1.726, + "args": { + "External id": 762602,"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": 688924471232.605, "dur": 0.552, + "args": { + "External id": 762603,"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": 688924471234.866, "dur": 1.932, + "args": { + "External id": 762604,"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": 688924471240.537, "dur": 0.320, + "args": { + "External id": 762605,"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": 688924471242.467, "dur": 0.308, + "args": { + "External id": 762606,"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": 688924471247.366, "dur": 0.438, + "args": { + "External id": 762607,"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": 688924471250.143, "dur": 0.367, + "args": { + "External id": 762608,"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": 688924471252.351, "dur": 0.458, + "args": { + "External id": 762609,"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": 688924471271.174, "dur": 18.622, + "args": { + "External id": 762610,"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": 688924471345.395, "dur": 120.504, + "args": { + "External id": 762611,"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": 688924471373.541, "dur": 89.019, + "args": { + "External id": 762612,"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": 688924471383.890, "dur": 74.566, + "args": { + "External id": 762613,"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": 688924471484.495, "dur": 1.787, + "args": { + "External id": 762614,"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": 688924471562.512, "dur": 1716.128, + "args": { + "External id": 762615,"Sequence number": 8961998, "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": 688924471562.512, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924471719.234, "dur": 119.602, + "args": { + "External id": 762616,"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": 688924471891.843, "dur": 41.105, + "args": { + "External id": 762617,"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": 688924471954.610, "dur": 47.091, + "args": { + "External id": 762618,"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": 688924472011.628, "dur": 27.138, + "args": { + "External id": 762619,"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": 688924472046.777, "dur": 31.715, + "args": { + "External id": 762620,"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": 688924472085.429, "dur": 21.461, + "args": { + "External id": 762621,"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": 688924472114.466, "dur": 31.344, + "args": { + "External id": 762622,"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": 688924472171.256, "dur": 27.011, + "args": { + "External id": 762623,"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": 688924472217.316, "dur": 27.282, + "args": { + "External id": 762624,"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": 688924472267.204, "dur": 20.036, + "args": { + "External id": 762625,"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": 688924472302.162, "dur": 15.302, + "args": { + "External id": 762626,"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": 688924472324.592, "dur": 39.534, + "args": { + "External id": 762627,"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": 688924472367.747, "dur": 29.876, + "args": { + "External id": 762628,"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": 688924472431.070, "dur": 169.254, + "args": { + "External id": 762629,"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": 688924472509.046, "dur": 7.626, + "args": { + "External id": 762630,"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": 688924472518.719, "dur": 2.479, + "args": { + "External id": 762631,"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": 688924472640.620, "dur": 69.568, + "args": { + "External id": 762632,"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": 688924472728.697, "dur": 16.015, + "args": { + "External id": 762633,"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": 688924472754.603, "dur": 70.995, + "args": { + "External id": 762634,"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": 688924472849.317, "dur": 47.271, + "args": { + "External id": 762635,"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": 688924472908.610, "dur": 31.796, + "args": { + "External id": 762636,"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": 688924472944.489, "dur": 26.188, + "args": { + "External id": 762637,"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": 688924472977.268, "dur": 29.392, + "args": { + "External id": 762638,"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": 688924473013.546, "dur": 26.793, + "args": { + "External id": 762639,"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": 688924473068.225, "dur": 24.831, + "args": { + "External id": 762640,"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": 688924473114.314, "dur": 28.123, + "args": { + "External id": 762641,"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": 688924473162.728, "dur": 16.761, + "args": { + "External id": 762642,"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": 688924473197.030, "dur": 15.195, + "args": { + "External id": 762643,"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": 688924473230.797, "dur": 16.655, + "args": { + "External id": 762644,"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": 688924473322.026, "dur": 15.411, + "args": { + "External id": 762645,"Record function id": 0, "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924473325.671, "dur": 10.842, + "args": { + "External id": 762646,"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": 688924473329.999, "dur": 5.549, + "args": { + "External id": 762647,"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": 688924473331.488, "dur": 3.952, + "args": { + "External id": 762648,"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": 688924473341.799, "dur": 5.225, + "args": { + "External id": 762649,"Record function id": 0, "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924473343.553, "dur": 3.033, + "args": { + "External id": 762650,"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": 688924473344.399, "dur": 1.622, + "args": { + "External id": 762651,"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": 688924473345.124, "dur": 0.795, + "args": { + "External id": 762652,"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": 688924473350.707, "dur": 6.603, + "args": { + "External id": 762653,"Record function id": 0, "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924473352.294, "dur": 4.611, + "args": { + "External id": 762654,"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": 688924473353.043, "dur": 3.381, + "args": { + "External id": 762655,"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": 688924473353.731, "dur": 2.591, + "args": { + "External id": 762656,"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": 688924473360.762, "dur": 4.788, + "args": { + "External id": 762657,"Record function id": 0, "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924473362.318, "dur": 2.805, + "args": { + "External id": 762658,"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": 688924473362.855, "dur": 1.551, + "args": { + "External id": 762659,"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": 688924473363.297, "dur": 1.023, + "args": { + "External id": 762660,"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": 688924473368.995, "dur": 4.745, + "args": { + "External id": 762661,"Record function id": 0, "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924473370.239, "dur": 2.997, + "args": { + "External id": 762662,"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": 688924473371.346, "dur": 1.140, + "args": { + "External id": 762663,"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": 688924473371.837, "dur": 0.574, + "args": { + "External id": 762664,"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": 688924473377.135, "dur": 4.473, + "args": { + "External id": 762665,"Record function id": 0, "Ev Idx": 1832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924473378.661, "dur": 2.517, + "args": { + "External id": 762666,"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": 688924473379.310, "dur": 1.317, + "args": { + "External id": 762667,"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": 688924473379.921, "dur": 0.642, + "args": { + "External id": 762668,"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": 688924473385.095, "dur": 4.626, + "args": { + "External id": 762669,"Record function id": 0, "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924473386.887, "dur": 2.417, + "args": { + "External id": 762670,"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": 688924473387.691, "dur": 0.915, + "args": { + "External id": 762671,"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": 688924473387.995, "dur": 0.534, + "args": { + "External id": 762672,"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": 688924473393.063, "dur": 5.274, + "args": { + "External id": 762673,"Record function id": 0, "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924473394.402, "dur": 3.521, + "args": { + "External id": 762674,"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": 688924473394.839, "dur": 2.668, + "args": { + "External id": 762675,"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": 688924473396.818, "dur": 0.612, + "args": { + "External id": 762676,"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": 688924473401.588, "dur": 3.801, + "args": { + "External id": 762677,"Record function id": 0, "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924473403.068, "dur": 1.856, + "args": { + "External id": 762678,"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": 688924473403.515, "dur": 0.981, + "args": { + "External id": 762679,"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": 688924473403.840, "dur": 0.590, + "args": { + "External id": 762680,"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": 688924473409.593, "dur": 15011.715, + "args": { + "External id": 762681,"Record function id": 0, "Sequence number": 8961997, "Fwd thread id": 1, "Ev Idx": 1848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924473410.780, "dur": 15002.073, + "args": { + "External id": 762682,"Sequence number": 8961997, "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": 688924473410.780, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 4183436, "tid": 31338, + "ts": 688924473440.229, "dur": 39.724, + "args": { + "External id": 762683,"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": 688924473487.735, "dur": 69.841, + "args": { + "External id": 762684,"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": 688924473565.289, "dur": 14840.178, + "args": { + "External id": 762685,"Record function id": 0, "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924473702.773, "dur": 8.220, + "args": { + "External id": 762686,"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": 688924473722.192, "dur": 6.786, + "args": { + "External id": 762687,"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": 688924473745.331, "dur": 13958.743, + "args": { + "External id": 762688,"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": 688924473758.977, "dur": 13935.848, + "args": { + "External id": 762689,"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": 688924473819.952, "dur": 17.472, + "args": { + "External id": 762690,"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": 688924473843.174, "dur": 13793.105, + "args": { + "External id": 762691,"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": 688924473845.686, "dur": 13790.000, + "args": { + "External id": 762692,"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": 688924473851.823, "dur": 5.559, + "args": { + "External id": 762693,"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": 688924473860.758, "dur": 13771.731, + "args": { + "External id": 762694,"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": 688924487804.450, "dur": 10.792, + "args": { + "External id": 762695,"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": 688924487807.571, "dur": 7.008, + "args": { + "External id": 762696,"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": 688924487845.089, "dur": 266.904, + "args": { + "External id": 762697,"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": 688924487873.883, "dur": 233.836, + "args": { + "External id": 762698,"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": 688924487887.076, "dur": 215.779, + "args": { + "External id": 762699,"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": 688924488131.444, "dur": 2.175, + "args": { + "External id": 762700,"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": 688924488189.447, "dur": 5.700, + "args": { + "External id": 762701,"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": 688924488239.074, "dur": 1.307, + "args": { + "External id": 762702,"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": 688924488260.421, "dur": 2.993, + "args": { + "External id": 762703,"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": 688924488276.663, "dur": 1.131, + "args": { + "External id": 762704,"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": 688924488291.572, "dur": 0.792, + "args": { + "External id": 762705,"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": 688924488303.432, "dur": 0.964, + "args": { + "External id": 762706,"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": 688924488316.331, "dur": 2.655, + "args": { + "External id": 762707,"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": 688924488331.219, "dur": 2.646, + "args": { + "External id": 762708,"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": 688924488345.125, "dur": 0.969, + "args": { + "External id": 762709,"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": 688924488435.268, "dur": 2808.460, + "args": { + "External id": 762710,"Record function id": 0, "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 4183436, "tid": 31338, + "ts": 688924488454.233, "dur": 1072.232, + "args": { + "External id": 762711,"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": 688924488469.089, "dur": 391.539, + "args": { + "External id": 762712,"Record function id": 0, "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924488548.182, "dur": 3.897, + "args": { + "External id": 762713,"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": 688924488555.605, "dur": 1.128, + "args": { + "External id": 762714,"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": 688924488558.472, "dur": 3.587, + "args": { + "External id": 762715,"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": 688924488565.057, "dur": 1.039, + "args": { + "External id": 762716,"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": 688924488567.725, "dur": 1.237, + "args": { + "External id": 762717,"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": 688924488570.401, "dur": 1.148, + "args": { + "External id": 762718,"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": 688924488573.124, "dur": 2.087, + "args": { + "External id": 762719,"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": 688924488578.299, "dur": 1.005, + "args": { + "External id": 762720,"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": 688924488580.965, "dur": 1.056, + "args": { + "External id": 762721,"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": 688924488583.404, "dur": 1.044, + "args": { + "External id": 762722,"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": 688924488600.910, "dur": 222.805, + "args": { + "External id": 762723,"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": 688924488616.804, "dur": 201.382, + "args": { + "External id": 762724,"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": 688924488633.411, "dur": 15.084, + "args": { + "External id": 762725,"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": 688924488702.367, "dur": 67.826, + "args": { + "External id": 762726,"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": 688924488705.719, "dur": 64.120, + "args": { + "External id": 762727,"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": 688924488710.510, "dur": 8.311, + "args": { + "External id": 762728,"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": 688924488720.887, "dur": 48.466, + "args": { + "External id": 762729,"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": 688924488957.333, "dur": 561.639, + "args": { + "External id": 762730,"Record function id": 0, "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 4183436, "tid": 31338, + "ts": 688924488975.602, "dur": 530.954, + "args": { + "External id": 762731,"Record function id": 0, "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924489038.369, "dur": 5.560, + "args": { + "External id": 762732,"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": 688924489058.818, "dur": 36.614, + "args": { + "External id": 762733,"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": 688924489063.674, "dur": 1.726, + "args": { + "External id": 762734,"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": 688924489069.676, "dur": 0.542, + "args": { + "External id": 762735,"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": 688924489071.813, "dur": 0.557, + "args": { + "External id": 762736,"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": 688924489073.944, "dur": 1.780, + "args": { + "External id": 762737,"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": 688924489077.611, "dur": 0.533, + "args": { + "External id": 762738,"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": 688924489079.862, "dur": 1.947, + "args": { + "External id": 762739,"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": 688924489085.071, "dur": 0.261, + "args": { + "External id": 762740,"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": 688924489086.782, "dur": 0.248, + "args": { + "External id": 762741,"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": 688924489088.580, "dur": 0.508, + "args": { + "External id": 762742,"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": 688924489105.990, "dur": 28.896, + "args": { + "External id": 762743,"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": 688924489165.802, "dur": 105.479, + "args": { + "External id": 762744,"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": 688924489175.663, "dur": 3.362, + "args": { + "External id": 762745,"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": 688924489183.768, "dur": 11.935, + "args": { + "External id": 762746,"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": 688924489188.021, "dur": 7.272, + "args": { + "External id": 762747,"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": 688924489192.441, "dur": 1.573, + "args": { + "External id": 762748,"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": 688924489202.355, "dur": 32.952, + "args": { + "External id": 762749,"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": 688924489204.337, "dur": 0.614, + "args": { + "External id": 762750,"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": 688924489206.511, "dur": 0.586, + "args": { + "External id": 762751,"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": 688924489213.406, "dur": 2.636, + "args": { + "External id": 762752,"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": 688924489218.539, "dur": 0.292, + "args": { + "External id": 762753,"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": 688924489220.168, "dur": 0.326, + "args": { + "External id": 762754,"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": 688924489221.919, "dur": 1.289, + "args": { + "External id": 762755,"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": 688924489224.457, "dur": 0.293, + "args": { + "External id": 762756,"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": 688924489226.091, "dur": 0.279, + "args": { + "External id": 762757,"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": 688924489229.017, "dur": 0.273, + "args": { + "External id": 762758,"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": 688924489244.431, "dur": 19.386, + "args": { + "External id": 762759,"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": 688924489313.399, "dur": 127.215, + "args": { + "External id": 762760,"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": 688924489346.122, "dur": 91.064, + "args": { + "External id": 762761,"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": 688924489355.624, "dur": 77.175, + "args": { + "External id": 762762,"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": 688924489457.877, "dur": 1.999, + "args": { + "External id": 762763,"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": 688924489533.524, "dur": 1686.978, + "args": { + "External id": 762764,"Sequence number": 8961996, "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": 688924489533.524, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924489642.933, "dur": 159.232, + "args": { + "External id": 762765,"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": 688924489852.202, "dur": 41.070, + "args": { + "External id": 762766,"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": 688924489914.331, "dur": 44.699, + "args": { + "External id": 762767,"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": 688924489970.958, "dur": 26.560, + "args": { + "External id": 762768,"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": 688924490002.991, "dur": 36.067, + "args": { + "External id": 762769,"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": 688924490045.633, "dur": 22.188, + "args": { + "External id": 762770,"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": 688924490094.029, "dur": 30.746, + "args": { + "External id": 762771,"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": 688924490154.870, "dur": 23.701, + "args": { + "External id": 762772,"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": 688924490198.688, "dur": 27.144, + "args": { + "External id": 762773,"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": 688924490246.269, "dur": 19.464, + "args": { + "External id": 762774,"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": 688924490280.005, "dur": 15.476, + "args": { + "External id": 762775,"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": 688924490303.979, "dur": 37.400, + "args": { + "External id": 762776,"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": 688924490344.731, "dur": 32.336, + "args": { + "External id": 762777,"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": 688924490410.691, "dur": 165.928, + "args": { + "External id": 762778,"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": 688924490485.822, "dur": 6.424, + "args": { + "External id": 762779,"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": 688924490494.231, "dur": 2.267, + "args": { + "External id": 762780,"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": 688924490613.020, "dur": 23.233, + "args": { + "External id": 762781,"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": 688924490649.416, "dur": 51.912, + "args": { + "External id": 762782,"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": 688924490712.504, "dur": 48.171, + "args": { + "External id": 762783,"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": 688924490766.558, "dur": 44.965, + "args": { + "External id": 762784,"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": 688924490822.849, "dur": 51.933, + "args": { + "External id": 762785,"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": 688924490884.747, "dur": 34.032, + "args": { + "External id": 762786,"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": 688924490928.508, "dur": 25.792, + "args": { + "External id": 762787,"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": 688924490961.540, "dur": 29.604, + "args": { + "External id": 762788,"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": 688924491014.826, "dur": 30.128, + "args": { + "External id": 762789,"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": 688924491064.676, "dur": 24.126, + "args": { + "External id": 762790,"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": 688924491108.880, "dur": 18.785, + "args": { + "External id": 762791,"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": 688924491142.224, "dur": 19.319, + "args": { + "External id": 762792,"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": 688924491176.641, "dur": 15.710, + "args": { + "External id": 762793,"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": 688924491265.974, "dur": 15.034, + "args": { + "External id": 762794,"Record function id": 0, "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924491269.796, "dur": 10.253, + "args": { + "External id": 762795,"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": 688924491273.902, "dur": 5.283, + "args": { + "External id": 762796,"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": 688924491275.099, "dur": 4.002, + "args": { + "External id": 762797,"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": 688924491285.102, "dur": 7.314, + "args": { + "External id": 762798,"Record function id": 0, "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924491286.954, "dur": 5.002, + "args": { + "External id": 762799,"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": 688924491287.857, "dur": 3.539, + "args": { + "External id": 762800,"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": 688924491288.341, "dur": 2.991, + "args": { + "External id": 762801,"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": 688924491295.719, "dur": 4.915, + "args": { + "External id": 762802,"Record function id": 0, "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924491297.441, "dur": 2.786, + "args": { + "External id": 762803,"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": 688924491297.972, "dur": 1.542, + "args": { + "External id": 762804,"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": 688924491298.690, "dur": 0.710, + "args": { + "External id": 762805,"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": 688924491303.880, "dur": 4.112, + "args": { + "External id": 762806,"Record function id": 0, "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924491305.079, "dur": 2.477, + "args": { + "External id": 762807,"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": 688924491305.825, "dur": 1.178, + "args": { + "External id": 762808,"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": 688924491306.359, "dur": 0.556, + "args": { + "External id": 762809,"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": 688924491311.230, "dur": 4.143, + "args": { + "External id": 762810,"Record function id": 0, "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924491312.606, "dur": 2.370, + "args": { + "External id": 762811,"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": 688924491313.214, "dur": 1.218, + "args": { + "External id": 762812,"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": 688924491313.515, "dur": 0.850, + "args": { + "External id": 762813,"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": 688924491318.512, "dur": 4.214, + "args": { + "External id": 762814,"Record function id": 0, "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924491319.970, "dur": 2.362, + "args": { + "External id": 762815,"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": 688924491320.596, "dur": 1.328, + "args": { + "External id": 762816,"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": 688924491321.162, "dur": 0.692, + "args": { + "External id": 762817,"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": 688924491325.890, "dur": 3.633, + "args": { + "External id": 762818,"Record function id": 0, "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924491327.269, "dur": 1.836, + "args": { + "External id": 762819,"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": 688924491327.725, "dur": 1.006, + "args": { + "External id": 762820,"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": 688924491327.985, "dur": 0.668, + "args": { + "External id": 762821,"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": 688924491332.575, "dur": 5.256, + "args": { + "External id": 762822,"Record function id": 0, "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924491333.891, "dur": 3.539, + "args": { + "External id": 762823,"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": 688924491334.363, "dur": 2.667, + "args": { + "External id": 762824,"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": 688924491336.345, "dur": 0.619, + "args": { + "External id": 762825,"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": 688924491340.921, "dur": 5.621, + "args": { + "External id": 762826,"Record function id": 0, "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924491342.244, "dur": 3.896, + "args": { + "External id": 762827,"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": 688924491342.699, "dur": 2.805, + "args": { + "External id": 762828,"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": 688924491343.024, "dur": 2.412, + "args": { + "External id": 762829,"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": 688924491351.718, "dur": 14999.669, + "args": { + "External id": 762830,"Record function id": 0, "Sequence number": 8961995, "Fwd thread id": 1, "Ev Idx": 1997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924491352.862, "dur": 14990.082, + "args": { + "External id": 762831,"Sequence number": 8961995, "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": 688924491352.862, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 4183436, "tid": 31338, + "ts": 688924491383.878, "dur": 36.448, + "args": { + "External id": 762832,"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": 688924491427.680, "dur": 69.686, + "args": { + "External id": 762833,"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": 688924491504.672, "dur": 14829.676, + "args": { + "External id": 762834,"Record function id": 0, "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924491594.182, "dur": 6.319, + "args": { + "External id": 762835,"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": 688924491609.708, "dur": 4.425, + "args": { + "External id": 762836,"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": 688924491627.194, "dur": 13938.787, + "args": { + "External id": 762837,"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": 688924491640.401, "dur": 13916.428, + "args": { + "External id": 762838,"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": 688924491743.535, "dur": 14.464, + "args": { + "External id": 762839,"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": 688924491762.855, "dur": 13756.811, + "args": { + "External id": 762840,"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": 688924491765.301, "dur": 13753.580, + "args": { + "External id": 762841,"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": 688924491769.438, "dur": 6.841, + "args": { + "External id": 762842,"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": 688924491779.308, "dur": 13736.409, + "args": { + "External id": 762843,"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": 688924505678.174, "dur": 10.805, + "args": { + "External id": 762844,"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": 688924505681.069, "dur": 7.337, + "args": { + "External id": 762845,"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": 688924505716.791, "dur": 321.508, + "args": { + "External id": 762846,"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": 688924505746.146, "dur": 287.244, + "args": { + "External id": 762847,"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": 688924505758.474, "dur": 269.369, + "args": { + "External id": 762848,"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": 688924506059.427, "dur": 2.719, + "args": { + "External id": 762849,"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": 688924506119.572, "dur": 6.298, + "args": { + "External id": 762850,"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": 688924506170.978, "dur": 3.284, + "args": { + "External id": 762851,"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": 688924506190.551, "dur": 1.393, + "args": { + "External id": 762852,"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": 688924506203.647, "dur": 1.140, + "args": { + "External id": 762853,"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": 688924506218.309, "dur": 0.942, + "args": { + "External id": 762854,"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": 688924506230.587, "dur": 2.789, + "args": { + "External id": 762855,"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": 688924506245.018, "dur": 1.092, + "args": { + "External id": 762856,"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": 688924506258.830, "dur": 2.620, + "args": { + "External id": 762857,"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": 688924506272.229, "dur": 1.120, + "args": { + "External id": 762858,"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": 688924506366.274, "dur": 2799.150, + "args": { + "External id": 762859,"Record function id": 0, "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 4183436, "tid": 31338, + "ts": 688924506385.712, "dur": 1088.012, + "args": { + "External id": 762860,"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": 688924506400.103, "dur": 347.380, + "args": { + "External id": 762861,"Record function id": 0, "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924506481.478, "dur": 5.690, + "args": { + "External id": 762862,"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": 688924506490.138, "dur": 1.064, + "args": { + "External id": 762863,"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": 688924506493.130, "dur": 1.062, + "args": { + "External id": 762864,"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": 688924506496.883, "dur": 0.739, + "args": { + "External id": 762865,"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": 688924506499.278, "dur": 1.238, + "args": { + "External id": 762866,"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": 688924506501.858, "dur": 0.854, + "args": { + "External id": 762867,"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": 688924506504.191, "dur": 1.557, + "args": { + "External id": 762868,"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": 688924506507.929, "dur": 0.705, + "args": { + "External id": 762869,"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": 688924506510.080, "dur": 2.446, + "args": { + "External id": 762870,"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": 688924506514.044, "dur": 0.945, + "args": { + "External id": 762871,"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": 688924506531.346, "dur": 184.314, + "args": { + "External id": 762872,"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": 688924506546.917, "dur": 163.756, + "args": { + "External id": 762873,"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": 688924506564.377, "dur": 11.880, + "args": { + "External id": 762874,"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": 688924506578.969, "dur": 60.882, + "args": { + "External id": 762875,"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": 688924506581.458, "dur": 58.131, + "args": { + "External id": 762876,"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": 688924506585.875, "dur": 6.846, + "args": { + "External id": 762877,"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": 688924506594.343, "dur": 44.661, + "args": { + "External id": 762878,"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": 688924506866.861, "dur": 599.353, + "args": { + "External id": 762879,"Record function id": 0, "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 4183436, "tid": 31338, + "ts": 688924506884.471, "dur": 568.532, + "args": { + "External id": 762880,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924506982.266, "dur": 6.872, + "args": { + "External id": 762881,"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": 688924507005.413, "dur": 33.133, + "args": { + "External id": 762882,"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": 688924507010.438, "dur": 2.515, + "args": { + "External id": 762883,"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": 688924507014.769, "dur": 0.423, + "args": { + "External id": 762884,"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": 688924507016.647, "dur": 0.247, + "args": { + "External id": 762885,"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": 688924507020.350, "dur": 2.122, + "args": { + "External id": 762886,"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": 688924507024.253, "dur": 0.322, + "args": { + "External id": 762887,"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": 688924507026.218, "dur": 0.394, + "args": { + "External id": 762888,"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": 688924507028.989, "dur": 0.396, + "args": { + "External id": 762889,"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": 688924507031.070, "dur": 0.323, + "args": { + "External id": 762890,"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": 688924507032.925, "dur": 1.440, + "args": { + "External id": 762891,"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": 688924507050.166, "dur": 34.986, + "args": { + "External id": 762892,"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": 688924507118.103, "dur": 107.003, + "args": { + "External id": 762893,"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": 688924507127.947, "dur": 3.285, + "args": { + "External id": 762894,"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": 688924507136.425, "dur": 9.829, + "args": { + "External id": 762895,"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": 688924507140.345, "dur": 5.493, + "args": { + "External id": 762896,"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": 688924507143.928, "dur": 0.697, + "args": { + "External id": 762897,"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": 688924507156.651, "dur": 27.596, + "args": { + "External id": 762898,"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": 688924507158.576, "dur": 2.449, + "args": { + "External id": 762899,"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": 688924507162.814, "dur": 0.442, + "args": { + "External id": 762900,"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": 688924507164.460, "dur": 1.233, + "args": { + "External id": 762901,"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": 688924507167.192, "dur": 0.298, + "args": { + "External id": 762902,"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": 688924507168.945, "dur": 0.407, + "args": { + "External id": 762903,"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": 688924507171.789, "dur": 0.446, + "args": { + "External id": 762904,"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": 688924507173.597, "dur": 0.348, + "args": { + "External id": 762905,"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": 688924507175.710, "dur": 0.273, + "args": { + "External id": 762906,"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": 688924507178.326, "dur": 2.403, + "args": { + "External id": 762907,"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": 688924507195.474, "dur": 22.636, + "args": { + "External id": 762908,"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": 688924507270.984, "dur": 116.635, + "args": { + "External id": 762909,"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": 688924507298.075, "dur": 85.901, + "args": { + "External id": 762910,"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": 688924507307.393, "dur": 72.614, + "args": { + "External id": 762911,"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": 688924507402.112, "dur": 1.808, + "args": { + "External id": 762912,"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": 688924507480.948, "dur": 1662.156, + "args": { + "External id": 762913,"Sequence number": 8961994, "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": 688924507480.948, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924507592.139, "dur": 148.421, + "args": { + "External id": 762914,"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": 688924507783.815, "dur": 55.260, + "args": { + "External id": 762915,"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": 688924507860.657, "dur": 51.069, + "args": { + "External id": 762916,"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": 688924507921.714, "dur": 30.217, + "args": { + "External id": 762917,"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": 688924507957.395, "dur": 33.059, + "args": { + "External id": 762918,"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": 688924507997.078, "dur": 22.592, + "args": { + "External id": 762919,"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": 688924508028.110, "dur": 27.292, + "args": { + "External id": 762920,"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": 688924508078.711, "dur": 23.004, + "args": { + "External id": 762921,"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": 688924508118.823, "dur": 26.085, + "args": { + "External id": 762922,"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": 688924508163.130, "dur": 20.880, + "args": { + "External id": 762923,"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": 688924508194.568, "dur": 15.077, + "args": { + "External id": 762924,"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": 688924508219.236, "dur": 35.638, + "args": { + "External id": 762925,"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": 688924508258.101, "dur": 32.394, + "args": { + "External id": 762926,"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": 688924508324.126, "dur": 178.252, + "args": { + "External id": 762927,"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": 688924508407.532, "dur": 6.600, + "args": { + "External id": 762928,"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": 688924508415.946, "dur": 2.553, + "args": { + "External id": 762929,"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": 688924508533.170, "dur": 27.172, + "args": { + "External id": 762930,"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": 688924508570.681, "dur": 13.863, + "args": { + "External id": 762931,"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": 688924508591.681, "dur": 45.753, + "args": { + "External id": 762932,"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": 688924508644.558, "dur": 70.770, + "args": { + "External id": 762933,"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": 688924508725.756, "dur": 29.354, + "args": { + "External id": 762934,"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": 688924508759.656, "dur": 62.724, + "args": { + "External id": 762935,"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": 688924508844.892, "dur": 40.464, + "args": { + "External id": 762936,"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": 688924508895.844, "dur": 31.241, + "args": { + "External id": 762937,"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": 688924508947.969, "dur": 27.909, + "args": { + "External id": 762938,"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": 688924508996.575, "dur": 23.674, + "args": { + "External id": 762939,"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": 688924509037.056, "dur": 17.108, + "args": { + "External id": 762940,"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": 688924509070.540, "dur": 15.257, + "args": { + "External id": 762941,"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": 688924509097.630, "dur": 17.376, + "args": { + "External id": 762942,"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": 688924509190.548, "dur": 16.168, + "args": { + "External id": 762943,"Record function id": 0, "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924509193.888, "dur": 11.961, + "args": { + "External id": 762944,"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": 688924509197.833, "dur": 7.194, + "args": { + "External id": 762945,"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": 688924509199.597, "dur": 5.314, + "args": { + "External id": 762946,"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": 688924509210.783, "dur": 4.964, + "args": { + "External id": 762947,"Record function id": 0, "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924509212.354, "dur": 2.783, + "args": { + "External id": 762948,"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": 688924509213.041, "dur": 1.555, + "args": { + "External id": 762949,"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": 688924509213.600, "dur": 0.872, + "args": { + "External id": 762950,"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": 688924509219.007, "dur": 4.860, + "args": { + "External id": 762951,"Record function id": 0, "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924509220.996, "dur": 2.461, + "args": { + "External id": 762952,"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": 688924509221.668, "dur": 1.211, + "args": { + "External id": 762953,"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": 688924509222.134, "dur": 0.667, + "args": { + "External id": 762954,"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": 688924509227.019, "dur": 4.593, + "args": { + "External id": 762955,"Record function id": 0, "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924509228.466, "dur": 2.721, + "args": { + "External id": 762956,"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": 688924509229.758, "dur": 1.027, + "args": { + "External id": 762957,"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": 688924509230.091, "dur": 0.628, + "args": { + "External id": 762958,"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": 688924509237.777, "dur": 3.974, + "args": { + "External id": 762959,"Record function id": 0, "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924509238.903, "dur": 2.439, + "args": { + "External id": 762960,"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": 688924509239.713, "dur": 1.204, + "args": { + "External id": 762961,"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": 688924509240.283, "dur": 0.560, + "args": { + "External id": 762962,"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": 688924509244.845, "dur": 4.529, + "args": { + "External id": 762963,"Record function id": 0, "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924509246.219, "dur": 2.719, + "args": { + "External id": 762964,"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": 688924509246.882, "dur": 1.464, + "args": { + "External id": 762965,"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": 688924509247.649, "dur": 0.622, + "args": { + "External id": 762966,"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": 688924509252.624, "dur": 4.432, + "args": { + "External id": 762967,"Record function id": 0, "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924509254.064, "dur": 2.594, + "args": { + "External id": 762968,"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": 688924509254.707, "dur": 1.417, + "args": { + "External id": 762969,"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": 688924509255.489, "dur": 0.560, + "args": { + "External id": 762970,"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": 688924509260.140, "dur": 5.919, + "args": { + "External id": 762971,"Record function id": 0, "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924509261.676, "dur": 3.995, + "args": { + "External id": 762972,"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": 688924509262.334, "dur": 2.929, + "args": { + "External id": 762973,"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": 688924509262.795, "dur": 2.398, + "args": { + "External id": 762974,"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": 688924509269.204, "dur": 3.735, + "args": { + "External id": 762975,"Record function id": 0, "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924509270.274, "dur": 2.253, + "args": { + "External id": 762976,"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": 688924509270.750, "dur": 1.341, + "args": { + "External id": 762977,"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": 688924509271.176, "dur": 0.843, + "args": { + "External id": 762978,"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": 688924509277.104, "dur": 14678.323, + "args": { + "External id": 762979,"Record function id": 0, "Sequence number": 8961993, "Fwd thread id": 1, "Ev Idx": 2146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924509278.488, "dur": 14668.203, + "args": { + "External id": 762980,"Sequence number": 8961993, "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": 688924509278.488, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 4183436, "tid": 31338, + "ts": 688924509308.928, "dur": 39.298, + "args": { + "External id": 762981,"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": 688924509356.237, "dur": 69.195, + "args": { + "External id": 762982,"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": 688924509431.540, "dur": 14506.752, + "args": { + "External id": 762983,"Record function id": 0, "Ev Idx": 2150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924509518.959, "dur": 6.391, + "args": { + "External id": 762984,"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": 688924509534.777, "dur": 4.308, + "args": { + "External id": 762985,"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": 688924509553.100, "dur": 13656.901, + "args": { + "External id": 762986,"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": 688924509569.190, "dur": 13632.529, + "args": { + "External id": 762987,"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": 688924509647.709, "dur": 48.572, + "args": { + "External id": 762988,"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": 688924509702.087, "dur": 13454.022, + "args": { + "External id": 762989,"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": 688924509706.403, "dur": 13448.999, + "args": { + "External id": 762990,"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": 688924509710.310, "dur": 5.682, + "args": { + "External id": 762991,"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": 688924509717.732, "dur": 13434.442, + "args": { + "External id": 762992,"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": 688924523306.844, "dur": 9.294, + "args": { + "External id": 762993,"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": 688924523309.947, "dur": 5.751, + "args": { + "External id": 762994,"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": 688924523345.208, "dur": 254.908, + "args": { + "External id": 762995,"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": 688924523371.216, "dur": 224.771, + "args": { + "External id": 762996,"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": 688924523382.151, "dur": 207.946, + "args": { + "External id": 762997,"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": 688924523616.770, "dur": 2.268, + "args": { + "External id": 762998,"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": 688924523704.842, "dur": 6.305, + "args": { + "External id": 762999,"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": 688924523757.941, "dur": 1.417, + "args": { + "External id": 763000,"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": 688924523775.729, "dur": 1.405, + "args": { + "External id": 763001,"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": 688924523808.075, "dur": 1.478, + "args": { + "External id": 763002,"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": 688924523823.492, "dur": 0.794, + "args": { + "External id": 763003,"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": 688924523837.669, "dur": 0.709, + "args": { + "External id": 763004,"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": 688924523849.700, "dur": 0.817, + "args": { + "External id": 763005,"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": 688924523861.960, "dur": 1.886, + "args": { + "External id": 763006,"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": 688924523874.741, "dur": 0.846, + "args": { + "External id": 763007,"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": 688924523972.495, "dur": 2666.330, + "args": { + "External id": 763008,"Record function id": 0, "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 4183436, "tid": 31338, + "ts": 688924523992.018, "dur": 1032.289, + "args": { + "External id": 763009,"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": 688924524006.806, "dur": 310.976, + "args": { + "External id": 763010,"Record function id": 0, "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924524090.441, "dur": 3.897, + "args": { + "External id": 763011,"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": 688924524097.281, "dur": 1.148, + "args": { + "External id": 763012,"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": 688924524099.834, "dur": 1.125, + "args": { + "External id": 763013,"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": 688924524102.760, "dur": 1.023, + "args": { + "External id": 763014,"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": 688924524105.019, "dur": 0.723, + "args": { + "External id": 763015,"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": 688924524106.947, "dur": 1.092, + "args": { + "External id": 763016,"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": 688924524109.707, "dur": 2.220, + "args": { + "External id": 763017,"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": 688924524113.194, "dur": 2.652, + "args": { + "External id": 763018,"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": 688924524117.465, "dur": 0.858, + "args": { + "External id": 763019,"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": 688924524120.039, "dur": 0.673, + "args": { + "External id": 763020,"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": 688924524137.162, "dur": 152.060, + "args": { + "External id": 763021,"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": 688924524151.479, "dur": 133.655, + "args": { + "External id": 763022,"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": 688924524178.228, "dur": 13.342, + "args": { + "External id": 763023,"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": 688924524194.348, "dur": 63.148, + "args": { + "External id": 763024,"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": 688924524196.878, "dur": 60.281, + "args": { + "External id": 763025,"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": 688924524200.579, "dur": 5.616, + "args": { + "External id": 763026,"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": 688924524208.010, "dur": 48.694, + "args": { + "External id": 763027,"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": 688924524405.217, "dur": 610.969, + "args": { + "External id": 763028,"Record function id": 0, "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 4183436, "tid": 31338, + "ts": 688924524422.419, "dur": 580.733, + "args": { + "External id": 763029,"Record function id": 0, "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924524482.703, "dur": 4.609, + "args": { + "External id": 763030,"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": 688924524502.665, "dur": 27.657, + "args": { + "External id": 763031,"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": 688924524506.864, "dur": 1.181, + "args": { + "External id": 763032,"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": 688924524511.541, "dur": 0.328, + "args": { + "External id": 763033,"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": 688924524513.146, "dur": 2.336, + "args": { + "External id": 763034,"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": 688924524516.482, "dur": 1.497, + "args": { + "External id": 763035,"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": 688924524518.714, "dur": 0.358, + "args": { + "External id": 763036,"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": 688924524519.882, "dur": 0.280, + "args": { + "External id": 763037,"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": 688924524522.986, "dur": 0.247, + "args": { + "External id": 763038,"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": 688924524523.952, "dur": 0.686, + "args": { + "External id": 763039,"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": 688924524525.339, "dur": 0.600, + "args": { + "External id": 763040,"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": 688924524540.081, "dur": 29.918, + "args": { + "External id": 763041,"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": 688924524599.061, "dur": 141.900, + "args": { + "External id": 763042,"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": 688924524608.087, "dur": 3.312, + "args": { + "External id": 763043,"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": 688924524616.218, "dur": 12.168, + "args": { + "External id": 763044,"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": 688924524619.955, "dur": 8.017, + "args": { + "External id": 763045,"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": 688924524623.240, "dur": 3.579, + "args": { + "External id": 763046,"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": 688924524634.967, "dur": 64.483, + "args": { + "External id": 763047,"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": 688924524636.318, "dur": 0.366, + "args": { + "External id": 763048,"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": 688924524637.634, "dur": 0.369, + "args": { + "External id": 763049,"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": 688924524638.753, "dur": 0.438, + "args": { + "External id": 763050,"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": 688924524642.157, "dur": 0.501, + "args": { + "External id": 763051,"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": 688924524643.593, "dur": 0.554, + "args": { + "External id": 763052,"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": 688924524644.910, "dur": 1.511, + "args": { + "External id": 763053,"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": 688924524647.335, "dur": 0.479, + "args": { + "External id": 763054,"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": 688924524648.622, "dur": 1.807, + "args": { + "External id": 763055,"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": 688924524693.292, "dur": 0.645, + "args": { + "External id": 763056,"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": 688924524711.529, "dur": 22.001, + "args": { + "External id": 763057,"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": 688924524801.148, "dur": 124.327, + "args": { + "External id": 763058,"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": 688924524828.699, "dur": 93.219, + "args": { + "External id": 763059,"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": 688924524837.981, "dur": 79.715, + "args": { + "External id": 763060,"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": 688924524944.021, "dur": 1.939, + "args": { + "External id": 763061,"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": 688924525031.853, "dur": 1583.078, + "args": { + "External id": 763062,"Sequence number": 8961992, "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": 688924525031.853, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924525143.739, "dur": 101.980, + "args": { + "External id": 763063,"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": 688924525286.549, "dur": 39.543, + "args": { + "External id": 763064,"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": 688924525344.006, "dur": 41.102, + "args": { + "External id": 763065,"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": 688924525393.916, "dur": 26.700, + "args": { + "External id": 763066,"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": 688924525426.079, "dur": 32.028, + "args": { + "External id": 763067,"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": 688924525463.970, "dur": 21.774, + "args": { + "External id": 763068,"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": 688924525494.796, "dur": 28.700, + "args": { + "External id": 763069,"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": 688924525545.455, "dur": 26.581, + "args": { + "External id": 763070,"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": 688924525589.634, "dur": 28.831, + "args": { + "External id": 763071,"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": 688924525636.032, "dur": 64.468, + "args": { + "External id": 763072,"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": 688924525717.661, "dur": 17.276, + "args": { + "External id": 763073,"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": 688924525745.391, "dur": 58.085, + "args": { + "External id": 763074,"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": 688924525808.809, "dur": 33.496, + "args": { + "External id": 763075,"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": 688924525873.122, "dur": 173.026, + "args": { + "External id": 763076,"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": 688924525953.437, "dur": 5.477, + "args": { + "External id": 763077,"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": 688924525960.767, "dur": 2.692, + "args": { + "External id": 763078,"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": 688924526081.662, "dur": 29.234, + "args": { + "External id": 763079,"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": 688924526122.286, "dur": 15.601, + "args": { + "External id": 763080,"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": 688924526150.739, "dur": 44.221, + "args": { + "External id": 763081,"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": 688924526200.455, "dur": 33.416, + "args": { + "External id": 763082,"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": 688924526246.406, "dur": 30.633, + "args": { + "External id": 763083,"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": 688924526280.993, "dur": 27.233, + "args": { + "External id": 763084,"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": 688924526314.578, "dur": 28.821, + "args": { + "External id": 763085,"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": 688924526352.037, "dur": 46.778, + "args": { + "External id": 763086,"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": 688924526419.900, "dur": 24.167, + "args": { + "External id": 763087,"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": 688924526461.226, "dur": 28.502, + "args": { + "External id": 763088,"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": 688924526504.464, "dur": 16.959, + "args": { + "External id": 763089,"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": 688924526540.652, "dur": 14.869, + "args": { + "External id": 763090,"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": 688924526566.776, "dur": 15.743, + "args": { + "External id": 763091,"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": 688924526702.661, "dur": 16.323, + "args": { + "External id": 763092,"Record function id": 0, "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924526706.794, "dur": 11.022, + "args": { + "External id": 763093,"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": 688924526711.013, "dur": 5.514, + "args": { + "External id": 763094,"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": 688924526712.327, "dur": 3.997, + "args": { + "External id": 763095,"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": 688924526724.008, "dur": 4.934, + "args": { + "External id": 763096,"Record function id": 0, "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924526726.012, "dur": 2.496, + "args": { + "External id": 763097,"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": 688924526726.577, "dur": 1.240, + "args": { + "External id": 763098,"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": 688924526726.950, "dur": 0.678, + "args": { + "External id": 763099,"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": 688924526732.274, "dur": 4.917, + "args": { + "External id": 763100,"Record function id": 0, "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924526734.041, "dur": 2.717, + "args": { + "External id": 763101,"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": 688924526734.677, "dur": 1.552, + "args": { + "External id": 763102,"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": 688924526735.189, "dur": 0.956, + "args": { + "External id": 763103,"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": 688924526740.402, "dur": 3.737, + "args": { + "External id": 763104,"Record function id": 0, "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924526741.972, "dur": 1.766, + "args": { + "External id": 763105,"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": 688924526742.428, "dur": 0.889, + "args": { + "External id": 763106,"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": 688924526742.707, "dur": 0.545, + "args": { + "External id": 763107,"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": 688924526747.097, "dur": 4.096, + "args": { + "External id": 763108,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924526748.489, "dur": 2.288, + "args": { + "External id": 763109,"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": 688924526748.906, "dur": 1.466, + "args": { + "External id": 763110,"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": 688924526749.691, "dur": 0.604, + "args": { + "External id": 763111,"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": 688924526754.304, "dur": 4.403, + "args": { + "External id": 763112,"Record function id": 0, "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924526755.484, "dur": 2.828, + "args": { + "External id": 763113,"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": 688924526756.019, "dur": 1.525, + "args": { + "External id": 763114,"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": 688924526756.785, "dur": 0.692, + "args": { + "External id": 763115,"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": 688924526761.862, "dur": 6.414, + "args": { + "External id": 763116,"Record function id": 0, "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924526763.339, "dur": 4.534, + "args": { + "External id": 763117,"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": 688924526763.804, "dur": 3.412, + "args": { + "External id": 763118,"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": 688924526764.416, "dur": 2.716, + "args": { + "External id": 763119,"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": 688924526771.279, "dur": 4.058, + "args": { + "External id": 763120,"Record function id": 0, "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924526772.610, "dur": 2.345, + "args": { + "External id": 763121,"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": 688924526773.063, "dur": 1.486, + "args": { + "External id": 763122,"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": 688924526773.666, "dur": 0.810, + "args": { + "External id": 763123,"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": 688924526778.305, "dur": 3.731, + "args": { + "External id": 763124,"Record function id": 0, "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924526779.566, "dur": 2.075, + "args": { + "External id": 763125,"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": 688924526780.015, "dur": 1.111, + "args": { + "External id": 763126,"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": 688924526780.515, "dur": 0.544, + "args": { + "External id": 763127,"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": 688924526800.849, "dur": 16099.834, + "args": { + "External id": 763128,"Record function id": 0, "Sequence number": 8961991, "Fwd thread id": 1, "Ev Idx": 2295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924526803.175, "dur": 16088.317, + "args": { + "External id": 763129,"Sequence number": 8961991, "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": 688924526803.175, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 4183436, "tid": 31338, + "ts": 688924526835.293, "dur": 40.682, + "args": { + "External id": 763130,"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": 688924526884.025, "dur": 69.864, + "args": { + "External id": 763131,"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": 688924526960.215, "dur": 15922.686, + "args": { + "External id": 763132,"Record function id": 0, "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924527049.085, "dur": 7.146, + "args": { + "External id": 763133,"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": 688924527065.811, "dur": 4.961, + "args": { + "External id": 763134,"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": 688924527084.370, "dur": 15033.476, + "args": { + "External id": 763135,"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": 688924527097.796, "dur": 15011.234, + "args": { + "External id": 763136,"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": 688924527135.076, "dur": 14.135, + "args": { + "External id": 763137,"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": 688924527153.951, "dur": 14917.578, + "args": { + "External id": 763138,"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": 688924527158.081, "dur": 14912.753, + "args": { + "External id": 763139,"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": 688924527161.990, "dur": 4.948, + "args": { + "External id": 763140,"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": 688924527168.837, "dur": 14898.846, + "args": { + "External id": 763141,"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": 688924542206.332, "dur": 9.228, + "args": { + "External id": 763142,"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": 688924542209.142, "dur": 6.096, + "args": { + "External id": 763143,"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": 688924542242.010, "dur": 296.298, + "args": { + "External id": 763144,"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": 688924542270.743, "dur": 263.233, + "args": { + "External id": 763145,"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": 688924542283.258, "dur": 246.141, + "args": { + "External id": 763146,"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": 688924542556.244, "dur": 2.220, + "args": { + "External id": 763147,"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": 688924542607.871, "dur": 8.270, + "args": { + "External id": 763148,"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": 688924542699.101, "dur": 2.472, + "args": { + "External id": 763149,"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": 688924542720.590, "dur": 1.293, + "args": { + "External id": 763150,"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": 688924542733.831, "dur": 1.166, + "args": { + "External id": 763151,"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": 688924542745.899, "dur": 2.974, + "args": { + "External id": 763152,"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": 688924542762.499, "dur": 0.914, + "args": { + "External id": 763153,"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": 688924542773.796, "dur": 1.069, + "args": { + "External id": 763154,"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": 688924542799.208, "dur": 2.719, + "args": { + "External id": 763155,"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": 688924542816.032, "dur": 2.515, + "args": { + "External id": 763156,"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": 688924542916.984, "dur": 2687.429, + "args": { + "External id": 763157,"Record function id": 0, "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 4183436, "tid": 31338, + "ts": 688924542940.423, "dur": 1043.133, + "args": { + "External id": 763158,"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": 688924542955.657, "dur": 314.992, + "args": { + "External id": 763159,"Record function id": 0, "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924543042.069, "dur": 3.995, + "args": { + "External id": 763160,"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": 688924543052.263, "dur": 0.832, + "args": { + "External id": 763161,"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": 688924543054.881, "dur": 1.219, + "args": { + "External id": 763162,"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": 688924543057.884, "dur": 1.129, + "args": { + "External id": 763163,"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": 688924543061.167, "dur": 1.163, + "args": { + "External id": 763164,"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": 688924543064.276, "dur": 0.654, + "args": { + "External id": 763165,"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": 688924543066.717, "dur": 3.580, + "args": { + "External id": 763166,"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": 688924543072.066, "dur": 1.023, + "args": { + "External id": 763167,"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": 688924543074.773, "dur": 0.956, + "args": { + "External id": 763168,"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": 688924543077.577, "dur": 0.840, + "args": { + "External id": 763169,"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": 688924543095.977, "dur": 146.923, + "args": { + "External id": 763170,"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": 688924543111.647, "dur": 126.512, + "args": { + "External id": 763171,"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": 688924543128.653, "dur": 12.239, + "args": { + "External id": 763172,"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": 688924543143.651, "dur": 64.243, + "args": { + "External id": 763173,"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": 688924543146.703, "dur": 60.847, + "args": { + "External id": 763174,"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": 688924543150.428, "dur": 8.065, + "args": { + "External id": 763175,"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": 688924543160.261, "dur": 46.723, + "args": { + "External id": 763176,"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": 688924543353.302, "dur": 618.974, + "args": { + "External id": 763177,"Record function id": 0, "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 4183436, "tid": 31338, + "ts": 688924543370.555, "dur": 589.033, + "args": { + "External id": 763178,"Record function id": 0, "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924543428.659, "dur": 4.079, + "args": { + "External id": 763179,"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": 688924543448.054, "dur": 34.397, + "args": { + "External id": 763180,"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": 688924543452.977, "dur": 2.974, + "args": { + "External id": 763181,"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": 688924543458.081, "dur": 2.397, + "args": { + "External id": 763182,"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": 688924543462.030, "dur": 0.722, + "args": { + "External id": 763183,"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": 688924543466.238, "dur": 0.593, + "args": { + "External id": 763184,"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": 688924543468.514, "dur": 0.348, + "args": { + "External id": 763185,"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": 688924543470.275, "dur": 0.286, + "args": { + "External id": 763186,"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": 688924543473.383, "dur": 0.266, + "args": { + "External id": 763187,"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": 688924543475.021, "dur": 0.515, + "args": { + "External id": 763188,"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": 688924543477.188, "dur": 0.939, + "args": { + "External id": 763189,"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": 688924543494.951, "dur": 29.597, + "args": { + "External id": 763190,"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": 688924543555.841, "dur": 141.820, + "args": { + "External id": 763191,"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": 688924543564.837, "dur": 5.505, + "args": { + "External id": 763192,"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": 688924543575.183, "dur": 10.100, + "args": { + "External id": 763193,"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": 688924543578.933, "dur": 5.967, + "args": { + "External id": 763194,"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": 688924543582.715, "dur": 0.840, + "args": { + "External id": 763195,"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": 688924543592.608, "dur": 27.501, + "args": { + "External id": 763196,"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": 688924543594.653, "dur": 0.592, + "args": { + "External id": 763197,"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": 688924543597.097, "dur": 0.991, + "args": { + "External id": 763198,"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": 688924543599.920, "dur": 0.524, + "args": { + "External id": 763199,"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": 688924543602.185, "dur": 0.421, + "args": { + "External id": 763200,"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": 688924543605.162, "dur": 0.233, + "args": { + "External id": 763201,"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": 688924543606.624, "dur": 0.396, + "args": { + "External id": 763202,"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": 688924543608.941, "dur": 2.373, + "args": { + "External id": 763203,"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": 688924543613.669, "dur": 0.320, + "args": { + "External id": 763204,"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": 688924543615.613, "dur": 0.460, + "args": { + "External id": 763205,"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": 688924543631.930, "dur": 18.825, + "args": { + "External id": 763206,"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": 688924543744.394, "dur": 141.745, + "args": { + "External id": 763207,"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": 688924543770.172, "dur": 112.261, + "args": { + "External id": 763208,"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": 688924543779.389, "dur": 98.594, + "args": { + "External id": 763209,"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": 688924543902.474, "dur": 2.110, + "args": { + "External id": 763210,"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": 688924543990.926, "dur": 1588.650, + "args": { + "External id": 763211,"Sequence number": 8961990, "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": 688924543990.926, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924544109.726, "dur": 99.974, + "args": { + "External id": 763212,"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": 688924544249.336, "dur": 39.433, + "args": { + "External id": 763213,"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": 688924544307.451, "dur": 42.787, + "args": { + "External id": 763214,"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": 688924544359.489, "dur": 25.987, + "args": { + "External id": 763215,"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": 688924544391.765, "dur": 35.855, + "args": { + "External id": 763216,"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": 688924544436.440, "dur": 21.866, + "args": { + "External id": 763217,"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": 688924544466.472, "dur": 28.642, + "args": { + "External id": 763218,"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": 688924544517.886, "dur": 20.201, + "args": { + "External id": 763219,"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": 688924544562.407, "dur": 25.975, + "args": { + "External id": 763220,"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": 688924544608.905, "dur": 21.776, + "args": { + "External id": 763221,"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": 688924544643.250, "dur": 58.693, + "args": { + "External id": 763222,"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": 688924544715.674, "dur": 41.954, + "args": { + "External id": 763223,"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": 688924544761.186, "dur": 46.124, + "args": { + "External id": 763224,"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": 688924544842.336, "dur": 172.007, + "args": { + "External id": 763225,"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": 688924544920.868, "dur": 6.733, + "args": { + "External id": 763226,"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": 688924544929.499, "dur": 5.185, + "args": { + "External id": 763227,"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": 688924545047.616, "dur": 25.268, + "args": { + "External id": 763228,"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": 688924545084.704, "dur": 14.919, + "args": { + "External id": 763229,"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": 688924545107.713, "dur": 47.124, + "args": { + "External id": 763230,"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": 688924545160.230, "dur": 30.423, + "args": { + "External id": 763231,"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": 688924545197.261, "dur": 27.206, + "args": { + "External id": 763232,"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": 688924545230.379, "dur": 27.511, + "args": { + "External id": 763233,"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": 688924545264.088, "dur": 43.594, + "args": { + "External id": 763234,"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": 688924545321.506, "dur": 36.383, + "args": { + "External id": 763235,"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": 688924545378.100, "dur": 25.290, + "args": { + "External id": 763236,"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": 688924545421.007, "dur": 24.025, + "args": { + "External id": 763237,"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": 688924545464.461, "dur": 16.553, + "args": { + "External id": 763238,"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": 688924545494.780, "dur": 17.869, + "args": { + "External id": 763239,"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": 688924545529.955, "dur": 16.756, + "args": { + "External id": 763240,"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": 688924545626.450, "dur": 17.145, + "args": { + "External id": 763241,"Record function id": 0, "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924545629.666, "dur": 12.992, + "args": { + "External id": 763242,"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": 688924545636.488, "dur": 5.311, + "args": { + "External id": 763243,"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": 688924545637.921, "dur": 3.761, + "args": { + "External id": 763244,"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": 688924545647.498, "dur": 45.404, + "args": { + "External id": 763245,"Record function id": 0, "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924545649.124, "dur": 38.790, + "args": { + "External id": 763246,"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": 688924545650.011, "dur": 1.404, + "args": { + "External id": 763247,"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": 688924545650.555, "dur": 0.775, + "args": { + "External id": 763248,"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": 688924545698.847, "dur": 6.909, + "args": { + "External id": 763249,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924545701.001, "dur": 4.278, + "args": { + "External id": 763250,"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": 688924545702.301, "dur": 2.264, + "args": { + "External id": 763251,"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": 688924545703.017, "dur": 1.462, + "args": { + "External id": 763252,"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": 688924545708.991, "dur": 7.228, + "args": { + "External id": 763253,"Record function id": 0, "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924545710.766, "dur": 5.034, + "args": { + "External id": 763254,"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": 688924545711.670, "dur": 3.549, + "args": { + "External id": 763255,"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": 688924545712.185, "dur": 2.953, + "args": { + "External id": 763256,"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": 688924545719.383, "dur": 4.969, + "args": { + "External id": 763257,"Record function id": 0, "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924545720.574, "dur": 3.360, + "args": { + "External id": 763258,"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": 688924545721.638, "dur": 1.596, + "args": { + "External id": 763259,"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": 688924545722.202, "dur": 0.963, + "args": { + "External id": 763260,"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": 688924545727.871, "dur": 4.992, + "args": { + "External id": 763261,"Record function id": 0, "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924545729.590, "dur": 2.820, + "args": { + "External id": 763262,"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": 688924545730.286, "dur": 1.508, + "args": { + "External id": 763263,"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": 688924545730.856, "dur": 0.870, + "args": { + "External id": 763264,"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": 688924545736.287, "dur": 4.392, + "args": { + "External id": 763265,"Record function id": 0, "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924545737.744, "dur": 2.504, + "args": { + "External id": 763266,"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": 688924545738.411, "dur": 1.424, + "args": { + "External id": 763267,"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": 688924545739.103, "dur": 0.659, + "args": { + "External id": 763268,"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": 688924545744.111, "dur": 7.513, + "args": { + "External id": 763269,"Record function id": 0, "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924545745.606, "dur": 5.612, + "args": { + "External id": 763270,"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": 688924545746.057, "dur": 4.480, + "args": { + "External id": 763271,"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": 688924545746.601, "dur": 3.872, + "args": { + "External id": 763272,"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": 688924545755.157, "dur": 4.528, + "args": { + "External id": 763273,"Record function id": 0, "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924545756.431, "dur": 2.819, + "args": { + "External id": 763274,"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": 688924545757.134, "dur": 1.477, + "args": { + "External id": 763275,"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": 688924545757.877, "dur": 0.662, + "args": { + "External id": 763276,"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": 688924545764.690, "dur": 14599.253, + "args": { + "External id": 763277,"Record function id": 0, "Sequence number": 8961989, "Fwd thread id": 1, "Ev Idx": 2444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924545766.584, "dur": 14588.557, + "args": { + "External id": 763278,"Sequence number": 8961989, "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": 688924545766.584, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 4183436, "tid": 31338, + "ts": 688924545814.340, "dur": 37.923, + "args": { + "External id": 763279,"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": 688924545861.112, "dur": 70.476, + "args": { + "External id": 763280,"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": 688924545938.227, "dur": 14408.858, + "args": { + "External id": 763281,"Record function id": 0, "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924546027.042, "dur": 6.952, + "args": { + "External id": 763282,"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": 688924546044.371, "dur": 4.903, + "args": { + "External id": 763283,"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": 688924546064.207, "dur": 13581.956, + "args": { + "External id": 763284,"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": 688924546077.915, "dur": 13559.850, + "args": { + "External id": 763285,"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": 688924546121.799, "dur": 15.020, + "args": { + "External id": 763286,"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": 688924546141.381, "dur": 13460.650, + "args": { + "External id": 763287,"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": 688924546144.032, "dur": 13457.309, + "args": { + "External id": 763288,"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": 688924546148.726, "dur": 4.755, + "args": { + "External id": 763289,"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": 688924546155.075, "dur": 13443.091, + "args": { + "External id": 763290,"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": 688924559760.985, "dur": 8.498, + "args": { + "External id": 763291,"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": 688924559763.675, "dur": 5.379, + "args": { + "External id": 763292,"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": 688924559812.111, "dur": 261.499, + "args": { + "External id": 763293,"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": 688924559840.689, "dur": 228.409, + "args": { + "External id": 763294,"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": 688924559854.097, "dur": 210.566, + "args": { + "External id": 763295,"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": 688924560092.093, "dur": 2.261, + "args": { + "External id": 763296,"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": 688924560147.951, "dur": 6.247, + "args": { + "External id": 763297,"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": 688924560195.652, "dur": 1.612, + "args": { + "External id": 763298,"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": 688924560212.880, "dur": 1.175, + "args": { + "External id": 763299,"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": 688924560228.352, "dur": 1.112, + "args": { + "External id": 763300,"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": 688924560239.832, "dur": 0.741, + "args": { + "External id": 763301,"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": 688924560250.971, "dur": 0.960, + "args": { + "External id": 763302,"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": 688924560262.284, "dur": 0.972, + "args": { + "External id": 763303,"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": 688924560275.565, "dur": 2.474, + "args": { + "External id": 763304,"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": 688924560287.594, "dur": 0.762, + "args": { + "External id": 763305,"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": 688924560378.647, "dur": 2771.551, + "args": { + "External id": 763306,"Record function id": 0, "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 4183436, "tid": 31338, + "ts": 688924560397.733, "dur": 1072.689, + "args": { + "External id": 763307,"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": 688924560412.017, "dur": 398.797, + "args": { + "External id": 763308,"Record function id": 0, "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924560495.281, "dur": 4.225, + "args": { + "External id": 763309,"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": 688924560502.508, "dur": 1.024, + "args": { + "External id": 763310,"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": 688924560505.374, "dur": 1.060, + "args": { + "External id": 763311,"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": 688924560511.241, "dur": 3.060, + "args": { + "External id": 763312,"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": 688924560516.258, "dur": 0.736, + "args": { + "External id": 763313,"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": 688924560518.626, "dur": 0.944, + "args": { + "External id": 763314,"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": 688924560521.763, "dur": 1.267, + "args": { + "External id": 763315,"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": 688924560524.580, "dur": 0.808, + "args": { + "External id": 763316,"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": 688924560526.778, "dur": 0.845, + "args": { + "External id": 763317,"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": 688924560529.420, "dur": 1.046, + "args": { + "External id": 763318,"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": 688924560547.657, "dur": 212.104, + "args": { + "External id": 763319,"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": 688924560573.312, "dur": 181.652, + "args": { + "External id": 763320,"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": 688924560586.953, "dur": 11.312, + "args": { + "External id": 763321,"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": 688924560600.894, "dur": 119.933, + "args": { + "External id": 763322,"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": 688924560603.609, "dur": 116.803, + "args": { + "External id": 763323,"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": 688924560607.432, "dur": 7.975, + "args": { + "External id": 763324,"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": 688924560616.940, "dur": 102.412, + "args": { + "External id": 763325,"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": 688924560912.991, "dur": 549.526, + "args": { + "External id": 763326,"Record function id": 0, "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 4183436, "tid": 31338, + "ts": 688924560932.413, "dur": 518.418, + "args": { + "External id": 763327,"Record function id": 0, "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924561001.584, "dur": 5.883, + "args": { + "External id": 763328,"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": 688924561022.537, "dur": 33.884, + "args": { + "External id": 763329,"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": 688924561027.477, "dur": 1.838, + "args": { + "External id": 763330,"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": 688924561031.906, "dur": 0.520, + "args": { + "External id": 763331,"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": 688924561033.889, "dur": 0.574, + "args": { + "External id": 763332,"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": 688924561037.617, "dur": 0.521, + "args": { + "External id": 763333,"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": 688924561039.625, "dur": 0.627, + "args": { + "External id": 763334,"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": 688924561041.902, "dur": 1.323, + "args": { + "External id": 763335,"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": 688924561044.672, "dur": 2.436, + "args": { + "External id": 763336,"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": 688924561048.539, "dur": 0.348, + "args": { + "External id": 763337,"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": 688924561051.503, "dur": 0.265, + "args": { + "External id": 763338,"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": 688924561067.177, "dur": 33.002, + "args": { + "External id": 763339,"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": 688924561129.966, "dur": 99.435, + "args": { + "External id": 763340,"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": 688924561140.782, "dur": 3.616, + "args": { + "External id": 763341,"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": 688924561149.699, "dur": 9.278, + "args": { + "External id": 763342,"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": 688924561153.624, "dur": 4.967, + "args": { + "External id": 763343,"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": 688924561156.968, "dur": 0.497, + "args": { + "External id": 763344,"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": 688924561165.623, "dur": 25.730, + "args": { + "External id": 763345,"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": 688924561167.941, "dur": 0.402, + "args": { + "External id": 763346,"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": 688924561169.894, "dur": 0.538, + "args": { + "External id": 763347,"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": 688924561172.717, "dur": 0.336, + "args": { + "External id": 763348,"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": 688924561174.367, "dur": 2.473, + "args": { + "External id": 763349,"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": 688924561178.856, "dur": 0.606, + "args": { + "External id": 763350,"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": 688924561181.002, "dur": 0.517, + "args": { + "External id": 763351,"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": 688924561182.962, "dur": 0.312, + "args": { + "External id": 763352,"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": 688924561184.711, "dur": 1.531, + "args": { + "External id": 763353,"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": 688924561187.796, "dur": 0.337, + "args": { + "External id": 763354,"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": 688924561201.981, "dur": 20.572, + "args": { + "External id": 763355,"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": 688924561274.829, "dur": 112.372, + "args": { + "External id": 763356,"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": 688924561299.781, "dur": 84.038, + "args": { + "External id": 763357,"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": 688924561309.095, "dur": 70.020, + "args": { + "External id": 763358,"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": 688924561400.653, "dur": 1.754, + "args": { + "External id": 763359,"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": 688924561478.082, "dur": 1649.757, + "args": { + "External id": 763360,"Sequence number": 8961988, "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": 688924561478.082, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924561592.928, "dur": 145.328, + "args": { + "External id": 763361,"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": 688924561783.648, "dur": 59.990, + "args": { + "External id": 763362,"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": 688924561864.724, "dur": 52.226, + "args": { + "External id": 763363,"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": 688924561927.223, "dur": 26.652, + "args": { + "External id": 763364,"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": 688924561962.322, "dur": 33.044, + "args": { + "External id": 763365,"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": 688924562002.726, "dur": 22.540, + "args": { + "External id": 763366,"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": 688924562032.706, "dur": 28.475, + "args": { + "External id": 763367,"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": 688924562085.883, "dur": 21.924, + "args": { + "External id": 763368,"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": 688924562126.612, "dur": 30.288, + "args": { + "External id": 763369,"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": 688924562177.256, "dur": 19.576, + "args": { + "External id": 763370,"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": 688924562212.981, "dur": 15.856, + "args": { + "External id": 763371,"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": 688924562238.333, "dur": 37.522, + "args": { + "External id": 763372,"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": 688924562282.344, "dur": 28.789, + "args": { + "External id": 763373,"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": 688924562344.396, "dur": 167.242, + "args": { + "External id": 763374,"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": 688924562422.308, "dur": 5.758, + "args": { + "External id": 763375,"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": 688924562429.990, "dur": 3.974, + "args": { + "External id": 763376,"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": 688924562554.729, "dur": 26.744, + "args": { + "External id": 763377,"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": 688924562593.389, "dur": 13.239, + "args": { + "External id": 763378,"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": 688924562615.229, "dur": 80.177, + "args": { + "External id": 763379,"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": 688924562704.648, "dur": 34.991, + "args": { + "External id": 763380,"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": 688924562750.193, "dur": 27.233, + "args": { + "External id": 763381,"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": 688924562782.491, "dur": 44.557, + "args": { + "External id": 763382,"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": 688924562835.762, "dur": 26.913, + "args": { + "External id": 763383,"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": 688924562870.590, "dur": 43.947, + "args": { + "External id": 763384,"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": 688924562940.097, "dur": 23.270, + "args": { + "External id": 763385,"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": 688924562982.527, "dur": 27.573, + "args": { + "External id": 763386,"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": 688924563023.914, "dur": 14.858, + "args": { + "External id": 763387,"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": 688924563059.184, "dur": 13.519, + "args": { + "External id": 763388,"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": 688924563083.582, "dur": 14.172, + "args": { + "External id": 763389,"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": 688924563175.930, "dur": 84.945, + "args": { + "External id": 763390,"Record function id": 0, "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924563179.557, "dur": 80.174, + "args": { + "External id": 763391,"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": 688924563183.628, "dur": 75.038, + "args": { + "External id": 763392,"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": 688924563254.148, "dur": 4.354, + "args": { + "External id": 763393,"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": 688924563266.147, "dur": 4.784, + "args": { + "External id": 763394,"Record function id": 0, "Ev Idx": 2561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924563267.830, "dur": 2.574, + "args": { + "External id": 763395,"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": 688924563268.603, "dur": 1.227, + "args": { + "External id": 763396,"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": 688924563269.115, "dur": 0.610, + "args": { + "External id": 763397,"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": 688924563274.902, "dur": 5.834, + "args": { + "External id": 763398,"Record function id": 0, "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924563276.218, "dur": 4.082, + "args": { + "External id": 763399,"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": 688924563276.935, "dur": 2.938, + "args": { + "External id": 763400,"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": 688924563277.287, "dur": 2.517, + "args": { + "External id": 763401,"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": 688924563284.648, "dur": 4.247, + "args": { + "External id": 763402,"Record function id": 0, "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924563285.779, "dur": 2.645, + "args": { + "External id": 763403,"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": 688924563286.529, "dur": 1.460, + "args": { + "External id": 763404,"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": 688924563287.009, "dur": 0.912, + "args": { + "External id": 763405,"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": 688924563292.626, "dur": 4.004, + "args": { + "External id": 763406,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924563293.637, "dur": 2.524, + "args": { + "External id": 763407,"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": 688924563294.550, "dur": 1.173, + "args": { + "External id": 763408,"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": 688924563295.026, "dur": 0.623, + "args": { + "External id": 763409,"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": 688924563300.388, "dur": 4.057, + "args": { + "External id": 763410,"Record function id": 0, "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924563301.768, "dur": 2.276, + "args": { + "External id": 763411,"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": 688924563302.398, "dur": 1.221, + "args": { + "External id": 763412,"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": 688924563302.712, "dur": 0.845, + "args": { + "External id": 763413,"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": 688924563311.001, "dur": 3.897, + "args": { + "External id": 763414,"Record function id": 0, "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924563312.227, "dur": 2.237, + "args": { + "External id": 763415,"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": 688924563312.855, "dur": 1.069, + "args": { + "External id": 763416,"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": 688924563313.203, "dur": 0.661, + "args": { + "External id": 763417,"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": 688924563318.496, "dur": 3.786, + "args": { + "External id": 763418,"Record function id": 0, "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924563319.717, "dur": 2.153, + "args": { + "External id": 763419,"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": 688924563320.384, "dur": 1.065, + "args": { + "External id": 763420,"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": 688924563320.729, "dur": 0.644, + "args": { + "External id": 763421,"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": 688924563326.204, "dur": 4.111, + "args": { + "External id": 763422,"Record function id": 0, "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924563327.744, "dur": 2.143, + "args": { + "External id": 763423,"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": 688924563328.400, "dur": 1.066, + "args": { + "External id": 763424,"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": 688924563328.753, "dur": 0.646, + "args": { + "External id": 763425,"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": 688924563335.272, "dur": 14603.587, + "args": { + "External id": 763426,"Record function id": 0, "Sequence number": 8961987, "Fwd thread id": 1, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924563336.624, "dur": 14593.432, + "args": { + "External id": 763427,"Sequence number": 8961987, "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": 688924563336.624, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 4183436, "tid": 31338, + "ts": 688924563369.065, "dur": 40.270, + "args": { + "External id": 763428,"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": 688924563416.777, "dur": 72.835, + "args": { + "External id": 763429,"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": 688924563495.297, "dur": 14426.372, + "args": { + "External id": 763430,"Record function id": 0, "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924563585.602, "dur": 6.653, + "args": { + "External id": 763431,"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": 688924563601.740, "dur": 6.393, + "args": { + "External id": 763432,"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": 688924563624.190, "dur": 13563.773, + "args": { + "External id": 763433,"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": 688924563637.079, "dur": 13542.495, + "args": { + "External id": 763434,"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": 688924563735.674, "dur": 14.750, + "args": { + "External id": 763435,"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": 688924563755.339, "dur": 13388.634, + "args": { + "External id": 763436,"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": 688924563757.664, "dur": 13385.516, + "args": { + "External id": 763437,"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": 688924563761.449, "dur": 7.149, + "args": { + "External id": 763438,"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": 688924563770.256, "dur": 13369.581, + "args": { + "External id": 763439,"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": 688924577282.863, "dur": 9.151, + "args": { + "External id": 763440,"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": 688924577285.772, "dur": 5.883, + "args": { + "External id": 763441,"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": 688924577321.208, "dur": 255.225, + "args": { + "External id": 763442,"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": 688924577348.864, "dur": 223.423, + "args": { + "External id": 763443,"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": 688924577360.769, "dur": 206.788, + "args": { + "External id": 763444,"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": 688924577594.106, "dur": 2.249, + "args": { + "External id": 763445,"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": 688924577647.723, "dur": 51.793, + "args": { + "External id": 763446,"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": 688924577746.590, "dur": 1.619, + "args": { + "External id": 763447,"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": 688924577764.443, "dur": 3.194, + "args": { + "External id": 763448,"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": 688924577779.217, "dur": 0.990, + "args": { + "External id": 763449,"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": 688924577807.982, "dur": 1.319, + "args": { + "External id": 763450,"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": 688924577820.696, "dur": 0.895, + "args": { + "External id": 763451,"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": 688924577832.262, "dur": 2.899, + "args": { + "External id": 763452,"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": 688924577846.548, "dur": 1.795, + "args": { + "External id": 763453,"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": 688924577858.303, "dur": 0.995, + "args": { + "External id": 763454,"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": 688924577953.178, "dur": 2623.922, + "args": { + "External id": 763455,"Record function id": 0, "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 4183436, "tid": 31338, + "ts": 688924577971.684, "dur": 1019.770, + "args": { + "External id": 763456,"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": 688924577986.015, "dur": 306.887, + "args": { + "External id": 763457,"Record function id": 0, "Ev Idx": 2624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924578066.373, "dur": 3.576, + "args": { + "External id": 763458,"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": 688924578075.709, "dur": 1.080, + "args": { + "External id": 763459,"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": 688924578078.716, "dur": 3.200, + "args": { + "External id": 763460,"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": 688924578083.896, "dur": 0.768, + "args": { + "External id": 763461,"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": 688924578086.489, "dur": 0.881, + "args": { + "External id": 763462,"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": 688924578088.870, "dur": 1.133, + "args": { + "External id": 763463,"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": 688924578092.169, "dur": 1.952, + "args": { + "External id": 763464,"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": 688924578095.708, "dur": 0.940, + "args": { + "External id": 763465,"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": 688924578098.330, "dur": 0.806, + "args": { + "External id": 763466,"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": 688924578100.898, "dur": 0.778, + "args": { + "External id": 763467,"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": 688924578118.403, "dur": 148.706, + "args": { + "External id": 763468,"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": 688924578137.604, "dur": 125.232, + "args": { + "External id": 763469,"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": 688924578152.570, "dur": 14.743, + "args": { + "External id": 763470,"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": 688924578170.278, "dur": 64.234, + "args": { + "External id": 763471,"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": 688924578172.976, "dur": 61.173, + "args": { + "External id": 763472,"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": 688924578177.055, "dur": 5.421, + "args": { + "External id": 763473,"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": 688924578184.235, "dur": 49.300, + "args": { + "External id": 763474,"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": 688924578376.950, "dur": 606.758, + "args": { + "External id": 763475,"Record function id": 0, "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 4183436, "tid": 31338, + "ts": 688924578392.833, "dur": 578.001, + "args": { + "External id": 763476,"Record function id": 0, "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924578450.725, "dur": 5.205, + "args": { + "External id": 763477,"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": 688924578470.078, "dur": 28.610, + "args": { + "External id": 763478,"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": 688924578474.635, "dur": 2.751, + "args": { + "External id": 763479,"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": 688924578479.319, "dur": 0.619, + "args": { + "External id": 763480,"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": 688924578480.807, "dur": 0.351, + "args": { + "External id": 763481,"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": 688924578483.398, "dur": 0.464, + "args": { + "External id": 763482,"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": 688924578484.855, "dur": 0.557, + "args": { + "External id": 763483,"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": 688924578486.563, "dur": 2.140, + "args": { + "External id": 763484,"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": 688924578490.863, "dur": 0.546, + "args": { + "External id": 763485,"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": 688924578492.921, "dur": 0.296, + "args": { + "External id": 763486,"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": 688924578494.189, "dur": 1.001, + "args": { + "External id": 763487,"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": 688924578508.272, "dur": 29.716, + "args": { + "External id": 763488,"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": 688924578569.784, "dur": 140.479, + "args": { + "External id": 763489,"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": 688924578578.238, "dur": 3.569, + "args": { + "External id": 763490,"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": 688924578586.656, "dur": 9.421, + "args": { + "External id": 763491,"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": 688924578590.727, "dur": 4.965, + "args": { + "External id": 763492,"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": 688924578593.849, "dur": 0.651, + "args": { + "External id": 763493,"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": 688924578603.175, "dur": 25.249, + "args": { + "External id": 763494,"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": 688924578604.989, "dur": 0.281, + "args": { + "External id": 763495,"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": 688924578606.523, "dur": 0.331, + "args": { + "External id": 763496,"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": 688924578608.260, "dur": 2.601, + "args": { + "External id": 763497,"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": 688924578611.841, "dur": 0.374, + "args": { + "External id": 763498,"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": 688924578613.727, "dur": 0.356, + "args": { + "External id": 763499,"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": 688924578615.775, "dur": 0.265, + "args": { + "External id": 763500,"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": 688924578617.447, "dur": 3.526, + "args": { + "External id": 763501,"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": 688924578621.864, "dur": 0.246, + "args": { + "External id": 763502,"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": 688924578623.998, "dur": 0.523, + "args": { + "External id": 763503,"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": 688924578639.421, "dur": 61.783, + "args": { + "External id": 763504,"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": 688924578756.345, "dur": 142.674, + "args": { + "External id": 763505,"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": 688924578782.040, "dur": 113.071, + "args": { + "External id": 763506,"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": 688924578807.440, "dur": 83.293, + "args": { + "External id": 763507,"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": 688924578915.636, "dur": 1.877, + "args": { + "External id": 763508,"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": 688924578999.039, "dur": 1557.968, + "args": { + "External id": 763509,"Sequence number": 8961986, "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": 688924578999.039, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924579112.473, "dur": 99.794, + "args": { + "External id": 763510,"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": 688924579253.402, "dur": 41.024, + "args": { + "External id": 763511,"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": 688924579311.641, "dur": 41.357, + "args": { + "External id": 763512,"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": 688924579364.236, "dur": 24.251, + "args": { + "External id": 763513,"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": 688924579393.962, "dur": 31.511, + "args": { + "External id": 763514,"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": 688924579432.045, "dur": 19.807, + "args": { + "External id": 763515,"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": 688924579461.922, "dur": 27.506, + "args": { + "External id": 763516,"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": 688924579517.676, "dur": 20.809, + "args": { + "External id": 763517,"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": 688924579557.960, "dur": 26.557, + "args": { + "External id": 763518,"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": 688924579602.676, "dur": 18.131, + "args": { + "External id": 763519,"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": 688924579633.708, "dur": 13.018, + "args": { + "External id": 763520,"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": 688924579697.512, "dur": 46.535, + "args": { + "External id": 763521,"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": 688924579748.138, "dur": 30.103, + "args": { + "External id": 763522,"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": 688924579828.208, "dur": 178.164, + "args": { + "External id": 763523,"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": 688924579916.074, "dur": 5.681, + "args": { + "External id": 763524,"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": 688924579923.752, "dur": 2.771, + "args": { + "External id": 763525,"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": 688924580040.200, "dur": 26.681, + "args": { + "External id": 763526,"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": 688924580077.303, "dur": 13.595, + "args": { + "External id": 763527,"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": 688924580098.486, "dur": 46.721, + "args": { + "External id": 763528,"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": 688924580151.206, "dur": 33.566, + "args": { + "External id": 763529,"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": 688924580193.057, "dur": 27.609, + "args": { + "External id": 763530,"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": 688924580228.335, "dur": 27.766, + "args": { + "External id": 763531,"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": 688924580261.917, "dur": 26.608, + "args": { + "External id": 763532,"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": 688924580306.154, "dur": 39.202, + "args": { + "External id": 763533,"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": 688924580368.317, "dur": 23.728, + "args": { + "External id": 763534,"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": 688924580410.375, "dur": 23.742, + "args": { + "External id": 763535,"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": 688924580448.919, "dur": 19.788, + "args": { + "External id": 763536,"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": 688924580484.019, "dur": 15.203, + "args": { + "External id": 763537,"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": 688924580514.505, "dur": 16.429, + "args": { + "External id": 763538,"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": 688924580599.041, "dur": 14.099, + "args": { + "External id": 763539,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924580601.898, "dur": 10.364, + "args": { + "External id": 763540,"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": 688924580605.968, "dur": 5.503, + "args": { + "External id": 763541,"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": 688924580607.389, "dur": 3.998, + "args": { + "External id": 763542,"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": 688924580617.410, "dur": 6.110, + "args": { + "External id": 763543,"Record function id": 0, "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924580619.078, "dur": 4.013, + "args": { + "External id": 763544,"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": 688924580619.788, "dur": 2.757, + "args": { + "External id": 763545,"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": 688924580620.313, "dur": 2.148, + "args": { + "External id": 763546,"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": 688924580627.508, "dur": 4.865, + "args": { + "External id": 763547,"Record function id": 0, "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924580628.762, "dur": 3.197, + "args": { + "External id": 763548,"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": 688924580629.441, "dur": 1.943, + "args": { + "External id": 763549,"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": 688924580629.886, "dur": 1.418, + "args": { + "External id": 763550,"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": 688924580635.715, "dur": 4.153, + "args": { + "External id": 763551,"Record function id": 0, "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924580636.884, "dur": 2.561, + "args": { + "External id": 763552,"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": 688924580637.711, "dur": 1.290, + "args": { + "External id": 763553,"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": 688924580638.216, "dur": 0.720, + "args": { + "External id": 763554,"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": 688924580643.238, "dur": 3.539, + "args": { + "External id": 763555,"Record function id": 0, "Ev Idx": 2722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924580644.319, "dur": 2.052, + "args": { + "External id": 763556,"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": 688924580644.852, "dur": 1.126, + "args": { + "External id": 763557,"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": 688924580645.260, "dur": 0.643, + "args": { + "External id": 763558,"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": 688924580650.123, "dur": 3.890, + "args": { + "External id": 763559,"Record function id": 0, "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924580651.277, "dur": 2.334, + "args": { + "External id": 763560,"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": 688924580651.753, "dur": 1.410, + "args": { + "External id": 763561,"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": 688924580652.561, "dur": 0.534, + "args": { + "External id": 763562,"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": 688924580697.895, "dur": 6.621, + "args": { + "External id": 763563,"Record function id": 0, "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924580699.602, "dur": 4.234, + "args": { + "External id": 763564,"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": 688924580700.681, "dur": 2.327, + "args": { + "External id": 763565,"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": 688924580701.457, "dur": 1.362, + "args": { + "External id": 763566,"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": 688924580708.000, "dur": 4.111, + "args": { + "External id": 763567,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924580709.367, "dur": 2.288, + "args": { + "External id": 763568,"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": 688924580710.046, "dur": 1.215, + "args": { + "External id": 763569,"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": 688924580710.430, "dur": 0.757, + "args": { + "External id": 763570,"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": 688924580715.413, "dur": 6.644, + "args": { + "External id": 763571,"Record function id": 0, "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924580716.752, "dur": 4.851, + "args": { + "External id": 763572,"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": 688924580717.246, "dur": 3.907, + "args": { + "External id": 763573,"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": 688924580718.257, "dur": 2.823, + "args": { + "External id": 763574,"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": 688924580726.544, "dur": 14705.745, + "args": { + "External id": 763575,"Record function id": 0, "Sequence number": 8961985, "Fwd thread id": 1, "Ev Idx": 2742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924580727.725, "dur": 14696.584, + "args": { + "External id": 763576,"Sequence number": 8961985, "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": 688924580727.725, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 4183436, "tid": 31338, + "ts": 688924580758.242, "dur": 52.020, + "args": { + "External id": 763577,"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": 688924580819.518, "dur": 72.651, + "args": { + "External id": 763578,"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": 688924580898.984, "dur": 14517.370, + "args": { + "External id": 763579,"Record function id": 0, "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924580994.965, "dur": 7.005, + "args": { + "External id": 763580,"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": 688924581012.522, "dur": 5.345, + "args": { + "External id": 763581,"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": 688924581033.973, "dur": 13653.653, + "args": { + "External id": 763582,"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": 688924581047.093, "dur": 13631.940, + "args": { + "External id": 763583,"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": 688924581082.076, "dur": 13.149, + "args": { + "External id": 763584,"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": 688924581099.735, "dur": 13520.671, + "args": { + "External id": 763585,"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": 688924581103.198, "dur": 13516.475, + "args": { + "External id": 763586,"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": 688924581106.737, "dur": 4.902, + "args": { + "External id": 763587,"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": 688924581113.185, "dur": 13502.908, + "args": { + "External id": 763588,"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": 688924594776.430, "dur": 8.695, + "args": { + "External id": 763589,"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": 688924594779.378, "dur": 5.363, + "args": { + "External id": 763590,"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": 688924594825.324, "dur": 317.502, + "args": { + "External id": 763591,"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": 688924594849.970, "dur": 288.569, + "args": { + "External id": 763592,"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": 688924594862.477, "dur": 270.572, + "args": { + "External id": 763593,"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": 688924595158.763, "dur": 2.179, + "args": { + "External id": 763594,"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": 688924595216.181, "dur": 6.097, + "args": { + "External id": 763595,"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": 688924595265.162, "dur": 3.247, + "args": { + "External id": 763596,"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": 688924595284.156, "dur": 1.232, + "args": { + "External id": 763597,"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": 688924595296.092, "dur": 1.214, + "args": { + "External id": 763598,"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": 688924595306.660, "dur": 0.820, + "args": { + "External id": 763599,"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": 688924595317.141, "dur": 3.046, + "args": { + "External id": 763600,"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": 688924595330.769, "dur": 0.884, + "args": { + "External id": 763601,"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": 688924595342.936, "dur": 2.156, + "args": { + "External id": 763602,"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": 688924595355.452, "dur": 0.815, + "args": { + "External id": 763603,"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": 688924595446.660, "dur": 2698.820, + "args": { + "External id": 763604,"Record function id": 0, "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 4183436, "tid": 31338, + "ts": 688924595466.746, "dur": 1016.471, + "args": { + "External id": 763605,"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": 688924595481.445, "dur": 380.725, + "args": { + "External id": 763606,"Record function id": 0, "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924595561.734, "dur": 5.464, + "args": { + "External id": 763607,"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": 688924595570.863, "dur": 1.008, + "args": { + "External id": 763608,"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": 688924595573.404, "dur": 1.176, + "args": { + "External id": 763609,"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": 688924595576.600, "dur": 0.830, + "args": { + "External id": 763610,"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": 688924595579.072, "dur": 0.938, + "args": { + "External id": 763611,"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": 688924595582.772, "dur": 0.878, + "args": { + "External id": 763612,"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": 688924595585.174, "dur": 1.631, + "args": { + "External id": 763613,"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": 688924595588.032, "dur": 0.867, + "args": { + "External id": 763614,"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": 688924595590.314, "dur": 2.148, + "args": { + "External id": 763615,"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": 688924595593.844, "dur": 0.845, + "args": { + "External id": 763616,"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": 688924595613.737, "dur": 212.166, + "args": { + "External id": 763617,"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": 688924595633.527, "dur": 187.148, + "args": { + "External id": 763618,"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": 688924595646.670, "dur": 56.527, + "args": { + "External id": 763619,"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": 688924595707.016, "dur": 63.211, + "args": { + "External id": 763620,"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": 688924595709.137, "dur": 60.797, + "args": { + "External id": 763621,"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": 688924595714.327, "dur": 6.034, + "args": { + "External id": 763622,"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": 688924595721.942, "dur": 47.286, + "args": { + "External id": 763623,"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": 688924595952.311, "dur": 522.896, + "args": { + "External id": 763624,"Record function id": 0, "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 4183436, "tid": 31338, + "ts": 688924595969.320, "dur": 494.297, + "args": { + "External id": 763625,"Record function id": 0, "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924596030.446, "dur": 5.435, + "args": { + "External id": 763626,"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": 688924596051.170, "dur": 32.323, + "args": { + "External id": 763627,"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": 688924596055.768, "dur": 1.536, + "args": { + "External id": 763628,"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": 688924596059.327, "dur": 1.584, + "args": { + "External id": 763629,"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": 688924596062.448, "dur": 0.529, + "args": { + "External id": 763630,"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": 688924596064.044, "dur": 2.152, + "args": { + "External id": 763631,"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": 688924596069.043, "dur": 0.321, + "args": { + "External id": 763632,"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": 688924596070.783, "dur": 0.451, + "args": { + "External id": 763633,"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": 688924596072.870, "dur": 0.573, + "args": { + "External id": 763634,"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": 688924596076.552, "dur": 0.702, + "args": { + "External id": 763635,"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": 688924596078.646, "dur": 0.632, + "args": { + "External id": 763636,"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": 688924596093.220, "dur": 28.381, + "args": { + "External id": 763637,"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": 688924596152.817, "dur": 94.866, + "args": { + "External id": 763638,"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": 688924596162.355, "dur": 3.033, + "args": { + "External id": 763639,"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": 688924596169.977, "dur": 9.099, + "args": { + "External id": 763640,"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": 688924596174.063, "dur": 4.635, + "args": { + "External id": 763641,"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": 688924596177.246, "dur": 0.405, + "args": { + "External id": 763642,"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": 688924596185.754, "dur": 28.128, + "args": { + "External id": 763643,"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": 688924596187.554, "dur": 2.322, + "args": { + "External id": 763644,"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": 688924596192.215, "dur": 0.580, + "args": { + "External id": 763645,"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": 688924596193.960, "dur": 0.460, + "args": { + "External id": 763646,"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": 688924596195.470, "dur": 1.395, + "args": { + "External id": 763647,"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": 688924596198.112, "dur": 0.456, + "args": { + "External id": 763648,"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": 688924596202.914, "dur": 0.506, + "args": { + "External id": 763649,"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": 688924596205.868, "dur": 0.244, + "args": { + "External id": 763650,"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": 688924596207.231, "dur": 0.427, + "args": { + "External id": 763651,"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": 688924596209.159, "dur": 1.781, + "args": { + "External id": 763652,"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": 688924596223.524, "dur": 17.226, + "args": { + "External id": 763653,"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": 688924596289.991, "dur": 111.291, + "args": { + "External id": 763654,"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": 688924596314.505, "dur": 83.663, + "args": { + "External id": 763655,"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": 688924596323.467, "dur": 70.697, + "args": { + "External id": 763656,"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": 688924596415.558, "dur": 1.762, + "args": { + "External id": 763657,"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": 688924596490.971, "dur": 1632.588, + "args": { + "External id": 763658,"Sequence number": 8961984, "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": 688924596490.971, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924596598.169, "dur": 149.295, + "args": { + "External id": 763659,"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": 688924596810.130, "dur": 40.798, + "args": { + "External id": 763660,"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": 688924596875.323, "dur": 50.743, + "args": { + "External id": 763661,"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": 688924596936.056, "dur": 27.533, + "args": { + "External id": 763662,"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": 688924596973.246, "dur": 32.995, + "args": { + "External id": 763663,"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": 688924597012.827, "dur": 25.238, + "args": { + "External id": 763664,"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": 688924597047.214, "dur": 28.676, + "args": { + "External id": 763665,"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": 688924597102.717, "dur": 23.692, + "args": { + "External id": 763666,"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": 688924597143.925, "dur": 26.745, + "args": { + "External id": 763667,"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": 688924597189.519, "dur": 19.504, + "args": { + "External id": 763668,"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": 688924597223.075, "dur": 14.109, + "args": { + "External id": 763669,"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": 688924597245.891, "dur": 37.592, + "args": { + "External id": 763670,"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": 688924597286.504, "dur": 30.355, + "args": { + "External id": 763671,"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": 688924597348.081, "dur": 166.089, + "args": { + "External id": 763672,"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": 688924597425.871, "dur": 5.566, + "args": { + "External id": 763673,"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": 688924597433.091, "dur": 2.977, + "args": { + "External id": 763674,"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": 688924597545.660, "dur": 23.173, + "args": { + "External id": 763675,"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": 688924597579.446, "dur": 12.904, + "args": { + "External id": 763676,"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": 688924597599.368, "dur": 39.391, + "args": { + "External id": 763677,"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": 688924597646.278, "dur": 71.358, + "args": { + "External id": 763678,"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": 688924597728.873, "dur": 31.680, + "args": { + "External id": 763679,"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": 688924597765.167, "dur": 41.207, + "args": { + "External id": 763680,"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": 688924597818.046, "dur": 29.150, + "args": { + "External id": 763681,"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": 688924597857.074, "dur": 45.201, + "args": { + "External id": 763682,"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": 688924597930.090, "dur": 24.452, + "args": { + "External id": 763683,"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": 688924597972.430, "dur": 27.472, + "args": { + "External id": 763684,"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": 688924598016.256, "dur": 16.992, + "args": { + "External id": 763685,"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": 688924598050.540, "dur": 15.437, + "args": { + "External id": 763686,"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": 688924598078.356, "dur": 15.483, + "args": { + "External id": 763687,"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": 688924598167.230, "dur": 16.493, + "args": { + "External id": 763688,"Record function id": 0, "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924598170.227, "dur": 12.644, + "args": { + "External id": 763689,"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": 688924598174.438, "dur": 7.621, + "args": { + "External id": 763690,"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": 688924598175.943, "dur": 6.031, + "args": { + "External id": 763691,"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": 688924598187.774, "dur": 4.673, + "args": { + "External id": 763692,"Record function id": 0, "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924598188.782, "dur": 3.133, + "args": { + "External id": 763693,"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": 688924598189.969, "dur": 1.338, + "args": { + "External id": 763694,"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": 688924598190.531, "dur": 0.690, + "args": { + "External id": 763695,"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": 688924598195.861, "dur": 4.761, + "args": { + "External id": 763696,"Record function id": 0, "Ev Idx": 2863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924598197.265, "dur": 2.939, + "args": { + "External id": 763697,"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": 688924598198.296, "dur": 1.471, + "args": { + "External id": 763698,"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": 688924598198.732, "dur": 0.959, + "args": { + "External id": 763699,"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": 688924598204.061, "dur": 5.558, + "args": { + "External id": 763700,"Record function id": 0, "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924598205.313, "dur": 3.888, + "args": { + "External id": 763701,"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": 688924598206.546, "dur": 2.095, + "args": { + "External id": 763702,"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": 688924598207.759, "dur": 0.808, + "args": { + "External id": 763703,"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": 688924598212.777, "dur": 5.107, + "args": { + "External id": 763704,"Record function id": 0, "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924598214.594, "dur": 2.870, + "args": { + "External id": 763705,"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": 688924598215.090, "dur": 1.839, + "args": { + "External id": 763706,"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": 688924598216.204, "dur": 0.649, + "args": { + "External id": 763707,"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": 688924598221.728, "dur": 3.463, + "args": { + "External id": 763708,"Record function id": 0, "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924598222.658, "dur": 2.087, + "args": { + "External id": 763709,"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": 688924598223.105, "dur": 1.116, + "args": { + "External id": 763710,"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": 688924598223.487, "dur": 0.670, + "args": { + "External id": 763711,"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": 688924598228.735, "dur": 3.966, + "args": { + "External id": 763712,"Record function id": 0, "Ev Idx": 2879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924598229.772, "dur": 2.529, + "args": { + "External id": 763713,"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": 688924598230.261, "dur": 1.479, + "args": { + "External id": 763714,"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": 688924598231.030, "dur": 0.632, + "args": { + "External id": 763715,"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": 688924598236.005, "dur": 6.040, + "args": { + "External id": 763716,"Record function id": 0, "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924598237.178, "dur": 4.400, + "args": { + "External id": 763717,"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": 688924598237.619, "dur": 3.556, + "args": { + "External id": 763718,"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": 688924598238.649, "dur": 2.444, + "args": { + "External id": 763719,"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": 688924598245.633, "dur": 3.702, + "args": { + "External id": 763720,"Record function id": 0, "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924598246.618, "dur": 2.271, + "args": { + "External id": 763721,"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": 688924598247.101, "dur": 1.100, + "args": { + "External id": 763722,"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": 688924598247.457, "dur": 0.668, + "args": { + "External id": 763723,"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": 688924598254.085, "dur": 14716.916, + "args": { + "External id": 763724,"Record function id": 0, "Sequence number": 8961983, "Fwd thread id": 1, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924598255.371, "dur": 14705.493, + "args": { + "External id": 763725,"Sequence number": 8961983, "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": 688924598255.371, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 4183436, "tid": 31338, + "ts": 688924598284.122, "dur": 36.465, + "args": { + "External id": 763726,"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": 688924598327.901, "dur": 69.685, + "args": { + "External id": 763727,"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": 688924598404.628, "dur": 14548.746, + "args": { + "External id": 763728,"Record function id": 0, "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924598491.287, "dur": 5.873, + "args": { + "External id": 763729,"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": 688924598506.266, "dur": 4.384, + "args": { + "External id": 763730,"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": 688924598524.274, "dur": 13728.024, + "args": { + "External id": 763731,"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": 688924598541.965, "dur": 13702.093, + "args": { + "External id": 763732,"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": 688924598562.397, "dur": 11.460, + "args": { + "External id": 763733,"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": 688924598578.393, "dur": 13628.855, + "args": { + "External id": 763734,"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": 688924598580.588, "dur": 13625.875, + "args": { + "External id": 763735,"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": 688924598585.337, "dur": 4.725, + "args": { + "External id": 763736,"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": 688924598591.717, "dur": 13611.157, + "args": { + "External id": 763737,"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": 688924612339.339, "dur": 9.600, + "args": { + "External id": 763738,"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": 688924612342.200, "dur": 6.365, + "args": { + "External id": 763739,"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": 688924612374.636, "dur": 250.988, + "args": { + "External id": 763740,"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": 688924612400.525, "dur": 221.148, + "args": { + "External id": 763741,"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": 688924612412.976, "dur": 203.805, + "args": { + "External id": 763742,"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": 688924612641.755, "dur": 2.343, + "args": { + "External id": 763743,"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": 688924612731.809, "dur": 6.819, + "args": { + "External id": 763744,"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": 688924612782.301, "dur": 1.246, + "args": { + "External id": 763745,"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": 688924612817.058, "dur": 1.622, + "args": { + "External id": 763746,"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": 688924612830.835, "dur": 0.718, + "args": { + "External id": 763747,"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": 688924612843.605, "dur": 0.841, + "args": { + "External id": 763748,"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": 688924612855.782, "dur": 1.022, + "args": { + "External id": 763749,"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": 688924612867.917, "dur": 1.225, + "args": { + "External id": 763750,"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": 688924612879.263, "dur": 1.755, + "args": { + "External id": 763751,"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": 688924612891.169, "dur": 1.061, + "args": { + "External id": 763752,"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": 688924612985.545, "dur": 2797.963, + "args": { + "External id": 763753,"Record function id": 0, "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 4183436, "tid": 31338, + "ts": 688924613004.401, "dur": 1129.582, + "args": { + "External id": 763754,"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": 688924613020.489, "dur": 285.112, + "args": { + "External id": 763755,"Record function id": 0, "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924613099.168, "dur": 4.105, + "args": { + "External id": 763756,"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": 688924613106.688, "dur": 1.060, + "args": { + "External id": 763757,"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": 688924613109.500, "dur": 0.990, + "args": { + "External id": 763758,"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": 688924613112.139, "dur": 0.845, + "args": { + "External id": 763759,"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": 688924613114.620, "dur": 0.947, + "args": { + "External id": 763760,"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": 688924613117.007, "dur": 0.966, + "args": { + "External id": 763761,"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": 688924613119.523, "dur": 1.744, + "args": { + "External id": 763762,"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": 688924613123.011, "dur": 2.757, + "args": { + "External id": 763763,"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": 688924613127.257, "dur": 0.853, + "args": { + "External id": 763764,"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": 688924613129.573, "dur": 0.988, + "args": { + "External id": 763765,"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": 688924613147.175, "dur": 133.772, + "args": { + "External id": 763766,"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": 688924613161.719, "dur": 115.354, + "args": { + "External id": 763767,"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": 688924613173.399, "dur": 14.399, + "args": { + "External id": 763768,"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": 688924613190.963, "dur": 59.858, + "args": { + "External id": 763769,"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": 688924613193.612, "dur": 56.945, + "args": { + "External id": 763770,"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": 688924613197.057, "dur": 5.236, + "args": { + "External id": 763771,"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": 688924613204.007, "dur": 46.025, + "args": { + "External id": 763772,"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": 688924613385.646, "dur": 739.627, + "args": { + "External id": 763773,"Record function id": 0, "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 4183436, "tid": 31338, + "ts": 688924613402.072, "dur": 709.603, + "args": { + "External id": 763774,"Record function id": 0, "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924613461.603, "dur": 4.715, + "args": { + "External id": 763775,"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": 688924613481.643, "dur": 31.022, + "args": { + "External id": 763776,"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": 688924613486.085, "dur": 2.331, + "args": { + "External id": 763777,"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": 688924613490.292, "dur": 0.419, + "args": { + "External id": 763778,"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": 688924613492.052, "dur": 2.381, + "args": { + "External id": 763779,"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": 688924613497.041, "dur": 0.452, + "args": { + "External id": 763780,"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": 688924613498.705, "dur": 0.630, + "args": { + "External id": 763781,"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": 688924613500.728, "dur": 0.852, + "args": { + "External id": 763782,"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": 688924613504.618, "dur": 0.634, + "args": { + "External id": 763783,"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": 688924613506.159, "dur": 0.529, + "args": { + "External id": 763784,"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": 688924613507.531, "dur": 1.567, + "args": { + "External id": 763785,"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": 688924613523.346, "dur": 29.915, + "args": { + "External id": 763786,"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": 688924613583.171, "dur": 148.331, + "args": { + "External id": 763787,"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": 688924613592.574, "dur": 4.083, + "args": { + "External id": 763788,"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": 688924613601.542, "dur": 11.638, + "args": { + "External id": 763789,"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": 688924613605.419, "dur": 7.317, + "args": { + "External id": 763790,"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": 688924613608.678, "dur": 2.881, + "args": { + "External id": 763791,"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": 688924613619.493, "dur": 26.078, + "args": { + "External id": 763792,"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": 688924613621.312, "dur": 0.559, + "args": { + "External id": 763793,"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": 688924613623.034, "dur": 1.990, + "args": { + "External id": 763794,"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": 688924613626.313, "dur": 0.591, + "args": { + "External id": 763795,"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": 688924613628.079, "dur": 0.659, + "args": { + "External id": 763796,"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": 688924613632.080, "dur": 0.241, + "args": { + "External id": 763797,"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": 688924613633.637, "dur": 0.609, + "args": { + "External id": 763798,"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": 688924613635.946, "dur": 0.557, + "args": { + "External id": 763799,"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": 688924613638.281, "dur": 2.407, + "args": { + "External id": 763800,"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": 688924613642.172, "dur": 0.323, + "args": { + "External id": 763801,"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": 688924613699.998, "dur": 22.751, + "args": { + "External id": 763802,"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": 688924613779.920, "dur": 239.394, + "args": { + "External id": 763803,"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": 688924613820.747, "dur": 193.560, + "args": { + "External id": 763804,"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": 688924613832.540, "dur": 95.244, + "args": { + "External id": 763805,"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": 688924614042.172, "dur": 2.759, + "args": { + "External id": 763806,"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": 688924614141.543, "dur": 1618.862, + "args": { + "External id": 763807,"Sequence number": 8961982, "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": 688924614141.543, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924614258.222, "dur": 107.635, + "args": { + "External id": 763808,"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": 688924614404.266, "dur": 41.475, + "args": { + "External id": 763809,"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": 688924614464.864, "dur": 43.998, + "args": { + "External id": 763810,"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": 688924614517.882, "dur": 26.830, + "args": { + "External id": 763811,"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": 688924614551.056, "dur": 32.101, + "args": { + "External id": 763812,"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": 688924614590.209, "dur": 22.753, + "args": { + "External id": 763813,"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": 688924614622.453, "dur": 64.336, + "args": { + "External id": 763814,"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": 688924614716.367, "dur": 24.873, + "args": { + "External id": 763815,"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": 688924614759.467, "dur": 40.392, + "args": { + "External id": 763816,"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": 688924614824.203, "dur": 22.334, + "args": { + "External id": 763817,"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": 688924614859.723, "dur": 14.762, + "args": { + "External id": 763818,"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": 688924614885.836, "dur": 42.719, + "args": { + "External id": 763819,"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": 688924614932.226, "dur": 30.145, + "args": { + "External id": 763820,"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": 688924614991.215, "dur": 181.002, + "args": { + "External id": 763821,"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": 688924615074.835, "dur": 6.176, + "args": { + "External id": 763822,"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": 688924615082.977, "dur": 4.901, + "args": { + "External id": 763823,"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": 688924615206.834, "dur": 24.279, + "args": { + "External id": 763824,"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": 688924615241.327, "dur": 13.579, + "args": { + "External id": 763825,"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": 688924615264.421, "dur": 43.830, + "args": { + "External id": 763826,"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": 688924615313.628, "dur": 29.398, + "args": { + "External id": 763827,"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": 688924615349.447, "dur": 44.145, + "args": { + "External id": 763828,"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": 688924615404.020, "dur": 34.315, + "args": { + "External id": 763829,"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": 688924615447.783, "dur": 26.722, + "args": { + "External id": 763830,"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": 688924615481.834, "dur": 29.471, + "args": { + "External id": 763831,"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": 688924615528.539, "dur": 25.506, + "args": { + "External id": 763832,"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": 688924615572.654, "dur": 24.200, + "args": { + "External id": 763833,"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": 688924615611.494, "dur": 16.032, + "args": { + "External id": 763834,"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": 688924615642.193, "dur": 52.277, + "args": { + "External id": 763835,"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": 688924615711.703, "dur": 18.585, + "args": { + "External id": 763836,"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": 688924615819.300, "dur": 16.673, + "args": { + "External id": 763837,"Record function id": 0, "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924615823.356, "dur": 11.517, + "args": { + "External id": 763838,"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": 688924615827.482, "dur": 5.983, + "args": { + "External id": 763839,"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": 688924615829.080, "dur": 4.180, + "args": { + "External id": 763840,"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": 688924615839.838, "dur": 4.203, + "args": { + "External id": 763841,"Record function id": 0, "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924615841.073, "dur": 2.531, + "args": { + "External id": 763842,"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": 688924615841.811, "dur": 1.337, + "args": { + "External id": 763843,"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": 688924615842.285, "dur": 0.747, + "args": { + "External id": 763844,"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": 688924615847.243, "dur": 3.664, + "args": { + "External id": 763845,"Record function id": 0, "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924615848.342, "dur": 2.150, + "args": { + "External id": 763846,"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": 688924615848.957, "dur": 1.108, + "args": { + "External id": 763847,"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": 688924615849.308, "dur": 0.681, + "args": { + "External id": 763848,"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": 688924615854.058, "dur": 5.058, + "args": { + "External id": 763849,"Record function id": 0, "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924615855.173, "dur": 3.499, + "args": { + "External id": 763850,"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": 688924615855.649, "dur": 2.344, + "args": { + "External id": 763851,"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": 688924615856.657, "dur": 1.273, + "args": { + "External id": 763852,"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": 688924615862.191, "dur": 5.937, + "args": { + "External id": 763853,"Record function id": 0, "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924615863.977, "dur": 3.727, + "args": { + "External id": 763854,"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": 688924615864.920, "dur": 2.089, + "args": { + "External id": 763855,"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": 688924615866.130, "dur": 0.802, + "args": { + "External id": 763856,"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": 688924615871.396, "dur": 4.781, + "args": { + "External id": 763857,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924615872.936, "dur": 2.826, + "args": { + "External id": 763858,"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": 688924615873.597, "dur": 1.652, + "args": { + "External id": 763859,"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": 688924615874.256, "dur": 0.925, + "args": { + "External id": 763860,"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": 688924615879.484, "dur": 5.647, + "args": { + "External id": 763861,"Record function id": 0, "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924615880.380, "dur": 4.349, + "args": { + "External id": 763862,"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": 688924615880.877, "dur": 3.285, + "args": { + "External id": 763863,"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": 688924615881.576, "dur": 2.520, + "args": { + "External id": 763864,"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": 688924615888.454, "dur": 4.010, + "args": { + "External id": 763865,"Record function id": 0, "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924615889.533, "dur": 2.492, + "args": { + "External id": 763866,"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": 688924615889.995, "dur": 1.494, + "args": { + "External id": 763867,"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": 688924615890.544, "dur": 0.878, + "args": { + "External id": 763868,"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": 688924615895.933, "dur": 3.789, + "args": { + "External id": 763869,"Record function id": 0, "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924615896.942, "dur": 2.372, + "args": { + "External id": 763870,"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": 688924615897.402, "dur": 1.198, + "args": { + "External id": 763871,"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": 688924615897.777, "dur": 0.758, + "args": { + "External id": 763872,"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": 688924615904.133, "dur": 14633.541, + "args": { + "External id": 763873,"Record function id": 0, "Sequence number": 8961981, "Fwd thread id": 1, "Ev Idx": 3040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924615905.358, "dur": 14622.736, + "args": { + "External id": 763874,"Sequence number": 8961981, "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": 688924615905.358, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 4183436, "tid": 31338, + "ts": 688924615937.554, "dur": 39.401, + "args": { + "External id": 763875,"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": 688924615984.681, "dur": 68.143, + "args": { + "External id": 763876,"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": 688924616059.171, "dur": 14461.059, + "args": { + "External id": 763877,"Record function id": 0, "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924616148.218, "dur": 6.875, + "args": { + "External id": 763878,"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": 688924616164.252, "dur": 4.505, + "args": { + "External id": 763879,"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": 688924616182.543, "dur": 13688.666, + "args": { + "External id": 763880,"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": 688924616199.777, "dur": 13663.035, + "args": { + "External id": 763881,"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": 688924616254.156, "dur": 17.514, + "args": { + "External id": 763882,"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": 688924616276.290, "dur": 13550.090, + "args": { + "External id": 763883,"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": 688924616278.750, "dur": 13546.796, + "args": { + "External id": 763884,"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": 688924616282.030, "dur": 6.202, + "args": { + "External id": 763885,"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": 688924616289.741, "dur": 13532.200, + "args": { + "External id": 763886,"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": 688924629961.744, "dur": 9.906, + "args": { + "External id": 763887,"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": 688924629965.478, "dur": 5.804, + "args": { + "External id": 763888,"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": 688924629998.303, "dur": 252.425, + "args": { + "External id": 763889,"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": 688924630025.063, "dur": 221.504, + "args": { + "External id": 763890,"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": 688924630035.819, "dur": 206.123, + "args": { + "External id": 763891,"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": 688924630267.748, "dur": 2.124, + "args": { + "External id": 763892,"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": 688924630320.287, "dur": 7.923, + "args": { + "External id": 763893,"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": 688924630370.290, "dur": 1.173, + "args": { + "External id": 763894,"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": 688924630388.171, "dur": 1.223, + "args": { + "External id": 763895,"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": 688924630401.042, "dur": 0.793, + "args": { + "External id": 763896,"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": 688924630413.241, "dur": 2.950, + "args": { + "External id": 763897,"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": 688924630425.729, "dur": 0.884, + "args": { + "External id": 763898,"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": 688924630436.899, "dur": 0.854, + "args": { + "External id": 763899,"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": 688924630448.532, "dur": 1.849, + "args": { + "External id": 763900,"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": 688924630460.670, "dur": 2.182, + "args": { + "External id": 763901,"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": 688924630551.625, "dur": 2754.784, + "args": { + "External id": 763902,"Record function id": 0, "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 4183436, "tid": 31338, + "ts": 688924630571.875, "dur": 1048.170, + "args": { + "External id": 763903,"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": 688924630586.539, "dur": 413.554, + "args": { + "External id": 763904,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924630754.190, "dur": 5.469, + "args": { + "External id": 763905,"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": 688924630764.111, "dur": 0.861, + "args": { + "External id": 763906,"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": 688924630766.767, "dur": 1.104, + "args": { + "External id": 763907,"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": 688924630769.248, "dur": 0.896, + "args": { + "External id": 763908,"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": 688924630771.782, "dur": 0.859, + "args": { + "External id": 763909,"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": 688924630774.331, "dur": 0.760, + "args": { + "External id": 763910,"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": 688924630776.559, "dur": 3.487, + "args": { + "External id": 763911,"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": 688924630781.653, "dur": 0.973, + "args": { + "External id": 763912,"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": 688924630784.143, "dur": 0.783, + "args": { + "External id": 763913,"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": 688924630802.663, "dur": 1.344, + "args": { + "External id": 763914,"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": 688924630824.477, "dur": 141.977, + "args": { + "External id": 763915,"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": 688924630840.094, "dur": 122.042, + "args": { + "External id": 763916,"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": 688924630854.452, "dur": 14.125, + "args": { + "External id": 763917,"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": 688924630871.556, "dur": 62.533, + "args": { + "External id": 763918,"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": 688924630873.805, "dur": 59.960, + "args": { + "External id": 763919,"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": 688924630877.573, "dur": 6.098, + "args": { + "External id": 763920,"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": 688924630885.211, "dur": 47.906, + "args": { + "External id": 763921,"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": 688924631095.029, "dur": 517.201, + "args": { + "External id": 763922,"Record function id": 0, "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 4183436, "tid": 31338, + "ts": 688924631112.754, "dur": 486.796, + "args": { + "External id": 763923,"Record function id": 0, "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924631172.415, "dur": 4.748, + "args": { + "External id": 763924,"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": 688924631192.299, "dur": 29.171, + "args": { + "External id": 763925,"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": 688924631196.909, "dur": 1.346, + "args": { + "External id": 763926,"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": 688924631200.411, "dur": 3.481, + "args": { + "External id": 763927,"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": 688924631205.028, "dur": 0.270, + "args": { + "External id": 763928,"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": 688924631206.830, "dur": 0.658, + "args": { + "External id": 763929,"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": 688924631209.518, "dur": 0.361, + "args": { + "External id": 763930,"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": 688924631211.234, "dur": 0.427, + "args": { + "External id": 763931,"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": 688924631212.566, "dur": 0.456, + "args": { + "External id": 763932,"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": 688924631215.726, "dur": 0.408, + "args": { + "External id": 763933,"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": 688924631217.048, "dur": 0.802, + "args": { + "External id": 763934,"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": 688924631231.095, "dur": 29.370, + "args": { + "External id": 763935,"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": 688924631291.864, "dur": 93.939, + "args": { + "External id": 763936,"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": 688924631301.016, "dur": 5.965, + "args": { + "External id": 763937,"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": 688924631311.757, "dur": 9.037, + "args": { + "External id": 763938,"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": 688924631315.368, "dur": 5.022, + "args": { + "External id": 763939,"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": 688924631318.634, "dur": 0.567, + "args": { + "External id": 763940,"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": 688924631327.272, "dur": 23.065, + "args": { + "External id": 763941,"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": 688924631328.654, "dur": 0.599, + "args": { + "External id": 763942,"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": 688924631331.614, "dur": 0.498, + "args": { + "External id": 763943,"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": 688924631333.390, "dur": 0.532, + "args": { + "External id": 763944,"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": 688924631335.402, "dur": 1.212, + "args": { + "External id": 763945,"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": 688924631337.826, "dur": 0.501, + "args": { + "External id": 763946,"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": 688924631339.607, "dur": 0.355, + "args": { + "External id": 763947,"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": 688924631342.113, "dur": 2.036, + "args": { + "External id": 763948,"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": 688924631345.121, "dur": 0.522, + "args": { + "External id": 763949,"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": 688924631346.754, "dur": 0.356, + "args": { + "External id": 763950,"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": 688924631360.830, "dur": 17.774, + "args": { + "External id": 763951,"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": 688924631426.190, "dur": 108.859, + "args": { + "External id": 763952,"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": 688924631447.857, "dur": 83.984, + "args": { + "External id": 763953,"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": 688924631457.919, "dur": 68.588, + "args": { + "External id": 763954,"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": 688924631551.366, "dur": 1.952, + "args": { + "External id": 763955,"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": 688924631628.016, "dur": 1655.744, + "args": { + "External id": 763956,"Sequence number": 8961980, "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": 688924631628.016, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924631784.946, "dur": 115.682, + "args": { + "External id": 763957,"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": 688924631942.775, "dur": 36.722, + "args": { + "External id": 763958,"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": 688924631998.461, "dur": 41.203, + "args": { + "External id": 763959,"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": 688924632049.035, "dur": 26.515, + "args": { + "External id": 763960,"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": 688924632082.253, "dur": 32.501, + "args": { + "External id": 763961,"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": 688924632122.881, "dur": 22.989, + "args": { + "External id": 763962,"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": 688924632153.630, "dur": 28.482, + "args": { + "External id": 763963,"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": 688924632204.009, "dur": 21.985, + "args": { + "External id": 763964,"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": 688924632243.505, "dur": 30.033, + "args": { + "External id": 763965,"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": 688924632293.855, "dur": 19.363, + "args": { + "External id": 763966,"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": 688924632324.994, "dur": 14.879, + "args": { + "External id": 763967,"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": 688924632350.305, "dur": 38.297, + "args": { + "External id": 763968,"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": 688924632391.816, "dur": 30.430, + "args": { + "External id": 763969,"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": 688924632449.670, "dur": 185.976, + "args": { + "External id": 763970,"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": 688924632531.855, "dur": 6.136, + "args": { + "External id": 763971,"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": 688924632539.430, "dur": 5.005, + "args": { + "External id": 763972,"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": 688924632712.938, "dur": 27.893, + "args": { + "External id": 763973,"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": 688924632755.310, "dur": 15.234, + "args": { + "External id": 763974,"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": 688924632780.334, "dur": 71.498, + "args": { + "External id": 763975,"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": 688924632860.026, "dur": 32.222, + "args": { + "External id": 763976,"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": 688924632900.675, "dur": 31.096, + "args": { + "External id": 763977,"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": 688924632947.191, "dur": 41.241, + "args": { + "External id": 763978,"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": 688924633001.574, "dur": 27.410, + "args": { + "External id": 763979,"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": 688924633036.540, "dur": 32.712, + "args": { + "External id": 763980,"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": 688924633091.059, "dur": 27.088, + "args": { + "External id": 763981,"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": 688924633135.943, "dur": 24.878, + "args": { + "External id": 763982,"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": 688924633177.572, "dur": 16.626, + "args": { + "External id": 763983,"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": 688924633209.502, "dur": 16.044, + "args": { + "External id": 763984,"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": 688924633239.982, "dur": 16.198, + "args": { + "External id": 763985,"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": 688924633328.493, "dur": 13.986, + "args": { + "External id": 763986,"Record function id": 0, "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924633331.646, "dur": 10.013, + "args": { + "External id": 763987,"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": 688924633335.577, "dur": 5.203, + "args": { + "External id": 763988,"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": 688924633336.768, "dur": 3.909, + "args": { + "External id": 763989,"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": 688924633346.463, "dur": 4.639, + "args": { + "External id": 763990,"Record function id": 0, "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924633347.576, "dur": 3.080, + "args": { + "External id": 763991,"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": 688924633348.245, "dur": 1.750, + "args": { + "External id": 763992,"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": 688924633348.965, "dur": 0.940, + "args": { + "External id": 763993,"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": 688924633354.262, "dur": 4.027, + "args": { + "External id": 763994,"Record function id": 0, "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924633355.350, "dur": 2.502, + "args": { + "External id": 763995,"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": 688924633355.936, "dur": 1.435, + "args": { + "External id": 763996,"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": 688924633356.476, "dur": 0.811, + "args": { + "External id": 763997,"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": 688924633361.371, "dur": 6.913, + "args": { + "External id": 763998,"Record function id": 0, "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924633362.742, "dur": 5.135, + "args": { + "External id": 763999,"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": 688924633363.700, "dur": 3.804, + "args": { + "External id": 764000,"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": 688924633364.248, "dur": 3.189, + "args": { + "External id": 764001,"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": 688924633371.417, "dur": 4.394, + "args": { + "External id": 764002,"Record function id": 0, "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924633372.588, "dur": 2.777, + "args": { + "External id": 764003,"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": 688924633373.231, "dur": 1.774, + "args": { + "External id": 764004,"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": 688924633374.030, "dur": 0.911, + "args": { + "External id": 764005,"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": 688924633378.890, "dur": 4.142, + "args": { + "External id": 764006,"Record function id": 0, "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924633380.275, "dur": 2.348, + "args": { + "External id": 764007,"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": 688924633380.983, "dur": 1.240, + "args": { + "External id": 764008,"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": 688924633381.466, "dur": 0.689, + "args": { + "External id": 764009,"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": 688924633386.359, "dur": 3.866, + "args": { + "External id": 764010,"Record function id": 0, "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924633387.519, "dur": 2.282, + "args": { + "External id": 764011,"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": 688924633387.968, "dur": 1.258, + "args": { + "External id": 764012,"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": 688924633388.448, "dur": 0.702, + "args": { + "External id": 764013,"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": 688924633393.370, "dur": 3.699, + "args": { + "External id": 764014,"Record function id": 0, "Ev Idx": 3181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924633394.211, "dur": 2.450, + "args": { + "External id": 764015,"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": 688924633394.836, "dur": 1.416, + "args": { + "External id": 764016,"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": 688924633395.376, "dur": 0.799, + "args": { + "External id": 764017,"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": 688924633400.151, "dur": 3.966, + "args": { + "External id": 764018,"Record function id": 0, "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924633401.165, "dur": 2.545, + "args": { + "External id": 764019,"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": 688924633401.595, "dur": 1.448, + "args": { + "External id": 764020,"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": 688924633402.015, "dur": 0.952, + "args": { + "External id": 764021,"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": 688924633407.771, "dur": 14862.482, + "args": { + "External id": 764022,"Record function id": 0, "Sequence number": 8961979, "Fwd thread id": 1, "Ev Idx": 3189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924633409.159, "dur": 14851.906, + "args": { + "External id": 764023,"Sequence number": 8961979, "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": 688924633409.159, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 4183436, "tid": 31338, + "ts": 688924633438.779, "dur": 37.939, + "args": { + "External id": 764024,"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": 688924633484.551, "dur": 68.440, + "args": { + "External id": 764025,"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": 688924633558.823, "dur": 14694.796, + "args": { + "External id": 764026,"Record function id": 0, "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924633647.901, "dur": 48.913, + "args": { + "External id": 764027,"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": 688924633709.640, "dur": 8.563, + "args": { + "External id": 764028,"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": 688924633734.203, "dur": 13767.339, + "args": { + "External id": 764029,"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": 688924633748.425, "dur": 13745.198, + "args": { + "External id": 764030,"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": 688924633769.060, "dur": 34.326, + "args": { + "External id": 764031,"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": 688924633808.957, "dur": 13650.908, + "args": { + "External id": 764032,"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": 688924633811.322, "dur": 13647.936, + "args": { + "External id": 764033,"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": 688924633816.240, "dur": 5.991, + "args": { + "External id": 764034,"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": 688924633823.905, "dur": 13631.962, + "args": { + "External id": 764035,"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": 688924647589.204, "dur": 8.412, + "args": { + "External id": 764036,"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": 688924647591.849, "dur": 5.419, + "args": { + "External id": 764037,"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": 688924647623.506, "dur": 349.699, + "args": { + "External id": 764038,"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": 688924647648.011, "dur": 319.998, + "args": { + "External id": 764039,"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": 688924647686.783, "dur": 275.884, + "args": { + "External id": 764040,"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": 688924647992.504, "dur": 2.552, + "args": { + "External id": 764041,"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": 688924648054.007, "dur": 6.275, + "args": { + "External id": 764042,"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": 688924648102.900, "dur": 1.634, + "args": { + "External id": 764043,"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": 688924648120.685, "dur": 1.110, + "args": { + "External id": 764044,"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": 688924648136.370, "dur": 0.734, + "args": { + "External id": 764045,"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": 688924648147.875, "dur": 0.915, + "args": { + "External id": 764046,"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": 688924648158.242, "dur": 0.960, + "args": { + "External id": 764047,"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": 688924648170.154, "dur": 0.823, + "args": { + "External id": 764048,"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": 688924648183.113, "dur": 1.882, + "args": { + "External id": 764049,"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": 688924648194.102, "dur": 0.753, + "args": { + "External id": 764050,"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": 688924648283.782, "dur": 2653.620, + "args": { + "External id": 764051,"Record function id": 0, "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 4183436, "tid": 31338, + "ts": 688924648303.977, "dur": 987.548, + "args": { + "External id": 764052,"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": 688924648318.921, "dur": 290.174, + "args": { + "External id": 764053,"Record function id": 0, "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924648399.166, "dur": 4.076, + "args": { + "External id": 764054,"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": 688924648406.470, "dur": 0.810, + "args": { + "External id": 764055,"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": 688924648408.782, "dur": 0.708, + "args": { + "External id": 764056,"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": 688924648411.126, "dur": 3.064, + "args": { + "External id": 764057,"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": 688924648416.014, "dur": 0.711, + "args": { + "External id": 764058,"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": 688924648418.282, "dur": 1.085, + "args": { + "External id": 764059,"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": 688924648420.920, "dur": 1.609, + "args": { + "External id": 764060,"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": 688924648423.909, "dur": 1.092, + "args": { + "External id": 764061,"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": 688924648426.793, "dur": 0.815, + "args": { + "External id": 764062,"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": 688924648429.122, "dur": 0.622, + "args": { + "External id": 764063,"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": 688924648446.087, "dur": 136.768, + "args": { + "External id": 764064,"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": 688924648462.771, "dur": 116.065, + "args": { + "External id": 764065,"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": 688924648474.982, "dur": 13.759, + "args": { + "External id": 764066,"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": 688924648491.499, "dur": 61.794, + "args": { + "External id": 764067,"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": 688924648493.886, "dur": 59.030, + "args": { + "External id": 764068,"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": 688924648497.344, "dur": 7.765, + "args": { + "External id": 764069,"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": 688924648506.967, "dur": 45.368, + "args": { + "External id": 764070,"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": 688924648745.330, "dur": 537.731, + "args": { + "External id": 764071,"Record function id": 0, "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 4183436, "tid": 31338, + "ts": 688924648764.747, "dur": 506.123, + "args": { + "External id": 764072,"Record function id": 0, "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924648844.500, "dur": 6.269, + "args": { + "External id": 764073,"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": 688924648866.738, "dur": 28.222, + "args": { + "External id": 764074,"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": 688924648871.571, "dur": 1.440, + "args": { + "External id": 764075,"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": 688924648875.725, "dur": 0.731, + "args": { + "External id": 764076,"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": 688924648877.603, "dur": 0.673, + "args": { + "External id": 764077,"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": 688924648879.284, "dur": 1.822, + "args": { + "External id": 764078,"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": 688924648881.995, "dur": 0.518, + "args": { + "External id": 764079,"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": 688924648883.400, "dur": 0.560, + "args": { + "External id": 764080,"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": 688924648886.611, "dur": 2.010, + "args": { + "External id": 764081,"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": 688924648889.361, "dur": 0.268, + "args": { + "External id": 764082,"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": 688924648890.601, "dur": 0.312, + "args": { + "External id": 764083,"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": 688924648906.272, "dur": 32.864, + "args": { + "External id": 764084,"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": 688924648969.644, "dur": 89.735, + "args": { + "External id": 764085,"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": 688924648979.845, "dur": 3.470, + "args": { + "External id": 764086,"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": 688924648987.951, "dur": 10.183, + "args": { + "External id": 764087,"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": 688924648992.035, "dur": 5.657, + "args": { + "External id": 764088,"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": 688924648995.025, "dur": 1.476, + "args": { + "External id": 764089,"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": 688924649004.187, "dur": 21.285, + "args": { + "External id": 764090,"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": 688924649005.942, "dur": 0.633, + "args": { + "External id": 764091,"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": 688924649007.720, "dur": 0.595, + "args": { + "External id": 764092,"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": 688924649009.077, "dur": 0.462, + "args": { + "External id": 764093,"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": 688924649012.044, "dur": 1.879, + "args": { + "External id": 764094,"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": 688924649014.708, "dur": 0.374, + "args": { + "External id": 764095,"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": 688924649016.401, "dur": 1.162, + "args": { + "External id": 764096,"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": 688924649018.309, "dur": 0.334, + "args": { + "External id": 764097,"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": 688924649019.778, "dur": 0.601, + "args": { + "External id": 764098,"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": 688924649022.613, "dur": 0.233, + "args": { + "External id": 764099,"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": 688924649034.893, "dur": 16.972, + "args": { + "External id": 764100,"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": 688924649102.972, "dur": 106.045, + "args": { + "External id": 764101,"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": 688924649122.537, "dur": 82.990, + "args": { + "External id": 764102,"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": 688924649131.050, "dur": 70.171, + "args": { + "External id": 764103,"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": 688924649221.731, "dur": 1.961, + "args": { + "External id": 764104,"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": 688924649300.002, "dur": 1616.052, + "args": { + "External id": 764105,"Sequence number": 8961978, "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": 688924649300.002, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924649409.390, "dur": 96.743, + "args": { + "External id": 764106,"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": 688924649543.228, "dur": 38.927, + "args": { + "External id": 764107,"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": 688924649599.335, "dur": 41.824, + "args": { + "External id": 764108,"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": 688924649651.192, "dur": 77.069, + "args": { + "External id": 764109,"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": 688924649739.146, "dur": 33.780, + "args": { + "External id": 764110,"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": 688924649784.133, "dur": 41.319, + "args": { + "External id": 764111,"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": 688924649836.449, "dur": 29.705, + "args": { + "External id": 764112,"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": 688924649891.276, "dur": 24.777, + "args": { + "External id": 764113,"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": 688924649936.381, "dur": 26.924, + "args": { + "External id": 764114,"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": 688924649979.923, "dur": 21.394, + "args": { + "External id": 764115,"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": 688924650016.628, "dur": 15.532, + "args": { + "External id": 764116,"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": 688924650040.962, "dur": 40.955, + "args": { + "External id": 764117,"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": 688924650085.472, "dur": 30.087, + "args": { + "External id": 764118,"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": 688924650146.739, "dur": 173.968, + "args": { + "External id": 764119,"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": 688924650226.902, "dur": 5.577, + "args": { + "External id": 764120,"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": 688924650234.073, "dur": 2.167, + "args": { + "External id": 764121,"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": 688924650352.387, "dur": 25.305, + "args": { + "External id": 764122,"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": 688924650387.999, "dur": 14.534, + "args": { + "External id": 764123,"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": 688924650410.493, "dur": 46.470, + "args": { + "External id": 764124,"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": 688924650462.678, "dur": 33.219, + "args": { + "External id": 764125,"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": 688924650504.186, "dur": 27.005, + "args": { + "External id": 764126,"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": 688924650535.696, "dur": 28.366, + "args": { + "External id": 764127,"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": 688924650569.029, "dur": 26.107, + "args": { + "External id": 764128,"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": 688924650603.018, "dur": 26.525, + "args": { + "External id": 764129,"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": 688924650644.132, "dur": 73.895, + "args": { + "External id": 764130,"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": 688924650747.648, "dur": 26.209, + "args": { + "External id": 764131,"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": 688924650801.545, "dur": 21.320, + "args": { + "External id": 764132,"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": 688924650843.074, "dur": 14.141, + "args": { + "External id": 764133,"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": 688924650869.398, "dur": 19.250, + "args": { + "External id": 764134,"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": 688924650958.592, "dur": 14.419, + "args": { + "External id": 764135,"Record function id": 0, "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924650961.595, "dur": 10.552, + "args": { + "External id": 764136,"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": 688924650965.630, "dur": 5.510, + "args": { + "External id": 764137,"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": 688924650967.181, "dur": 3.824, + "args": { + "External id": 764138,"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": 688924650976.937, "dur": 4.916, + "args": { + "External id": 764139,"Record function id": 0, "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924650978.370, "dur": 3.053, + "args": { + "External id": 764140,"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": 688924650979.138, "dur": 1.639, + "args": { + "External id": 764141,"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": 688924650979.838, "dur": 0.826, + "args": { + "External id": 764142,"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": 688924650985.281, "dur": 5.349, + "args": { + "External id": 764143,"Record function id": 0, "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924650986.258, "dur": 3.976, + "args": { + "External id": 764144,"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": 688924650986.910, "dur": 2.922, + "args": { + "External id": 764145,"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": 688924650987.347, "dur": 2.403, + "args": { + "External id": 764146,"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": 688924650993.832, "dur": 4.859, + "args": { + "External id": 764147,"Record function id": 0, "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924650995.421, "dur": 2.860, + "args": { + "External id": 764148,"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": 688924650996.430, "dur": 1.460, + "args": { + "External id": 764149,"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": 688924650996.935, "dur": 0.868, + "args": { + "External id": 764150,"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": 688924651001.809, "dur": 4.337, + "args": { + "External id": 764151,"Record function id": 0, "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924651002.974, "dur": 2.784, + "args": { + "External id": 764152,"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": 688924651003.927, "dur": 1.199, + "args": { + "External id": 764153,"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": 688924651004.476, "dur": 0.583, + "args": { + "External id": 764154,"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": 688924651009.371, "dur": 3.681, + "args": { + "External id": 764155,"Record function id": 0, "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924651010.319, "dur": 2.325, + "args": { + "External id": 764156,"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": 688924651010.855, "dur": 1.186, + "args": { + "External id": 764157,"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": 688924651011.326, "dur": 0.649, + "args": { + "External id": 764158,"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": 688924651016.261, "dur": 3.306, + "args": { + "External id": 764159,"Record function id": 0, "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924651017.370, "dur": 1.807, + "args": { + "External id": 764160,"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": 688924651017.841, "dur": 0.952, + "args": { + "External id": 764161,"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": 688924651018.175, "dur": 0.545, + "args": { + "External id": 764162,"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": 688924651022.652, "dur": 3.542, + "args": { + "External id": 764163,"Record function id": 0, "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924651023.994, "dur": 1.828, + "args": { + "External id": 764164,"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": 688924651024.446, "dur": 0.973, + "args": { + "External id": 764165,"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": 688924651024.774, "dur": 0.569, + "args": { + "External id": 764166,"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": 688924651029.263, "dur": 3.418, + "args": { + "External id": 764167,"Record function id": 0, "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924651030.309, "dur": 1.961, + "args": { + "External id": 764168,"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": 688924651030.786, "dur": 1.041, + "args": { + "External id": 764169,"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": 688924651031.101, "dur": 0.654, + "args": { + "External id": 764170,"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": 688924651036.465, "dur": 14880.519, + "args": { + "External id": 764171,"Record function id": 0, "Sequence number": 8961977, "Fwd thread id": 1, "Ev Idx": 3338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924651037.766, "dur": 14870.375, + "args": { + "External id": 764172,"Sequence number": 8961977, "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": 688924651037.766, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 4183436, "tid": 31338, + "ts": 688924651066.839, "dur": 39.325, + "args": { + "External id": 764173,"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": 688924651113.930, "dur": 68.487, + "args": { + "External id": 764174,"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": 688924651188.390, "dur": 14711.647, + "args": { + "External id": 764175,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924651278.144, "dur": 6.486, + "args": { + "External id": 764176,"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": 688924651293.948, "dur": 6.022, + "args": { + "External id": 764177,"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": 688924651313.356, "dur": 13889.346, + "args": { + "External id": 764178,"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": 688924651329.747, "dur": 13863.858, + "args": { + "External id": 764179,"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": 688924651376.052, "dur": 16.568, + "args": { + "External id": 764180,"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": 688924651397.056, "dur": 13763.655, + "args": { + "External id": 764181,"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": 688924651400.715, "dur": 13759.251, + "args": { + "External id": 764182,"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": 688924651404.333, "dur": 4.655, + "args": { + "External id": 764183,"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": 688924651410.620, "dur": 13745.867, + "args": { + "External id": 764184,"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": 688924665292.766, "dur": 8.694, + "args": { + "External id": 764185,"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": 688924665295.284, "dur": 5.774, + "args": { + "External id": 764186,"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": 688924665328.271, "dur": 250.794, + "args": { + "External id": 764187,"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": 688924665351.741, "dur": 223.471, + "args": { + "External id": 764188,"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": 688924665363.892, "dur": 206.691, + "args": { + "External id": 764189,"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": 688924665594.835, "dur": 2.037, + "args": { + "External id": 764190,"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": 688924665645.556, "dur": 38.531, + "args": { + "External id": 764191,"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": 688924665729.195, "dur": 1.986, + "args": { + "External id": 764192,"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": 688924665746.019, "dur": 2.878, + "args": { + "External id": 764193,"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": 688924665760.618, "dur": 0.998, + "args": { + "External id": 764194,"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": 688924665773.045, "dur": 0.817, + "args": { + "External id": 764195,"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": 688924665783.213, "dur": 0.769, + "args": { + "External id": 764196,"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": 688924665811.319, "dur": 3.280, + "args": { + "External id": 764197,"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": 688924665826.657, "dur": 1.661, + "args": { + "External id": 764198,"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": 688924665838.033, "dur": 0.672, + "args": { + "External id": 764199,"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": 688924665933.393, "dur": 2570.785, + "args": { + "External id": 764200,"Record function id": 0, "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 4183436, "tid": 31338, + "ts": 688924665952.376, "dur": 988.987, + "args": { + "External id": 764201,"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": 688924665967.316, "dur": 291.901, + "args": { + "External id": 764202,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924666049.138, "dur": 4.238, + "args": { + "External id": 764203,"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": 688924666056.552, "dur": 1.316, + "args": { + "External id": 764204,"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": 688924666059.732, "dur": 2.676, + "args": { + "External id": 764205,"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": 688924666064.254, "dur": 1.186, + "args": { + "External id": 764206,"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": 688924666067.306, "dur": 0.773, + "args": { + "External id": 764207,"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": 688924666070.114, "dur": 1.014, + "args": { + "External id": 764208,"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": 688924666073.120, "dur": 1.644, + "args": { + "External id": 764209,"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": 688924666076.235, "dur": 1.057, + "args": { + "External id": 764210,"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": 688924666078.945, "dur": 0.766, + "args": { + "External id": 764211,"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": 688924666081.364, "dur": 0.657, + "args": { + "External id": 764212,"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": 688924666098.023, "dur": 136.130, + "args": { + "External id": 764213,"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": 688924666113.245, "dur": 117.194, + "args": { + "External id": 764214,"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": 688924666127.031, "dur": 13.989, + "args": { + "External id": 764215,"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": 688924666143.989, "dur": 62.320, + "args": { + "External id": 764216,"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": 688924666146.690, "dur": 59.170, + "args": { + "External id": 764217,"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": 688924666150.446, "dur": 6.174, + "args": { + "External id": 764218,"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": 688924666158.208, "dur": 47.066, + "args": { + "External id": 764219,"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": 688924666341.830, "dur": 592.166, + "args": { + "External id": 764220,"Record function id": 0, "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 4183436, "tid": 31338, + "ts": 688924666357.653, "dur": 564.230, + "args": { + "External id": 764221,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924666417.073, "dur": 4.537, + "args": { + "External id": 764222,"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": 688924666436.119, "dur": 27.114, + "args": { + "External id": 764223,"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": 688924666440.593, "dur": 1.312, + "args": { + "External id": 764224,"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": 688924666444.049, "dur": 0.371, + "args": { + "External id": 764225,"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": 688924666445.738, "dur": 0.458, + "args": { + "External id": 764226,"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": 688924666447.987, "dur": 0.391, + "args": { + "External id": 764227,"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": 688924666449.485, "dur": 0.977, + "args": { + "External id": 764228,"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": 688924666451.397, "dur": 2.868, + "args": { + "External id": 764229,"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": 688924666455.480, "dur": 0.391, + "args": { + "External id": 764230,"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": 688924666457.080, "dur": 0.467, + "args": { + "External id": 764231,"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": 688924666459.920, "dur": 0.414, + "args": { + "External id": 764232,"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": 688924666473.576, "dur": 28.846, + "args": { + "External id": 764233,"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": 688924666530.564, "dur": 87.170, + "args": { + "External id": 764234,"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": 688924666539.543, "dur": 2.954, + "args": { + "External id": 764235,"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": 688924666547.106, "dur": 8.923, + "args": { + "External id": 764236,"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": 688924666550.772, "dur": 4.903, + "args": { + "External id": 764237,"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": 688924666554.079, "dur": 0.478, + "args": { + "External id": 764238,"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": 688924666562.175, "dur": 22.175, + "args": { + "External id": 764239,"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": 688924666563.815, "dur": 0.511, + "args": { + "External id": 764240,"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": 688924666565.587, "dur": 0.513, + "args": { + "External id": 764241,"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": 688924666568.324, "dur": 2.280, + "args": { + "External id": 764242,"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": 688924666571.816, "dur": 0.483, + "args": { + "External id": 764243,"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": 688924666573.244, "dur": 0.365, + "args": { + "External id": 764244,"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": 688924666575.041, "dur": 0.608, + "args": { + "External id": 764245,"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": 688924666576.586, "dur": 0.643, + "args": { + "External id": 764246,"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": 688924666578.435, "dur": 1.017, + "args": { + "External id": 764247,"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": 688924666580.535, "dur": 0.342, + "args": { + "External id": 764248,"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": 688924666593.893, "dur": 16.990, + "args": { + "External id": 764249,"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": 688924666715.009, "dur": 132.238, + "args": { + "External id": 764250,"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": 688924666739.643, "dur": 103.903, + "args": { + "External id": 764251,"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": 688924666749.987, "dur": 88.447, + "args": { + "External id": 764252,"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": 688924666862.506, "dur": 2.166, + "args": { + "External id": 764253,"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": 688924666949.069, "dur": 1533.482, + "args": { + "External id": 764254,"Sequence number": 8961976, "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": 688924666949.069, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924667059.610, "dur": 97.075, + "args": { + "External id": 764255,"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": 688924667195.668, "dur": 37.237, + "args": { + "External id": 764256,"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": 688924667250.180, "dur": 38.202, + "args": { + "External id": 764257,"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": 688924667298.035, "dur": 33.466, + "args": { + "External id": 764258,"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": 688924667338.908, "dur": 31.554, + "args": { + "External id": 764259,"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": 688924667377.496, "dur": 22.225, + "args": { + "External id": 764260,"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": 688924667406.539, "dur": 27.974, + "args": { + "External id": 764261,"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": 688924667455.143, "dur": 24.566, + "args": { + "External id": 764262,"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": 688924667494.848, "dur": 29.591, + "args": { + "External id": 764263,"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": 688924667542.812, "dur": 20.266, + "args": { + "External id": 764264,"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": 688924667580.212, "dur": 15.303, + "args": { + "External id": 764265,"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": 688924667603.428, "dur": 34.752, + "args": { + "External id": 764266,"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": 688924667641.333, "dur": 71.086, + "args": { + "External id": 764267,"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": 688924667748.173, "dur": 197.026, + "args": { + "External id": 764268,"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": 688924667846.475, "dur": 7.938, + "args": { + "External id": 764269,"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": 688924667856.577, "dur": 3.490, + "args": { + "External id": 764270,"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": 688924667980.767, "dur": 23.902, + "args": { + "External id": 764271,"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": 688924668016.320, "dur": 15.960, + "args": { + "External id": 764272,"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": 688924668039.533, "dur": 52.878, + "args": { + "External id": 764273,"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": 688924668098.183, "dur": 30.439, + "args": { + "External id": 764274,"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": 688924668134.659, "dur": 27.027, + "args": { + "External id": 764275,"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": 688924668168.458, "dur": 28.006, + "args": { + "External id": 764276,"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": 688924668202.145, "dur": 26.491, + "args": { + "External id": 764277,"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": 688924668236.187, "dur": 27.494, + "args": { + "External id": 764278,"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": 688924668279.565, "dur": 20.044, + "args": { + "External id": 764279,"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": 688924668317.366, "dur": 35.442, + "args": { + "External id": 764280,"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": 688924668373.520, "dur": 19.731, + "args": { + "External id": 764281,"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": 688924668409.035, "dur": 14.084, + "args": { + "External id": 764282,"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": 688924668436.876, "dur": 18.216, + "args": { + "External id": 764283,"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": 688924668528.600, "dur": 14.541, + "args": { + "External id": 764284,"Record function id": 0, "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924668531.609, "dur": 10.717, + "args": { + "External id": 764285,"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": 688924668536.022, "dur": 5.347, + "args": { + "External id": 764286,"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": 688924668537.693, "dur": 3.567, + "args": { + "External id": 764287,"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": 688924668547.151, "dur": 5.004, + "args": { + "External id": 764288,"Record function id": 0, "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924668548.629, "dur": 3.095, + "args": { + "External id": 764289,"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": 688924668549.496, "dur": 1.747, + "args": { + "External id": 764290,"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": 688924668550.378, "dur": 0.741, + "args": { + "External id": 764291,"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": 688924668555.773, "dur": 4.160, + "args": { + "External id": 764292,"Record function id": 0, "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924668556.814, "dur": 2.670, + "args": { + "External id": 764293,"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": 688924668557.496, "dur": 1.247, + "args": { + "External id": 764294,"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": 688924668558.075, "dur": 0.590, + "args": { + "External id": 764295,"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": 688924668563.301, "dur": 4.303, + "args": { + "External id": 764296,"Record function id": 0, "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924668564.345, "dur": 2.857, + "args": { + "External id": 764297,"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": 688924668565.325, "dur": 1.448, + "args": { + "External id": 764298,"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": 688924668565.855, "dur": 0.814, + "args": { + "External id": 764299,"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": 688924668570.676, "dur": 5.300, + "args": { + "External id": 764300,"Record function id": 0, "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924668572.044, "dur": 3.500, + "args": { + "External id": 764301,"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": 688924668572.519, "dur": 2.636, + "args": { + "External id": 764302,"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": 688924668572.881, "dur": 2.208, + "args": { + "External id": 764303,"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": 688924668579.115, "dur": 3.695, + "args": { + "External id": 764304,"Record function id": 0, "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924668580.324, "dur": 2.087, + "args": { + "External id": 764305,"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": 688924668580.870, "dur": 1.136, + "args": { + "External id": 764306,"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": 688924668581.326, "dur": 0.607, + "args": { + "External id": 764307,"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": 688924668586.126, "dur": 3.984, + "args": { + "External id": 764308,"Record function id": 0, "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924668587.376, "dur": 2.342, + "args": { + "External id": 764309,"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": 688924668587.898, "dur": 1.228, + "args": { + "External id": 764310,"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": 688924668588.486, "dur": 0.564, + "args": { + "External id": 764311,"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": 688924668593.185, "dur": 3.891, + "args": { + "External id": 764312,"Record function id": 0, "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924668594.466, "dur": 2.227, + "args": { + "External id": 764313,"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": 688924668594.951, "dur": 1.354, + "args": { + "External id": 764314,"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": 688924668595.504, "dur": 0.737, + "args": { + "External id": 764315,"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": 688924668600.205, "dur": 3.802, + "args": { + "External id": 764316,"Record function id": 0, "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924668601.313, "dur": 2.276, + "args": { + "External id": 764317,"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": 688924668601.996, "dur": 1.053, + "args": { + "External id": 764318,"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": 688924668602.506, "dur": 0.472, + "args": { + "External id": 764319,"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": 688924668607.817, "dur": 16444.537, + "args": { + "External id": 764320,"Record function id": 0, "Sequence number": 8961975, "Fwd thread id": 1, "Ev Idx": 3487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924668609.305, "dur": 16434.147, + "args": { + "External id": 764321,"Sequence number": 8961975, "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": 688924668609.305, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 4183436, "tid": 31338, + "ts": 688924668638.224, "dur": 73.757, + "args": { + "External id": 764322,"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": 688924668720.933, "dur": 86.498, + "args": { + "External id": 764323,"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": 688924668815.536, "dur": 16219.771, + "args": { + "External id": 764324,"Record function id": 0, "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924668908.155, "dur": 6.923, + "args": { + "External id": 764325,"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": 688924668925.763, "dur": 5.076, + "args": { + "External id": 764326,"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": 688924668944.473, "dur": 15353.083, + "args": { + "External id": 764327,"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": 688924668958.163, "dur": 15331.815, + "args": { + "External id": 764328,"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": 688924668979.185, "dur": 12.585, + "args": { + "External id": 764329,"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": 688924668996.706, "dur": 15260.466, + "args": { + "External id": 764330,"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": 688924669000.474, "dur": 15255.938, + "args": { + "External id": 764331,"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": 688924669004.355, "dur": 6.348, + "args": { + "External id": 764332,"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": 688924669012.145, "dur": 15240.402, + "args": { + "External id": 764333,"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": 688924684381.740, "dur": 8.611, + "args": { + "External id": 764334,"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": 688924684384.614, "dur": 5.428, + "args": { + "External id": 764335,"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": 688924684416.724, "dur": 324.732, + "args": { + "External id": 764336,"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": 688924684442.526, "dur": 293.650, + "args": { + "External id": 764337,"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": 688924684453.932, "dur": 276.813, + "args": { + "External id": 764338,"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": 688924684761.159, "dur": 2.146, + "args": { + "External id": 764339,"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": 688924684832.830, "dur": 6.689, + "args": { + "External id": 764340,"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": 688924684884.531, "dur": 1.344, + "args": { + "External id": 764341,"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": 688924684901.689, "dur": 1.153, + "args": { + "External id": 764342,"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": 688924684913.642, "dur": 2.472, + "args": { + "External id": 764343,"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": 688924684927.421, "dur": 1.003, + "args": { + "External id": 764344,"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": 688924684937.923, "dur": 0.734, + "args": { + "External id": 764345,"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": 688924684948.509, "dur": 0.936, + "args": { + "External id": 764346,"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": 688924684960.626, "dur": 3.320, + "args": { + "External id": 764347,"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": 688924684973.241, "dur": 0.943, + "args": { + "External id": 764348,"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": 688924685066.754, "dur": 2779.979, + "args": { + "External id": 764349,"Record function id": 0, "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 4183436, "tid": 31338, + "ts": 688924685086.673, "dur": 1010.703, + "args": { + "External id": 764350,"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": 688924685101.581, "dur": 297.196, + "args": { + "External id": 764351,"Record function id": 0, "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924685187.538, "dur": 3.801, + "args": { + "External id": 764352,"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": 688924685194.163, "dur": 1.014, + "args": { + "External id": 764353,"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": 688924685196.874, "dur": 1.077, + "args": { + "External id": 764354,"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": 688924685199.913, "dur": 0.968, + "args": { + "External id": 764355,"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": 688924685202.549, "dur": 3.588, + "args": { + "External id": 764356,"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": 688924685207.870, "dur": 1.195, + "args": { + "External id": 764357,"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": 688924685211.146, "dur": 0.962, + "args": { + "External id": 764358,"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": 688924685213.702, "dur": 0.802, + "args": { + "External id": 764359,"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": 688924685216.128, "dur": 1.391, + "args": { + "External id": 764360,"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": 688924685219.370, "dur": 1.124, + "args": { + "External id": 764361,"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": 688924685236.039, "dur": 132.834, + "args": { + "External id": 764362,"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": 688924685250.779, "dur": 114.049, + "args": { + "External id": 764363,"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": 688924685263.552, "dur": 12.429, + "args": { + "External id": 764364,"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": 688924685278.433, "dur": 61.860, + "args": { + "External id": 764365,"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": 688924685282.075, "dur": 57.927, + "args": { + "External id": 764366,"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": 688924685285.855, "dur": 5.517, + "args": { + "External id": 764367,"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": 688924685293.111, "dur": 46.212, + "args": { + "External id": 764368,"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": 688924685482.916, "dur": 606.469, + "args": { + "External id": 764369,"Record function id": 0, "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 4183436, "tid": 31338, + "ts": 688924685499.521, "dur": 577.765, + "args": { + "External id": 764370,"Record function id": 0, "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924685557.227, "dur": 5.272, + "args": { + "External id": 764371,"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": 688924685580.127, "dur": 27.492, + "args": { + "External id": 764372,"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": 688924685584.751, "dur": 1.232, + "args": { + "External id": 764373,"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": 688924685589.153, "dur": 0.464, + "args": { + "External id": 764374,"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": 688924685590.832, "dur": 0.541, + "args": { + "External id": 764375,"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": 688924685592.682, "dur": 0.504, + "args": { + "External id": 764376,"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": 688924685595.190, "dur": 0.684, + "args": { + "External id": 764377,"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": 688924685597.039, "dur": 0.630, + "args": { + "External id": 764378,"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": 688924685598.676, "dur": 1.181, + "args": { + "External id": 764379,"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": 688924685600.865, "dur": 1.984, + "args": { + "External id": 764380,"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": 688924685603.985, "dur": 0.531, + "args": { + "External id": 764381,"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": 688924685617.897, "dur": 30.546, + "args": { + "External id": 764382,"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": 688924685724.984, "dur": 132.915, + "args": { + "External id": 764383,"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": 688924685735.686, "dur": 4.794, + "args": { + "External id": 764384,"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": 688924685746.119, "dur": 10.833, + "args": { + "External id": 764385,"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": 688924685750.485, "dur": 6.026, + "args": { + "External id": 764386,"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": 688924685753.894, "dur": 0.792, + "args": { + "External id": 764387,"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": 688924685765.659, "dur": 47.475, + "args": { + "External id": 764388,"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": 688924685767.837, "dur": 1.811, + "args": { + "External id": 764389,"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": 688924685771.279, "dur": 0.428, + "args": { + "External id": 764390,"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": 688924685772.439, "dur": 0.452, + "args": { + "External id": 764391,"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": 688924685775.886, "dur": 0.338, + "args": { + "External id": 764392,"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": 688924685777.641, "dur": 2.205, + "args": { + "External id": 764393,"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": 688924685780.835, "dur": 0.193, + "args": { + "External id": 764394,"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": 688924685782.801, "dur": 0.729, + "args": { + "External id": 764395,"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": 688924685784.534, "dur": 0.538, + "args": { + "External id": 764396,"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": 688924685804.401, "dur": 1.887, + "args": { + "External id": 764397,"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": 688924685825.838, "dur": 23.870, + "args": { + "External id": 764398,"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": 688924685903.461, "dur": 109.118, + "args": { + "External id": 764399,"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": 688924685926.532, "dur": 82.773, + "args": { + "External id": 764400,"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": 688924685935.684, "dur": 69.425, + "args": { + "External id": 764401,"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": 688924686026.694, "dur": 1.840, + "args": { + "External id": 764402,"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": 688924686105.531, "dur": 1717.264, + "args": { + "External id": 764403,"Sequence number": 8961974, "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": 688924686105.531, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924686215.494, "dur": 100.035, + "args": { + "External id": 764404,"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": 688924686356.592, "dur": 36.713, + "args": { + "External id": 764405,"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": 688924686410.631, "dur": 38.603, + "args": { + "External id": 764406,"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": 688924686458.333, "dur": 24.122, + "args": { + "External id": 764407,"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": 688924686488.077, "dur": 32.341, + "args": { + "External id": 764408,"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": 688924686528.439, "dur": 21.898, + "args": { + "External id": 764409,"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": 688924686556.507, "dur": 27.739, + "args": { + "External id": 764410,"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": 688924686605.663, "dur": 22.213, + "args": { + "External id": 764411,"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": 688924686648.712, "dur": 75.938, + "args": { + "External id": 764412,"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": 688924686749.134, "dur": 24.435, + "args": { + "External id": 764413,"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": 688924686802.671, "dur": 21.329, + "args": { + "External id": 764414,"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": 688924686836.155, "dur": 45.966, + "args": { + "External id": 764415,"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": 688924686885.923, "dur": 31.019, + "args": { + "External id": 764416,"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": 688924687006.516, "dur": 179.163, + "args": { + "External id": 764417,"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": 688924687087.383, "dur": 6.433, + "args": { + "External id": 764418,"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": 688924687095.656, "dur": 3.252, + "args": { + "External id": 764419,"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": 688924687222.910, "dur": 23.485, + "args": { + "External id": 764420,"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": 688924687258.075, "dur": 12.856, + "args": { + "External id": 764421,"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": 688924687282.879, "dur": 46.079, + "args": { + "External id": 764422,"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": 688924687339.969, "dur": 29.997, + "args": { + "External id": 764423,"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": 688924687375.781, "dur": 26.866, + "args": { + "External id": 764424,"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": 688924687407.325, "dur": 27.066, + "args": { + "External id": 764425,"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": 688924687439.331, "dur": 39.220, + "args": { + "External id": 764426,"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": 688924687493.176, "dur": 33.176, + "args": { + "External id": 764427,"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": 688924687546.327, "dur": 20.929, + "args": { + "External id": 764428,"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": 688924687617.899, "dur": 27.511, + "args": { + "External id": 764429,"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": 688924687698.940, "dur": 18.827, + "args": { + "External id": 764430,"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": 688924687734.680, "dur": 14.475, + "args": { + "External id": 764431,"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": 688924687761.576, "dur": 15.701, + "args": { + "External id": 764432,"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": 688924687869.141, "dur": 15.191, + "args": { + "External id": 764433,"Record function id": 0, "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924687872.433, "dur": 10.926, + "args": { + "External id": 764434,"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": 688924687876.820, "dur": 5.510, + "args": { + "External id": 764435,"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": 688924687878.151, "dur": 4.069, + "args": { + "External id": 764436,"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": 688924687888.165, "dur": 7.835, + "args": { + "External id": 764437,"Record function id": 0, "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924687889.577, "dur": 5.950, + "args": { + "External id": 764438,"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": 688924687890.594, "dur": 4.484, + "args": { + "External id": 764439,"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": 688924687890.951, "dur": 4.065, + "args": { + "External id": 764440,"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": 688924687899.225, "dur": 5.542, + "args": { + "External id": 764441,"Record function id": 0, "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924687900.364, "dur": 3.945, + "args": { + "External id": 764442,"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": 688924687901.058, "dur": 2.844, + "args": { + "External id": 764443,"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": 688924687901.451, "dur": 2.369, + "args": { + "External id": 764444,"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": 688924687907.973, "dur": 4.274, + "args": { + "External id": 764445,"Record function id": 0, "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924687909.306, "dur": 2.495, + "args": { + "External id": 764446,"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": 688924687910.161, "dur": 1.024, + "args": { + "External id": 764447,"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": 688924687910.441, "dur": 0.673, + "args": { + "External id": 764448,"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": 688924687915.321, "dur": 4.152, + "args": { + "External id": 764449,"Record function id": 0, "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924687916.496, "dur": 2.539, + "args": { + "External id": 764450,"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": 688924687917.295, "dur": 1.076, + "args": { + "External id": 764451,"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": 688924687917.627, "dur": 0.640, + "args": { + "External id": 764452,"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": 688924687922.764, "dur": 4.447, + "args": { + "External id": 764453,"Record function id": 0, "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924687924.247, "dur": 2.544, + "args": { + "External id": 764454,"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": 688924687924.888, "dur": 1.313, + "args": { + "External id": 764455,"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": 688924687925.564, "dur": 0.562, + "args": { + "External id": 764456,"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": 688924687930.387, "dur": 4.374, + "args": { + "External id": 764457,"Record function id": 0, "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924687931.560, "dur": 2.746, + "args": { + "External id": 764458,"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": 688924687932.260, "dur": 1.416, + "args": { + "External id": 764459,"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": 688924687932.879, "dur": 0.736, + "args": { + "External id": 764460,"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": 688924687937.793, "dur": 4.508, + "args": { + "External id": 764461,"Record function id": 0, "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924687938.745, "dur": 3.145, + "args": { + "External id": 764462,"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": 688924687939.414, "dur": 1.912, + "args": { + "External id": 764463,"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": 688924687940.611, "dur": 0.650, + "args": { + "External id": 764464,"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": 688924687945.375, "dur": 4.028, + "args": { + "External id": 764465,"Record function id": 0, "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924687946.679, "dur": 2.283, + "args": { + "External id": 764466,"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": 688924687947.375, "dur": 1.214, + "args": { + "External id": 764467,"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": 688924687948.086, "dur": 0.438, + "args": { + "External id": 764468,"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": 688924687956.412, "dur": 14536.728, + "args": { + "External id": 764469,"Record function id": 0, "Sequence number": 8961973, "Fwd thread id": 1, "Ev Idx": 3636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924687957.575, "dur": 14527.315, + "args": { + "External id": 764470,"Sequence number": 8961973, "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": 688924687957.575, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 4183436, "tid": 31338, + "ts": 688924687987.050, "dur": 36.747, + "args": { + "External id": 764471,"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": 688924688031.937, "dur": 65.272, + "args": { + "External id": 764472,"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": 688924688102.772, "dur": 14374.448, + "args": { + "External id": 764473,"Record function id": 0, "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924688191.690, "dur": 5.966, + "args": { + "External id": 764474,"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": 688924688207.062, "dur": 6.119, + "args": { + "External id": 764475,"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": 688924688226.491, "dur": 13607.543, + "args": { + "External id": 764476,"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": 688924688239.684, "dur": 13585.724, + "args": { + "External id": 764477,"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": 688924688295.931, "dur": 16.647, + "args": { + "External id": 764478,"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": 688924688317.068, "dur": 13463.056, + "args": { + "External id": 764479,"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": 688924688319.421, "dur": 13459.885, + "args": { + "External id": 764480,"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": 688924688323.715, "dur": 4.868, + "args": { + "External id": 764481,"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": 688924688330.112, "dur": 13445.381, + "args": { + "External id": 764482,"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": 688924701924.427, "dur": 8.966, + "args": { + "External id": 764483,"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": 688924701927.213, "dur": 5.775, + "args": { + "External id": 764484,"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": 688924701962.200, "dur": 250.700, + "args": { + "External id": 764485,"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": 688924701987.956, "dur": 220.632, + "args": { + "External id": 764486,"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": 688924701998.640, "dur": 205.518, + "args": { + "External id": 764487,"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": 688924702229.536, "dur": 1.903, + "args": { + "External id": 764488,"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": 688924702281.551, "dur": 5.745, + "args": { + "External id": 764489,"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": 688924702329.370, "dur": 1.447, + "args": { + "External id": 764490,"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": 688924702345.210, "dur": 1.074, + "args": { + "External id": 764491,"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": 688924702357.441, "dur": 2.596, + "args": { + "External id": 764492,"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": 688924702370.865, "dur": 0.679, + "args": { + "External id": 764493,"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": 688924702381.906, "dur": 0.995, + "args": { + "External id": 764494,"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": 688924702393.244, "dur": 0.767, + "args": { + "External id": 764495,"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": 688924702405.393, "dur": 2.643, + "args": { + "External id": 764496,"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": 688924702417.017, "dur": 1.229, + "args": { + "External id": 764497,"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": 688924702506.378, "dur": 2722.264, + "args": { + "External id": 764498,"Record function id": 0, "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 4183436, "tid": 31338, + "ts": 688924702526.139, "dur": 1026.212, + "args": { + "External id": 764499,"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": 688924702540.027, "dur": 362.129, + "args": { + "External id": 764500,"Record function id": 0, "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924702620.223, "dur": 3.810, + "args": { + "External id": 764501,"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": 688924702627.158, "dur": 0.953, + "args": { + "External id": 764502,"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": 688924702630.133, "dur": 1.205, + "args": { + "External id": 764503,"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": 688924702633.134, "dur": 0.953, + "args": { + "External id": 764504,"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": 688924702635.991, "dur": 3.175, + "args": { + "External id": 764505,"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": 688924702641.067, "dur": 0.991, + "args": { + "External id": 764506,"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": 688924702643.752, "dur": 0.916, + "args": { + "External id": 764507,"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": 688924702646.420, "dur": 1.023, + "args": { + "External id": 764508,"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": 688924702649.619, "dur": 1.218, + "args": { + "External id": 764509,"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": 688924702692.473, "dur": 1.659, + "args": { + "External id": 764510,"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": 688924702714.530, "dur": 153.588, + "args": { + "External id": 764511,"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": 688924702730.677, "dur": 132.995, + "args": { + "External id": 764512,"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": 688924702743.775, "dur": 12.380, + "args": { + "External id": 764513,"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": 688924702758.845, "dur": 77.446, + "args": { + "External id": 764514,"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": 688924702761.186, "dur": 74.705, + "args": { + "External id": 764515,"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": 688924702764.756, "dur": 5.769, + "args": { + "External id": 764516,"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": 688924702772.040, "dur": 62.968, + "args": { + "External id": 764517,"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": 688924703000.016, "dur": 544.826, + "args": { + "External id": 764518,"Record function id": 0, "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 4183436, "tid": 31338, + "ts": 688924703018.099, "dur": 515.522, + "args": { + "External id": 764519,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924703082.131, "dur": 7.246, + "args": { + "External id": 764520,"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": 688924703104.717, "dur": 32.411, + "args": { + "External id": 764521,"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": 688924703109.666, "dur": 4.937, + "args": { + "External id": 764522,"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": 688924703116.622, "dur": 0.384, + "args": { + "External id": 764523,"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": 688924703118.181, "dur": 0.656, + "args": { + "External id": 764524,"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": 688924703120.088, "dur": 0.605, + "args": { + "External id": 764525,"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": 688924703122.350, "dur": 0.450, + "args": { + "External id": 764526,"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": 688924703124.055, "dur": 0.355, + "args": { + "External id": 764527,"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": 688924703125.746, "dur": 0.473, + "args": { + "External id": 764528,"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": 688924703127.211, "dur": 2.670, + "args": { + "External id": 764529,"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": 688924703130.986, "dur": 0.331, + "args": { + "External id": 764530,"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": 688924703147.598, "dur": 33.854, + "args": { + "External id": 764531,"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": 688924703210.793, "dur": 100.172, + "args": { + "External id": 764532,"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": 688924703220.182, "dur": 3.758, + "args": { + "External id": 764533,"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": 688924703228.858, "dur": 12.389, + "args": { + "External id": 764534,"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": 688924703235.956, "dur": 4.903, + "args": { + "External id": 764535,"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": 688924703238.985, "dur": 0.362, + "args": { + "External id": 764536,"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": 688924703247.579, "dur": 24.901, + "args": { + "External id": 764537,"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": 688924703249.695, "dur": 0.331, + "args": { + "External id": 764538,"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": 688924703251.760, "dur": 0.745, + "args": { + "External id": 764539,"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": 688924703254.248, "dur": 0.412, + "args": { + "External id": 764540,"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": 688924703255.552, "dur": 0.517, + "args": { + "External id": 764541,"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": 688924703257.567, "dur": 2.310, + "args": { + "External id": 764542,"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": 688924703260.852, "dur": 0.871, + "args": { + "External id": 764543,"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": 688924703263.073, "dur": 0.423, + "args": { + "External id": 764544,"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": 688924703264.539, "dur": 0.601, + "args": { + "External id": 764545,"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": 688924703266.769, "dur": 0.378, + "args": { + "External id": 764546,"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": 688924703281.694, "dur": 22.025, + "args": { + "External id": 764547,"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": 688924703355.777, "dur": 114.432, + "args": { + "External id": 764548,"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": 688924703379.894, "dur": 87.080, + "args": { + "External id": 764549,"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": 688924703388.550, "dur": 74.037, + "args": { + "External id": 764550,"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": 688924703484.294, "dur": 1.803, + "args": { + "External id": 764551,"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": 688924703559.563, "dur": 1649.314, + "args": { + "External id": 764552,"Sequence number": 8961972, "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": 688924703559.563, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924703709.690, "dur": 116.692, + "args": { + "External id": 764553,"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": 688924703874.525, "dur": 37.310, + "args": { + "External id": 764554,"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": 688924703933.231, "dur": 42.155, + "args": { + "External id": 764555,"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": 688924703984.490, "dur": 25.077, + "args": { + "External id": 764556,"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": 688924704015.231, "dur": 33.060, + "args": { + "External id": 764557,"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": 688924704056.581, "dur": 19.955, + "args": { + "External id": 764558,"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": 688924704084.764, "dur": 27.858, + "args": { + "External id": 764559,"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": 688924704135.330, "dur": 24.524, + "args": { + "External id": 764560,"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": 688924704177.204, "dur": 30.524, + "args": { + "External id": 764561,"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": 688924704227.204, "dur": 19.347, + "args": { + "External id": 764562,"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": 688924704259.025, "dur": 15.713, + "args": { + "External id": 764563,"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": 688924704284.124, "dur": 37.858, + "args": { + "External id": 764564,"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": 688924704325.198, "dur": 29.604, + "args": { + "External id": 764565,"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": 688924704381.414, "dur": 175.767, + "args": { + "External id": 764566,"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": 688924704462.636, "dur": 6.132, + "args": { + "External id": 764567,"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": 688924704470.651, "dur": 3.025, + "args": { + "External id": 764568,"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": 688924704591.103, "dur": 25.139, + "args": { + "External id": 764569,"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": 688924704628.765, "dur": 17.921, + "args": { + "External id": 764570,"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": 688924704691.717, "dur": 56.827, + "args": { + "External id": 764571,"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": 688924704757.666, "dur": 48.990, + "args": { + "External id": 764572,"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": 688924704816.515, "dur": 34.118, + "args": { + "External id": 764573,"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": 688924704855.173, "dur": 27.677, + "args": { + "External id": 764574,"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": 688924704891.533, "dur": 40.077, + "args": { + "External id": 764575,"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": 688924704949.949, "dur": 34.401, + "args": { + "External id": 764576,"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": 688924705008.966, "dur": 25.567, + "args": { + "External id": 764577,"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": 688924705052.406, "dur": 32.234, + "args": { + "External id": 764578,"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": 688924705099.580, "dur": 20.581, + "args": { + "External id": 764579,"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": 688924705135.775, "dur": 15.811, + "args": { + "External id": 764580,"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": 688924705163.530, "dur": 15.701, + "args": { + "External id": 764581,"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": 688924705250.016, "dur": 14.152, + "args": { + "External id": 764582,"Record function id": 0, "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924705252.750, "dur": 10.577, + "args": { + "External id": 764583,"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": 688924705256.774, "dur": 5.662, + "args": { + "External id": 764584,"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": 688924705257.999, "dur": 4.328, + "args": { + "External id": 764585,"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": 688924705268.010, "dur": 4.389, + "args": { + "External id": 764586,"Record function id": 0, "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924705269.305, "dur": 2.630, + "args": { + "External id": 764587,"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": 688924705270.174, "dur": 1.192, + "args": { + "External id": 764588,"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": 688924705270.514, "dur": 0.737, + "args": { + "External id": 764589,"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": 688924705275.752, "dur": 4.193, + "args": { + "External id": 764590,"Record function id": 0, "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924705277.059, "dur": 2.456, + "args": { + "External id": 764591,"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": 688924705277.618, "dur": 1.179, + "args": { + "External id": 764592,"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": 688924705277.951, "dur": 0.723, + "args": { + "External id": 764593,"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": 688924705283.094, "dur": 6.409, + "args": { + "External id": 764594,"Record function id": 0, "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924705284.443, "dur": 4.636, + "args": { + "External id": 764595,"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": 688924705285.001, "dur": 3.638, + "args": { + "External id": 764596,"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": 688924705285.354, "dur": 3.206, + "args": { + "External id": 764597,"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": 688924705292.670, "dur": 4.593, + "args": { + "External id": 764598,"Record function id": 0, "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924705293.725, "dur": 3.118, + "args": { + "External id": 764599,"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": 688924705294.238, "dur": 2.216, + "args": { + "External id": 764600,"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": 688924705294.566, "dur": 1.821, + "args": { + "External id": 764601,"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": 688924705300.309, "dur": 4.349, + "args": { + "External id": 764602,"Record function id": 0, "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924705301.447, "dur": 2.769, + "args": { + "External id": 764603,"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": 688924705302.113, "dur": 1.682, + "args": { + "External id": 764604,"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": 688924705303.047, "dur": 0.664, + "args": { + "External id": 764605,"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": 688924705307.841, "dur": 5.046, + "args": { + "External id": 764606,"Record function id": 0, "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924705309.215, "dur": 3.237, + "args": { + "External id": 764607,"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": 688924705309.691, "dur": 2.089, + "args": { + "External id": 764608,"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": 688924705311.029, "dur": 0.673, + "args": { + "External id": 764609,"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": 688924705316.009, "dur": 3.962, + "args": { + "External id": 764610,"Record function id": 0, "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924705317.049, "dur": 2.534, + "args": { + "External id": 764611,"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": 688924705317.875, "dur": 1.263, + "args": { + "External id": 764612,"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": 688924705318.454, "dur": 0.618, + "args": { + "External id": 764613,"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": 688924705323.618, "dur": 3.646, + "args": { + "External id": 764614,"Record function id": 0, "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924705324.648, "dur": 2.161, + "args": { + "External id": 764615,"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": 688924705325.157, "dur": 1.020, + "args": { + "External id": 764616,"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": 688924705325.513, "dur": 0.596, + "args": { + "External id": 764617,"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": 688924705331.448, "dur": 14724.245, + "args": { + "External id": 764618,"Record function id": 0, "Sequence number": 8961971, "Fwd thread id": 1, "Ev Idx": 3785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924705332.950, "dur": 14713.791, + "args": { + "External id": 764619,"Sequence number": 8961971, "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": 688924705332.950, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 4183436, "tid": 31338, + "ts": 688924705362.546, "dur": 36.689, + "args": { + "External id": 764620,"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": 688924705406.777, "dur": 66.133, + "args": { + "External id": 764621,"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": 688924705479.124, "dur": 14559.736, + "args": { + "External id": 764622,"Record function id": 0, "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924705570.801, "dur": 6.037, + "args": { + "External id": 764623,"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": 688924705586.147, "dur": 4.451, + "args": { + "External id": 764624,"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": 688924705603.950, "dur": 13728.204, + "args": { + "External id": 764625,"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": 688924705617.570, "dur": 13706.503, + "args": { + "External id": 764626,"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": 688924705695.370, "dur": 17.020, + "args": { + "External id": 764627,"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": 688924705717.437, "dur": 13568.779, + "args": { + "External id": 764628,"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": 688924705720.591, "dur": 13565.006, + "args": { + "External id": 764629,"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": 688924705724.766, "dur": 6.317, + "args": { + "External id": 764630,"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": 688924705733.112, "dur": 13548.725, + "args": { + "External id": 764631,"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": 688924719423.213, "dur": 9.015, + "args": { + "External id": 764632,"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": 688924719425.825, "dur": 6.048, + "args": { + "External id": 764633,"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": 688924719464.697, "dur": 282.920, + "args": { + "External id": 764634,"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": 688924719491.563, "dur": 251.365, + "args": { + "External id": 764635,"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": 688924719502.504, "dur": 235.135, + "args": { + "External id": 764636,"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": 688924719768.018, "dur": 2.034, + "args": { + "External id": 764637,"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": 688924719838.198, "dur": 6.720, + "args": { + "External id": 764638,"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": 688924719887.713, "dur": 1.258, + "args": { + "External id": 764639,"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": 688924719903.631, "dur": 1.667, + "args": { + "External id": 764640,"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": 688924719916.725, "dur": 2.877, + "args": { + "External id": 764641,"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": 688924719930.954, "dur": 1.067, + "args": { + "External id": 764642,"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": 688924719942.402, "dur": 1.057, + "args": { + "External id": 764643,"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": 688924719953.607, "dur": 0.846, + "args": { + "External id": 764644,"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": 688924719965.529, "dur": 3.062, + "args": { + "External id": 764645,"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": 688924719979.027, "dur": 0.970, + "args": { + "External id": 764646,"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": 688924720070.351, "dur": 2568.149, + "args": { + "External id": 764647,"Record function id": 0, "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 4183436, "tid": 31338, + "ts": 688924720089.228, "dur": 999.626, + "args": { + "External id": 764648,"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": 688924720103.645, "dur": 288.822, + "args": { + "External id": 764649,"Record function id": 0, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924720184.363, "dur": 4.119, + "args": { + "External id": 764650,"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": 688924720191.277, "dur": 1.027, + "args": { + "External id": 764651,"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": 688924720194.055, "dur": 1.136, + "args": { + "External id": 764652,"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": 688924720197.181, "dur": 0.818, + "args": { + "External id": 764653,"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": 688924720199.817, "dur": 3.141, + "args": { + "External id": 764654,"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": 688924720204.900, "dur": 0.813, + "args": { + "External id": 764655,"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": 688924720207.624, "dur": 1.029, + "args": { + "External id": 764656,"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": 688924720210.029, "dur": 1.260, + "args": { + "External id": 764657,"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": 688924720212.929, "dur": 0.838, + "args": { + "External id": 764658,"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": 688924720215.068, "dur": 1.316, + "args": { + "External id": 764659,"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": 688924720233.484, "dur": 132.714, + "args": { + "External id": 764660,"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": 688924720249.797, "dur": 112.589, + "args": { + "External id": 764661,"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": 688924720261.581, "dur": 12.606, + "args": { + "External id": 764662,"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": 688924720276.665, "dur": 58.811, + "args": { + "External id": 764663,"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": 688924720278.985, "dur": 56.192, + "args": { + "External id": 764664,"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": 688924720282.815, "dur": 5.301, + "args": { + "External id": 764665,"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": 688924720289.754, "dur": 44.959, + "args": { + "External id": 764666,"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": 688924720475.338, "dur": 606.326, + "args": { + "External id": 764667,"Record function id": 0, "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 4183436, "tid": 31338, + "ts": 688924720490.063, "dur": 579.191, + "args": { + "External id": 764668,"Record function id": 0, "Ev Idx": 3835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924720546.539, "dur": 6.734, + "args": { + "External id": 764669,"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": 688924720568.408, "dur": 26.373, + "args": { + "External id": 764670,"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": 688924720573.005, "dur": 1.019, + "args": { + "External id": 764671,"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": 688924720576.331, "dur": 0.583, + "args": { + "External id": 764672,"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": 688924720577.994, "dur": 0.450, + "args": { + "External id": 764673,"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": 688924720579.708, "dur": 0.392, + "args": { + "External id": 764674,"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": 688924720581.291, "dur": 0.640, + "args": { + "External id": 764675,"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": 688924720583.774, "dur": 0.653, + "args": { + "External id": 764676,"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": 688924720585.836, "dur": 0.421, + "args": { + "External id": 764677,"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": 688924720587.582, "dur": 1.793, + "args": { + "External id": 764678,"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": 688924720590.679, "dur": 0.336, + "args": { + "External id": 764679,"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": 688924720605.058, "dur": 30.876, + "args": { + "External id": 764680,"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": 688924720711.849, "dur": 119.900, + "args": { + "External id": 764681,"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": 688924720722.946, "dur": 4.740, + "args": { + "External id": 764682,"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": 688924720732.832, "dur": 10.495, + "args": { + "External id": 764683,"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": 688924720736.919, "dur": 5.997, + "args": { + "External id": 764684,"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": 688924720740.210, "dur": 0.837, + "args": { + "External id": 764685,"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": 688924720750.146, "dur": 23.583, + "args": { + "External id": 764686,"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": 688924720752.006, "dur": 0.350, + "args": { + "External id": 764687,"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": 688924720753.545, "dur": 0.661, + "args": { + "External id": 764688,"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": 688924720755.057, "dur": 0.429, + "args": { + "External id": 764689,"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": 688924720760.063, "dur": 0.529, + "args": { + "External id": 764690,"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": 688924720762.145, "dur": 2.083, + "args": { + "External id": 764691,"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": 688924720765.490, "dur": 0.530, + "args": { + "External id": 764692,"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": 688924720767.216, "dur": 0.289, + "args": { + "External id": 764693,"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": 688924720768.581, "dur": 0.495, + "args": { + "External id": 764694,"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": 688924720770.313, "dur": 0.324, + "args": { + "External id": 764695,"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": 688924720783.924, "dur": 35.703, + "args": { + "External id": 764696,"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": 688924720882.847, "dur": 116.652, + "args": { + "External id": 764697,"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": 688924720907.484, "dur": 85.470, + "args": { + "External id": 764698,"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": 688924720916.251, "dur": 72.218, + "args": { + "External id": 764699,"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": 688924721012.561, "dur": 1.929, + "args": { + "External id": 764700,"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": 688924721095.943, "dur": 1520.721, + "args": { + "External id": 764701,"Sequence number": 8961970, "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": 688924721095.943, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924721206.707, "dur": 99.218, + "args": { + "External id": 764702,"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": 688924721343.439, "dur": 38.425, + "args": { + "External id": 764703,"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": 688924721398.220, "dur": 44.629, + "args": { + "External id": 764704,"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": 688924721451.551, "dur": 30.392, + "args": { + "External id": 764705,"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": 688924721487.778, "dur": 31.562, + "args": { + "External id": 764706,"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": 688924721527.217, "dur": 19.556, + "args": { + "External id": 764707,"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": 688924721553.940, "dur": 28.416, + "args": { + "External id": 764708,"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": 688924721603.045, "dur": 21.640, + "args": { + "External id": 764709,"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": 688924721640.947, "dur": 71.705, + "args": { + "External id": 764710,"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": 688924721736.920, "dur": 18.724, + "args": { + "External id": 764711,"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": 688924721770.757, "dur": 13.965, + "args": { + "External id": 764712,"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": 688924721811.412, "dur": 43.024, + "args": { + "External id": 764713,"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": 688924721858.528, "dur": 30.082, + "args": { + "External id": 764714,"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": 688924721916.215, "dur": 172.068, + "args": { + "External id": 764715,"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": 688924721998.913, "dur": 5.675, + "args": { + "External id": 764716,"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": 688924722006.741, "dur": 3.028, + "args": { + "External id": 764717,"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": 688924722120.515, "dur": 26.218, + "args": { + "External id": 764718,"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": 688924722157.615, "dur": 13.063, + "args": { + "External id": 764719,"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": 688924722178.163, "dur": 42.295, + "args": { + "External id": 764720,"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": 688924722227.271, "dur": 29.471, + "args": { + "External id": 764721,"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": 688924722262.805, "dur": 26.305, + "args": { + "External id": 764722,"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": 688924722294.235, "dur": 28.724, + "args": { + "External id": 764723,"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": 688924722328.731, "dur": 26.521, + "args": { + "External id": 764724,"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": 688924722362.997, "dur": 29.924, + "args": { + "External id": 764725,"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": 688924722408.832, "dur": 21.756, + "args": { + "External id": 764726,"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": 688924722448.751, "dur": 36.554, + "args": { + "External id": 764727,"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": 688924722509.420, "dur": 19.997, + "args": { + "External id": 764728,"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": 688924722543.027, "dur": 15.000, + "args": { + "External id": 764729,"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": 688924722570.169, "dur": 16.488, + "args": { + "External id": 764730,"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": 688924722698.551, "dur": 18.005, + "args": { + "External id": 764731,"Record function id": 0, "Ev Idx": 3898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924722703.322, "dur": 11.957, + "args": { + "External id": 764732,"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": 688924722707.857, "dur": 5.967, + "args": { + "External id": 764733,"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": 688924722709.367, "dur": 4.197, + "args": { + "External id": 764734,"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": 688924722725.082, "dur": 4.709, + "args": { + "External id": 764735,"Record function id": 0, "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924722726.391, "dur": 2.907, + "args": { + "External id": 764736,"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": 688924722727.445, "dur": 1.388, + "args": { + "External id": 764737,"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": 688924722727.954, "dur": 0.807, + "args": { + "External id": 764738,"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": 688924722733.100, "dur": 5.116, + "args": { + "External id": 764739,"Record function id": 0, "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924722734.920, "dur": 2.842, + "args": { + "External id": 764740,"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": 688924722735.615, "dur": 1.732, + "args": { + "External id": 764741,"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": 688924722736.479, "dur": 0.799, + "args": { + "External id": 764742,"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": 688924722741.455, "dur": 5.657, + "args": { + "External id": 764743,"Record function id": 0, "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924722742.377, "dur": 4.287, + "args": { + "External id": 764744,"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": 688924722743.033, "dur": 3.207, + "args": { + "External id": 764745,"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": 688924722743.533, "dur": 2.620, + "args": { + "External id": 764746,"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": 688924722750.407, "dur": 5.403, + "args": { + "External id": 764747,"Record function id": 0, "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924722751.634, "dur": 3.719, + "args": { + "External id": 764748,"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": 688924722752.958, "dur": 1.802, + "args": { + "External id": 764749,"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": 688924722753.848, "dur": 0.823, + "args": { + "External id": 764750,"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": 688924722759.053, "dur": 4.159, + "args": { + "External id": 764751,"Record function id": 0, "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924722760.382, "dur": 2.372, + "args": { + "External id": 764752,"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": 688924722760.860, "dur": 1.480, + "args": { + "External id": 764753,"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": 688924722761.545, "dur": 0.721, + "args": { + "External id": 764754,"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": 688924722766.538, "dur": 5.261, + "args": { + "External id": 764755,"Record function id": 0, "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924722768.142, "dur": 3.188, + "args": { + "External id": 764756,"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": 688924722768.882, "dur": 1.753, + "args": { + "External id": 764757,"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": 688924722769.764, "dur": 0.797, + "args": { + "External id": 764758,"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": 688924722774.919, "dur": 6.829, + "args": { + "External id": 764759,"Record function id": 0, "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924722776.138, "dur": 5.207, + "args": { + "External id": 764760,"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": 688924722779.616, "dur": 1.325, + "args": { + "External id": 764761,"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": 688924722780.098, "dur": 0.779, + "args": { + "External id": 764762,"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": 688924722784.843, "dur": 21.959, + "args": { + "External id": 764763,"Record function id": 0, "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924722800.016, "dur": 6.079, + "args": { + "External id": 764764,"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": 688924722801.090, "dur": 4.186, + "args": { + "External id": 764765,"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": 688924722803.839, "dur": 1.187, + "args": { + "External id": 764766,"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": 688924722812.579, "dur": 14910.715, + "args": { + "External id": 764767,"Record function id": 0, "Sequence number": 8961969, "Fwd thread id": 1, "Ev Idx": 3934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924722814.410, "dur": 14899.192, + "args": { + "External id": 764768,"Sequence number": 8961969, "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": 688924722814.410, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 4183436, "tid": 31338, + "ts": 688924722846.906, "dur": 34.851, + "args": { + "External id": 764769,"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": 688924722889.681, "dur": 71.754, + "args": { + "External id": 764770,"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": 688924722967.129, "dur": 14737.274, + "args": { + "External id": 764771,"Record function id": 0, "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924723054.847, "dur": 6.978, + "args": { + "External id": 764772,"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": 688924723074.658, "dur": 5.061, + "args": { + "External id": 764773,"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": 688924723092.697, "dur": 13870.078, + "args": { + "External id": 764774,"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": 688924723105.156, "dur": 13848.510, + "args": { + "External id": 764775,"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": 688924723147.759, "dur": 15.377, + "args": { + "External id": 764776,"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": 688924723167.681, "dur": 13748.067, + "args": { + "External id": 764777,"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": 688924723170.124, "dur": 13744.855, + "args": { + "External id": 764778,"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": 688924723174.405, "dur": 5.199, + "args": { + "External id": 764779,"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": 688924723181.531, "dur": 13729.338, + "args": { + "External id": 764780,"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": 688924737056.087, "dur": 9.652, + "args": { + "External id": 764781,"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": 688924737058.852, "dur": 6.492, + "args": { + "External id": 764782,"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": 688924737094.123, "dur": 292.021, + "args": { + "External id": 764783,"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": 688924737119.463, "dur": 261.921, + "args": { + "External id": 764784,"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": 688924737130.751, "dur": 246.252, + "args": { + "External id": 764785,"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": 688924737402.230, "dur": 2.380, + "args": { + "External id": 764786,"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": 688924737455.866, "dur": 6.433, + "args": { + "External id": 764787,"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": 688924737507.130, "dur": 1.341, + "args": { + "External id": 764788,"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": 688924737525.475, "dur": 1.175, + "args": { + "External id": 764789,"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": 688924737538.483, "dur": 2.614, + "args": { + "External id": 764790,"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": 688924737551.161, "dur": 0.739, + "args": { + "External id": 764791,"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": 688924737561.794, "dur": 0.754, + "args": { + "External id": 764792,"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": 688924737572.485, "dur": 0.808, + "args": { + "External id": 764793,"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": 688924737584.751, "dur": 2.506, + "args": { + "External id": 764794,"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": 688924737597.502, "dur": 1.238, + "args": { + "External id": 764795,"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": 688924737739.894, "dur": 2613.109, + "args": { + "External id": 764796,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 4183436, "tid": 31338, + "ts": 688924737761.739, "dur": 975.871, + "args": { + "External id": 764797,"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": 688924737775.936, "dur": 310.775, + "args": { + "External id": 764798,"Record function id": 0, "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924737874.260, "dur": 4.748, + "args": { + "External id": 764799,"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": 688924737882.433, "dur": 0.781, + "args": { + "External id": 764800,"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": 688924737884.905, "dur": 1.300, + "args": { + "External id": 764801,"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": 688924737887.870, "dur": 0.818, + "args": { + "External id": 764802,"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": 688924737890.416, "dur": 2.170, + "args": { + "External id": 764803,"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": 688924737894.117, "dur": 0.851, + "args": { + "External id": 764804,"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": 688924737896.582, "dur": 1.184, + "args": { + "External id": 764805,"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": 688924737899.519, "dur": 0.754, + "args": { + "External id": 764806,"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": 688924737901.982, "dur": 0.586, + "args": { + "External id": 764807,"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": 688924737904.161, "dur": 1.021, + "args": { + "External id": 764808,"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": 688924737922.579, "dur": 135.572, + "args": { + "External id": 764809,"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": 688924737938.006, "dur": 116.030, + "args": { + "External id": 764810,"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": 688924737950.511, "dur": 11.775, + "args": { + "External id": 764811,"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": 688924737965.244, "dur": 61.302, + "args": { + "External id": 764812,"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": 688924737967.653, "dur": 58.566, + "args": { + "External id": 764813,"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": 688924737971.612, "dur": 5.573, + "args": { + "External id": 764814,"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": 688924737978.862, "dur": 46.718, + "args": { + "External id": 764815,"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": 688924738174.354, "dur": 555.448, + "args": { + "External id": 764816,"Record function id": 0, "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 4183436, "tid": 31338, + "ts": 688924738189.595, "dur": 526.450, + "args": { + "External id": 764817,"Record function id": 0, "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924738245.815, "dur": 6.241, + "args": { + "External id": 764818,"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": 688924738267.532, "dur": 24.261, + "args": { + "External id": 764819,"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": 688924738271.984, "dur": 1.457, + "args": { + "External id": 764820,"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": 688924738275.168, "dur": 0.457, + "args": { + "External id": 764821,"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": 688924738276.627, "dur": 0.446, + "args": { + "External id": 764822,"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": 688924738278.186, "dur": 0.477, + "args": { + "External id": 764823,"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": 688924738280.002, "dur": 0.347, + "args": { + "External id": 764824,"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": 688924738281.591, "dur": 0.682, + "args": { + "External id": 764825,"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": 688924738283.651, "dur": 0.194, + "args": { + "External id": 764826,"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": 688924738284.809, "dur": 2.200, + "args": { + "External id": 764827,"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": 688924738288.327, "dur": 0.569, + "args": { + "External id": 764828,"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": 688924738300.843, "dur": 28.652, + "args": { + "External id": 764829,"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": 688924738362.359, "dur": 92.854, + "args": { + "External id": 764830,"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": 688924738371.585, "dur": 3.061, + "args": { + "External id": 764831,"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": 688924738379.650, "dur": 9.667, + "args": { + "External id": 764832,"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": 688924738383.869, "dur": 5.066, + "args": { + "External id": 764833,"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": 688924738387.109, "dur": 0.599, + "args": { + "External id": 764834,"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": 688924738396.059, "dur": 26.387, + "args": { + "External id": 764835,"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": 688924738398.223, "dur": 0.285, + "args": { + "External id": 764836,"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": 688924738399.660, "dur": 0.413, + "args": { + "External id": 764837,"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": 688924738401.920, "dur": 0.847, + "args": { + "External id": 764838,"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": 688924738404.038, "dur": 0.333, + "args": { + "External id": 764839,"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": 688924738405.775, "dur": 1.823, + "args": { + "External id": 764840,"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": 688924738408.436, "dur": 0.639, + "args": { + "External id": 764841,"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": 688924738410.342, "dur": 0.157, + "args": { + "External id": 764842,"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": 688924738411.443, "dur": 0.401, + "args": { + "External id": 764843,"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": 688924738413.540, "dur": 0.772, + "args": { + "External id": 764844,"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": 688924738431.714, "dur": 16.920, + "args": { + "External id": 764845,"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": 688924738498.639, "dur": 109.578, + "args": { + "External id": 764846,"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": 688924738520.821, "dur": 84.336, + "args": { + "External id": 764847,"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": 688924738529.068, "dur": 72.167, + "args": { + "External id": 764848,"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": 688924738621.480, "dur": 1.950, + "args": { + "External id": 764849,"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": 688924738745.807, "dur": 1583.165, + "args": { + "External id": 764850,"Sequence number": 8961968, "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": 688924738745.807, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924738879.738, "dur": 108.503, + "args": { + "External id": 764851,"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": 688924739028.731, "dur": 42.145, + "args": { + "External id": 764852,"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": 688924739088.604, "dur": 41.267, + "args": { + "External id": 764853,"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": 688924739139.700, "dur": 26.823, + "args": { + "External id": 764854,"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": 688924739172.615, "dur": 32.306, + "args": { + "External id": 764855,"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": 688924739213.199, "dur": 21.468, + "args": { + "External id": 764856,"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": 688924739241.615, "dur": 28.897, + "args": { + "External id": 764857,"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": 688924739293.704, "dur": 23.713, + "args": { + "External id": 764858,"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": 688924739334.867, "dur": 26.855, + "args": { + "External id": 764859,"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": 688924739380.498, "dur": 20.944, + "args": { + "External id": 764860,"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": 688924739414.876, "dur": 15.998, + "args": { + "External id": 764861,"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": 688924739440.367, "dur": 36.011, + "args": { + "External id": 764862,"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": 688924739479.754, "dur": 29.291, + "args": { + "External id": 764863,"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": 688924739534.956, "dur": 217.244, + "args": { + "External id": 764864,"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": 688924739614.397, "dur": 5.420, + "args": { + "External id": 764865,"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": 688924739621.528, "dur": 3.214, + "args": { + "External id": 764866,"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": 688924739801.040, "dur": 28.407, + "args": { + "External id": 764867,"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": 688924739841.907, "dur": 15.177, + "args": { + "External id": 764868,"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": 688924739866.417, "dur": 55.720, + "args": { + "External id": 764869,"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": 688924739933.485, "dur": 30.629, + "args": { + "External id": 764870,"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": 688924739970.196, "dur": 27.658, + "args": { + "External id": 764871,"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": 688924740002.437, "dur": 27.211, + "args": { + "External id": 764872,"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": 688924740034.929, "dur": 30.387, + "args": { + "External id": 764873,"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": 688924740073.723, "dur": 46.719, + "args": { + "External id": 764874,"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": 688924740144.543, "dur": 26.349, + "args": { + "External id": 764875,"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": 688924740187.622, "dur": 23.499, + "args": { + "External id": 764876,"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": 688924740227.986, "dur": 16.316, + "args": { + "External id": 764877,"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": 688924740257.128, "dur": 14.370, + "args": { + "External id": 764878,"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": 688924740286.420, "dur": 14.931, + "args": { + "External id": 764879,"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": 688924740373.741, "dur": 14.550, + "args": { + "External id": 764880,"Record function id": 0, "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924740377.089, "dur": 10.238, + "args": { + "External id": 764881,"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": 688924740381.262, "dur": 5.301, + "args": { + "External id": 764882,"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": 688924740382.525, "dur": 3.941, + "args": { + "External id": 764883,"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": 688924740392.254, "dur": 4.357, + "args": { + "External id": 764884,"Record function id": 0, "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924740393.815, "dur": 2.336, + "args": { + "External id": 764885,"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": 688924740394.577, "dur": 1.115, + "args": { + "External id": 764886,"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": 688924740394.911, "dur": 0.709, + "args": { + "External id": 764887,"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": 688924740402.755, "dur": 4.488, + "args": { + "External id": 764888,"Record function id": 0, "Ev Idx": 4055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924740404.243, "dur": 2.534, + "args": { + "External id": 764889,"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": 688924740404.743, "dur": 1.419, + "args": { + "External id": 764890,"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": 688924740405.184, "dur": 0.891, + "args": { + "External id": 764891,"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": 688924740410.529, "dur": 5.564, + "args": { + "External id": 764892,"Record function id": 0, "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924740411.660, "dur": 4.002, + "args": { + "External id": 764893,"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": 688924740412.490, "dur": 2.596, + "args": { + "External id": 764894,"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": 688924740412.768, "dur": 2.251, + "args": { + "External id": 764895,"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": 688924740419.282, "dur": 4.084, + "args": { + "External id": 764896,"Record function id": 0, "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924740420.502, "dur": 2.406, + "args": { + "External id": 764897,"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": 688924740421.174, "dur": 1.166, + "args": { + "External id": 764898,"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": 688924740421.600, "dur": 0.668, + "args": { + "External id": 764899,"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": 688924740426.461, "dur": 3.976, + "args": { + "External id": 764900,"Record function id": 0, "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924740427.656, "dur": 2.360, + "args": { + "External id": 764901,"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": 688924740428.109, "dur": 1.375, + "args": { + "External id": 764902,"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": 688924740428.872, "dur": 0.537, + "args": { + "External id": 764903,"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": 688924740433.646, "dur": 4.149, + "args": { + "External id": 764904,"Record function id": 0, "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924740434.937, "dur": 2.337, + "args": { + "External id": 764905,"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": 688924740435.464, "dur": 1.390, + "args": { + "External id": 764906,"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": 688924740436.082, "dur": 0.697, + "args": { + "External id": 764907,"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": 688924740440.901, "dur": 3.886, + "args": { + "External id": 764908,"Record function id": 0, "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924740442.014, "dur": 2.371, + "args": { + "External id": 764909,"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": 688924740442.704, "dur": 1.272, + "args": { + "External id": 764910,"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": 688924740443.137, "dur": 0.762, + "args": { + "External id": 764911,"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": 688924740448.534, "dur": 3.905, + "args": { + "External id": 764912,"Record function id": 0, "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924740449.679, "dur": 2.320, + "args": { + "External id": 764913,"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": 688924740450.156, "dur": 1.088, + "args": { + "External id": 764914,"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": 688924740450.708, "dur": 0.472, + "args": { + "External id": 764915,"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": 688924740456.479, "dur": 14873.905, + "args": { + "External id": 764916,"Record function id": 0, "Sequence number": 8961967, "Fwd thread id": 1, "Ev Idx": 4083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924740460.888, "dur": 14861.162, + "args": { + "External id": 764917,"Sequence number": 8961967, "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": 688924740460.888, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 4183436, "tid": 31338, + "ts": 688924740490.174, "dur": 40.180, + "args": { + "External id": 764918,"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": 688924740538.533, "dur": 72.910, + "args": { + "External id": 764919,"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": 688924740617.222, "dur": 14697.118, + "args": { + "External id": 764920,"Record function id": 0, "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924740749.828, "dur": 6.863, + "args": { + "External id": 764921,"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": 688924740767.372, "dur": 5.002, + "args": { + "External id": 764922,"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": 688924740801.056, "dur": 13790.596, + "args": { + "External id": 764923,"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": 688924740815.881, "dur": 13766.431, + "args": { + "External id": 764924,"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": 688924740837.727, "dur": 15.090, + "args": { + "External id": 764925,"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": 688924740857.399, "dur": 13688.608, + "args": { + "External id": 764926,"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": 688924740860.044, "dur": 13685.131, + "args": { + "External id": 764927,"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": 688924740863.732, "dur": 5.123, + "args": { + "External id": 764928,"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": 688924740933.638, "dur": 13607.735, + "args": { + "External id": 764929,"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": 688924754714.509, "dur": 9.625, + "args": { + "External id": 764930,"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": 688924754717.387, "dur": 6.267, + "args": { + "External id": 764931,"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": 688924754751.243, "dur": 283.648, + "args": { + "External id": 764932,"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": 688924754777.980, "dur": 251.841, + "args": { + "External id": 764933,"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": 688924754800.974, "dur": 224.538, + "args": { + "External id": 764934,"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": 688924755052.532, "dur": 2.034, + "args": { + "External id": 764935,"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": 688924755109.049, "dur": 5.803, + "args": { + "External id": 764936,"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": 688924755158.398, "dur": 1.388, + "args": { + "External id": 764937,"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": 688924755176.643, "dur": 1.175, + "args": { + "External id": 764938,"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": 688924755190.120, "dur": 2.024, + "args": { + "External id": 764939,"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": 688924755205.080, "dur": 0.833, + "args": { + "External id": 764940,"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": 688924755215.921, "dur": 1.001, + "args": { + "External id": 764941,"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": 688924755229.521, "dur": 0.949, + "args": { + "External id": 764942,"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": 688924755241.657, "dur": 2.323, + "args": { + "External id": 764943,"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": 688924755253.584, "dur": 0.727, + "args": { + "External id": 764944,"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": 688924755343.775, "dur": 2735.970, + "args": { + "External id": 764945,"Record function id": 0, "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 4183436, "tid": 31338, + "ts": 688924755361.791, "dur": 1027.527, + "args": { + "External id": 764946,"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": 688924755374.998, "dur": 345.046, + "args": { + "External id": 764947,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924755455.326, "dur": 3.852, + "args": { + "External id": 764948,"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": 688924755462.284, "dur": 0.784, + "args": { + "External id": 764949,"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": 688924755464.919, "dur": 0.965, + "args": { + "External id": 764950,"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": 688924755467.779, "dur": 0.600, + "args": { + "External id": 764951,"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": 688924755469.886, "dur": 1.645, + "args": { + "External id": 764952,"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": 688924755473.081, "dur": 0.804, + "args": { + "External id": 764953,"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": 688924755475.552, "dur": 0.895, + "args": { + "External id": 764954,"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": 688924755478.135, "dur": 0.674, + "args": { + "External id": 764955,"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": 688924755480.543, "dur": 0.725, + "args": { + "External id": 764956,"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": 688924755482.864, "dur": 0.603, + "args": { + "External id": 764957,"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": 688924755500.023, "dur": 146.902, + "args": { + "External id": 764958,"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": 688924755515.003, "dur": 127.506, + "args": { + "External id": 764959,"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": 688924755540.083, "dur": 13.050, + "args": { + "External id": 764960,"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": 688924755555.869, "dur": 59.247, + "args": { + "External id": 764961,"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": 688924755558.273, "dur": 56.536, + "args": { + "External id": 764962,"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": 688924755562.067, "dur": 5.401, + "args": { + "External id": 764963,"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": 688924755568.990, "dur": 45.132, + "args": { + "External id": 764964,"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": 688924755831.994, "dur": 549.723, + "args": { + "External id": 764965,"Record function id": 0, "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 4183436, "tid": 31338, + "ts": 688924755851.447, "dur": 518.227, + "args": { + "External id": 764966,"Record function id": 0, "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924755915.918, "dur": 7.950, + "args": { + "External id": 764967,"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": 688924755939.392, "dur": 37.181, + "args": { + "External id": 764968,"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": 688924755944.455, "dur": 1.451, + "args": { + "External id": 764969,"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": 688924755947.704, "dur": 0.411, + "args": { + "External id": 764970,"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": 688924755949.713, "dur": 0.547, + "args": { + "External id": 764971,"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": 688924755951.373, "dur": 0.660, + "args": { + "External id": 764972,"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": 688924755953.764, "dur": 0.717, + "args": { + "External id": 764973,"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": 688924755955.726, "dur": 0.713, + "args": { + "External id": 764974,"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": 688924755967.365, "dur": 0.484, + "args": { + "External id": 764975,"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": 688924755969.066, "dur": 2.283, + "args": { + "External id": 764976,"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": 688924755972.849, "dur": 0.497, + "args": { + "External id": 764977,"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": 688924755987.757, "dur": 36.138, + "args": { + "External id": 764978,"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": 688924756056.866, "dur": 95.682, + "args": { + "External id": 764979,"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": 688924756067.060, "dur": 3.157, + "args": { + "External id": 764980,"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": 688924756075.128, "dur": 9.290, + "args": { + "External id": 764981,"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": 688924756079.141, "dur": 4.877, + "args": { + "External id": 764982,"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": 688924756082.249, "dur": 0.609, + "args": { + "External id": 764983,"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": 688924756091.856, "dur": 24.934, + "args": { + "External id": 764984,"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": 688924756092.984, "dur": 0.499, + "args": { + "External id": 764985,"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": 688924756094.904, "dur": 0.474, + "args": { + "External id": 764986,"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": 688924756096.833, "dur": 0.761, + "args": { + "External id": 764987,"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": 688924756099.177, "dur": 0.339, + "args": { + "External id": 764988,"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": 688924756100.883, "dur": 2.261, + "args": { + "External id": 764989,"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": 688924756104.738, "dur": 0.840, + "args": { + "External id": 764990,"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": 688924756106.812, "dur": 0.436, + "args": { + "External id": 764991,"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": 688924756108.508, "dur": 0.480, + "args": { + "External id": 764992,"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": 688924756110.096, "dur": 0.553, + "args": { + "External id": 764993,"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": 688924756126.309, "dur": 18.658, + "args": { + "External id": 764994,"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": 688924756196.565, "dur": 108.493, + "args": { + "External id": 764995,"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": 688924756222.034, "dur": 79.706, + "args": { + "External id": 764996,"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": 688924756231.423, "dur": 66.332, + "args": { + "External id": 764997,"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": 688924756319.761, "dur": 1.649, + "args": { + "External id": 764998,"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": 688924756397.296, "dur": 1662.284, + "args": { + "External id": 764999,"Sequence number": 8961966, "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": 688924756397.296, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924756503.966, "dur": 99.233, + "args": { + "External id": 765000,"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": 688924756643.265, "dur": 83.221, + "args": { + "External id": 765001,"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": 688924756747.493, "dur": 65.486, + "args": { + "External id": 765002,"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": 688924756826.716, "dur": 30.246, + "args": { + "External id": 765003,"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": 688924756863.422, "dur": 33.646, + "args": { + "External id": 765004,"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": 688924756905.136, "dur": 21.751, + "args": { + "External id": 765005,"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": 688924756933.852, "dur": 27.658, + "args": { + "External id": 765006,"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": 688924756986.381, "dur": 23.867, + "args": { + "External id": 765007,"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": 688924757061.152, "dur": 27.791, + "args": { + "External id": 765008,"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": 688924757108.789, "dur": 20.545, + "args": { + "External id": 765009,"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": 688924757141.875, "dur": 15.657, + "args": { + "External id": 765010,"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": 688924757167.187, "dur": 42.624, + "args": { + "External id": 765011,"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": 688924757213.369, "dur": 29.189, + "args": { + "External id": 765012,"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": 688924757269.466, "dur": 166.697, + "args": { + "External id": 765013,"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": 688924757344.465, "dur": 5.538, + "args": { + "External id": 765014,"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": 688924757351.681, "dur": 2.732, + "args": { + "External id": 765015,"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": 688924757470.882, "dur": 23.855, + "args": { + "External id": 765016,"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": 688924757506.223, "dur": 14.766, + "args": { + "External id": 765017,"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": 688924757527.775, "dur": 42.196, + "args": { + "External id": 765018,"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": 688924757577.385, "dur": 29.337, + "args": { + "External id": 765019,"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": 688924757612.796, "dur": 26.632, + "args": { + "External id": 765020,"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": 688924757643.680, "dur": 67.651, + "args": { + "External id": 765021,"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": 688924757720.709, "dur": 46.546, + "args": { + "External id": 765022,"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": 688924757782.915, "dur": 59.953, + "args": { + "External id": 765023,"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": 688924757870.463, "dur": 23.221, + "args": { + "External id": 765024,"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": 688924757912.309, "dur": 25.915, + "args": { + "External id": 765025,"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": 688924757953.121, "dur": 16.018, + "args": { + "External id": 765026,"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": 688924757987.604, "dur": 12.784, + "args": { + "External id": 765027,"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": 688924758012.545, "dur": 15.102, + "args": { + "External id": 765028,"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": 688924758104.416, "dur": 14.311, + "args": { + "External id": 765029,"Record function id": 0, "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924758107.643, "dur": 10.123, + "args": { + "External id": 765030,"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": 688924758111.667, "dur": 5.312, + "args": { + "External id": 765031,"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": 688924758112.902, "dur": 3.973, + "args": { + "External id": 765032,"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": 688924758122.611, "dur": 5.008, + "args": { + "External id": 765033,"Record function id": 0, "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924758124.450, "dur": 2.733, + "args": { + "External id": 765034,"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": 688924758125.363, "dur": 1.365, + "args": { + "External id": 765035,"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": 688924758125.701, "dur": 0.964, + "args": { + "External id": 765036,"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": 688924758130.905, "dur": 4.510, + "args": { + "External id": 765037,"Record function id": 0, "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924758132.722, "dur": 2.270, + "args": { + "External id": 765038,"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": 688924758133.388, "dur": 1.208, + "args": { + "External id": 765039,"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": 688924758133.798, "dur": 0.730, + "args": { + "External id": 765040,"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": 688924758138.569, "dur": 6.316, + "args": { + "External id": 765041,"Record function id": 0, "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924758139.954, "dur": 4.486, + "args": { + "External id": 765042,"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": 688924758140.836, "dur": 3.197, + "args": { + "External id": 765043,"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": 688924758141.131, "dur": 2.819, + "args": { + "External id": 765044,"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": 688924758148.150, "dur": 4.165, + "args": { + "External id": 765045,"Record function id": 0, "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924758149.512, "dur": 2.352, + "args": { + "External id": 765046,"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": 688924758149.995, "dur": 1.332, + "args": { + "External id": 765047,"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": 688924758150.279, "dur": 0.968, + "args": { + "External id": 765048,"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": 688924758158.907, "dur": 4.130, + "args": { + "External id": 765049,"Record function id": 0, "Ev Idx": 4216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924758160.104, "dur": 2.466, + "args": { + "External id": 765050,"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": 688924758160.759, "dur": 1.367, + "args": { + "External id": 765051,"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": 688924758161.400, "dur": 0.650, + "args": { + "External id": 765052,"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": 688924758166.443, "dur": 4.256, + "args": { + "External id": 765053,"Record function id": 0, "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924758167.658, "dur": 2.630, + "args": { + "External id": 765054,"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": 688924758168.196, "dur": 1.478, + "args": { + "External id": 765055,"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": 688924758168.732, "dur": 0.867, + "args": { + "External id": 765056,"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": 688924758173.738, "dur": 4.649, + "args": { + "External id": 765057,"Record function id": 0, "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924758175.409, "dur": 2.547, + "args": { + "External id": 765058,"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": 688924758176.088, "dur": 1.486, + "args": { + "External id": 765059,"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": 688924758176.841, "dur": 0.659, + "args": { + "External id": 765060,"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": 688924758181.843, "dur": 4.620, + "args": { + "External id": 765061,"Record function id": 0, "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924758182.998, "dur": 3.042, + "args": { + "External id": 765062,"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": 688924758183.805, "dur": 1.874, + "args": { + "External id": 765063,"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": 688924758184.843, "dur": 0.769, + "args": { + "External id": 765064,"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": 688924758190.570, "dur": 14907.513, + "args": { + "External id": 765065,"Record function id": 0, "Sequence number": 8961965, "Fwd thread id": 1, "Ev Idx": 4232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924758192.157, "dur": 14896.787, + "args": { + "External id": 765066,"Sequence number": 8961965, "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": 688924758192.157, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 4183436, "tid": 31338, + "ts": 688924758223.505, "dur": 36.888, + "args": { + "External id": 765067,"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": 688924758267.886, "dur": 70.341, + "args": { + "External id": 765068,"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": 688924758343.959, "dur": 14737.294, + "args": { + "External id": 765069,"Record function id": 0, "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924758431.052, "dur": 6.084, + "args": { + "External id": 765070,"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": 688924758446.596, "dur": 4.680, + "args": { + "External id": 765071,"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": 688924758464.564, "dur": 13923.935, + "args": { + "External id": 765072,"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": 688924758477.825, "dur": 13902.760, + "args": { + "External id": 765073,"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": 688924758531.609, "dur": 15.210, + "args": { + "External id": 765074,"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": 688924758551.535, "dur": 13795.893, + "args": { + "External id": 765075,"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": 688924758554.153, "dur": 13792.484, + "args": { + "External id": 765076,"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": 688924758558.253, "dur": 4.966, + "args": { + "External id": 765077,"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": 688924758564.724, "dur": 13778.237, + "args": { + "External id": 765078,"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": 688924772478.944, "dur": 9.087, + "args": { + "External id": 765079,"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": 688924772481.869, "dur": 5.794, + "args": { + "External id": 765080,"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": 688924772512.693, "dur": 291.407, + "args": { + "External id": 765081,"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": 688924772539.205, "dur": 259.295, + "args": { + "External id": 765082,"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": 688924772550.091, "dur": 230.368, + "args": { + "External id": 765083,"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": 688924772824.712, "dur": 2.690, + "args": { + "External id": 765084,"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": 688924772884.145, "dur": 6.209, + "args": { + "External id": 765085,"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": 688924772932.347, "dur": 1.636, + "args": { + "External id": 765086,"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": 688924772950.207, "dur": 1.330, + "args": { + "External id": 765087,"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": 688924772963.133, "dur": 2.779, + "args": { + "External id": 765088,"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": 688924772977.800, "dur": 1.265, + "args": { + "External id": 765089,"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": 688924772989.119, "dur": 0.932, + "args": { + "External id": 765090,"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": 688924772999.930, "dur": 1.015, + "args": { + "External id": 765091,"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": 688924773011.706, "dur": 2.648, + "args": { + "External id": 765092,"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": 688924773023.889, "dur": 0.739, + "args": { + "External id": 765093,"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": 688924773112.486, "dur": 2534.903, + "args": { + "External id": 765094,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 4183436, "tid": 31338, + "ts": 688924773131.217, "dur": 990.951, + "args": { + "External id": 765095,"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": 688924773145.626, "dur": 285.633, + "args": { + "External id": 765096,"Record function id": 0, "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924773224.454, "dur": 3.913, + "args": { + "External id": 765097,"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": 688924773231.648, "dur": 1.119, + "args": { + "External id": 765098,"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": 688924773234.791, "dur": 1.027, + "args": { + "External id": 765099,"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": 688924773237.949, "dur": 1.244, + "args": { + "External id": 765100,"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": 688924773240.727, "dur": 2.461, + "args": { + "External id": 765101,"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": 688924773244.990, "dur": 1.289, + "args": { + "External id": 765102,"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": 688924773248.114, "dur": 0.780, + "args": { + "External id": 765103,"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": 688924773250.280, "dur": 1.149, + "args": { + "External id": 765104,"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": 688924773253.205, "dur": 1.268, + "args": { + "External id": 765105,"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": 688924773256.530, "dur": 1.237, + "args": { + "External id": 765106,"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": 688924773274.180, "dur": 131.484, + "args": { + "External id": 765107,"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": 688924773290.382, "dur": 111.343, + "args": { + "External id": 765108,"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": 688924773301.623, "dur": 12.252, + "args": { + "External id": 765109,"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": 688924773316.633, "dur": 60.029, + "args": { + "External id": 765110,"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": 688924773319.389, "dur": 56.930, + "args": { + "External id": 765111,"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": 688924773323.098, "dur": 5.517, + "args": { + "External id": 765112,"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": 688924773330.859, "dur": 44.878, + "args": { + "External id": 765113,"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": 688924773513.587, "dur": 601.263, + "args": { + "External id": 765114,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 4183436, "tid": 31338, + "ts": 688924773529.552, "dur": 571.599, + "args": { + "External id": 765115,"Record function id": 0, "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924773589.364, "dur": 5.767, + "args": { + "External id": 765116,"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": 688924773610.078, "dur": 24.719, + "args": { + "External id": 765117,"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": 688924773614.316, "dur": 1.127, + "args": { + "External id": 765118,"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": 688924773617.336, "dur": 0.399, + "args": { + "External id": 765119,"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": 688924773618.993, "dur": 0.276, + "args": { + "External id": 765120,"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": 688924773620.649, "dur": 0.592, + "args": { + "External id": 765121,"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": 688924773622.447, "dur": 0.471, + "args": { + "External id": 765122,"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": 688924773624.484, "dur": 0.580, + "args": { + "External id": 765123,"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": 688924773626.238, "dur": 0.576, + "args": { + "External id": 765124,"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": 688924773627.946, "dur": 2.409, + "args": { + "External id": 765125,"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": 688924773631.660, "dur": 0.704, + "args": { + "External id": 765126,"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": 688924773644.556, "dur": 72.051, + "args": { + "External id": 765127,"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": 688924773750.964, "dur": 125.609, + "args": { + "External id": 765128,"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": 688924773761.816, "dur": 4.551, + "args": { + "External id": 765129,"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": 688924773771.627, "dur": 10.093, + "args": { + "External id": 765130,"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": 688924773775.626, "dur": 5.712, + "args": { + "External id": 765131,"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": 688924773778.958, "dur": 0.735, + "args": { + "External id": 765132,"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": 688924773804.723, "dur": 29.910, + "args": { + "External id": 765133,"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": 688924773807.140, "dur": 0.679, + "args": { + "External id": 765134,"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": 688924773809.708, "dur": 0.489, + "args": { + "External id": 765135,"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": 688924773812.309, "dur": 0.322, + "args": { + "External id": 765136,"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": 688924773814.227, "dur": 0.389, + "args": { + "External id": 765137,"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": 688924773816.588, "dur": 2.210, + "args": { + "External id": 765138,"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": 688924773820.015, "dur": 0.703, + "args": { + "External id": 765139,"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": 688924773822.201, "dur": 0.684, + "args": { + "External id": 765140,"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": 688924773824.574, "dur": 0.320, + "args": { + "External id": 765141,"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": 688924773826.214, "dur": 0.451, + "args": { + "External id": 765142,"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": 688924773846.122, "dur": 22.984, + "args": { + "External id": 765143,"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": 688924773925.138, "dur": 109.984, + "args": { + "External id": 765144,"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": 688924773951.054, "dur": 80.855, + "args": { + "External id": 765145,"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": 688924773960.533, "dur": 67.363, + "args": { + "External id": 765146,"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": 688924774050.518, "dur": 1.809, + "args": { + "External id": 765147,"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": 688924774129.387, "dur": 1496.481, + "args": { + "External id": 765148,"Sequence number": 8961964, "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": 688924774129.387, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924774240.544, "dur": 95.970, + "args": { + "External id": 765149,"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": 688924774375.673, "dur": 38.001, + "args": { + "External id": 765150,"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": 688924774430.141, "dur": 38.287, + "args": { + "External id": 765151,"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": 688924774478.472, "dur": 24.522, + "args": { + "External id": 765152,"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": 688924774509.354, "dur": 31.214, + "args": { + "External id": 765153,"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": 688924774548.034, "dur": 19.717, + "args": { + "External id": 765154,"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": 688924774574.680, "dur": 28.379, + "args": { + "External id": 765155,"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": 688924774623.119, "dur": 20.008, + "args": { + "External id": 765156,"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": 688924774700.181, "dur": 27.724, + "args": { + "External id": 765157,"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": 688924774748.689, "dur": 18.351, + "args": { + "External id": 765158,"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": 688924774778.468, "dur": 30.359, + "args": { + "External id": 765159,"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": 688924774820.674, "dur": 44.065, + "args": { + "External id": 765160,"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": 688924774867.999, "dur": 30.603, + "args": { + "External id": 765161,"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": 688924774925.479, "dur": 172.432, + "args": { + "External id": 765162,"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": 688924775003.697, "dur": 5.631, + "args": { + "External id": 765163,"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": 688924775011.176, "dur": 2.801, + "args": { + "External id": 765164,"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": 688924775133.247, "dur": 25.237, + "args": { + "External id": 765165,"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": 688924775169.355, "dur": 14.264, + "args": { + "External id": 765166,"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": 688924775191.163, "dur": 40.565, + "args": { + "External id": 765167,"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": 688924775237.234, "dur": 29.373, + "args": { + "External id": 765168,"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": 688924775272.488, "dur": 26.266, + "args": { + "External id": 765169,"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": 688924775305.016, "dur": 30.682, + "args": { + "External id": 765170,"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": 688924775341.380, "dur": 26.506, + "args": { + "External id": 765171,"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": 688924775377.375, "dur": 27.629, + "args": { + "External id": 765172,"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": 688924775419.401, "dur": 25.561, + "args": { + "External id": 765173,"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": 688924775459.330, "dur": 23.191, + "args": { + "External id": 765174,"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": 688924775510.783, "dur": 24.771, + "args": { + "External id": 765175,"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": 688924775554.566, "dur": 15.763, + "args": { + "External id": 765176,"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": 688924775582.701, "dur": 16.179, + "args": { + "External id": 765177,"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": 688924775708.859, "dur": 16.248, + "args": { + "External id": 765178,"Record function id": 0, "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924775712.756, "dur": 11.177, + "args": { + "External id": 765179,"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": 688924775716.882, "dur": 5.729, + "args": { + "External id": 765180,"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": 688924775718.069, "dur": 4.346, + "args": { + "External id": 765181,"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": 688924775729.242, "dur": 7.799, + "args": { + "External id": 765182,"Record function id": 0, "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924775730.768, "dur": 5.820, + "args": { + "External id": 765183,"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": 688924775731.543, "dur": 4.443, + "args": { + "External id": 765184,"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": 688924775731.881, "dur": 0.892, + "args": { + "External id": 765185,"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": 688924775740.312, "dur": 4.945, + "args": { + "External id": 765186,"Record function id": 0, "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924775741.608, "dur": 3.206, + "args": { + "External id": 765187,"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": 688924775742.408, "dur": 1.833, + "args": { + "External id": 765188,"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": 688924775743.183, "dur": 0.951, + "args": { + "External id": 765189,"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": 688924775748.372, "dur": 3.917, + "args": { + "External id": 765190,"Record function id": 0, "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924775749.479, "dur": 2.388, + "args": { + "External id": 765191,"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": 688924775750.109, "dur": 1.197, + "args": { + "External id": 765192,"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": 688924775750.421, "dur": 0.812, + "args": { + "External id": 765193,"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": 688924775755.449, "dur": 3.843, + "args": { + "External id": 765194,"Record function id": 0, "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924775756.577, "dur": 2.277, + "args": { + "External id": 765195,"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": 688924775757.077, "dur": 1.339, + "args": { + "External id": 765196,"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": 688924775757.411, "dur": 0.941, + "args": { + "External id": 765197,"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": 688924775762.386, "dur": 3.975, + "args": { + "External id": 765198,"Record function id": 0, "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924775763.493, "dur": 2.441, + "args": { + "External id": 765199,"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": 688924775763.942, "dur": 1.564, + "args": { + "External id": 765200,"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": 688924775764.450, "dur": 0.989, + "args": { + "External id": 765201,"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": 688924775769.770, "dur": 4.342, + "args": { + "External id": 765202,"Record function id": 0, "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924775771.199, "dur": 2.485, + "args": { + "External id": 765203,"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": 688924775771.661, "dur": 1.588, + "args": { + "External id": 765204,"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": 688924775772.136, "dur": 1.044, + "args": { + "External id": 765205,"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": 688924775777.209, "dur": 3.948, + "args": { + "External id": 765206,"Record function id": 0, "Ev Idx": 4373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924775778.213, "dur": 2.536, + "args": { + "External id": 765207,"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": 688924775778.692, "dur": 1.620, + "args": { + "External id": 765208,"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": 688924775779.294, "dur": 0.951, + "args": { + "External id": 765209,"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": 688924775784.494, "dur": 24.813, + "args": { + "External id": 765210,"Record function id": 0, "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924775803.425, "dur": 4.930, + "args": { + "External id": 765211,"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": 688924775804.610, "dur": 2.904, + "args": { + "External id": 765212,"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": 688924775805.572, "dur": 1.681, + "args": { + "External id": 765213,"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": 688924775815.068, "dur": 14937.074, + "args": { + "External id": 765214,"Record function id": 0, "Sequence number": 8961963, "Fwd thread id": 1, "Ev Idx": 4381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924775816.651, "dur": 14925.216, + "args": { + "External id": 765215,"Sequence number": 8961963, "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": 688924775816.651, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 4183436, "tid": 31338, + "ts": 688924775845.449, "dur": 40.102, + "args": { + "External id": 765216,"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": 688924775892.943, "dur": 73.146, + "args": { + "External id": 765217,"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": 688924775975.091, "dur": 14757.473, + "args": { + "External id": 765218,"Record function id": 0, "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924776060.946, "dur": 7.087, + "args": { + "External id": 765219,"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": 688924776077.663, "dur": 4.600, + "args": { + "External id": 765220,"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": 688924776095.634, "dur": 13913.324, + "args": { + "External id": 765221,"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": 688924776108.373, "dur": 13891.811, + "args": { + "External id": 765222,"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": 688924776145.664, "dur": 13.585, + "args": { + "External id": 765223,"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": 688924776164.172, "dur": 13799.763, + "args": { + "External id": 765224,"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": 688924776166.809, "dur": 13796.410, + "args": { + "External id": 765225,"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": 688924776170.520, "dur": 5.532, + "args": { + "External id": 765226,"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": 688924776178.133, "dur": 13781.613, + "args": { + "External id": 765227,"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": 688924790096.878, "dur": 9.313, + "args": { + "External id": 765228,"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": 688924790099.617, "dur": 6.241, + "args": { + "External id": 765229,"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": 688924790131.301, "dur": 293.074, + "args": { + "External id": 765230,"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": 688924790157.176, "dur": 262.993, + "args": { + "External id": 765231,"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": 688924790168.178, "dur": 247.271, + "args": { + "External id": 765232,"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": 688924790441.741, "dur": 2.059, + "args": { + "External id": 765233,"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": 688924790494.010, "dur": 5.607, + "args": { + "External id": 765234,"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": 688924790542.803, "dur": 1.604, + "args": { + "External id": 765235,"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": 688924790560.113, "dur": 1.410, + "args": { + "External id": 765236,"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": 688924790574.177, "dur": 1.433, + "args": { + "External id": 765237,"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": 688924790586.488, "dur": 1.206, + "args": { + "External id": 765238,"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": 688924790597.583, "dur": 0.987, + "args": { + "External id": 765239,"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": 688924790609.641, "dur": 1.053, + "args": { + "External id": 765240,"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": 688924790621.836, "dur": 1.246, + "args": { + "External id": 765241,"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": 688924790632.948, "dur": 1.015, + "args": { + "External id": 765242,"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": 688924790767.626, "dur": 2047.026, + "args": { + "External id": 765243,"Record function id": 0, "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 4183436, "tid": 31338, + "ts": 688924790803.720, "dur": 417.161, + "args": { + "External id": 765244,"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": 688924790821.266, "dur": 306.003, + "args": { + "External id": 765245,"Record function id": 0, "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 31338, + "ts": 688924790910.055, "dur": 4.910, + "args": { + "External id": 765246,"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": 688924790918.690, "dur": 1.430, + "args": { + "External id": 765247,"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": 688924790922.300, "dur": 1.249, + "args": { + "External id": 765248,"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": 688924790925.498, "dur": 1.168, + "args": { + "External id": 765249,"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": 688924790928.436, "dur": 1.259, + "args": { + "External id": 765250,"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": 688924790931.641, "dur": 1.193, + "args": { + "External id": 765251,"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": 688924790934.504, "dur": 1.144, + "args": { + "External id": 765252,"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": 688924790937.567, "dur": 0.860, + "args": { + "External id": 765253,"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": 688924790940.326, "dur": 1.239, + "args": { + "External id": 765254,"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": 688924790943.409, "dur": 1.163, + "args": { + "External id": 765255,"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": 688924790960.980, "dur": 137.065, + "args": { + "External id": 765256,"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": 688924790977.053, "dur": 117.222, + "args": { + "External id": 765257,"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": 688924790988.746, "dur": 13.484, + "args": { + "External id": 765258,"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": 688924791004.895, "dur": 61.333, + "args": { + "External id": 765259,"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": 688924791007.813, "dur": 58.074, + "args": { + "External id": 765260,"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": 688924791011.488, "dur": 6.008, + "args": { + "External id": 765261,"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": 688924791019.202, "dur": 46.153, + "args": { + "External id": 765262,"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": 688924791228.307, "dur": 1547.064, + "args": { + "External id": 765263,"Sequence number": 8961962, "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": 688924791228.307, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 31338, + "ts": 688924791334.258, "dur": 97.928, + "args": { + "External id": 765264,"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": 688924791468.683, "dur": 38.053, + "args": { + "External id": 765265,"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": 688924791522.904, "dur": 40.877, + "args": { + "External id": 765266,"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": 688924791573.404, "dur": 27.550, + "args": { + "External id": 765267,"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": 688924791607.468, "dur": 31.760, + "args": { + "External id": 765268,"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": 688924791645.829, "dur": 69.022, + "args": { + "External id": 765269,"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": 688924791727.055, "dur": 31.438, + "args": { + "External id": 765270,"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": 688924791784.385, "dur": 39.813, + "args": { + "External id": 765271,"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": 688924791846.459, "dur": 28.660, + "args": { + "External id": 765272,"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": 688924791897.031, "dur": 19.492, + "args": { + "External id": 765273,"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": 688924791930.169, "dur": 15.740, + "args": { + "External id": 765274,"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": 688924791954.088, "dur": 41.193, + "args": { + "External id": 765275,"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": 688924791998.732, "dur": 29.976, + "args": { + "External id": 765276,"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": 688924792055.400, "dur": 165.904, + "args": { + "External id": 765277,"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": 688924792129.821, "dur": 6.277, + "args": { + "External id": 765278,"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": 688924792137.959, "dur": 3.036, + "args": { + "External id": 765279,"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": 688924792253.788, "dur": 26.758, + "args": { + "External id": 765280,"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": 688924792292.015, "dur": 13.932, + "args": { + "External id": 765281,"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": 688924792313.484, "dur": 44.645, + "args": { + "External id": 765282,"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": 688924792364.256, "dur": 29.687, + "args": { + "External id": 765283,"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": 688924792400.511, "dur": 27.648, + "args": { + "External id": 765284,"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": 688924792433.208, "dur": 27.670, + "args": { + "External id": 765285,"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": 688924792466.450, "dur": 26.530, + "args": { + "External id": 765286,"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": 688924792500.024, "dur": 28.077, + "args": { + "External id": 765287,"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": 688924792544.816, "dur": 24.165, + "args": { + "External id": 765288,"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": 688924792585.137, "dur": 25.327, + "args": { + "External id": 765289,"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": 688924792624.402, "dur": 17.800, + "args": { + "External id": 765290,"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": 688924792693.730, "dur": 19.446, + "args": { + "External id": 765291,"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": 688924792728.982, "dur": 17.095, + "args": { + "External id": 765292,"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": 688924792836.630, "dur": 15.811, + "args": { + "External id": 765293,"Record function id": 0, "Ev Idx": 4460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924792840.601, "dur": 10.965, + "args": { + "External id": 765294,"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": 688924792844.854, "dur": 5.890, + "args": { + "External id": 765295,"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": 688924792846.227, "dur": 4.398, + "args": { + "External id": 765296,"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": 688924792856.283, "dur": 5.303, + "args": { + "External id": 765297,"Record function id": 0, "Ev Idx": 4464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924792858.066, "dur": 3.088, + "args": { + "External id": 765298,"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": 688924792859.194, "dur": 1.510, + "args": { + "External id": 765299,"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": 688924792859.706, "dur": 0.913, + "args": { + "External id": 765300,"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": 688924792864.812, "dur": 4.333, + "args": { + "External id": 765301,"Record function id": 0, "Ev Idx": 4468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924792866.475, "dur": 2.273, + "args": { + "External id": 765302,"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": 688924792866.986, "dur": 1.380, + "args": { + "External id": 765303,"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": 688924792867.497, "dur": 0.806, + "args": { + "External id": 765304,"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": 688924792872.242, "dur": 4.967, + "args": { + "External id": 765305,"Record function id": 0, "Ev Idx": 4472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924792873.937, "dur": 2.868, + "args": { + "External id": 765306,"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": 688924792874.465, "dur": 1.907, + "args": { + "External id": 765307,"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": 688924792875.162, "dur": 1.143, + "args": { + "External id": 765308,"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": 688924792880.272, "dur": 8.100, + "args": { + "External id": 765309,"Record function id": 0, "Ev Idx": 4476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924792885.419, "dur": 2.559, + "args": { + "External id": 765310,"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": 688924792886.147, "dur": 1.281, + "args": { + "External id": 765311,"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": 688924792886.523, "dur": 0.829, + "args": { + "External id": 765312,"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": 688924792891.436, "dur": 4.672, + "args": { + "External id": 765313,"Record function id": 0, "Ev Idx": 4480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924792893.123, "dur": 2.591, + "args": { + "External id": 765314,"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": 688924792893.997, "dur": 1.333, + "args": { + "External id": 765315,"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": 688924792894.660, "dur": 0.594, + "args": { + "External id": 765316,"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": 688924792899.291, "dur": 4.987, + "args": { + "External id": 765317,"Record function id": 0, "Ev Idx": 4484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924792900.913, "dur": 2.965, + "args": { + "External id": 765318,"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": 688924792901.378, "dur": 1.719, + "args": { + "External id": 765319,"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": 688924792902.094, "dur": 0.937, + "args": { + "External id": 765320,"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": 688924792907.647, "dur": 5.196, + "args": { + "External id": 765321,"Record function id": 0, "Ev Idx": 4488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924792909.382, "dur": 3.028, + "args": { + "External id": 765322,"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": 688924792909.855, "dur": 2.149, + "args": { + "External id": 765323,"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": 688924792910.934, "dur": 1.002, + "args": { + "External id": 765324,"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": 688924792916.041, "dur": 5.298, + "args": { + "External id": 765325,"Record function id": 0, "Ev Idx": 4492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924792917.950, "dur": 2.979, + "args": { + "External id": 765326,"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": 688924792918.995, "dur": 1.313, + "args": { + "External id": 765327,"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": 688924792919.534, "dur": 0.705, + "args": { + "External id": 765328,"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": 688924792925.592, "dur": 15452.191, + "args": { + "External id": 765329,"Record function id": 0, "Sequence number": 8961961, "Fwd thread id": 1, "Ev Idx": 4496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924792926.964, "dur": 15441.689, + "args": { + "External id": 765330,"Sequence number": 8961961, "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": 688924792926.964, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 4183436, "tid": 31338, + "ts": 688924792961.024, "dur": 38.961, + "args": { + "External id": 765331,"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": 688924793007.330, "dur": 75.351, + "args": { + "External id": 765332,"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": 688924793091.970, "dur": 15269.058, + "args": { + "External id": 765333,"Record function id": 0, "Ev Idx": 4500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924793202.169, "dur": 10.381, + "args": { + "External id": 765334,"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": 688924793222.378, "dur": 4.784, + "args": { + "External id": 765335,"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": 688924793241.980, "dur": 14451.506, + "args": { + "External id": 765336,"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": 688924793255.238, "dur": 14429.672, + "args": { + "External id": 765337,"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": 688924793277.386, "dur": 14.056, + "args": { + "External id": 765338,"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": 688924793296.187, "dur": 14330.193, + "args": { + "External id": 765339,"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": 688924793298.912, "dur": 14326.781, + "args": { + "External id": 765340,"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": 688924793303.410, "dur": 5.348, + "args": { + "External id": 765341,"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": 688924793310.319, "dur": 14312.285, + "args": { + "External id": 765342,"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": 688924807781.176, "dur": 21.269, + "args": { + "External id": 765343,"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": 688924807783.885, "dur": 17.717, + "args": { + "External id": 765344,"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": 688924807830.522, "dur": 257.451, + "args": { + "External id": 765345,"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": 688924807856.498, "dur": 227.230, + "args": { + "External id": 765346,"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": 688924807869.346, "dur": 209.428, + "args": { + "External id": 765347,"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": 688924808103.839, "dur": 2.560, + "args": { + "External id": 765348,"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": 688924808159.327, "dur": 6.132, + "args": { + "External id": 765349,"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": 688924808209.092, "dur": 1.644, + "args": { + "External id": 765350,"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": 688924808227.215, "dur": 1.454, + "args": { + "External id": 765351,"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": 688924808240.919, "dur": 1.189, + "args": { + "External id": 765352,"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": 688924808253.677, "dur": 1.033, + "args": { + "External id": 765353,"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": 688924808264.423, "dur": 1.209, + "args": { + "External id": 765354,"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": 688924808277.941, "dur": 0.906, + "args": { + "External id": 765355,"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": 688924808290.143, "dur": 1.151, + "args": { + "External id": 765356,"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": 688924808300.780, "dur": 0.896, + "args": { + "External id": 765357,"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": 688924808391.456, "dur": 251.348, + "args": { + "External id": 765358,"Record function id": 0, "Sequence number": 8961960, "Fwd thread id": 1, "Ev Idx": 4525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183436, "tid": 31338, + "ts": 688924808394.284, "dur": 238.913, + "args": { + "External id": 765359,"Sequence number": 8961960, "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": 688924808394.284, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 4183436, "tid": 31338, + "ts": 688924808503.391, "dur": 39.468, + "args": { + "External id": 765360,"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": 688924808556.947, "dur": 26.580, + "args": { + "External id": 765361,"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": 688924808598.340, "dur": 20.006, + "args": { + "External id": 765362,"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": 688924808690.715, "dur": 16.677, + "args": { + "External id": 765363,"Record function id": 0, "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183436, "tid": 31338, + "ts": 688924808695.349, "dur": 10.756, + "args": { + "External id": 765364,"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": 688924808699.125, "dur": 5.560, + "args": { + "External id": 765365,"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": 688924808700.344, "dur": 4.088, + "args": { + "External id": 765366,"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": 688924808731.896, "dur": 6807.133, + "args": { + "External id": 765367,"Record function id": 0, "Ev Idx": 4534 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 4183436, "tid": 31338, + "ts": 688924808750.141, "dur": 34.176, + "args": { + "External id": 765368,"Record function id": 0, "Ev Idx": 4535 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 4183436, "tid": 31338, + "ts": 688924808806.538, "dur": 269.623, + "args": { + "External id": 765369,"Record function id": 0, "Ev Idx": 4536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 4183436, "tid": 31338, + "ts": 688924809082.475, "dur": 6252.646, + "args": { + "External id": 765370,"Record function id": 0, "Ev Idx": 4537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 31338, + "ts": 688924809200.632, "dur": 7.465, + "args": { + "External id": 765371,"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": 688924809218.522, "dur": 4.955, + "args": { + "External id": 765372,"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": 688924809242.361, "dur": 4832.815, + "args": { + "External id": 765373,"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": 688924809261.594, "dur": 4802.447, + "args": { + "External id": 765374,"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": 688924809387.905, "dur": 12.499, + "args": { + "External id": 765375,"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": 688924809425.784, "dur": 4596.643, + "args": { + "External id": 765376,"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": 688924809428.252, "dur": 4593.550, + "args": { + "External id": 765377,"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": 688924809433.629, "dur": 6.339, + "args": { + "External id": 765378,"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": 688924809441.423, "dur": 4576.514, + "args": { + "External id": 765379,"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": 688924814200.043, "dur": 9.701, + "args": { + "External id": 765380,"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": 688924814203.177, "dur": 6.252, + "args": { + "External id": 765381,"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": 688924814237.044, "dur": 391.399, + "args": { + "External id": 765382,"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": 688924814273.671, "dur": 350.325, + "args": { + "External id": 765383,"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": 688924814286.432, "dur": 331.901, + "args": { + "External id": 765384,"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": 688924814650.216, "dur": 48.300, + "args": { + "External id": 765385,"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": 688924814763.104, "dur": 6.739, + "args": { + "External id": 765386,"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": 688924814830.649, "dur": 2.194, + "args": { + "External id": 765387,"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": 688924814849.585, "dur": 1.238, + "args": { + "External id": 765388,"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": 688924814864.275, "dur": 1.302, + "args": { + "External id": 765389,"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": 688924814876.865, "dur": 1.181, + "args": { + "External id": 765390,"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": 688924814887.551, "dur": 0.950, + "args": { + "External id": 765391,"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": 688924814899.298, "dur": 1.453, + "args": { + "External id": 765392,"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": 688924814911.874, "dur": 1.062, + "args": { + "External id": 765393,"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": 688924814923.501, "dur": 1.358, + "args": { + "External id": 765394,"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": 688924814934.724, "dur": 1.441, + "args": { + "External id": 765395,"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": 688924814947.941, "dur": 1.313, + "args": { + "External id": 765396,"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": 688924814958.568, "dur": 1.180, + "args": { + "External id": 765397,"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": 688924814970.154, "dur": 1.399, + "args": { + "External id": 765398,"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": 688924814982.052, "dur": 1.300, + "args": { + "External id": 765399,"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": 688924814993.073, "dur": 1.391, + "args": { + "External id": 765400,"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": 688924815003.333, "dur": 1.668, + "args": { + "External id": 765401,"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": 688924815014.719, "dur": 1.223, + "args": { + "External id": 765402,"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": 688924815025.546, "dur": 1.354, + "args": { + "External id": 765403,"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": 688924815036.988, "dur": 1.475, + "args": { + "External id": 765404,"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": 688924815048.881, "dur": 1.240, + "args": { + "External id": 765405,"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": 688924815060.827, "dur": 1.283, + "args": { + "External id": 765406,"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": 688924815071.748, "dur": 1.759, + "args": { + "External id": 765407,"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": 688924815084.941, "dur": 1.054, + "args": { + "External id": 765408,"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": 688924815096.059, "dur": 1.230, + "args": { + "External id": 765409,"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": 688924815108.087, "dur": 1.137, + "args": { + "External id": 765410,"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": 688924815119.419, "dur": 1.252, + "args": { + "External id": 765411,"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": 688924815130.555, "dur": 1.218, + "args": { + "External id": 765412,"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": 688924815141.383, "dur": 1.450, + "args": { + "External id": 765413,"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": 688924815152.498, "dur": 0.948, + "args": { + "External id": 765414,"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": 688924815164.097, "dur": 1.568, + "args": { + "External id": 765415,"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": 688924815176.139, "dur": 1.212, + "args": { + "External id": 765416,"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": 688924815187.923, "dur": 1.436, + "args": { + "External id": 765417,"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": 688924815199.298, "dur": 1.432, + "args": { + "External id": 765418,"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": 688924815211.229, "dur": 1.295, + "args": { + "External id": 765419,"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": 688924815223.201, "dur": 1.293, + "args": { + "External id": 765420,"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": 688924815234.509, "dur": 1.237, + "args": { + "External id": 765421,"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": 688924815245.751, "dur": 1.216, + "args": { + "External id": 765422,"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": 688924815256.356, "dur": 1.023, + "args": { + "External id": 765423,"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": 688924815267.076, "dur": 1.101, + "args": { + "External id": 765424,"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#39935", "pid": 4183436, "tid": 4183436, + "ts": 688924052600.915, "dur": 777750.978, + "args": { + "External id": 756737,"Record function id": 0, "Ev Idx": 4592 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 4183436, "tid": 4183436, + "ts": 688924052639.174, "dur": 594.691, + "args": { + "External id": 756738,"Record function id": 0, "Ev Idx": 4593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 4183436, "tid": 4183436, + "ts": 688924053277.084, "dur": 2110.293, + "args": { + "External id": 756739,"Record function id": 0, "Ev Idx": 4594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924054287.550, "dur": 8.459, + "args": { + "External id": 756740,"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": 688924054318.949, "dur": 6.586, + "args": { + "External id": 756741,"Sequence number": 8961960, "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": 688924054830.003, "dur": 2.272, + "args": { + "External id": 756742,"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": 688924054843.488, "dur": 2.457, + "args": { + "External id": 756743,"Sequence number": 8961960, "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": 688924055209.527, "dur": 1.755, + "args": { + "External id": 756744,"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": 688924055215.883, "dur": 2.071, + "args": { + "External id": 756745,"Sequence number": 8961960, "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": 688924056057.098, "dur": 16.899, + "args": { + "External id": 756746,"Sequence number": 8961960, "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": 688924056067.958, "dur": 2.370, + "args": { + "External id": 756747,"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": 688924056075.994, "dur": 4.395, + "args": { + "External id": 756748,"Sequence number": 8961960, "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": 688924056078.507, "dur": 0.823, + "args": { + "External id": 756749,"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": 688924056105.277, "dur": 505.444, + "args": { + "External id": 756750,"Sequence number": 8961960, "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": 688924056113.235, "dur": 496.744, + "args": { + "External id": 756751,"Sequence number": 8961960, "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": 688924056124.991, "dur": 10.568, + "args": { + "External id": 756752,"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": 688924056137.636, "dur": 471.232, + "args": { + "External id": 756753,"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": 688924056147.738, "dur": 0.654, + "args": { + "External id": 756754,"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": 688924056151.433, "dur": 7.163, + "args": { + "External id": 756755,"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": 688924056154.402, "dur": 3.824, + "args": { + "External id": 756756,"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": 688924056157.421, "dur": 0.523, + "args": { + "External id": 756757,"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": 688924056160.945, "dur": 191.415, + "args": { + "External id": 756758,"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": 688924056165.789, "dur": 186.316, + "args": { + "External id": 756759,"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": 688924056168.211, "dur": 18.322, + "args": { + "External id": 756760,"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": 688924056170.639, "dur": 15.304, + "args": { + "External id": 756761,"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": 688924056187.410, "dur": 164.066, + "args": { + "External id": 756762,"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": 688924056354.535, "dur": 251.374, + "args": { + "External id": 756763,"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": 688924056624.061, "dur": 587.494, + "args": { + "External id": 756764,"Sequence number": 8961960, "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": 688924056626.475, "dur": 583.840, + "args": { + "External id": 756765,"Sequence number": 8961960, "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": 688924056635.691, "dur": 6.202, + "args": { + "External id": 756766,"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": 688924056643.011, "dur": 561.974, + "args": { + "External id": 756767,"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": 688924057246.086, "dur": 56.237, + "args": { + "External id": 756768,"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": 688924057251.951, "dur": 6.693, + "args": { + "External id": 756769,"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": 688924057261.940, "dur": 40.014, + "args": { + "External id": 756770,"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": 688924057266.738, "dur": 6.703, + "args": { + "External id": 756771,"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": 688924057313.318, "dur": 77.998, + "args": { + "External id": 756772,"Sequence number": 8961960, "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": 688924057321.205, "dur": 8.070, + "args": { + "External id": 756773,"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": 688924057326.883, "dur": 2.004, + "args": { + "External id": 756774,"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": 688924057330.360, "dur": 4.472, + "args": { + "External id": 756775,"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": 688924057337.569, "dur": 4.601, + "args": { + "External id": 756776,"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": 688924057345.120, "dur": 8.441, + "args": { + "External id": 756777,"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": 688924057352.901, "dur": 0.451, + "args": { + "External id": 756778,"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": 688924057354.492, "dur": 5.590, + "args": { + "External id": 756779,"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": 688924057358.744, "dur": 1.227, + "args": { + "External id": 756780,"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": 688924057362.153, "dur": 3.472, + "args": { + "External id": 756781,"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": 688924057363.311, "dur": 2.189, + "args": { + "External id": 756782,"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": 688924057364.718, "dur": 0.682, + "args": { + "External id": 756783,"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": 688924057366.695, "dur": 23.841, + "args": { + "External id": 756784,"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": 688924057399.923, "dur": 29.301, + "args": { + "External id": 756785,"Sequence number": 8961960, "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": 688924057401.564, "dur": 27.496, + "args": { + "External id": 756786,"Sequence number": 8961960, "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": 688924057407.255, "dur": 3.566, + "args": { + "External id": 756787,"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": 688924057411.665, "dur": 16.982, + "args": { + "External id": 756788,"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": 688924057548.986, "dur": 199.862, + "args": { + "External id": 756789,"Record function id": 0, "Ev Idx": 4644 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 4183436, "tid": 4183436, + "ts": 688924057633.862, "dur": 103.478, + "args": { + "External id": 756790,"Record function id": 0, "Ev Idx": 4645 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924057757.164, "dur": 62.237, + "args": { + "External id": 756791,"Record function id": 0, "Ev Idx": 4646 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 4183436, "tid": 4183436, + "ts": 688924057829.914, "dur": 7317.737, + "args": { + "External id": 756792,"Record function id": 0, "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 4183436, "tid": 4183436, + "ts": 688924057840.036, "dur": 1330.095, + "args": { + "External id": 756793,"Record function id": 0, "Ev Idx": 4648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924057971.466, "dur": 8.153, + "args": { + "External id": 756794,"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": 688924057999.092, "dur": 146.153, + "args": { + "External id": 756795,"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": 688924058004.415, "dur": 1.764, + "args": { + "External id": 756796,"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": 688924058013.028, "dur": 0.629, + "args": { + "External id": 756797,"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": 688924058014.501, "dur": 0.536, + "args": { + "External id": 756798,"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": 688924058015.883, "dur": 2.876, + "args": { + "External id": 756799,"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": 688924058023.954, "dur": 0.612, + "args": { + "External id": 756800,"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": 688924058025.429, "dur": 0.557, + "args": { + "External id": 756801,"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": 688924058026.532, "dur": 2.826, + "args": { + "External id": 756802,"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": 688924058032.811, "dur": 0.892, + "args": { + "External id": 756803,"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": 688924058034.284, "dur": 1.020, + "args": { + "External id": 756804,"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": 688924058040.445, "dur": 0.389, + "args": { + "External id": 756805,"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": 688924058041.818, "dur": 0.251, + "args": { + "External id": 756806,"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": 688924058043.097, "dur": 2.334, + "args": { + "External id": 756807,"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": 688924058048.899, "dur": 0.642, + "args": { + "External id": 756808,"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": 688924058050.501, "dur": 0.687, + "args": { + "External id": 756809,"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": 688924058051.855, "dur": 2.417, + "args": { + "External id": 756810,"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": 688924058056.994, "dur": 0.548, + "args": { + "External id": 756811,"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": 688924058058.417, "dur": 0.554, + "args": { + "External id": 756812,"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": 688924058064.670, "dur": 0.316, + "args": { + "External id": 756813,"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": 688924058065.450, "dur": 0.587, + "args": { + "External id": 756814,"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": 688924058066.907, "dur": 2.507, + "args": { + "External id": 756815,"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": 688924058072.688, "dur": 0.449, + "args": { + "External id": 756816,"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": 688924058074.484, "dur": 0.801, + "args": { + "External id": 756817,"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": 688924058075.732, "dur": 2.458, + "args": { + "External id": 756818,"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": 688924058082.119, "dur": 0.403, + "args": { + "External id": 756819,"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": 688924058083.320, "dur": 0.511, + "args": { + "External id": 756820,"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": 688924058089.193, "dur": 0.547, + "args": { + "External id": 756821,"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": 688924058090.394, "dur": 0.504, + "args": { + "External id": 756822,"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": 688924058091.824, "dur": 2.345, + "args": { + "External id": 756823,"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": 688924058097.802, "dur": 0.410, + "args": { + "External id": 756824,"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": 688924058099.252, "dur": 0.666, + "args": { + "External id": 756825,"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": 688924058100.574, "dur": 1.949, + "args": { + "External id": 756826,"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": 688924058105.295, "dur": 0.276, + "args": { + "External id": 756827,"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": 688924058106.295, "dur": 0.350, + "args": { + "External id": 756828,"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": 688924058111.897, "dur": 0.582, + "args": { + "External id": 756829,"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": 688924058113.215, "dur": 0.359, + "args": { + "External id": 756830,"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": 688924058114.391, "dur": 2.652, + "args": { + "External id": 756831,"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": 688924058120.503, "dur": 0.584, + "args": { + "External id": 756832,"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": 688924058122.074, "dur": 0.196, + "args": { + "External id": 756833,"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": 688924058122.944, "dur": 2.749, + "args": { + "External id": 756834,"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": 688924058173.156, "dur": 55.186, + "args": { + "External id": 756835,"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": 688924058301.832, "dur": 256.773, + "args": { + "External id": 756836,"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": 688924058318.556, "dur": 4.807, + "args": { + "External id": 756837,"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": 688924058330.688, "dur": 14.066, + "args": { + "External id": 756838,"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": 688924058335.431, "dur": 8.898, + "args": { + "External id": 756839,"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": 688924058340.925, "dur": 0.660, + "args": { + "External id": 756840,"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": 688924058353.052, "dur": 128.760, + "args": { + "External id": 756841,"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": 688924058354.874, "dur": 0.875, + "args": { + "External id": 756842,"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": 688924058357.295, "dur": 1.040, + "args": { + "External id": 756843,"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": 688924058361.705, "dur": 2.211, + "args": { + "External id": 756844,"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": 688924058364.785, "dur": 0.802, + "args": { + "External id": 756845,"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": 688924058368.349, "dur": 0.497, + "args": { + "External id": 756846,"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": 688924058369.938, "dur": 0.632, + "args": { + "External id": 756847,"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": 688924058371.631, "dur": 0.806, + "args": { + "External id": 756848,"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": 688924058375.784, "dur": 0.751, + "args": { + "External id": 756849,"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": 688924058377.344, "dur": 1.132, + "args": { + "External id": 756850,"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": 688924058379.236, "dur": 0.853, + "args": { + "External id": 756851,"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": 688924058382.782, "dur": 2.502, + "args": { + "External id": 756852,"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": 688924058386.563, "dur": 0.341, + "args": { + "External id": 756853,"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": 688924058389.598, "dur": 2.588, + "args": { + "External id": 756854,"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": 688924058393.380, "dur": 0.383, + "args": { + "External id": 756855,"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": 688924058394.524, "dur": 0.673, + "args": { + "External id": 756856,"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": 688924058399.044, "dur": 0.552, + "args": { + "External id": 756857,"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": 688924058400.099, "dur": 0.970, + "args": { + "External id": 756858,"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": 688924058401.835, "dur": 0.583, + "args": { + "External id": 756859,"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": 688924058407.954, "dur": 2.240, + "args": { + "External id": 756860,"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": 688924058410.847, "dur": 0.367, + "args": { + "External id": 756861,"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": 688924058414.242, "dur": 2.391, + "args": { + "External id": 756862,"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": 688924058417.342, "dur": 0.471, + "args": { + "External id": 756863,"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": 688924058418.441, "dur": 0.321, + "args": { + "External id": 756864,"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": 688924058423.065, "dur": 0.339, + "args": { + "External id": 756865,"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": 688924058424.087, "dur": 0.569, + "args": { + "External id": 756866,"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": 688924058425.314, "dur": 0.499, + "args": { + "External id": 756867,"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": 688924058430.575, "dur": 1.900, + "args": { + "External id": 756868,"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": 688924058433.354, "dur": 0.361, + "args": { + "External id": 756869,"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": 688924058437.341, "dur": 3.057, + "args": { + "External id": 756870,"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": 688924058441.591, "dur": 0.373, + "args": { + "External id": 756871,"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": 688924058442.414, "dur": 0.505, + "args": { + "External id": 756872,"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": 688924058447.936, "dur": 0.834, + "args": { + "External id": 756873,"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": 688924058449.206, "dur": 0.543, + "args": { + "External id": 756874,"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": 688924058450.383, "dur": 0.295, + "args": { + "External id": 756875,"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": 688924058454.573, "dur": 2.182, + "args": { + "External id": 756876,"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": 688924058457.405, "dur": 1.005, + "args": { + "External id": 756877,"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": 688924058460.920, "dur": 3.169, + "args": { + "External id": 756878,"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": 688924058465.076, "dur": 0.326, + "args": { + "External id": 756879,"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": 688924058466.039, "dur": 0.540, + "args": { + "External id": 756880,"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": 688924058506.472, "dur": 35.001, + "args": { + "External id": 756881,"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": 688924058615.316, "dur": 428.470, + "args": { + "External id": 756882,"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": 688924058652.504, "dur": 385.355, + "args": { + "External id": 756883,"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": 688924058704.204, "dur": 327.617, + "args": { + "External id": 756884,"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": 688924059075.936, "dur": 2.536, + "args": { + "External id": 756885,"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": 688924059187.562, "dur": 5744.517, + "args": { + "External id": 756886,"Record function id": 0, "Ev Idx": 4741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924059420.153, "dur": 7.420, + "args": { + "External id": 756887,"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": 688924059431.335, "dur": 1.338, + "args": { + "External id": 756888,"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": 688924059434.393, "dur": 1.270, + "args": { + "External id": 756889,"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": 688924059437.702, "dur": 2.805, + "args": { + "External id": 756890,"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": 688924059442.365, "dur": 1.159, + "args": { + "External id": 756891,"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": 688924059445.168, "dur": 1.638, + "args": { + "External id": 756892,"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": 688924059450.586, "dur": 1.203, + "args": { + "External id": 756893,"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": 688924059453.111, "dur": 2.033, + "args": { + "External id": 756894,"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": 688924059459.293, "dur": 1.459, + "args": { + "External id": 756895,"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": 688924059462.322, "dur": 1.164, + "args": { + "External id": 756896,"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": 688924059467.055, "dur": 1.026, + "args": { + "External id": 756897,"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": 688924059469.343, "dur": 2.035, + "args": { + "External id": 756898,"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": 688924059472.602, "dur": 1.004, + "args": { + "External id": 756899,"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": 688924059474.957, "dur": 1.433, + "args": { + "External id": 756900,"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": 688924059479.703, "dur": 0.967, + "args": { + "External id": 756901,"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": 688924059482.078, "dur": 2.009, + "args": { + "External id": 756902,"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": 688924059488.107, "dur": 0.641, + "args": { + "External id": 756903,"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": 688924059490.214, "dur": 0.858, + "args": { + "External id": 756904,"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": 688924059494.742, "dur": 0.940, + "args": { + "External id": 756905,"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": 688924059497.086, "dur": 2.628, + "args": { + "External id": 756906,"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": 688924059501.522, "dur": 0.962, + "args": { + "External id": 756907,"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": 688924059503.662, "dur": 0.711, + "args": { + "External id": 756908,"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": 688924059508.421, "dur": 0.641, + "args": { + "External id": 756909,"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": 688924059510.248, "dur": 2.307, + "args": { + "External id": 756910,"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": 688924059533.174, "dur": 0.975, + "args": { + "External id": 756911,"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": 688924059535.634, "dur": 0.924, + "args": { + "External id": 756912,"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": 688924059541.390, "dur": 0.736, + "args": { + "External id": 756913,"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": 688924059543.646, "dur": 2.693, + "args": { + "External id": 756914,"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": 688924059548.319, "dur": 0.699, + "args": { + "External id": 756915,"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": 688924059550.373, "dur": 0.899, + "args": { + "External id": 756916,"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": 688924059556.518, "dur": 0.578, + "args": { + "External id": 756917,"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": 688924059558.328, "dur": 2.896, + "args": { + "External id": 756918,"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": 688924059565.511, "dur": 0.787, + "args": { + "External id": 756919,"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": 688924059567.504, "dur": 1.151, + "args": { + "External id": 756920,"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": 688924059572.381, "dur": 1.395, + "args": { + "External id": 756921,"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": 688924059575.122, "dur": 2.249, + "args": { + "External id": 756922,"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": 688924059578.944, "dur": 1.073, + "args": { + "External id": 756923,"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": 688924059581.152, "dur": 0.779, + "args": { + "External id": 756924,"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": 688924059586.114, "dur": 0.675, + "args": { + "External id": 756925,"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": 688924059588.038, "dur": 2.643, + "args": { + "External id": 756926,"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": 688924059621.796, "dur": 5252.448, + "args": { + "External id": 756927,"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": 688924059646.635, "dur": 5216.901, + "args": { + "External id": 756928,"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": 688924059705.460, "dur": 6.444, + "args": { + "External id": 756929,"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": 688924059717.684, "dur": 5104.236, + "args": { + "External id": 756930,"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": 688924059722.635, "dur": 5098.706, + "args": { + "External id": 756931,"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": 688924059730.780, "dur": 7.260, + "args": { + "External id": 756932,"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": 688924059740.296, "dur": 5077.890, + "args": { + "External id": 756933,"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": 688924065233.387, "dur": 39.479, + "args": { + "External id": 756934,"Record function id": 0, "Ev Idx": 4789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 4183436, "tid": 4183436, + "ts": 688924065275.081, "dur": 219.635, + "args": { + "External id": 756935,"Record function id": 0, "Ev Idx": 4790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924065321.620, "dur": 164.700, + "args": { + "External id": 756936,"Sequence number": 8961960, "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": 688924065321.620, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 4183436, "tid": 4183436, + "ts": 688924065400.268, "dur": 48.763, + "args": { + "External id": 756937,"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": 688924065557.929, "dur": 56.104, + "args": { + "External id": 756938,"Record function id": 0, "Ev Idx": 4793 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 4183436, "tid": 4183436, + "ts": 688924065624.821, "dur": 7142.656, + "args": { + "External id": 756939,"Record function id": 0, "Ev Idx": 4794 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 4183436, "tid": 4183436, + "ts": 688924065634.067, "dur": 873.587, + "args": { + "External id": 756940,"Record function id": 0, "Ev Idx": 4795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924065758.659, "dur": 11.932, + "args": { + "External id": 756941,"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": 688924065784.977, "dur": 64.905, + "args": { + "External id": 756942,"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": 688924065810.990, "dur": 2.631, + "args": { + "External id": 756943,"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": 688924065815.728, "dur": 0.507, + "args": { + "External id": 756944,"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": 688924065817.560, "dur": 2.960, + "args": { + "External id": 756945,"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": 688924065824.256, "dur": 0.273, + "args": { + "External id": 756946,"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": 688924065825.453, "dur": 0.431, + "args": { + "External id": 756947,"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": 688924065828.875, "dur": 0.642, + "args": { + "External id": 756948,"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": 688924065832.739, "dur": 0.325, + "args": { + "External id": 756949,"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": 688924065833.639, "dur": 2.509, + "args": { + "External id": 756950,"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": 688924065841.844, "dur": 0.371, + "args": { + "External id": 756951,"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": 688924065861.766, "dur": 40.407, + "args": { + "External id": 756952,"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": 688924065938.003, "dur": 119.946, + "args": { + "External id": 756953,"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": 688924065949.506, "dur": 6.889, + "args": { + "External id": 756954,"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": 688924065961.865, "dur": 12.294, + "args": { + "External id": 756955,"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": 688924065966.464, "dur": 7.313, + "args": { + "External id": 756956,"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": 688924065971.637, "dur": 0.934, + "args": { + "External id": 756957,"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": 688924065980.738, "dur": 32.184, + "args": { + "External id": 756958,"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": 688924065982.405, "dur": 0.627, + "args": { + "External id": 756959,"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": 688924065986.968, "dur": 0.553, + "args": { + "External id": 756960,"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": 688924065990.632, "dur": 0.400, + "args": { + "External id": 756961,"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": 688924065991.788, "dur": 0.342, + "args": { + "External id": 756962,"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": 688924065995.389, "dur": 3.136, + "args": { + "External id": 756963,"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": 688924065999.297, "dur": 0.464, + "args": { + "External id": 756964,"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": 688924066002.833, "dur": 0.300, + "args": { + "External id": 756965,"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": 688924066006.409, "dur": 0.367, + "args": { + "External id": 756966,"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": 688924066007.680, "dur": 0.376, + "args": { + "External id": 756967,"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": 688924066026.369, "dur": 22.343, + "args": { + "External id": 756968,"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": 688924066113.728, "dur": 305.978, + "args": { + "External id": 756969,"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": 688924066145.429, "dur": 270.055, + "args": { + "External id": 756970,"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": 688924066155.421, "dur": 254.327, + "args": { + "External id": 756971,"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": 688924066443.899, "dur": 2.282, + "args": { + "External id": 756972,"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": 688924066527.983, "dur": 5991.232, + "args": { + "External id": 756973,"Record function id": 0, "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924066633.911, "dur": 5.858, + "args": { + "External id": 756974,"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": 688924066643.179, "dur": 1.498, + "args": { + "External id": 756975,"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": 688924066646.373, "dur": 1.202, + "args": { + "External id": 756976,"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": 688924066651.274, "dur": 44.926, + "args": { + "External id": 756977,"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": 688924066700.497, "dur": 1.331, + "args": { + "External id": 756978,"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": 688924066703.383, "dur": 1.240, + "args": { + "External id": 756979,"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": 688924066706.315, "dur": 1.195, + "args": { + "External id": 756980,"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": 688924066711.823, "dur": 2.256, + "args": { + "External id": 756981,"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": 688924066718.123, "dur": 1.230, + "args": { + "External id": 756982,"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": 688924066720.695, "dur": 1.536, + "args": { + "External id": 756983,"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": 688924066740.348, "dur": 5739.928, + "args": { + "External id": 756984,"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": 688924066758.937, "dur": 5714.417, + "args": { + "External id": 756985,"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": 688924066784.384, "dur": 28.542, + "args": { + "External id": 756986,"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": 688924066817.066, "dur": 5624.794, + "args": { + "External id": 756987,"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": 688924066819.826, "dur": 5621.470, + "args": { + "External id": 756988,"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": 688924066826.329, "dur": 7.571, + "args": { + "External id": 756989,"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": 688924066835.709, "dur": 5602.473, + "args": { + "External id": 756990,"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": 688924072705.447, "dur": 34.301, + "args": { + "External id": 756991,"Sequence number": 8961961, "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": 688924072705.447, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924072723.971, "dur": 10.756, + "args": { + "External id": 756992,"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": 688924072729.732, "dur": 4.582, + "args": { + "External id": 756993,"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": 688924072826.347, "dur": 102.611, + "args": { + "External id": 756994,"Record function id": 0, "Ev Idx": 4849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924072931.118, "dur": 1179.230, + "args": { + "External id": 756995,"Record function id": 0, "Ev Idx": 4850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924072976.575, "dur": 1118.101, + "args": { + "External id": 756996,"Sequence number": 8961962, "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": 688924072976.575, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924073050.862, "dur": 45.815, + "args": { + "External id": 756997,"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": 688924073110.539, "dur": 99.348, + "args": { + "External id": 756998,"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": 688924073221.102, "dur": 36.293, + "args": { + "External id": 756999,"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": 688924073269.598, "dur": 29.565, + "args": { + "External id": 757000,"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": 688924073323.064, "dur": 26.686, + "args": { + "External id": 757001,"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": 688924073373.094, "dur": 15.219, + "args": { + "External id": 757002,"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": 688924073410.072, "dur": 137.803, + "args": { + "External id": 757003,"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": 688924073467.315, "dur": 11.981, + "args": { + "External id": 757004,"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": 688924073472.178, "dur": 6.417, + "args": { + "External id": 757005,"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": 688924073482.168, "dur": 3.642, + "args": { + "External id": 757006,"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": 688924073489.721, "dur": 1.159, + "args": { + "External id": 757007,"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": 688924073493.150, "dur": 2.968, + "args": { + "External id": 757008,"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": 688924073559.370, "dur": 43.536, + "args": { + "External id": 757009,"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": 688924073641.747, "dur": 85.640, + "args": { + "External id": 757010,"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": 688924073738.881, "dur": 43.297, + "args": { + "External id": 757011,"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": 688924073817.553, "dur": 48.902, + "args": { + "External id": 757012,"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": 688924073891.843, "dur": 27.232, + "args": { + "External id": 757013,"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": 688924073925.541, "dur": 36.908, + "args": { + "External id": 757014,"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": 688924073990.642, "dur": 20.346, + "args": { + "External id": 757015,"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": 688924074178.975, "dur": 84.970, + "args": { + "External id": 757016,"Record function id": 0, "Ev Idx": 4871 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924074340.360, "dur": 48.629, + "args": { + "External id": 757017,"Record function id": 0, "Ev Idx": 4872 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 4183436, "tid": 4183436, + "ts": 688924074398.394, "dur": 10334.605, + "args": { + "External id": 757018,"Record function id": 0, "Ev Idx": 4873 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 4183436, "tid": 4183436, + "ts": 688924074409.229, "dur": 1029.365, + "args": { + "External id": 757019,"Record function id": 0, "Ev Idx": 4874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924074494.816, "dur": 7.966, + "args": { + "External id": 757020,"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": 688924074517.051, "dur": 47.088, + "args": { + "External id": 757021,"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": 688924074524.054, "dur": 3.920, + "args": { + "External id": 757022,"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": 688924074530.059, "dur": 0.803, + "args": { + "External id": 757023,"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": 688924074531.595, "dur": 0.573, + "args": { + "External id": 757024,"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": 688924074538.041, "dur": 1.011, + "args": { + "External id": 757025,"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": 688924074539.780, "dur": 2.793, + "args": { + "External id": 757026,"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": 688924074546.119, "dur": 0.580, + "args": { + "External id": 757027,"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": 688924074550.180, "dur": 0.782, + "args": { + "External id": 757028,"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": 688924074552.130, "dur": 0.254, + "args": { + "External id": 757029,"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": 688924074555.304, "dur": 2.534, + "args": { + "External id": 757030,"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": 688924074575.597, "dur": 41.198, + "args": { + "External id": 757031,"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": 688924074722.306, "dur": 182.627, + "args": { + "External id": 757032,"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": 688924074736.462, "dur": 6.875, + "args": { + "External id": 757033,"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": 688924074749.580, "dur": 14.273, + "args": { + "External id": 757034,"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": 688924074754.127, "dur": 9.326, + "args": { + "External id": 757035,"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": 688924074760.682, "dur": 1.031, + "args": { + "External id": 757036,"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": 688924074771.039, "dur": 74.118, + "args": { + "External id": 757037,"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": 688924074772.919, "dur": 0.650, + "args": { + "External id": 757038,"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": 688924074777.770, "dur": 2.347, + "args": { + "External id": 757039,"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": 688924074780.793, "dur": 2.467, + "args": { + "External id": 757040,"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": 688924074824.611, "dur": 0.637, + "args": { + "External id": 757041,"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": 688924074826.643, "dur": 0.706, + "args": { + "External id": 757042,"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": 688924074830.760, "dur": 0.654, + "args": { + "External id": 757043,"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": 688924074835.063, "dur": 0.570, + "args": { + "External id": 757044,"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": 688924074836.315, "dur": 0.540, + "args": { + "External id": 757045,"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": 688924074839.713, "dur": 0.351, + "args": { + "External id": 757046,"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": 688924074862.924, "dur": 31.145, + "args": { + "External id": 757047,"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": 688924074964.702, "dur": 380.461, + "args": { + "External id": 757048,"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": 688924074999.494, "dur": 341.086, + "args": { + "External id": 757049,"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": 688924075012.455, "dur": 323.065, + "args": { + "External id": 757050,"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": 688924075368.126, "dur": 2.389, + "args": { + "External id": 757051,"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": 688924075460.147, "dur": 9010.006, + "args": { + "External id": 757052,"Record function id": 0, "Ev Idx": 4907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924075560.428, "dur": 5.393, + "args": { + "External id": 757053,"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": 688924075569.295, "dur": 1.788, + "args": { + "External id": 757054,"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": 688924075573.282, "dur": 2.191, + "args": { + "External id": 757055,"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": 688924075577.417, "dur": 1.360, + "args": { + "External id": 757056,"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": 688924075580.824, "dur": 1.621, + "args": { + "External id": 757057,"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": 688924075586.253, "dur": 1.461, + "args": { + "External id": 757058,"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": 688924075589.357, "dur": 1.964, + "args": { + "External id": 757059,"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": 688924075595.099, "dur": 5.378, + "args": { + "External id": 757060,"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": 688924075602.142, "dur": 1.218, + "args": { + "External id": 757061,"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": 688924075606.910, "dur": 0.719, + "args": { + "External id": 757062,"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": 688924075624.924, "dur": 8801.770, + "args": { + "External id": 757063,"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": 688924075642.441, "dur": 8776.440, + "args": { + "External id": 757064,"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": 688924075722.026, "dur": 15.021, + "args": { + "External id": 757065,"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": 688924075740.384, "dur": 8642.492, + "args": { + "External id": 757066,"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": 688924075743.332, "dur": 8638.971, + "args": { + "External id": 757067,"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": 688924075749.383, "dur": 6.402, + "args": { + "External id": 757068,"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": 688924075757.614, "dur": 8621.350, + "args": { + "External id": 757069,"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": 688924084618.581, "dur": 81.248, + "args": { + "External id": 757070,"Sequence number": 8961963, "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": 688924084618.581, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924084635.477, "dur": 11.219, + "args": { + "External id": 757071,"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": 688924084641.447, "dur": 5.002, + "args": { + "External id": 757072,"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": 688924084778.815, "dur": 125.412, + "args": { + "External id": 757073,"Record function id": 0, "Ev Idx": 4928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924084907.123, "dur": 1160.423, + "args": { + "External id": 757074,"Record function id": 0, "Ev Idx": 4929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924084954.246, "dur": 1098.330, + "args": { + "External id": 757075,"Sequence number": 8961964, "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": 688924084954.246, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924085038.474, "dur": 45.905, + "args": { + "External id": 757076,"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": 688924085101.199, "dur": 97.106, + "args": { + "External id": 757077,"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": 688924085206.627, "dur": 34.173, + "args": { + "External id": 757078,"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": 688924085247.336, "dur": 29.306, + "args": { + "External id": 757079,"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": 688924085309.565, "dur": 34.396, + "args": { + "External id": 757080,"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": 688924085360.675, "dur": 18.218, + "args": { + "External id": 757081,"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": 688924085394.985, "dur": 138.123, + "args": { + "External id": 757082,"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": 688924085446.872, "dur": 16.507, + "args": { + "External id": 757083,"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": 688924085452.020, "dur": 10.389, + "args": { + "External id": 757084,"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": 688924085467.994, "dur": 4.602, + "args": { + "External id": 757085,"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": 688924085473.591, "dur": 3.262, + "args": { + "External id": 757086,"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": 688924085479.363, "dur": 2.586, + "args": { + "External id": 757087,"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": 688924085544.260, "dur": 42.790, + "args": { + "External id": 757088,"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": 688924085617.849, "dur": 30.021, + "args": { + "External id": 757089,"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": 688924085710.322, "dur": 44.526, + "args": { + "External id": 757090,"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": 688924085763.693, "dur": 61.942, + "args": { + "External id": 757091,"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": 688924085855.422, "dur": 30.162, + "args": { + "External id": 757092,"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": 688924085892.363, "dur": 47.057, + "args": { + "External id": 757093,"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": 688924085958.210, "dur": 22.943, + "args": { + "External id": 757094,"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": 688924086136.175, "dur": 81.400, + "args": { + "External id": 757095,"Record function id": 0, "Ev Idx": 4950 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924086292.810, "dur": 48.783, + "args": { + "External id": 757096,"Record function id": 0, "Ev Idx": 4951 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 4183436, "tid": 4183436, + "ts": 688924086351.370, "dur": 8972.743, + "args": { + "External id": 757097,"Record function id": 0, "Ev Idx": 4952 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 4183436, "tid": 4183436, + "ts": 688924086363.719, "dur": 1031.722, + "args": { + "External id": 757098,"Record function id": 0, "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924086447.892, "dur": 8.769, + "args": { + "External id": 757099,"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": 688924086469.387, "dur": 46.897, + "args": { + "External id": 757100,"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": 688924086477.885, "dur": 2.201, + "args": { + "External id": 757101,"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": 688924086484.351, "dur": 0.481, + "args": { + "External id": 757102,"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": 688924086488.084, "dur": 0.870, + "args": { + "External id": 757103,"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": 688924086489.849, "dur": 0.555, + "args": { + "External id": 757104,"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": 688924086494.003, "dur": 0.745, + "args": { + "External id": 757105,"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": 688924086497.861, "dur": 0.909, + "args": { + "External id": 757106,"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": 688924086499.789, "dur": 3.772, + "args": { + "External id": 757107,"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": 688924086504.224, "dur": 0.694, + "args": { + "External id": 757108,"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": 688924086508.628, "dur": 0.319, + "args": { + "External id": 757109,"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": 688924086527.198, "dur": 41.637, + "args": { + "External id": 757110,"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": 688924086600.549, "dur": 185.102, + "args": { + "External id": 757111,"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": 688924086615.832, "dur": 3.776, + "args": { + "External id": 757112,"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": 688924086624.804, "dur": 10.559, + "args": { + "External id": 757113,"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": 688924086629.555, "dur": 5.418, + "args": { + "External id": 757114,"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": 688924086632.953, "dur": 0.781, + "args": { + "External id": 757115,"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": 688924086642.151, "dur": 93.625, + "args": { + "External id": 757116,"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": 688924086646.045, "dur": 2.621, + "args": { + "External id": 757117,"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": 688924086649.834, "dur": 0.214, + "args": { + "External id": 757118,"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": 688924086703.684, "dur": 0.702, + "args": { + "External id": 757119,"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": 688924086711.170, "dur": 1.843, + "args": { + "External id": 757120,"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": 688924086714.061, "dur": 0.497, + "args": { + "External id": 757121,"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": 688924086715.282, "dur": 0.913, + "args": { + "External id": 757122,"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": 688924086721.875, "dur": 0.589, + "args": { + "External id": 757123,"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": 688924086723.375, "dur": 0.386, + "args": { + "External id": 757124,"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": 688924086727.314, "dur": 2.838, + "args": { + "External id": 757125,"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": 688924086747.825, "dur": 28.853, + "args": { + "External id": 757126,"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": 688924086876.571, "dur": 419.678, + "args": { + "External id": 757127,"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": 688924086916.163, "dur": 374.987, + "args": { + "External id": 757128,"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": 688924086927.159, "dur": 354.685, + "args": { + "External id": 757129,"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": 688924087318.673, "dur": 2.829, + "args": { + "External id": 757130,"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": 688924087416.806, "dur": 7697.111, + "args": { + "External id": 757131,"Record function id": 0, "Ev Idx": 4986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924087523.350, "dur": 6.724, + "args": { + "External id": 757132,"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": 688924087533.498, "dur": 1.013, + "args": { + "External id": 757133,"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": 688924087536.134, "dur": 3.352, + "args": { + "External id": 757134,"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": 688924087541.647, "dur": 1.112, + "args": { + "External id": 757135,"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": 688924087544.257, "dur": 0.976, + "args": { + "External id": 757136,"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": 688924087548.450, "dur": 0.896, + "args": { + "External id": 757137,"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": 688924087553.289, "dur": 1.211, + "args": { + "External id": 757138,"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": 688924087556.267, "dur": 2.217, + "args": { + "External id": 757139,"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": 688924087559.736, "dur": 0.768, + "args": { + "External id": 757140,"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": 688924087564.312, "dur": 0.499, + "args": { + "External id": 757141,"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": 688924087582.500, "dur": 7486.966, + "args": { + "External id": 757142,"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": 688924087600.004, "dur": 7461.428, + "args": { + "External id": 757143,"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": 688924087615.810, "dur": 14.149, + "args": { + "External id": 757144,"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": 688924087632.854, "dur": 7389.836, + "args": { + "External id": 757145,"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": 688924087635.694, "dur": 7386.266, + "args": { + "External id": 757146,"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": 688924087641.634, "dur": 4.761, + "args": { + "External id": 757147,"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": 688924087648.199, "dur": 7370.512, + "args": { + "External id": 757148,"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": 688924095264.411, "dur": 34.083, + "args": { + "External id": 757149,"Sequence number": 8961965, "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": 688924095264.411, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924095282.402, "dur": 11.276, + "args": { + "External id": 757150,"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": 688924095288.639, "dur": 4.761, + "args": { + "External id": 757151,"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": 688924095367.039, "dur": 91.861, + "args": { + "External id": 757152,"Record function id": 0, "Ev Idx": 5007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924095460.716, "dur": 1107.574, + "args": { + "External id": 757153,"Record function id": 0, "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924095502.613, "dur": 1051.458, + "args": { + "External id": 757154,"Sequence number": 8961966, "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": 688924095502.613, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924095571.412, "dur": 43.270, + "args": { + "External id": 757155,"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": 688924095628.127, "dur": 133.700, + "args": { + "External id": 757156,"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": 688924095777.802, "dur": 58.366, + "args": { + "External id": 757157,"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": 688924095847.383, "dur": 31.607, + "args": { + "External id": 757158,"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": 688924095907.269, "dur": 30.795, + "args": { + "External id": 757159,"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": 688924095959.922, "dur": 15.566, + "args": { + "External id": 757160,"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": 688924095995.230, "dur": 136.691, + "args": { + "External id": 757161,"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": 688924096050.209, "dur": 13.438, + "args": { + "External id": 757162,"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": 688924096054.893, "dur": 8.037, + "args": { + "External id": 757163,"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": 688924096068.379, "dur": 4.097, + "args": { + "External id": 757164,"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": 688924096073.722, "dur": 0.909, + "args": { + "External id": 757165,"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": 688924096077.004, "dur": 4.110, + "args": { + "External id": 757166,"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": 688924096142.772, "dur": 46.071, + "args": { + "External id": 757167,"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": 688924096218.496, "dur": 27.382, + "args": { + "External id": 757168,"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": 688924096254.967, "dur": 38.417, + "args": { + "External id": 757169,"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": 688924096301.938, "dur": 32.315, + "args": { + "External id": 757170,"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": 688924096359.517, "dur": 26.817, + "args": { + "External id": 757171,"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": 688924096392.171, "dur": 45.579, + "args": { + "External id": 757172,"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": 688924096460.654, "dur": 19.882, + "args": { + "External id": 757173,"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": 688924096634.928, "dur": 125.050, + "args": { + "External id": 757174,"Record function id": 0, "Ev Idx": 5029 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924096860.152, "dur": 51.654, + "args": { + "External id": 757175,"Record function id": 0, "Ev Idx": 5030 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 4183436, "tid": 4183436, + "ts": 688924096922.895, "dur": 8541.187, + "args": { + "External id": 757176,"Record function id": 0, "Ev Idx": 5031 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 4183436, "tid": 4183436, + "ts": 688924096934.654, "dur": 1036.877, + "args": { + "External id": 757177,"Record function id": 0, "Ev Idx": 5032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924097021.087, "dur": 10.054, + "args": { + "External id": 757178,"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": 688924097044.473, "dur": 67.220, + "args": { + "External id": 757179,"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": 688924097052.311, "dur": 2.361, + "args": { + "External id": 757180,"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": 688924097058.949, "dur": 0.319, + "args": { + "External id": 757181,"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": 688924097062.690, "dur": 0.236, + "args": { + "External id": 757182,"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": 688924097085.412, "dur": 0.446, + "args": { + "External id": 757183,"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": 688924097089.369, "dur": 0.981, + "args": { + "External id": 757184,"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": 688924097093.750, "dur": 0.519, + "args": { + "External id": 757185,"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": 688924097094.984, "dur": 4.456, + "args": { + "External id": 757186,"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": 688924097100.362, "dur": 0.607, + "args": { + "External id": 757187,"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": 688924097104.133, "dur": 0.643, + "args": { + "External id": 757188,"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": 688924097123.922, "dur": 48.801, + "args": { + "External id": 757189,"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": 688924097207.865, "dur": 165.743, + "args": { + "External id": 757190,"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": 688924097224.594, "dur": 4.328, + "args": { + "External id": 757191,"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": 688924097234.386, "dur": 10.574, + "args": { + "External id": 757192,"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": 688924097239.473, "dur": 5.115, + "args": { + "External id": 757193,"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": 688924097242.696, "dur": 0.714, + "args": { + "External id": 757194,"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": 688924097252.276, "dur": 36.250, + "args": { + "External id": 757195,"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": 688924097256.877, "dur": 1.203, + "args": { + "External id": 757196,"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": 688924097259.257, "dur": 0.183, + "args": { + "External id": 757197,"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": 688924097260.172, "dur": 0.417, + "args": { + "External id": 757198,"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": 688924097266.033, "dur": 2.277, + "args": { + "External id": 757199,"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": 688924097269.107, "dur": 0.371, + "args": { + "External id": 757200,"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": 688924097270.512, "dur": 0.486, + "args": { + "External id": 757201,"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": 688924097276.153, "dur": 0.360, + "args": { + "External id": 757202,"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": 688924097277.448, "dur": 0.552, + "args": { + "External id": 757203,"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": 688924097280.934, "dur": 2.947, + "args": { + "External id": 757204,"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": 688924097337.297, "dur": 27.130, + "args": { + "External id": 757205,"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": 688924097429.012, "dur": 436.185, + "args": { + "External id": 757206,"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": 688924097464.474, "dur": 394.956, + "args": { + "External id": 757207,"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": 688924097476.358, "dur": 376.781, + "args": { + "External id": 757208,"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": 688924097892.041, "dur": 2.802, + "args": { + "External id": 757209,"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": 688924097993.581, "dur": 7264.502, + "args": { + "External id": 757210,"Record function id": 0, "Ev Idx": 5065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924098101.169, "dur": 6.887, + "args": { + "External id": 757211,"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": 688924098111.335, "dur": 1.387, + "args": { + "External id": 757212,"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": 688924098114.568, "dur": 2.257, + "args": { + "External id": 757213,"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": 688924098118.268, "dur": 1.201, + "args": { + "External id": 757214,"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": 688924098120.807, "dur": 1.164, + "args": { + "External id": 757215,"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": 688924098125.505, "dur": 1.124, + "args": { + "External id": 757216,"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": 688924098130.616, "dur": 1.024, + "args": { + "External id": 757217,"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": 688924098132.954, "dur": 2.583, + "args": { + "External id": 757218,"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": 688924098137.073, "dur": 1.051, + "args": { + "External id": 757219,"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": 688924098141.513, "dur": 1.350, + "args": { + "External id": 757220,"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": 688924098160.318, "dur": 7060.397, + "args": { + "External id": 757221,"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": 688924098178.114, "dur": 7035.795, + "args": { + "External id": 757222,"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": 688924098193.202, "dur": 15.360, + "args": { + "External id": 757223,"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": 688924098211.382, "dur": 6968.146, + "args": { + "External id": 757224,"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": 688924098214.327, "dur": 6964.668, + "args": { + "External id": 757225,"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": 688924098220.401, "dur": 6.144, + "args": { + "External id": 757226,"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": 688924098228.550, "dur": 6947.625, + "args": { + "External id": 757227,"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": 688924105399.130, "dur": 40.000, + "args": { + "External id": 757228,"Sequence number": 8961967, "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": 688924105399.130, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924105424.491, "dur": 9.485, + "args": { + "External id": 757229,"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": 688924105429.318, "dur": 4.406, + "args": { + "External id": 757230,"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": 688924105508.091, "dur": 90.077, + "args": { + "External id": 757231,"Record function id": 0, "Ev Idx": 5086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924105600.159, "dur": 1254.691, + "args": { + "External id": 757232,"Record function id": 0, "Ev Idx": 5087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924105639.360, "dur": 1198.967, + "args": { + "External id": 757233,"Sequence number": 8961968, "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": 688924105639.360, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924105743.671, "dur": 59.546, + "args": { + "External id": 757234,"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": 688924105818.667, "dur": 96.729, + "args": { + "External id": 757235,"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": 688924105929.463, "dur": 36.617, + "args": { + "External id": 757236,"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": 688924105972.161, "dur": 30.033, + "args": { + "External id": 757237,"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": 688924106035.854, "dur": 28.991, + "args": { + "External id": 757238,"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": 688924106081.686, "dur": 17.077, + "args": { + "External id": 757239,"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": 688924106119.020, "dur": 135.536, + "args": { + "External id": 757240,"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": 688924106169.989, "dur": 11.562, + "args": { + "External id": 757241,"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": 688924106174.758, "dur": 5.969, + "args": { + "External id": 757242,"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": 688924106185.604, "dur": 6.618, + "args": { + "External id": 757243,"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": 688924106193.383, "dur": 0.982, + "args": { + "External id": 757244,"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": 688924106198.958, "dur": 3.064, + "args": { + "External id": 757245,"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": 688924106265.519, "dur": 44.747, + "args": { + "External id": 757246,"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": 688924106343.620, "dur": 31.294, + "args": { + "External id": 757247,"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": 688924106385.493, "dur": 40.173, + "args": { + "External id": 757248,"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": 688924106501.900, "dur": 48.540, + "args": { + "External id": 757249,"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": 688924106580.904, "dur": 28.588, + "args": { + "External id": 757250,"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": 688924106615.676, "dur": 77.467, + "args": { + "External id": 757251,"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": 688924106719.008, "dur": 26.770, + "args": { + "External id": 757252,"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": 688924106926.809, "dur": 84.460, + "args": { + "External id": 757253,"Record function id": 0, "Ev Idx": 5108 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924107087.704, "dur": 49.827, + "args": { + "External id": 757254,"Record function id": 0, "Ev Idx": 5109 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 4183436, "tid": 4183436, + "ts": 688924107147.939, "dur": 8479.229, + "args": { + "External id": 757255,"Record function id": 0, "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 4183436, "tid": 4183436, + "ts": 688924107157.864, "dur": 958.463, + "args": { + "External id": 757256,"Record function id": 0, "Ev Idx": 5111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924107246.342, "dur": 9.847, + "args": { + "External id": 757257,"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": 688924107269.315, "dur": 41.072, + "args": { + "External id": 757258,"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": 688924107276.564, "dur": 2.160, + "args": { + "External id": 757259,"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": 688924107283.023, "dur": 0.493, + "args": { + "External id": 757260,"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": 688924107285.860, "dur": 0.179, + "args": { + "External id": 757261,"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": 688924107287.070, "dur": 0.575, + "args": { + "External id": 757262,"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": 688924107290.419, "dur": 0.718, + "args": { + "External id": 757263,"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": 688924107293.841, "dur": 0.851, + "args": { + "External id": 757264,"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": 688924107295.422, "dur": 3.537, + "args": { + "External id": 757265,"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": 688924107299.822, "dur": 0.577, + "args": { + "External id": 757266,"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": 688924107302.823, "dur": 0.366, + "args": { + "External id": 757267,"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": 688924107321.886, "dur": 44.451, + "args": { + "External id": 757268,"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": 688924107399.925, "dur": 119.348, + "args": { + "External id": 757269,"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": 688924107414.732, "dur": 4.676, + "args": { + "External id": 757270,"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": 688924107424.759, "dur": 9.943, + "args": { + "External id": 757271,"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": 688924107429.343, "dur": 4.986, + "args": { + "External id": 757272,"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": 688924107432.501, "dur": 0.584, + "args": { + "External id": 757273,"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": 688924107441.640, "dur": 36.759, + "args": { + "External id": 757274,"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": 688924107445.408, "dur": 3.374, + "args": { + "External id": 757275,"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": 688924107449.578, "dur": 0.367, + "args": { + "External id": 757276,"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": 688924107450.692, "dur": 0.536, + "args": { + "External id": 757277,"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": 688924107456.368, "dur": 1.966, + "args": { + "External id": 757278,"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": 688924107458.992, "dur": 0.668, + "args": { + "External id": 757279,"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": 688924107460.551, "dur": 0.381, + "args": { + "External id": 757280,"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": 688924107466.140, "dur": 0.454, + "args": { + "External id": 757281,"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": 688924107467.282, "dur": 0.356, + "args": { + "External id": 757282,"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": 688924107470.356, "dur": 2.818, + "args": { + "External id": 757283,"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": 688924107489.157, "dur": 22.056, + "args": { + "External id": 757284,"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": 688924107575.048, "dur": 436.368, + "args": { + "External id": 757285,"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": 688924107611.652, "dur": 393.655, + "args": { + "External id": 757286,"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": 688924107621.900, "dur": 376.824, + "args": { + "External id": 757287,"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": 688924108037.442, "dur": 2.929, + "args": { + "External id": 757288,"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": 688924108138.836, "dur": 7289.831, + "args": { + "External id": 757289,"Record function id": 0, "Ev Idx": 5144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924108242.147, "dur": 6.753, + "args": { + "External id": 757290,"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": 688924108252.242, "dur": 1.237, + "args": { + "External id": 757291,"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": 688924108255.197, "dur": 3.048, + "args": { + "External id": 757292,"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": 688924108259.846, "dur": 1.214, + "args": { + "External id": 757293,"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": 688924108262.299, "dur": 0.847, + "args": { + "External id": 757294,"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": 688924108264.548, "dur": 0.927, + "args": { + "External id": 757295,"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": 688924108269.783, "dur": 1.140, + "args": { + "External id": 757296,"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": 688924108272.222, "dur": 2.249, + "args": { + "External id": 757297,"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": 688924108275.664, "dur": 1.008, + "args": { + "External id": 757298,"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": 688924108277.939, "dur": 0.765, + "args": { + "External id": 757299,"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": 688924108299.194, "dur": 7090.026, + "args": { + "External id": 757300,"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": 688924108316.362, "dur": 7065.635, + "args": { + "External id": 757301,"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": 688924108333.289, "dur": 16.282, + "args": { + "External id": 757302,"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": 688924108352.357, "dur": 6996.550, + "args": { + "External id": 757303,"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": 688924108354.945, "dur": 6993.462, + "args": { + "External id": 757304,"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": 688924108360.743, "dur": 4.842, + "args": { + "External id": 757305,"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": 688924108367.256, "dur": 6978.131, + "args": { + "External id": 757306,"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": 688924115570.208, "dur": 30.978, + "args": { + "External id": 757307,"Sequence number": 8961969, "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": 688924115570.208, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924115586.643, "dur": 9.916, + "args": { + "External id": 757308,"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": 688924115591.904, "dur": 4.426, + "args": { + "External id": 757309,"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": 688924115702.149, "dur": 116.740, + "args": { + "External id": 757310,"Record function id": 0, "Ev Idx": 5165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924115822.149, "dur": 1146.067, + "args": { + "External id": 757311,"Record function id": 0, "Ev Idx": 5166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924115867.433, "dur": 1086.658, + "args": { + "External id": 757312,"Sequence number": 8961970, "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": 688924115867.433, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924115938.967, "dur": 48.228, + "args": { + "External id": 757313,"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": 688924116000.989, "dur": 96.995, + "args": { + "External id": 757314,"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": 688924116108.373, "dur": 35.980, + "args": { + "External id": 757315,"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": 688924116153.340, "dur": 30.361, + "args": { + "External id": 757316,"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": 688924116208.668, "dur": 28.538, + "args": { + "External id": 757317,"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": 688924116257.286, "dur": 17.462, + "args": { + "External id": 757318,"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": 688924116295.457, "dur": 139.545, + "args": { + "External id": 757319,"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": 688924116347.520, "dur": 10.747, + "args": { + "External id": 757320,"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": 688924116352.083, "dur": 5.380, + "args": { + "External id": 757321,"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": 688924116362.705, "dur": 7.034, + "args": { + "External id": 757322,"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": 688924116371.189, "dur": 0.928, + "args": { + "External id": 757323,"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": 688924116374.238, "dur": 4.035, + "args": { + "External id": 757324,"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": 688924116446.577, "dur": 44.914, + "args": { + "External id": 757325,"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": 688924116522.501, "dur": 29.567, + "args": { + "External id": 757326,"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": 688924116561.010, "dur": 37.753, + "args": { + "External id": 757327,"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": 688924116607.314, "dur": 33.326, + "args": { + "External id": 757328,"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": 688924116717.814, "dur": 29.417, + "args": { + "External id": 757329,"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": 688924116754.613, "dur": 65.252, + "args": { + "External id": 757330,"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": 688924116848.339, "dur": 22.411, + "args": { + "External id": 757331,"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": 688924117038.657, "dur": 83.791, + "args": { + "External id": 757332,"Record function id": 0, "Ev Idx": 5187 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924117200.503, "dur": 51.530, + "args": { + "External id": 757333,"Record function id": 0, "Ev Idx": 5188 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 4183436, "tid": 4183436, + "ts": 688924117262.911, "dur": 8724.253, + "args": { + "External id": 757334,"Record function id": 0, "Ev Idx": 5189 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 4183436, "tid": 4183436, + "ts": 688924117274.474, "dur": 990.204, + "args": { + "External id": 757335,"Record function id": 0, "Ev Idx": 5190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924117359.436, "dur": 8.550, + "args": { + "External id": 757336,"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": 688924117381.099, "dur": 43.189, + "args": { + "External id": 757337,"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": 688924117388.753, "dur": 2.429, + "args": { + "External id": 757338,"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": 688924117395.713, "dur": 0.464, + "args": { + "External id": 757339,"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": 688924117398.895, "dur": 0.664, + "args": { + "External id": 757340,"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": 688924117400.605, "dur": 0.222, + "args": { + "External id": 757341,"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": 688924117403.835, "dur": 0.654, + "args": { + "External id": 757342,"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": 688924117407.058, "dur": 0.290, + "args": { + "External id": 757343,"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": 688924117407.989, "dur": 4.149, + "args": { + "External id": 757344,"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": 688924117412.662, "dur": 0.363, + "args": { + "External id": 757345,"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": 688924117416.254, "dur": 0.317, + "args": { + "External id": 757346,"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": 688924117435.992, "dur": 41.160, + "args": { + "External id": 757347,"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": 688924117510.044, "dur": 123.237, + "args": { + "External id": 757348,"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": 688924117524.168, "dur": 4.105, + "args": { + "External id": 757349,"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": 688924117533.533, "dur": 10.280, + "args": { + "External id": 757350,"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": 688924117538.306, "dur": 5.127, + "args": { + "External id": 757351,"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": 688924117541.417, "dur": 0.727, + "args": { + "External id": 757352,"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": 688924117550.275, "dur": 32.430, + "args": { + "External id": 757353,"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": 688924117553.164, "dur": 2.564, + "args": { + "External id": 757354,"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": 688924117556.698, "dur": 0.370, + "args": { + "External id": 757355,"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": 688924117558.259, "dur": 0.328, + "args": { + "External id": 757356,"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": 688924117562.590, "dur": 1.826, + "args": { + "External id": 757357,"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": 688924117565.024, "dur": 0.348, + "args": { + "External id": 757358,"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": 688924117567.319, "dur": 0.357, + "args": { + "External id": 757359,"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": 688924117571.221, "dur": 0.166, + "args": { + "External id": 757360,"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": 688924117573.214, "dur": 0.157, + "args": { + "External id": 757361,"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": 688924117574.678, "dur": 2.475, + "args": { + "External id": 757362,"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": 688924117599.503, "dur": 25.791, + "args": { + "External id": 757363,"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": 688924117743.178, "dur": 419.369, + "args": { + "External id": 757364,"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": 688924117779.415, "dur": 377.560, + "args": { + "External id": 757365,"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": 688924117822.670, "dur": 329.215, + "args": { + "External id": 757366,"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": 688924118187.950, "dur": 2.164, + "args": { + "External id": 757367,"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": 688924118286.495, "dur": 7479.713, + "args": { + "External id": 757368,"Record function id": 0, "Ev Idx": 5223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924118389.490, "dur": 7.063, + "args": { + "External id": 757369,"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": 688924118399.757, "dur": 1.260, + "args": { + "External id": 757370,"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": 688924118403.494, "dur": 2.582, + "args": { + "External id": 757371,"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": 688924118408.162, "dur": 1.029, + "args": { + "External id": 757372,"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": 688924118410.849, "dur": 0.959, + "args": { + "External id": 757373,"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": 688924118413.436, "dur": 0.959, + "args": { + "External id": 757374,"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": 688924118417.069, "dur": 1.065, + "args": { + "External id": 757375,"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": 688924118419.803, "dur": 2.227, + "args": { + "External id": 757376,"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": 688924118424.173, "dur": 0.694, + "args": { + "External id": 757377,"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": 688924118426.466, "dur": 0.578, + "args": { + "External id": 757378,"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": 688924118447.041, "dur": 7274.178, + "args": { + "External id": 757379,"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": 688924118470.540, "dur": 7243.736, + "args": { + "External id": 757380,"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": 688924118485.645, "dur": 15.907, + "args": { + "External id": 757381,"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": 688924118504.343, "dur": 7176.508, + "args": { + "External id": 757382,"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": 688924118507.248, "dur": 7172.916, + "args": { + "External id": 757383,"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": 688924118513.714, "dur": 5.079, + "args": { + "External id": 757384,"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": 688924118520.657, "dur": 7129.414, + "args": { + "External id": 757385,"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": 688924125927.683, "dur": 31.158, + "args": { + "External id": 757386,"Sequence number": 8961971, "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": 688924125927.683, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924125944.897, "dur": 9.176, + "args": { + "External id": 757387,"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": 688924125948.853, "dur": 4.800, + "args": { + "External id": 757388,"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": 688924126031.241, "dur": 89.794, + "args": { + "External id": 757389,"Record function id": 0, "Ev Idx": 5244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924126123.150, "dur": 1128.996, + "args": { + "External id": 757390,"Record function id": 0, "Ev Idx": 5245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924126165.492, "dur": 1072.316, + "args": { + "External id": 757391,"Sequence number": 8961972, "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": 688924126165.492, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924126237.128, "dur": 43.280, + "args": { + "External id": 757392,"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": 688924126292.531, "dur": 96.402, + "args": { + "External id": 757393,"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": 688924126398.274, "dur": 34.154, + "args": { + "External id": 757394,"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": 688924126442.325, "dur": 30.026, + "args": { + "External id": 757395,"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": 688924126497.057, "dur": 27.658, + "args": { + "External id": 757396,"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": 688924126543.035, "dur": 17.152, + "args": { + "External id": 757397,"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": 688924126584.086, "dur": 181.553, + "args": { + "External id": 757398,"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": 688924126634.451, "dur": 13.587, + "args": { + "External id": 757399,"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": 688924126639.702, "dur": 7.522, + "args": { + "External id": 757400,"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": 688924126694.555, "dur": 5.446, + "args": { + "External id": 757401,"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": 688924126702.485, "dur": 0.997, + "args": { + "External id": 757402,"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": 688924126706.156, "dur": 4.051, + "args": { + "External id": 757403,"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": 688924126777.508, "dur": 71.168, + "args": { + "External id": 757404,"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": 688924126889.659, "dur": 31.637, + "args": { + "External id": 757405,"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": 688924126930.417, "dur": 40.850, + "args": { + "External id": 757406,"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": 688924126979.707, "dur": 49.483, + "args": { + "External id": 757407,"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": 688924127052.603, "dur": 27.220, + "args": { + "External id": 757408,"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": 688924127085.191, "dur": 41.983, + "args": { + "External id": 757409,"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": 688924127149.620, "dur": 19.298, + "args": { + "External id": 757410,"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": 688924127321.486, "dur": 78.199, + "args": { + "External id": 757411,"Record function id": 0, "Ev Idx": 5266 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924127475.562, "dur": 46.657, + "args": { + "External id": 757412,"Record function id": 0, "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 4183436, "tid": 4183436, + "ts": 688924127532.596, "dur": 8714.102, + "args": { + "External id": 757413,"Record function id": 0, "Ev Idx": 5268 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 4183436, "tid": 4183436, + "ts": 688924127542.333, "dur": 960.700, + "args": { + "External id": 757414,"Record function id": 0, "Ev Idx": 5269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924127626.767, "dur": 8.460, + "args": { + "External id": 757415,"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": 688924127649.613, "dur": 81.906, + "args": { + "External id": 757416,"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": 688924127696.775, "dur": 2.415, + "args": { + "External id": 757417,"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": 688924127704.800, "dur": 0.331, + "args": { + "External id": 757418,"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": 688924127706.689, "dur": 0.257, + "args": { + "External id": 757419,"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": 688924127708.571, "dur": 0.395, + "args": { + "External id": 757420,"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": 688924127712.476, "dur": 0.365, + "args": { + "External id": 757421,"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": 688924127714.309, "dur": 0.457, + "args": { + "External id": 757422,"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": 688924127716.390, "dur": 4.249, + "args": { + "External id": 757423,"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": 688924127722.307, "dur": 0.328, + "args": { + "External id": 757424,"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": 688924127724.266, "dur": 0.462, + "args": { + "External id": 757425,"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": 688924127744.784, "dur": 60.077, + "args": { + "External id": 757426,"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": 688924127842.803, "dur": 127.634, + "args": { + "External id": 757427,"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": 688924127857.055, "dur": 5.902, + "args": { + "External id": 757428,"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": 688924127868.592, "dur": 10.980, + "args": { + "External id": 757429,"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": 688924127873.202, "dur": 5.982, + "args": { + "External id": 757430,"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": 688924127877.202, "dur": 0.531, + "args": { + "External id": 757431,"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": 688924127887.537, "dur": 34.607, + "args": { + "External id": 757432,"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": 688924127890.329, "dur": 3.145, + "args": { + "External id": 757433,"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": 688924127895.358, "dur": 0.325, + "args": { + "External id": 757434,"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": 688924127897.304, "dur": 0.171, + "args": { + "External id": 757435,"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": 688924127901.775, "dur": 1.423, + "args": { + "External id": 757436,"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": 688924127904.591, "dur": 0.148, + "args": { + "External id": 757437,"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": 688924127906.803, "dur": 0.188, + "args": { + "External id": 757438,"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": 688924127910.464, "dur": 0.142, + "args": { + "External id": 757439,"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": 688924127912.223, "dur": 0.237, + "args": { + "External id": 757440,"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": 688924127913.867, "dur": 3.117, + "args": { + "External id": 757441,"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": 688924127935.694, "dur": 26.318, + "args": { + "External id": 757442,"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": 688924128027.946, "dur": 379.497, + "args": { + "External id": 757443,"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": 688924128061.186, "dur": 341.330, + "args": { + "External id": 757444,"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": 688924128072.119, "dur": 325.053, + "args": { + "External id": 757445,"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": 688924128428.871, "dur": 2.600, + "args": { + "External id": 757446,"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": 688924128523.804, "dur": 7517.350, + "args": { + "External id": 757447,"Record function id": 0, "Ev Idx": 5302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924128623.266, "dur": 6.104, + "args": { + "External id": 757448,"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": 688924128633.294, "dur": 1.057, + "args": { + "External id": 757449,"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": 688924128636.346, "dur": 2.396, + "args": { + "External id": 757450,"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": 688924128640.391, "dur": 0.813, + "args": { + "External id": 757451,"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": 688924128642.654, "dur": 1.034, + "args": { + "External id": 757452,"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": 688924128645.329, "dur": 1.021, + "args": { + "External id": 757453,"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": 688924128649.133, "dur": 0.925, + "args": { + "External id": 757454,"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": 688924128692.491, "dur": 3.478, + "args": { + "External id": 757455,"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": 688924128698.022, "dur": 0.637, + "args": { + "External id": 757456,"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": 688924128700.379, "dur": 0.797, + "args": { + "External id": 757457,"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": 688924128721.634, "dur": 7274.325, + "args": { + "External id": 757458,"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": 688924128738.814, "dur": 7249.727, + "args": { + "External id": 757459,"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": 688924128758.268, "dur": 15.644, + "args": { + "External id": 757460,"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": 688924128776.653, "dur": 7178.973, + "args": { + "External id": 757461,"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": 688924128779.159, "dur": 7175.927, + "args": { + "External id": 757462,"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": 688924128785.596, "dur": 23.230, + "args": { + "External id": 757463,"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": 688924128811.280, "dur": 7140.678, + "args": { + "External id": 757464,"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": 688924136189.786, "dur": 30.304, + "args": { + "External id": 757465,"Sequence number": 8961973, "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": 688924136189.786, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924136206.779, "dur": 8.439, + "args": { + "External id": 757466,"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": 688924136210.420, "dur": 4.623, + "args": { + "External id": 757467,"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": 688924136288.644, "dur": 90.195, + "args": { + "External id": 757468,"Record function id": 0, "Ev Idx": 5323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924136380.604, "dur": 1122.308, + "args": { + "External id": 757469,"Record function id": 0, "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924136423.556, "dur": 1064.952, + "args": { + "External id": 757470,"Sequence number": 8961974, "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": 688924136423.556, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924136488.413, "dur": 42.075, + "args": { + "External id": 757471,"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": 688924136542.852, "dur": 92.609, + "args": { + "External id": 757472,"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": 688924136645.790, "dur": 83.245, + "args": { + "External id": 757473,"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": 688924136742.693, "dur": 36.999, + "args": { + "External id": 757474,"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": 688924136820.768, "dur": 29.825, + "args": { + "External id": 757475,"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": 688924136868.946, "dur": 15.872, + "args": { + "External id": 757476,"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": 688924136905.001, "dur": 135.091, + "args": { + "External id": 757477,"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": 688924136960.768, "dur": 12.255, + "args": { + "External id": 757478,"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": 688924136966.445, "dur": 5.736, + "args": { + "External id": 757479,"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": 688924136975.797, "dur": 6.755, + "args": { + "External id": 757480,"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": 688924136983.881, "dur": 1.016, + "args": { + "External id": 757481,"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": 688924136987.230, "dur": 3.358, + "args": { + "External id": 757482,"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": 688924137052.523, "dur": 50.275, + "args": { + "External id": 757483,"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": 688924137132.838, "dur": 29.130, + "args": { + "External id": 757484,"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": 688924137170.471, "dur": 37.977, + "args": { + "External id": 757485,"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": 688924137216.163, "dur": 46.347, + "args": { + "External id": 757486,"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": 688924137285.446, "dur": 29.904, + "args": { + "External id": 757487,"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": 688924137321.456, "dur": 48.932, + "args": { + "External id": 757488,"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": 688924137391.147, "dur": 20.626, + "args": { + "External id": 757489,"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": 688924137571.088, "dur": 119.482, + "args": { + "External id": 757490,"Record function id": 0, "Ev Idx": 5345 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924137776.169, "dur": 66.923, + "args": { + "External id": 757491,"Record function id": 0, "Ev Idx": 5346 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 4183436, "tid": 4183436, + "ts": 688924137854.889, "dur": 8863.012, + "args": { + "External id": 757492,"Record function id": 0, "Ev Idx": 5347 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 4183436, "tid": 4183436, + "ts": 688924137864.140, "dur": 966.209, + "args": { + "External id": 757493,"Record function id": 0, "Ev Idx": 5348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924137951.000, "dur": 9.769, + "args": { + "External id": 757494,"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": 688924137975.884, "dur": 43.496, + "args": { + "External id": 757495,"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": 688924137982.071, "dur": 2.349, + "args": { + "External id": 757496,"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": 688924137989.996, "dur": 0.323, + "args": { + "External id": 757497,"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": 688924137991.950, "dur": 0.474, + "args": { + "External id": 757498,"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": 688924137993.957, "dur": 0.529, + "args": { + "External id": 757499,"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": 688924137997.982, "dur": 0.321, + "args": { + "External id": 757500,"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": 688924137999.773, "dur": 0.253, + "args": { + "External id": 757501,"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": 688924138001.492, "dur": 4.498, + "args": { + "External id": 757502,"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": 688924138007.754, "dur": 0.235, + "args": { + "External id": 757503,"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": 688924138009.761, "dur": 0.195, + "args": { + "External id": 757504,"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": 688924138032.633, "dur": 46.426, + "args": { + "External id": 757505,"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": 688924138113.769, "dur": 122.088, + "args": { + "External id": 757506,"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": 688924138127.735, "dur": 3.492, + "args": { + "External id": 757507,"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": 688924138136.307, "dur": 10.513, + "args": { + "External id": 757508,"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": 688924138140.713, "dur": 5.679, + "args": { + "External id": 757509,"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": 688924138144.621, "dur": 0.410, + "args": { + "External id": 757510,"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": 688924138154.180, "dur": 35.355, + "args": { + "External id": 757511,"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": 688924138156.146, "dur": 2.720, + "args": { + "External id": 757512,"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": 688924138160.645, "dur": 0.435, + "args": { + "External id": 757513,"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": 688924138162.846, "dur": 0.211, + "args": { + "External id": 757514,"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": 688924138167.489, "dur": 1.892, + "args": { + "External id": 757515,"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": 688924138170.698, "dur": 0.270, + "args": { + "External id": 757516,"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": 688924138172.518, "dur": 0.264, + "args": { + "External id": 757517,"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": 688924138176.073, "dur": 0.180, + "args": { + "External id": 757518,"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": 688924138178.187, "dur": 0.304, + "args": { + "External id": 757519,"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": 688924138179.802, "dur": 2.808, + "args": { + "External id": 757520,"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": 688924138203.665, "dur": 23.821, + "args": { + "External id": 757521,"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": 688924138289.975, "dur": 415.621, + "args": { + "External id": 757522,"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": 688924138322.448, "dur": 376.592, + "args": { + "External id": 757523,"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": 688924138332.783, "dur": 358.777, + "args": { + "External id": 757524,"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": 688924138731.940, "dur": 3.116, + "args": { + "External id": 757525,"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": 688924138854.869, "dur": 7622.576, + "args": { + "External id": 757526,"Record function id": 0, "Ev Idx": 5381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924138968.875, "dur": 7.187, + "args": { + "External id": 757527,"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": 688924138979.996, "dur": 1.110, + "args": { + "External id": 757528,"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": 688924138983.255, "dur": 2.625, + "args": { + "External id": 757529,"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": 688924138989.124, "dur": 0.804, + "args": { + "External id": 757530,"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": 688924138991.707, "dur": 0.714, + "args": { + "External id": 757531,"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": 688924138993.969, "dur": 1.333, + "args": { + "External id": 757532,"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": 688924138997.106, "dur": 0.846, + "args": { + "External id": 757533,"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": 688924139001.510, "dur": 3.066, + "args": { + "External id": 757534,"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": 688924139006.236, "dur": 0.943, + "args": { + "External id": 757535,"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": 688924139008.683, "dur": 0.747, + "args": { + "External id": 757536,"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": 688924139028.988, "dur": 7406.094, + "args": { + "External id": 757537,"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": 688924139045.327, "dur": 7383.116, + "args": { + "External id": 757538,"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": 688924139060.159, "dur": 14.838, + "args": { + "External id": 757539,"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": 688924139079.692, "dur": 7316.943, + "args": { + "External id": 757540,"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": 688924139082.138, "dur": 7313.999, + "args": { + "External id": 757541,"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": 688924139088.777, "dur": 6.860, + "args": { + "External id": 757542,"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": 688924139097.389, "dur": 7295.588, + "args": { + "External id": 757543,"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": 688924146622.049, "dur": 66.358, + "args": { + "External id": 757544,"Sequence number": 8961975, "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": 688924146622.049, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924146639.888, "dur": 8.282, + "args": { + "External id": 757545,"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": 688924146643.771, "dur": 4.196, + "args": { + "External id": 757546,"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": 688924146761.811, "dur": 111.194, + "args": { + "External id": 757547,"Record function id": 0, "Ev Idx": 5402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924146876.054, "dur": 1110.165, + "args": { + "External id": 757548,"Record function id": 0, "Ev Idx": 5403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924146922.292, "dur": 1048.548, + "args": { + "External id": 757549,"Sequence number": 8961976, "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": 688924146922.292, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924146992.237, "dur": 43.977, + "args": { + "External id": 757550,"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": 688924147049.553, "dur": 98.916, + "args": { + "External id": 757551,"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": 688924147157.996, "dur": 36.134, + "args": { + "External id": 757552,"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": 688924147203.248, "dur": 30.473, + "args": { + "External id": 757553,"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": 688924147257.430, "dur": 25.594, + "args": { + "External id": 757554,"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": 688924147302.007, "dur": 14.789, + "args": { + "External id": 757555,"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": 688924147336.694, "dur": 139.438, + "args": { + "External id": 757556,"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": 688924147386.388, "dur": 12.354, + "args": { + "External id": 757557,"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": 688924147392.140, "dur": 5.818, + "args": { + "External id": 757558,"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": 688924147401.710, "dur": 5.826, + "args": { + "External id": 757559,"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": 688924147417.475, "dur": 1.261, + "args": { + "External id": 757560,"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": 688924147421.117, "dur": 4.138, + "args": { + "External id": 757561,"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": 688924147486.637, "dur": 42.037, + "args": { + "External id": 757562,"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": 688924147559.353, "dur": 27.425, + "args": { + "External id": 757563,"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": 688924147596.268, "dur": 37.952, + "args": { + "External id": 757564,"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": 688924147642.884, "dur": 79.339, + "args": { + "External id": 757565,"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": 688924147748.460, "dur": 29.598, + "args": { + "External id": 757566,"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": 688924147783.932, "dur": 70.725, + "args": { + "External id": 757567,"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": 688924147877.854, "dur": 18.650, + "args": { + "External id": 757568,"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": 688924148055.670, "dur": 85.368, + "args": { + "External id": 757569,"Record function id": 0, "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924148220.147, "dur": 49.860, + "args": { + "External id": 757570,"Record function id": 0, "Ev Idx": 5425 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 4183436, "tid": 4183436, + "ts": 688924148279.914, "dur": 8639.432, + "args": { + "External id": 757571,"Record function id": 0, "Ev Idx": 5426 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 4183436, "tid": 4183436, + "ts": 688924148288.007, "dur": 1007.597, + "args": { + "External id": 757572,"Record function id": 0, "Ev Idx": 5427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924148373.258, "dur": 8.653, + "args": { + "External id": 757573,"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": 688924148395.693, "dur": 44.138, + "args": { + "External id": 757574,"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": 688924148402.129, "dur": 2.262, + "args": { + "External id": 757575,"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": 688924148410.595, "dur": 0.524, + "args": { + "External id": 757576,"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": 688924148412.724, "dur": 0.350, + "args": { + "External id": 757577,"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": 688924148414.902, "dur": 0.398, + "args": { + "External id": 757578,"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": 688924148419.003, "dur": 0.346, + "args": { + "External id": 757579,"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": 688924148420.911, "dur": 0.586, + "args": { + "External id": 757580,"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": 688924148422.968, "dur": 4.273, + "args": { + "External id": 757581,"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": 688924148429.036, "dur": 0.379, + "args": { + "External id": 757582,"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": 688924148430.731, "dur": 0.470, + "args": { + "External id": 757583,"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": 688924148452.935, "dur": 41.124, + "args": { + "External id": 757584,"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": 688924148528.350, "dur": 117.855, + "args": { + "External id": 757585,"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": 688924148539.098, "dur": 3.619, + "args": { + "External id": 757586,"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": 688924148547.733, "dur": 10.770, + "args": { + "External id": 757587,"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": 688924148552.379, "dur": 5.675, + "args": { + "External id": 757588,"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": 688924148556.436, "dur": 0.360, + "args": { + "External id": 757589,"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": 688924148566.020, "dur": 36.764, + "args": { + "External id": 757590,"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": 688924148567.962, "dur": 2.678, + "args": { + "External id": 757591,"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": 688924148572.931, "dur": 0.647, + "args": { + "External id": 757592,"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": 688924148575.565, "dur": 0.310, + "args": { + "External id": 757593,"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": 688924148579.971, "dur": 2.355, + "args": { + "External id": 757594,"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": 688924148583.995, "dur": 0.189, + "args": { + "External id": 757595,"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": 688924148585.878, "dur": 0.534, + "args": { + "External id": 757596,"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": 688924148589.641, "dur": 0.189, + "args": { + "External id": 757597,"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": 688924148591.311, "dur": 0.581, + "args": { + "External id": 757598,"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": 688924148593.360, "dur": 2.292, + "args": { + "External id": 757599,"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": 688924148613.860, "dur": 24.407, + "args": { + "External id": 757600,"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": 688924148753.233, "dur": 434.980, + "args": { + "External id": 757601,"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": 688924148807.167, "dur": 375.295, + "args": { + "External id": 757602,"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": 688924148819.881, "dur": 357.145, + "args": { + "External id": 757603,"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": 688924149214.015, "dur": 2.382, + "args": { + "External id": 757604,"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": 688924149317.943, "dur": 7377.954, + "args": { + "External id": 757605,"Record function id": 0, "Ev Idx": 5460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924149427.194, "dur": 7.274, + "args": { + "External id": 757606,"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": 688924149438.366, "dur": 1.545, + "args": { + "External id": 757607,"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": 688924149441.885, "dur": 2.457, + "args": { + "External id": 757608,"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": 688924149445.954, "dur": 1.112, + "args": { + "External id": 757609,"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": 688924149448.844, "dur": 1.346, + "args": { + "External id": 757610,"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": 688924149452.368, "dur": 0.779, + "args": { + "External id": 757611,"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": 688924149455.048, "dur": 1.263, + "args": { + "External id": 757612,"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": 688924149458.593, "dur": 2.993, + "args": { + "External id": 757613,"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": 688924149463.499, "dur": 0.899, + "args": { + "External id": 757614,"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": 688924149465.979, "dur": 0.965, + "args": { + "External id": 757615,"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": 688924149497.796, "dur": 7126.067, + "args": { + "External id": 757616,"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": 688924149515.318, "dur": 7100.258, + "args": { + "External id": 757617,"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": 688924149529.794, "dur": 15.956, + "args": { + "External id": 757618,"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": 688924149548.712, "dur": 7033.708, + "args": { + "External id": 757619,"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": 688924149551.750, "dur": 7029.972, + "args": { + "External id": 757620,"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": 688924149557.790, "dur": 6.994, + "args": { + "External id": 757621,"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": 688924149566.725, "dur": 7011.607, + "args": { + "External id": 757622,"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": 688924156859.946, "dur": 30.890, + "args": { + "External id": 757623,"Sequence number": 8961977, "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": 688924156859.946, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924156877.515, "dur": 8.729, + "args": { + "External id": 757624,"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": 688924156881.071, "dur": 4.731, + "args": { + "External id": 757625,"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": 688924156960.631, "dur": 91.399, + "args": { + "External id": 757626,"Record function id": 0, "Ev Idx": 5481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924157053.740, "dur": 1116.504, + "args": { + "External id": 757627,"Record function id": 0, "Ev Idx": 5482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924157095.040, "dur": 1060.805, + "args": { + "External id": 757628,"Sequence number": 8961978, "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": 688924157095.040, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924157161.871, "dur": 45.618, + "args": { + "External id": 757629,"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": 688924157219.741, "dur": 94.713, + "args": { + "External id": 757630,"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": 688924157324.359, "dur": 34.650, + "args": { + "External id": 757631,"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": 688924157368.736, "dur": 28.894, + "args": { + "External id": 757632,"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": 688924157420.728, "dur": 26.947, + "args": { + "External id": 757633,"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": 688924157465.939, "dur": 14.539, + "args": { + "External id": 757634,"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": 688924157499.177, "dur": 130.944, + "args": { + "External id": 757635,"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": 688924157549.676, "dur": 11.477, + "args": { + "External id": 757636,"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": 688924157554.706, "dur": 5.635, + "args": { + "External id": 757637,"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": 688924157563.818, "dur": 5.651, + "args": { + "External id": 757638,"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": 688924157570.486, "dur": 1.166, + "args": { + "External id": 757639,"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": 688924157574.313, "dur": 4.705, + "args": { + "External id": 757640,"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": 688924157640.195, "dur": 93.426, + "args": { + "External id": 757641,"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": 688924157769.275, "dur": 45.849, + "args": { + "External id": 757642,"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": 688924157827.442, "dur": 43.192, + "args": { + "External id": 757643,"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": 688924157880.578, "dur": 49.829, + "args": { + "External id": 757644,"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": 688924157952.166, "dur": 28.028, + "args": { + "External id": 757645,"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": 688924157985.978, "dur": 51.913, + "args": { + "External id": 757646,"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": 688924158058.735, "dur": 19.686, + "args": { + "External id": 757647,"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": 688924158237.529, "dur": 79.499, + "args": { + "External id": 757648,"Record function id": 0, "Ev Idx": 5503 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924158392.911, "dur": 50.029, + "args": { + "External id": 757649,"Record function id": 0, "Ev Idx": 5504 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 4183436, "tid": 4183436, + "ts": 688924158452.944, "dur": 8632.634, + "args": { + "External id": 757650,"Record function id": 0, "Ev Idx": 5505 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 4183436, "tid": 4183436, + "ts": 688924158461.131, "dur": 988.029, + "args": { + "External id": 757651,"Record function id": 0, "Ev Idx": 5506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924158548.760, "dur": 8.647, + "args": { + "External id": 757652,"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": 688924158570.285, "dur": 37.768, + "args": { + "External id": 757653,"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": 688924158575.722, "dur": 2.311, + "args": { + "External id": 757654,"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": 688924158582.569, "dur": 0.289, + "args": { + "External id": 757655,"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": 688924158584.055, "dur": 0.376, + "args": { + "External id": 757656,"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": 688924158585.520, "dur": 0.587, + "args": { + "External id": 757657,"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": 688924158589.183, "dur": 0.467, + "args": { + "External id": 757658,"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": 688924158590.780, "dur": 0.464, + "args": { + "External id": 757659,"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": 688924158592.357, "dur": 3.781, + "args": { + "External id": 757660,"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": 688924158597.462, "dur": 0.367, + "args": { + "External id": 757661,"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": 688924158599.066, "dur": 0.469, + "args": { + "External id": 757662,"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": 688924158620.247, "dur": 87.129, + "args": { + "External id": 757663,"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": 688924158746.440, "dur": 186.408, + "args": { + "External id": 757664,"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": 688924158758.181, "dur": 6.142, + "args": { + "External id": 757665,"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": 688924158769.767, "dur": 11.596, + "args": { + "External id": 757666,"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": 688924158774.665, "dur": 6.302, + "args": { + "External id": 757667,"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": 688924158778.514, "dur": 0.759, + "args": { + "External id": 757668,"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": 688924158804.199, "dur": 33.825, + "args": { + "External id": 757669,"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": 688924158806.738, "dur": 3.080, + "args": { + "External id": 757670,"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": 688924158815.248, "dur": 0.506, + "args": { + "External id": 757671,"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": 688924158817.137, "dur": 0.204, + "args": { + "External id": 757672,"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": 688924158820.031, "dur": 1.731, + "args": { + "External id": 757673,"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": 688924158822.901, "dur": 0.461, + "args": { + "External id": 757674,"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": 688924158824.408, "dur": 2.158, + "args": { + "External id": 757675,"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": 688924158827.594, "dur": 0.433, + "args": { + "External id": 757676,"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": 688924158829.146, "dur": 0.188, + "args": { + "External id": 757677,"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": 688924158832.597, "dur": 0.317, + "args": { + "External id": 757678,"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": 688924158887.160, "dur": 36.185, + "args": { + "External id": 757679,"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": 688924158993.497, "dur": 361.729, + "args": { + "External id": 757680,"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": 688924159023.881, "dur": 327.049, + "args": { + "External id": 757681,"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": 688924159036.445, "dur": 308.782, + "args": { + "External id": 757682,"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": 688924159374.637, "dur": 2.234, + "args": { + "External id": 757683,"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": 688924159471.219, "dur": 7418.020, + "args": { + "External id": 757684,"Record function id": 0, "Ev Idx": 5539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924159573.767, "dur": 5.411, + "args": { + "External id": 757685,"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": 688924159582.895, "dur": 1.150, + "args": { + "External id": 757686,"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": 688924159585.788, "dur": 2.351, + "args": { + "External id": 757687,"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": 688924159589.936, "dur": 1.021, + "args": { + "External id": 757688,"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": 688924159592.698, "dur": 0.931, + "args": { + "External id": 757689,"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": 688924159595.499, "dur": 0.958, + "args": { + "External id": 757690,"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": 688924159598.234, "dur": 0.973, + "args": { + "External id": 757691,"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": 688924159600.653, "dur": 1.992, + "args": { + "External id": 757692,"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": 688924159604.088, "dur": 0.758, + "args": { + "External id": 757693,"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": 688924159606.568, "dur": 0.706, + "args": { + "External id": 757694,"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": 688924159624.715, "dur": 7222.318, + "args": { + "External id": 757695,"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": 688924159640.674, "dur": 7199.194, + "args": { + "External id": 757696,"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": 688924159698.248, "dur": 17.130, + "args": { + "External id": 757697,"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": 688924159718.632, "dur": 7086.434, + "args": { + "External id": 757698,"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": 688924159721.337, "dur": 7083.193, + "args": { + "External id": 757699,"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": 688924159727.430, "dur": 7.703, + "args": { + "External id": 757700,"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": 688924159736.896, "dur": 7064.627, + "args": { + "External id": 757701,"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": 688924167030.615, "dur": 30.338, + "args": { + "External id": 757702,"Sequence number": 8961979, "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": 688924167030.615, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924167047.819, "dur": 8.565, + "args": { + "External id": 757703,"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": 688924167051.791, "dur": 4.380, + "args": { + "External id": 757704,"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": 688924167127.037, "dur": 91.785, + "args": { + "External id": 757705,"Record function id": 0, "Ev Idx": 5560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924167220.477, "dur": 1153.871, + "args": { + "External id": 757706,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924167258.230, "dur": 1101.089, + "args": { + "External id": 757707,"Sequence number": 8961980, "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": 688924167258.230, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924167326.575, "dur": 40.950, + "args": { + "External id": 757708,"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": 688924167379.585, "dur": 97.378, + "args": { + "External id": 757709,"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": 688924167486.706, "dur": 36.199, + "args": { + "External id": 757710,"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": 688924167531.420, "dur": 30.279, + "args": { + "External id": 757711,"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": 688924167586.481, "dur": 26.953, + "args": { + "External id": 757712,"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": 688924167631.686, "dur": 17.907, + "args": { + "External id": 757713,"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": 688924167731.528, "dur": 163.464, + "args": { + "External id": 757714,"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": 688924167784.742, "dur": 33.645, + "args": { + "External id": 757715,"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": 688924167809.460, "dur": 7.937, + "args": { + "External id": 757716,"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": 688924167821.100, "dur": 6.095, + "args": { + "External id": 757717,"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": 688924167828.748, "dur": 1.354, + "args": { + "External id": 757718,"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": 688924167832.623, "dur": 4.160, + "args": { + "External id": 757719,"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": 688924167906.590, "dur": 56.466, + "args": { + "External id": 757720,"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": 688924167996.290, "dur": 30.261, + "args": { + "External id": 757721,"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": 688924168047.547, "dur": 54.010, + "args": { + "External id": 757722,"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": 688924168110.195, "dur": 53.446, + "args": { + "External id": 757723,"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": 688924168183.910, "dur": 28.228, + "args": { + "External id": 757724,"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": 688924168218.178, "dur": 33.373, + "args": { + "External id": 757725,"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": 688924168271.933, "dur": 19.194, + "args": { + "External id": 757726,"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": 688924168442.272, "dur": 79.415, + "args": { + "External id": 757727,"Record function id": 0, "Ev Idx": 5582 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924168599.824, "dur": 48.113, + "args": { + "External id": 757728,"Record function id": 0, "Ev Idx": 5583 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 4183436, "tid": 4183436, + "ts": 688924168706.450, "dur": 8901.066, + "args": { + "External id": 757729,"Record function id": 0, "Ev Idx": 5584 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 4183436, "tid": 4183436, + "ts": 688924168716.813, "dur": 1090.125, + "args": { + "External id": 757730,"Record function id": 0, "Ev Idx": 5585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924168828.267, "dur": 10.877, + "args": { + "External id": 757731,"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": 688924168853.371, "dur": 41.295, + "args": { + "External id": 757732,"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": 688924168859.545, "dur": 2.357, + "args": { + "External id": 757733,"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": 688924168867.291, "dur": 0.294, + "args": { + "External id": 757734,"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": 688924168869.652, "dur": 0.513, + "args": { + "External id": 757735,"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": 688924168871.532, "dur": 0.336, + "args": { + "External id": 757736,"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": 688924168875.825, "dur": 0.293, + "args": { + "External id": 757737,"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": 688924168878.118, "dur": 0.456, + "args": { + "External id": 757738,"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": 688924168880.280, "dur": 4.019, + "args": { + "External id": 757739,"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": 688924168885.906, "dur": 0.174, + "args": { + "External id": 757740,"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": 688924168887.640, "dur": 0.178, + "args": { + "External id": 757741,"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": 688924168907.750, "dur": 45.939, + "args": { + "External id": 757742,"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": 688924168989.188, "dur": 117.041, + "args": { + "External id": 757743,"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": 688924168999.693, "dur": 4.483, + "args": { + "External id": 757744,"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": 688924169009.246, "dur": 10.701, + "args": { + "External id": 757745,"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": 688924169013.855, "dur": 5.731, + "args": { + "External id": 757746,"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": 688924169017.819, "dur": 0.437, + "args": { + "External id": 757747,"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": 688924169027.622, "dur": 33.740, + "args": { + "External id": 757748,"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": 688924169030.444, "dur": 2.562, + "args": { + "External id": 757749,"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": 688924169034.796, "dur": 0.390, + "args": { + "External id": 757750,"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": 688924169037.034, "dur": 0.245, + "args": { + "External id": 757751,"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": 688924169041.415, "dur": 1.683, + "args": { + "External id": 757752,"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": 688924169044.760, "dur": 0.282, + "args": { + "External id": 757753,"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": 688924169046.336, "dur": 0.249, + "args": { + "External id": 757754,"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": 688924169050.679, "dur": 0.154, + "args": { + "External id": 757755,"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": 688924169052.255, "dur": 0.153, + "args": { + "External id": 757756,"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": 688924169053.850, "dur": 2.316, + "args": { + "External id": 757757,"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": 688924169073.508, "dur": 24.671, + "args": { + "External id": 757758,"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": 688924169161.579, "dur": 471.565, + "args": { + "External id": 757759,"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": 688924169189.717, "dur": 437.969, + "args": { + "External id": 757760,"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": 688924169275.899, "dur": 343.415, + "args": { + "External id": 757761,"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": 688924169697.825, "dur": 3.681, + "args": { + "External id": 757762,"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": 688924169834.941, "dur": 7573.958, + "args": { + "External id": 757763,"Record function id": 0, "Ev Idx": 5618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924169943.585, "dur": 7.431, + "args": { + "External id": 757764,"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": 688924169954.169, "dur": 1.457, + "args": { + "External id": 757765,"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": 688924169957.209, "dur": 2.527, + "args": { + "External id": 757766,"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": 688924169961.387, "dur": 0.677, + "args": { + "External id": 757767,"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": 688924169963.619, "dur": 1.054, + "args": { + "External id": 757768,"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": 688924169966.299, "dur": 0.815, + "args": { + "External id": 757769,"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": 688924169969.050, "dur": 0.839, + "args": { + "External id": 757770,"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": 688924169972.203, "dur": 2.075, + "args": { + "External id": 757771,"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": 688924169976.441, "dur": 1.116, + "args": { + "External id": 757772,"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": 688924169979.368, "dur": 0.747, + "args": { + "External id": 757773,"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": 688924169999.768, "dur": 7371.082, + "args": { + "External id": 757774,"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": 688924170017.068, "dur": 7346.991, + "args": { + "External id": 757775,"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": 688924170033.268, "dur": 15.524, + "args": { + "External id": 757776,"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": 688924170052.040, "dur": 7277.975, + "args": { + "External id": 757777,"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": 688924170054.660, "dur": 7274.791, + "args": { + "External id": 757778,"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": 688924170062.086, "dur": 6.928, + "args": { + "External id": 757779,"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": 688924170070.972, "dur": 7255.326, + "args": { + "External id": 757780,"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": 688924177549.833, "dur": 31.871, + "args": { + "External id": 757781,"Sequence number": 8961981, "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": 688924177549.833, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924177569.678, "dur": 7.574, + "args": { + "External id": 757782,"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": 688924177573.052, "dur": 3.983, + "args": { + "External id": 757783,"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": 688924177648.999, "dur": 117.440, + "args": { + "External id": 757784,"Record function id": 0, "Ev Idx": 5639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924177769.733, "dur": 1073.060, + "args": { + "External id": 757785,"Record function id": 0, "Ev Idx": 5640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924177830.948, "dur": 996.236, + "args": { + "External id": 757786,"Sequence number": 8961982, "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": 688924177830.948, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924177896.515, "dur": 47.406, + "args": { + "External id": 757787,"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": 688924177957.100, "dur": 96.078, + "args": { + "External id": 757788,"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": 688924178062.413, "dur": 35.339, + "args": { + "External id": 757789,"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": 688924178107.037, "dur": 29.813, + "args": { + "External id": 757790,"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": 688924178159.197, "dur": 26.087, + "args": { + "External id": 757791,"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": 688924178202.465, "dur": 14.897, + "args": { + "External id": 757792,"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": 688924178236.445, "dur": 131.288, + "args": { + "External id": 757793,"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": 688924178285.565, "dur": 11.898, + "args": { + "External id": 757794,"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": 688924178290.544, "dur": 6.168, + "args": { + "External id": 757795,"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": 688924178300.531, "dur": 6.360, + "args": { + "External id": 757796,"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": 688924178308.893, "dur": 1.186, + "args": { + "External id": 757797,"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": 688924178312.328, "dur": 4.438, + "args": { + "External id": 757798,"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": 688924178378.426, "dur": 43.677, + "args": { + "External id": 757799,"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": 688924178450.314, "dur": 29.656, + "args": { + "External id": 757800,"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": 688924178489.230, "dur": 36.833, + "args": { + "External id": 757801,"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": 688924178534.584, "dur": 32.524, + "args": { + "External id": 757802,"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": 688924178588.106, "dur": 25.244, + "args": { + "External id": 757803,"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": 688924178618.519, "dur": 72.693, + "args": { + "External id": 757804,"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": 688924178716.150, "dur": 24.269, + "args": { + "External id": 757805,"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": 688924178912.088, "dur": 79.092, + "args": { + "External id": 757806,"Record function id": 0, "Ev Idx": 5661 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924179067.572, "dur": 50.236, + "args": { + "External id": 757807,"Record function id": 0, "Ev Idx": 5662 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 4183436, "tid": 4183436, + "ts": 688924179127.602, "dur": 9214.068, + "args": { + "External id": 757808,"Record function id": 0, "Ev Idx": 5663 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 4183436, "tid": 4183436, + "ts": 688924179135.455, "dur": 955.834, + "args": { + "External id": 757809,"Record function id": 0, "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924179225.161, "dur": 9.645, + "args": { + "External id": 757810,"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": 688924179248.409, "dur": 42.717, + "args": { + "External id": 757811,"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": 688924179254.184, "dur": 2.059, + "args": { + "External id": 757812,"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": 688924179261.927, "dur": 0.440, + "args": { + "External id": 757813,"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": 688924179264.639, "dur": 0.701, + "args": { + "External id": 757814,"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": 688924179267.282, "dur": 0.314, + "args": { + "External id": 757815,"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": 688924179271.338, "dur": 0.441, + "args": { + "External id": 757816,"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": 688924179273.671, "dur": 0.471, + "args": { + "External id": 757817,"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": 688924179275.659, "dur": 4.313, + "args": { + "External id": 757818,"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": 688924179281.953, "dur": 0.400, + "args": { + "External id": 757819,"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": 688924179283.916, "dur": 0.184, + "args": { + "External id": 757820,"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": 688924179305.823, "dur": 44.871, + "args": { + "External id": 757821,"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": 688924179385.254, "dur": 121.169, + "args": { + "External id": 757822,"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": 688924179396.454, "dur": 6.396, + "args": { + "External id": 757823,"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": 688924179408.104, "dur": 11.228, + "args": { + "External id": 757824,"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": 688924179412.646, "dur": 6.116, + "args": { + "External id": 757825,"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": 688924179416.851, "dur": 0.633, + "args": { + "External id": 757826,"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": 688924179426.623, "dur": 33.339, + "args": { + "External id": 757827,"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": 688924179429.326, "dur": 0.333, + "args": { + "External id": 757828,"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": 688924179431.607, "dur": 2.541, + "args": { + "External id": 757829,"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": 688924179435.937, "dur": 0.424, + "args": { + "External id": 757830,"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": 688924179438.113, "dur": 1.528, + "args": { + "External id": 757831,"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": 688924179443.211, "dur": 0.183, + "args": { + "External id": 757832,"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": 688924179445.122, "dur": 0.364, + "args": { + "External id": 757833,"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": 688924179447.121, "dur": 0.348, + "args": { + "External id": 757834,"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": 688924179451.347, "dur": 0.616, + "args": { + "External id": 757835,"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": 688924179453.524, "dur": 0.427, + "args": { + "External id": 757836,"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": 688924179472.753, "dur": 26.001, + "args": { + "External id": 757837,"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": 688924179559.035, "dur": 428.788, + "args": { + "External id": 757838,"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": 688924179589.584, "dur": 391.910, + "args": { + "External id": 757839,"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": 688924179599.926, "dur": 375.052, + "args": { + "External id": 757840,"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": 688924180012.709, "dur": 2.492, + "args": { + "External id": 757841,"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": 688924180114.116, "dur": 8025.002, + "args": { + "External id": 757842,"Record function id": 0, "Ev Idx": 5697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924180224.814, "dur": 6.952, + "args": { + "External id": 757843,"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": 688924180235.041, "dur": 1.676, + "args": { + "External id": 757844,"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": 688924180238.408, "dur": 2.404, + "args": { + "External id": 757845,"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": 688924180242.430, "dur": 0.836, + "args": { + "External id": 757846,"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": 688924180244.999, "dur": 1.353, + "args": { + "External id": 757847,"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": 688924180248.009, "dur": 1.201, + "args": { + "External id": 757848,"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": 688924180251.145, "dur": 0.831, + "args": { + "External id": 757849,"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": 688924180254.223, "dur": 2.806, + "args": { + "External id": 757850,"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": 688924180258.795, "dur": 0.929, + "args": { + "External id": 757851,"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": 688924180261.346, "dur": 0.786, + "args": { + "External id": 757852,"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": 688924180280.992, "dur": 7817.690, + "args": { + "External id": 757853,"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": 688924180297.777, "dur": 7794.328, + "args": { + "External id": 757854,"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": 688924180319.025, "dur": 15.703, + "args": { + "External id": 757855,"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": 688924180337.461, "dur": 7721.197, + "args": { + "External id": 757856,"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": 688924180340.440, "dur": 7717.564, + "args": { + "External id": 757857,"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": 688924180346.708, "dur": 5.446, + "args": { + "External id": 757858,"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": 688924180354.302, "dur": 7700.698, + "args": { + "External id": 757859,"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": 688924188281.648, "dur": 34.401, + "args": { + "External id": 757860,"Sequence number": 8961983, "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": 688924188281.648, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924188302.521, "dur": 7.939, + "args": { + "External id": 757861,"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": 688924188305.874, "dur": 4.315, + "args": { + "External id": 757862,"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": 688924188382.936, "dur": 91.681, + "args": { + "External id": 757863,"Record function id": 0, "Ev Idx": 5718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924188476.273, "dur": 1084.883, + "args": { + "External id": 757864,"Record function id": 0, "Ev Idx": 5719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924188517.669, "dur": 1028.789, + "args": { + "External id": 757865,"Sequence number": 8961984, "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": 688924188517.669, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924188583.469, "dur": 41.879, + "args": { + "External id": 757866,"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": 688924188638.276, "dur": 135.326, + "args": { + "External id": 757867,"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": 688924188803.163, "dur": 41.823, + "args": { + "External id": 757868,"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": 688924188856.492, "dur": 29.978, + "args": { + "External id": 757869,"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": 688924188912.192, "dur": 29.031, + "args": { + "External id": 757870,"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": 688924188958.649, "dur": 16.407, + "args": { + "External id": 757871,"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": 688924188995.038, "dur": 132.705, + "args": { + "External id": 757872,"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": 688924189045.831, "dur": 12.233, + "args": { + "External id": 757873,"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": 688924189051.242, "dur": 6.049, + "args": { + "External id": 757874,"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": 688924189060.942, "dur": 5.775, + "args": { + "External id": 757875,"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": 688924189068.033, "dur": 1.257, + "args": { + "External id": 757876,"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": 688924189071.532, "dur": 4.411, + "args": { + "External id": 757877,"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": 688924189137.335, "dur": 46.957, + "args": { + "External id": 757878,"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": 688924189214.414, "dur": 27.731, + "args": { + "External id": 757879,"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": 688924189251.351, "dur": 38.141, + "args": { + "External id": 757880,"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": 688924189299.909, "dur": 31.649, + "args": { + "External id": 757881,"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": 688924189352.719, "dur": 25.489, + "args": { + "External id": 757882,"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": 688924189383.636, "dur": 47.209, + "args": { + "External id": 757883,"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": 688924189450.361, "dur": 19.330, + "args": { + "External id": 757884,"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": 688924189627.230, "dur": 122.058, + "args": { + "External id": 757885,"Record function id": 0, "Ev Idx": 5740 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924189847.558, "dur": 50.762, + "args": { + "External id": 757886,"Record function id": 0, "Ev Idx": 5741 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 4183436, "tid": 4183436, + "ts": 688924189909.010, "dur": 8660.658, + "args": { + "External id": 757887,"Record function id": 0, "Ev Idx": 5742 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 4183436, "tid": 4183436, + "ts": 688924189916.959, "dur": 949.507, + "args": { + "External id": 757888,"Record function id": 0, "Ev Idx": 5743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924190002.360, "dur": 9.953, + "args": { + "External id": 757889,"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": 688924190029.212, "dur": 43.914, + "args": { + "External id": 757890,"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": 688924190035.508, "dur": 2.427, + "args": { + "External id": 757891,"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": 688924190042.541, "dur": 0.643, + "args": { + "External id": 757892,"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": 688924190045.042, "dur": 0.337, + "args": { + "External id": 757893,"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": 688924190047.370, "dur": 2.862, + "args": { + "External id": 757894,"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": 688924190052.012, "dur": 0.403, + "args": { + "External id": 757895,"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": 688924190054.054, "dur": 0.357, + "args": { + "External id": 757896,"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": 688924190058.811, "dur": 1.692, + "args": { + "External id": 757897,"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": 688924190062.673, "dur": 0.487, + "args": { + "External id": 757898,"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": 688924190064.953, "dur": 0.306, + "args": { + "External id": 757899,"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": 688924190084.695, "dur": 46.591, + "args": { + "External id": 757900,"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": 688924190165.327, "dur": 119.213, + "args": { + "External id": 757901,"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": 688924190175.917, "dur": 4.145, + "args": { + "External id": 757902,"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": 688924190185.398, "dur": 13.732, + "args": { + "External id": 757903,"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": 688924190190.083, "dur": 8.533, + "args": { + "External id": 757904,"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": 688924190194.192, "dur": 3.050, + "args": { + "External id": 757905,"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": 688924190206.948, "dur": 31.468, + "args": { + "External id": 757906,"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": 688924190209.392, "dur": 0.393, + "args": { + "External id": 757907,"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": 688924190211.741, "dur": 0.455, + "args": { + "External id": 757908,"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": 688924190213.885, "dur": 0.309, + "args": { + "External id": 757909,"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": 688924190217.709, "dur": 1.373, + "args": { + "External id": 757910,"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": 688924190220.774, "dur": 0.250, + "args": { + "External id": 757911,"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": 688924190222.398, "dur": 2.592, + "args": { + "External id": 757912,"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": 688924190226.462, "dur": 0.932, + "args": { + "External id": 757913,"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": 688924190229.086, "dur": 0.308, + "args": { + "External id": 757914,"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": 688924190233.000, "dur": 0.349, + "args": { + "External id": 757915,"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": 688924190250.029, "dur": 25.876, + "args": { + "External id": 757916,"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": 688924190337.975, "dur": 407.984, + "args": { + "External id": 757917,"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": 688924190365.690, "dur": 374.832, + "args": { + "External id": 757918,"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": 688924190376.377, "dur": 358.112, + "args": { + "External id": 757919,"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": 688924190769.872, "dur": 3.018, + "args": { + "External id": 757920,"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": 688924190891.199, "dur": 7482.397, + "args": { + "External id": 757921,"Record function id": 0, "Ev Idx": 5776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924191002.344, "dur": 6.889, + "args": { + "External id": 757922,"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": 688924191012.771, "dur": 1.073, + "args": { + "External id": 757923,"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": 688924191015.523, "dur": 1.315, + "args": { + "External id": 757924,"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": 688924191018.714, "dur": 0.995, + "args": { + "External id": 757925,"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": 688924191021.155, "dur": 1.608, + "args": { + "External id": 757926,"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": 688924191024.433, "dur": 1.247, + "args": { + "External id": 757927,"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": 688924191027.605, "dur": 1.324, + "args": { + "External id": 757928,"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": 688924191030.952, "dur": 2.684, + "args": { + "External id": 757929,"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": 688924191035.321, "dur": 1.074, + "args": { + "External id": 757930,"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": 688924191038.069, "dur": 1.607, + "args": { + "External id": 757931,"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": 688924191059.060, "dur": 7276.901, + "args": { + "External id": 757932,"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": 688924191076.589, "dur": 7252.314, + "args": { + "External id": 757933,"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": 688924191097.484, "dur": 15.026, + "args": { + "External id": 757934,"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": 688924191115.386, "dur": 7182.956, + "args": { + "External id": 757935,"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": 688924191118.135, "dur": 7179.640, + "args": { + "External id": 757936,"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": 688924191124.680, "dur": 7.126, + "args": { + "External id": 757937,"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": 688924191133.740, "dur": 7161.162, + "args": { + "External id": 757938,"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": 688924198511.894, "dur": 32.438, + "args": { + "External id": 757939,"Sequence number": 8961985, "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": 688924198511.894, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924198530.499, "dur": 8.714, + "args": { + "External id": 757940,"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": 688924198534.262, "dur": 4.684, + "args": { + "External id": 757941,"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": 688924198610.580, "dur": 127.014, + "args": { + "External id": 757942,"Record function id": 0, "Ev Idx": 5797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924198740.661, "dur": 1107.708, + "args": { + "External id": 757943,"Record function id": 0, "Ev Idx": 5798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924198785.054, "dur": 1047.018, + "args": { + "External id": 757944,"Sequence number": 8961986, "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": 688924198785.054, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924198869.506, "dur": 45.674, + "args": { + "External id": 757945,"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": 688924198929.186, "dur": 94.078, + "args": { + "External id": 757946,"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": 688924199032.853, "dur": 35.733, + "args": { + "External id": 757947,"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": 688924199077.937, "dur": 29.437, + "args": { + "External id": 757948,"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": 688924199130.382, "dur": 26.086, + "args": { + "External id": 757949,"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": 688924199173.452, "dur": 13.864, + "args": { + "External id": 757950,"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": 688924199205.927, "dur": 132.788, + "args": { + "External id": 757951,"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": 688924199259.200, "dur": 11.831, + "args": { + "External id": 757952,"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": 688924199264.238, "dur": 5.749, + "args": { + "External id": 757953,"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": 688924199273.592, "dur": 6.630, + "args": { + "External id": 757954,"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": 688924199281.482, "dur": 1.870, + "args": { + "External id": 757955,"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": 688924199285.839, "dur": 3.618, + "args": { + "External id": 757956,"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": 688924199350.004, "dur": 42.187, + "args": { + "External id": 757957,"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": 688924199420.557, "dur": 29.725, + "args": { + "External id": 757958,"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": 688924199458.328, "dur": 38.516, + "args": { + "External id": 757959,"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": 688924199505.104, "dur": 32.113, + "args": { + "External id": 757960,"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": 688924199566.402, "dur": 25.666, + "args": { + "External id": 757961,"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": 688924199600.532, "dur": 49.431, + "args": { + "External id": 757962,"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": 688924199721.542, "dur": 24.135, + "args": { + "External id": 757963,"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": 688924199917.558, "dur": 80.129, + "args": { + "External id": 757964,"Record function id": 0, "Ev Idx": 5819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924200072.712, "dur": 51.663, + "args": { + "External id": 757965,"Record function id": 0, "Ev Idx": 5820 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 4183436, "tid": 4183436, + "ts": 688924200133.638, "dur": 8611.583, + "args": { + "External id": 757966,"Record function id": 0, "Ev Idx": 5821 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 4183436, "tid": 4183436, + "ts": 688924200141.301, "dur": 977.755, + "args": { + "External id": 757967,"Record function id": 0, "Ev Idx": 5822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924200228.584, "dur": 9.461, + "args": { + "External id": 757968,"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": 688924200251.051, "dur": 37.171, + "args": { + "External id": 757969,"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": 688924200256.716, "dur": 2.397, + "args": { + "External id": 757970,"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": 688924200263.931, "dur": 0.695, + "args": { + "External id": 757971,"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": 688924200265.540, "dur": 0.622, + "args": { + "External id": 757972,"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": 688924200267.678, "dur": 0.845, + "args": { + "External id": 757973,"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": 688924200272.325, "dur": 0.789, + "args": { + "External id": 757974,"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": 688924200274.452, "dur": 0.519, + "args": { + "External id": 757975,"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": 688924200275.805, "dur": 2.270, + "args": { + "External id": 757976,"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": 688924200279.109, "dur": 0.597, + "args": { + "External id": 757977,"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": 688924200280.731, "dur": 0.635, + "args": { + "External id": 757978,"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": 688924200299.636, "dur": 45.811, + "args": { + "External id": 757979,"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": 688924200378.640, "dur": 119.938, + "args": { + "External id": 757980,"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": 688924200389.185, "dur": 4.894, + "args": { + "External id": 757981,"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": 688924200399.415, "dur": 11.215, + "args": { + "External id": 757982,"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": 688924200404.308, "dur": 5.950, + "args": { + "External id": 757983,"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": 688924200407.872, "dur": 1.033, + "args": { + "External id": 757984,"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": 688924200417.392, "dur": 33.568, + "args": { + "External id": 757985,"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": 688924200419.601, "dur": 2.739, + "args": { + "External id": 757986,"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": 688924200423.977, "dur": 0.642, + "args": { + "External id": 757987,"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": 688924200426.015, "dur": 0.650, + "args": { + "External id": 757988,"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": 688924200430.665, "dur": 0.534, + "args": { + "External id": 757989,"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": 688924200432.854, "dur": 0.778, + "args": { + "External id": 757990,"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": 688924200434.909, "dur": 0.731, + "args": { + "External id": 757991,"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": 688924200438.728, "dur": 0.847, + "args": { + "External id": 757992,"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": 688924200440.887, "dur": 0.571, + "args": { + "External id": 757993,"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": 688924200442.933, "dur": 3.056, + "args": { + "External id": 757994,"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": 688924200464.394, "dur": 25.936, + "args": { + "External id": 757995,"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": 688924200553.111, "dur": 459.977, + "args": { + "External id": 757996,"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": 688924200579.820, "dur": 426.568, + "args": { + "External id": 757997,"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": 688924200590.144, "dur": 410.313, + "args": { + "External id": 757998,"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": 688924201037.691, "dur": 2.497, + "args": { + "External id": 757999,"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": 688924201143.226, "dur": 7377.799, + "args": { + "External id": 758000,"Record function id": 0, "Ev Idx": 5855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924201255.150, "dur": 7.623, + "args": { + "External id": 758001,"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": 688924201266.213, "dur": 1.471, + "args": { + "External id": 758002,"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": 688924201269.400, "dur": 1.458, + "args": { + "External id": 758003,"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": 688924201272.436, "dur": 1.785, + "args": { + "External id": 758004,"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": 688924201275.957, "dur": 1.095, + "args": { + "External id": 758005,"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": 688924201279.065, "dur": 1.427, + "args": { + "External id": 758006,"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": 688924201282.492, "dur": 1.077, + "args": { + "External id": 758007,"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": 688924201285.476, "dur": 2.495, + "args": { + "External id": 758008,"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": 688924201289.711, "dur": 0.920, + "args": { + "External id": 758009,"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": 688924201292.484, "dur": 1.187, + "args": { + "External id": 758010,"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": 688924201312.122, "dur": 7169.953, + "args": { + "External id": 758011,"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": 688924201328.433, "dur": 7146.929, + "args": { + "External id": 758012,"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": 688924201347.504, "dur": 15.307, + "args": { + "External id": 758013,"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": 688924201365.646, "dur": 7077.278, + "args": { + "External id": 758014,"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": 688924201368.147, "dur": 7074.229, + "args": { + "External id": 758015,"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": 688924201374.092, "dur": 7.470, + "args": { + "External id": 758016,"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": 688924201383.318, "dur": 7056.143, + "args": { + "External id": 758017,"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": 688924208686.972, "dur": 31.631, + "args": { + "External id": 758018,"Sequence number": 8961987, "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": 688924208686.972, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924208704.689, "dur": 8.374, + "args": { + "External id": 758019,"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": 688924208707.914, "dur": 4.722, + "args": { + "External id": 758020,"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": 688924208798.321, "dur": 92.502, + "args": { + "External id": 758021,"Record function id": 0, "Ev Idx": 5876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924208893.070, "dur": 1113.700, + "args": { + "External id": 758022,"Record function id": 0, "Ev Idx": 5877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924208938.218, "dur": 1053.006, + "args": { + "External id": 758023,"Sequence number": 8961988, "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": 688924208938.218, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924209008.883, "dur": 45.663, + "args": { + "External id": 758024,"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": 688924209068.937, "dur": 96.868, + "args": { + "External id": 758025,"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": 688924209174.354, "dur": 36.151, + "args": { + "External id": 758026,"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": 688924209220.764, "dur": 29.552, + "args": { + "External id": 758027,"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": 688924209274.634, "dur": 27.952, + "args": { + "External id": 758028,"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": 688924209321.312, "dur": 16.814, + "args": { + "External id": 758029,"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": 688924209356.848, "dur": 132.750, + "args": { + "External id": 758030,"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": 688924209406.584, "dur": 11.887, + "args": { + "External id": 758031,"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": 688924209411.881, "dur": 5.735, + "args": { + "External id": 758032,"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": 688924209421.365, "dur": 7.432, + "args": { + "External id": 758033,"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": 688924209430.159, "dur": 1.748, + "args": { + "External id": 758034,"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": 688924209434.350, "dur": 3.413, + "args": { + "External id": 758035,"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": 688924209501.193, "dur": 42.954, + "args": { + "External id": 758036,"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": 688924209575.823, "dur": 30.537, + "args": { + "External id": 758037,"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": 688924209614.448, "dur": 79.443, + "args": { + "External id": 758038,"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": 688924209708.197, "dur": 37.865, + "args": { + "External id": 758039,"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": 688924209769.099, "dur": 45.386, + "args": { + "External id": 758040,"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": 688924209822.929, "dur": 52.356, + "args": { + "External id": 758041,"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": 688924209896.698, "dur": 19.949, + "args": { + "External id": 758042,"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": 688924210076.348, "dur": 82.169, + "args": { + "External id": 758043,"Record function id": 0, "Ev Idx": 5898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924210235.359, "dur": 48.000, + "args": { + "External id": 758044,"Record function id": 0, "Ev Idx": 5899 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 4183436, "tid": 4183436, + "ts": 688924210293.044, "dur": 8435.553, + "args": { + "External id": 758045,"Record function id": 0, "Ev Idx": 5900 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 4183436, "tid": 4183436, + "ts": 688924210301.113, "dur": 958.060, + "args": { + "External id": 758046,"Record function id": 0, "Ev Idx": 5901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924210387.235, "dur": 8.342, + "args": { + "External id": 758047,"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": 688924210408.957, "dur": 76.021, + "args": { + "External id": 758048,"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": 688924210444.825, "dur": 3.904, + "args": { + "External id": 758049,"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": 688924210453.418, "dur": 0.749, + "args": { + "External id": 758050,"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": 688924210455.950, "dur": 0.817, + "args": { + "External id": 758051,"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": 688924210458.505, "dur": 3.116, + "args": { + "External id": 758052,"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": 688924210463.060, "dur": 0.686, + "args": { + "External id": 758053,"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": 688924210467.080, "dur": 0.656, + "args": { + "External id": 758054,"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": 688924210470.767, "dur": 0.846, + "args": { + "External id": 758055,"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": 688924210472.799, "dur": 0.593, + "args": { + "External id": 758056,"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": 688924210474.942, "dur": 2.487, + "args": { + "External id": 758057,"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": 688924210496.831, "dur": 41.633, + "args": { + "External id": 758058,"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": 688924210572.452, "dur": 162.095, + "args": { + "External id": 758059,"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": 688924210583.143, "dur": 4.988, + "args": { + "External id": 758060,"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": 688924210593.782, "dur": 10.530, + "args": { + "External id": 758061,"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": 688924210598.465, "dur": 5.468, + "args": { + "External id": 758062,"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": 688924210601.929, "dur": 0.750, + "args": { + "External id": 758063,"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": 688924210611.592, "dur": 30.043, + "args": { + "External id": 758064,"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": 688924210613.296, "dur": 0.922, + "args": { + "External id": 758065,"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": 688924210615.616, "dur": 0.705, + "args": { + "External id": 758066,"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": 688924210617.623, "dur": 2.810, + "args": { + "External id": 758067,"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": 688924210621.685, "dur": 0.604, + "args": { + "External id": 758068,"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": 688924210623.495, "dur": 0.739, + "args": { + "External id": 758069,"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": 688924210627.965, "dur": 0.690, + "args": { + "External id": 758070,"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": 688924210630.170, "dur": 0.434, + "args": { + "External id": 758071,"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": 688924210631.988, "dur": 0.926, + "args": { + "External id": 758072,"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": 688924210635.825, "dur": 0.605, + "args": { + "External id": 758073,"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": 688924210694.638, "dur": 29.502, + "args": { + "External id": 758074,"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": 688924210808.640, "dur": 358.356, + "args": { + "External id": 758075,"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": 688924210837.995, "dur": 324.112, + "args": { + "External id": 758076,"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": 688924210849.614, "dur": 307.046, + "args": { + "External id": 758077,"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": 688924211186.343, "dur": 2.166, + "args": { + "External id": 758078,"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": 688924211280.260, "dur": 7217.502, + "args": { + "External id": 758079,"Record function id": 0, "Ev Idx": 5934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924211385.034, "dur": 6.873, + "args": { + "External id": 758080,"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": 688924211394.825, "dur": 1.829, + "args": { + "External id": 758081,"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": 688924211398.229, "dur": 1.515, + "args": { + "External id": 758082,"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": 688924211401.283, "dur": 1.301, + "args": { + "External id": 758083,"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": 688924211404.528, "dur": 1.182, + "args": { + "External id": 758084,"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": 688924211407.408, "dur": 1.592, + "args": { + "External id": 758085,"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": 688924211411.112, "dur": 1.571, + "args": { + "External id": 758086,"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": 688924211414.550, "dur": 2.704, + "args": { + "External id": 758087,"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": 688924211418.987, "dur": 1.327, + "args": { + "External id": 758088,"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": 688924211422.221, "dur": 1.005, + "args": { + "External id": 758089,"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": 688924211441.521, "dur": 7017.221, + "args": { + "External id": 758090,"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": 688924211457.109, "dur": 6994.905, + "args": { + "External id": 758091,"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": 688924211472.261, "dur": 13.482, + "args": { + "External id": 758092,"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": 688924211488.658, "dur": 6926.472, + "args": { + "External id": 758093,"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": 688924211491.805, "dur": 6922.751, + "args": { + "External id": 758094,"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": 688924211497.416, "dur": 7.780, + "args": { + "External id": 758095,"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": 688924211507.090, "dur": 6904.412, + "args": { + "External id": 758096,"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": 688924218645.326, "dur": 55.132, + "args": { + "External id": 758097,"Sequence number": 8961989, "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": 688924218645.326, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924218685.751, "dur": 9.378, + "args": { + "External id": 758098,"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": 688924218688.920, "dur": 5.750, + "args": { + "External id": 758099,"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": 688924218770.206, "dur": 103.077, + "args": { + "External id": 758100,"Record function id": 0, "Ev Idx": 5955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924218876.712, "dur": 1097.527, + "args": { + "External id": 758101,"Record function id": 0, "Ev Idx": 5956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924218919.544, "dur": 1040.063, + "args": { + "External id": 758102,"Sequence number": 8961990, "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": 688924218919.544, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924218988.680, "dur": 47.088, + "args": { + "External id": 758103,"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": 688924219048.788, "dur": 97.638, + "args": { + "External id": 758104,"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": 688924219155.847, "dur": 35.914, + "args": { + "External id": 758105,"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": 688924219201.272, "dur": 29.568, + "args": { + "External id": 758106,"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": 688924219252.882, "dur": 27.445, + "args": { + "External id": 758107,"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": 688924219298.269, "dur": 13.970, + "args": { + "External id": 758108,"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": 688924219330.281, "dur": 136.317, + "args": { + "External id": 758109,"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": 688924219388.540, "dur": 11.910, + "args": { + "External id": 758110,"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": 688924219393.687, "dur": 5.982, + "args": { + "External id": 758111,"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": 688924219403.067, "dur": 7.062, + "args": { + "External id": 758112,"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": 688924219411.645, "dur": 1.517, + "args": { + "External id": 758113,"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": 688924219415.328, "dur": 3.057, + "args": { + "External id": 758114,"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": 688924219478.508, "dur": 41.848, + "args": { + "External id": 758115,"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": 688924219551.076, "dur": 30.343, + "args": { + "External id": 758116,"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": 688924219589.681, "dur": 37.639, + "args": { + "External id": 758117,"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": 688924219636.316, "dur": 76.171, + "args": { + "External id": 758118,"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": 688924219739.717, "dur": 28.081, + "args": { + "External id": 758119,"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": 688924219774.372, "dur": 73.601, + "args": { + "External id": 758120,"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": 688924219872.628, "dur": 19.045, + "args": { + "External id": 758121,"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": 688924220042.394, "dur": 81.903, + "args": { + "External id": 758122,"Record function id": 0, "Ev Idx": 5977 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924220202.853, "dur": 48.966, + "args": { + "External id": 758123,"Record function id": 0, "Ev Idx": 5978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 4183436, "tid": 4183436, + "ts": 688924220261.423, "dur": 8756.630, + "args": { + "External id": 758124,"Record function id": 0, "Ev Idx": 5979 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 4183436, "tid": 4183436, + "ts": 688924220270.093, "dur": 976.951, + "args": { + "External id": 758125,"Record function id": 0, "Ev Idx": 5980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924220354.770, "dur": 9.065, + "args": { + "External id": 758126,"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": 688924220377.732, "dur": 37.530, + "args": { + "External id": 758127,"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": 688924220383.505, "dur": 2.173, + "args": { + "External id": 758128,"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": 688924220390.695, "dur": 0.749, + "args": { + "External id": 758129,"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": 688924220392.743, "dur": 0.488, + "args": { + "External id": 758130,"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": 688924220394.670, "dur": 0.738, + "args": { + "External id": 758131,"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": 688924220398.634, "dur": 0.662, + "args": { + "External id": 758132,"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": 688924220400.843, "dur": 0.601, + "args": { + "External id": 758133,"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": 688924220402.394, "dur": 2.216, + "args": { + "External id": 758134,"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": 688924220405.864, "dur": 0.421, + "args": { + "External id": 758135,"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": 688924220407.571, "dur": 0.672, + "args": { + "External id": 758136,"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": 688924220427.243, "dur": 41.481, + "args": { + "External id": 758137,"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": 688924220500.248, "dur": 203.901, + "args": { + "External id": 758138,"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": 688924220510.949, "dur": 5.068, + "args": { + "External id": 758139,"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": 688924220521.589, "dur": 11.597, + "args": { + "External id": 758140,"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": 688924220526.584, "dur": 6.211, + "args": { + "External id": 758141,"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": 688924220530.275, "dur": 1.216, + "args": { + "External id": 758142,"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": 688924220539.595, "dur": 31.680, + "args": { + "External id": 758143,"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": 688924220541.549, "dur": 2.786, + "args": { + "External id": 758144,"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": 688924220546.157, "dur": 0.602, + "args": { + "External id": 758145,"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": 688924220547.814, "dur": 0.703, + "args": { + "External id": 758146,"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": 688924220552.115, "dur": 0.906, + "args": { + "External id": 758147,"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": 688924220554.080, "dur": 0.937, + "args": { + "External id": 758148,"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": 688924220556.711, "dur": 0.506, + "args": { + "External id": 758149,"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": 688924220560.140, "dur": 0.991, + "args": { + "External id": 758150,"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": 688924220562.872, "dur": 0.627, + "args": { + "External id": 758151,"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": 688924220564.242, "dur": 2.513, + "args": { + "External id": 758152,"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": 688924220625.578, "dur": 25.097, + "args": { + "External id": 758153,"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": 688924220766.302, "dur": 383.810, + "args": { + "External id": 758154,"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": 688924220810.393, "dur": 334.234, + "args": { + "External id": 758155,"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": 688924220824.253, "dur": 314.781, + "args": { + "External id": 758156,"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": 688924221170.676, "dur": 2.599, + "args": { + "External id": 758157,"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": 688924221269.445, "dur": 7541.408, + "args": { + "External id": 758158,"Record function id": 0, "Ev Idx": 6013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924221375.247, "dur": 6.903, + "args": { + "External id": 758159,"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": 688924221385.283, "dur": 1.555, + "args": { + "External id": 758160,"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": 688924221388.537, "dur": 1.853, + "args": { + "External id": 758161,"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": 688924221391.793, "dur": 1.580, + "args": { + "External id": 758162,"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": 688924221394.951, "dur": 1.320, + "args": { + "External id": 758163,"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": 688924221397.998, "dur": 1.358, + "args": { + "External id": 758164,"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": 688924221401.141, "dur": 1.102, + "args": { + "External id": 758165,"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": 688924221404.031, "dur": 2.499, + "args": { + "External id": 758166,"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": 688924221408.144, "dur": 1.011, + "args": { + "External id": 758167,"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": 688924221411.051, "dur": 1.574, + "args": { + "External id": 758168,"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": 688924221431.980, "dur": 7327.787, + "args": { + "External id": 758169,"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": 688924221448.285, "dur": 7304.176, + "args": { + "External id": 758170,"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": 688924221462.726, "dur": 14.703, + "args": { + "External id": 758171,"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": 688924221480.449, "dur": 7239.221, + "args": { + "External id": 758172,"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": 688924221483.135, "dur": 7235.963, + "args": { + "External id": 758173,"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": 688924221489.717, "dur": 8.111, + "args": { + "External id": 758174,"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": 688924221499.551, "dur": 7216.499, + "args": { + "External id": 758175,"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": 688924228959.267, "dur": 33.303, + "args": { + "External id": 758176,"Sequence number": 8961991, "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": 688924228959.267, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924228978.451, "dur": 8.933, + "args": { + "External id": 758177,"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": 688924228981.978, "dur": 5.141, + "args": { + "External id": 758178,"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": 688924229057.734, "dur": 87.797, + "args": { + "External id": 758179,"Record function id": 0, "Ev Idx": 6034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924229147.587, "dur": 1138.952, + "args": { + "External id": 758180,"Record function id": 0, "Ev Idx": 6035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924229190.285, "dur": 1081.988, + "args": { + "External id": 758181,"Sequence number": 8961992, "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": 688924229190.285, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924229258.280, "dur": 43.377, + "args": { + "External id": 758182,"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": 688924229315.160, "dur": 94.906, + "args": { + "External id": 758183,"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": 688924229418.956, "dur": 35.385, + "args": { + "External id": 758184,"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": 688924229463.684, "dur": 30.220, + "args": { + "External id": 758185,"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": 688924229516.636, "dur": 25.865, + "args": { + "External id": 758186,"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": 688924229559.738, "dur": 14.886, + "args": { + "External id": 758187,"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": 688924229591.587, "dur": 216.771, + "args": { + "External id": 758188,"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": 688924229644.465, "dur": 68.577, + "args": { + "External id": 758189,"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": 688924229649.631, "dur": 61.864, + "args": { + "External id": 758190,"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": 688924229716.982, "dur": 6.273, + "args": { + "External id": 758191,"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": 688924229724.697, "dur": 1.577, + "args": { + "External id": 758192,"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": 688924229729.206, "dur": 2.990, + "args": { + "External id": 758193,"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": 688924229824.099, "dur": 57.328, + "args": { + "External id": 758194,"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": 688924229916.356, "dur": 31.997, + "args": { + "External id": 758195,"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": 688924229957.996, "dur": 39.086, + "args": { + "External id": 758196,"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": 688924230006.719, "dur": 45.914, + "args": { + "External id": 758197,"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": 688924230074.318, "dur": 27.445, + "args": { + "External id": 758198,"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": 688924230108.423, "dur": 43.918, + "args": { + "External id": 758199,"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": 688924230174.234, "dur": 19.328, + "args": { + "External id": 758200,"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": 688924230353.254, "dur": 80.246, + "args": { + "External id": 758201,"Record function id": 0, "Ev Idx": 6056 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924230509.631, "dur": 47.702, + "args": { + "External id": 758202,"Record function id": 0, "Ev Idx": 6057 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 4183436, "tid": 4183436, + "ts": 688924230566.353, "dur": 8621.355, + "args": { + "External id": 758203,"Record function id": 0, "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 4183436, "tid": 4183436, + "ts": 688924230574.566, "dur": 928.840, + "args": { + "External id": 758204,"Record function id": 0, "Ev Idx": 6059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924230697.318, "dur": 10.466, + "args": { + "External id": 758205,"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": 688924230723.274, "dur": 40.608, + "args": { + "External id": 758206,"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": 688924230729.382, "dur": 2.311, + "args": { + "External id": 758207,"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": 688924230736.904, "dur": 0.802, + "args": { + "External id": 758208,"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": 688924230739.379, "dur": 1.229, + "args": { + "External id": 758209,"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": 688924230742.397, "dur": 0.691, + "args": { + "External id": 758210,"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": 688924230745.893, "dur": 0.687, + "args": { + "External id": 758211,"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": 688924230748.037, "dur": 0.943, + "args": { + "External id": 758212,"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": 688924230750.248, "dur": 2.685, + "args": { + "External id": 758213,"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": 688924230754.654, "dur": 0.842, + "args": { + "External id": 758214,"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": 688924230756.637, "dur": 0.493, + "args": { + "External id": 758215,"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": 688924230778.894, "dur": 58.287, + "args": { + "External id": 758216,"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": 688924230874.783, "dur": 117.350, + "args": { + "External id": 758217,"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": 688924230886.489, "dur": 7.487, + "args": { + "External id": 758218,"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": 688924230899.146, "dur": 11.589, + "args": { + "External id": 758219,"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": 688924230903.897, "dur": 6.458, + "args": { + "External id": 758220,"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": 688924230907.667, "dur": 0.922, + "args": { + "External id": 758221,"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": 688924230917.966, "dur": 31.928, + "args": { + "External id": 758222,"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": 688924230920.041, "dur": 0.922, + "args": { + "External id": 758223,"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": 688924230922.946, "dur": 2.715, + "args": { + "External id": 758224,"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": 688924230927.106, "dur": 0.483, + "args": { + "External id": 758225,"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": 688924230929.047, "dur": 0.671, + "args": { + "External id": 758226,"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": 688924230934.001, "dur": 0.739, + "args": { + "External id": 758227,"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": 688924230936.339, "dur": 0.580, + "args": { + "External id": 758228,"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": 688924230938.408, "dur": 0.540, + "args": { + "External id": 758229,"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": 688924230942.087, "dur": 0.646, + "args": { + "External id": 758230,"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": 688924230943.870, "dur": 0.678, + "args": { + "External id": 758231,"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": 688924230960.630, "dur": 23.287, + "args": { + "External id": 758232,"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": 688924231048.393, "dur": 360.672, + "args": { + "External id": 758233,"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": 688924231075.589, "dur": 329.000, + "args": { + "External id": 758234,"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": 688924231086.095, "dur": 313.113, + "args": { + "External id": 758235,"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": 688924231429.348, "dur": 2.586, + "args": { + "External id": 758236,"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": 688924231526.547, "dur": 7454.785, + "args": { + "External id": 758237,"Record function id": 0, "Ev Idx": 6092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924231629.965, "dur": 6.263, + "args": { + "External id": 758238,"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": 688924231639.498, "dur": 1.413, + "args": { + "External id": 758239,"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": 688924231642.631, "dur": 1.382, + "args": { + "External id": 758240,"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": 688924231645.594, "dur": 1.468, + "args": { + "External id": 758241,"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": 688924231648.849, "dur": 1.572, + "args": { + "External id": 758242,"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": 688924231694.551, "dur": 1.903, + "args": { + "External id": 758243,"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": 688924231699.096, "dur": 1.028, + "args": { + "External id": 758244,"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": 688924231702.000, "dur": 2.700, + "args": { + "External id": 758245,"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": 688924231706.815, "dur": 1.166, + "args": { + "External id": 758246,"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": 688924231709.784, "dur": 1.299, + "args": { + "External id": 758247,"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": 688924231731.507, "dur": 7208.753, + "args": { + "External id": 758248,"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": 688924231748.310, "dur": 7184.975, + "args": { + "External id": 758249,"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": 688924231765.007, "dur": 15.412, + "args": { + "External id": 758250,"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": 688924231783.492, "dur": 7117.478, + "args": { + "External id": 758251,"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": 688924231801.007, "dur": 7099.321, + "args": { + "External id": 758252,"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": 688924231808.155, "dur": 8.700, + "args": { + "External id": 758253,"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": 688924231818.936, "dur": 7078.416, + "args": { + "External id": 758254,"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": 688924239131.348, "dur": 30.707, + "args": { + "External id": 758255,"Sequence number": 8961993, "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": 688924239131.348, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924239148.834, "dur": 8.061, + "args": { + "External id": 758256,"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": 688924239152.014, "dur": 4.596, + "args": { + "External id": 758257,"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": 688924239228.190, "dur": 90.853, + "args": { + "External id": 758258,"Record function id": 0, "Ev Idx": 6113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924239320.498, "dur": 1220.043, + "args": { + "External id": 758259,"Record function id": 0, "Ev Idx": 6114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924239361.285, "dur": 1163.329, + "args": { + "External id": 758260,"Sequence number": 8961994, "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": 688924239361.285, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924239427.140, "dur": 42.302, + "args": { + "External id": 758261,"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": 688924239482.914, "dur": 93.470, + "args": { + "External id": 758262,"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": 688924239585.265, "dur": 34.965, + "args": { + "External id": 758263,"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": 688924239629.267, "dur": 73.598, + "args": { + "External id": 758264,"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": 688924239740.187, "dur": 30.047, + "args": { + "External id": 758265,"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": 688924239801.977, "dur": 19.066, + "args": { + "External id": 758266,"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": 688924239841.089, "dur": 137.055, + "args": { + "External id": 758267,"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": 688924239896.531, "dur": 13.392, + "args": { + "External id": 758268,"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": 688924239902.237, "dur": 6.876, + "args": { + "External id": 758269,"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": 688924239912.333, "dur": 6.209, + "args": { + "External id": 758270,"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": 688924239919.917, "dur": 1.572, + "args": { + "External id": 758271,"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": 688924239924.099, "dur": 5.170, + "args": { + "External id": 758272,"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": 688924240077.003, "dur": 64.552, + "args": { + "External id": 758273,"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": 688924240178.386, "dur": 30.671, + "args": { + "External id": 758274,"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": 688924240217.823, "dur": 58.760, + "args": { + "External id": 758275,"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": 688924240285.978, "dur": 40.638, + "args": { + "External id": 758276,"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": 688924240349.418, "dur": 25.987, + "args": { + "External id": 758277,"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": 688924240381.880, "dur": 32.822, + "args": { + "External id": 758278,"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": 688924240435.809, "dur": 18.404, + "args": { + "External id": 758279,"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": 688924240608.846, "dur": 122.226, + "args": { + "External id": 758280,"Record function id": 0, "Ev Idx": 6135 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924240832.121, "dur": 52.766, + "args": { + "External id": 758281,"Record function id": 0, "Ev Idx": 6136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 4183436, "tid": 4183436, + "ts": 688924240895.305, "dur": 8601.693, + "args": { + "External id": 758282,"Record function id": 0, "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 4183436, "tid": 4183436, + "ts": 688924240905.024, "dur": 923.606, + "args": { + "External id": 758283,"Record function id": 0, "Ev Idx": 6138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924240991.030, "dur": 10.514, + "args": { + "External id": 758284,"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": 688924241015.599, "dur": 37.777, + "args": { + "External id": 758285,"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": 688924241021.551, "dur": 2.313, + "args": { + "External id": 758286,"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": 688924241029.126, "dur": 0.617, + "args": { + "External id": 758287,"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": 688924241030.756, "dur": 0.642, + "args": { + "External id": 758288,"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": 688924241032.928, "dur": 0.475, + "args": { + "External id": 758289,"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": 688924241036.425, "dur": 0.565, + "args": { + "External id": 758290,"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": 688924241038.384, "dur": 0.413, + "args": { + "External id": 758291,"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": 688924241040.019, "dur": 2.524, + "args": { + "External id": 758292,"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": 688924241043.856, "dur": 0.832, + "args": { + "External id": 758293,"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": 688924241045.655, "dur": 0.640, + "args": { + "External id": 758294,"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": 688924241064.754, "dur": 47.318, + "args": { + "External id": 758295,"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": 688924241144.296, "dur": 115.025, + "args": { + "External id": 758296,"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": 688924241155.055, "dur": 4.858, + "args": { + "External id": 758297,"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": 688924241164.915, "dur": 10.997, + "args": { + "External id": 758298,"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": 688924241169.591, "dur": 5.926, + "args": { + "External id": 758299,"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": 688924241172.952, "dur": 1.225, + "args": { + "External id": 758300,"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": 688924241182.555, "dur": 32.239, + "args": { + "External id": 758301,"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": 688924241184.511, "dur": 3.007, + "args": { + "External id": 758302,"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": 688924241189.337, "dur": 0.708, + "args": { + "External id": 758303,"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": 688924241191.029, "dur": 0.940, + "args": { + "External id": 758304,"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": 688924241195.785, "dur": 0.801, + "args": { + "External id": 758305,"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": 688924241197.744, "dur": 0.806, + "args": { + "External id": 758306,"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": 688924241200.119, "dur": 0.835, + "args": { + "External id": 758307,"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": 688924241203.778, "dur": 0.733, + "args": { + "External id": 758308,"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": 688924241206.176, "dur": 0.741, + "args": { + "External id": 758309,"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": 688924241208.104, "dur": 2.203, + "args": { + "External id": 758310,"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": 688924241226.239, "dur": 24.776, + "args": { + "External id": 758311,"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": 688924241315.566, "dur": 396.192, + "args": { + "External id": 758312,"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": 688924241342.768, "dur": 362.833, + "args": { + "External id": 758313,"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": 688924241353.310, "dur": 345.979, + "args": { + "External id": 758314,"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": 688924241736.069, "dur": 2.568, + "args": { + "External id": 758315,"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": 688924241852.341, "dur": 7452.663, + "args": { + "External id": 758316,"Record function id": 0, "Ev Idx": 6171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924241958.287, "dur": 6.860, + "args": { + "External id": 758317,"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": 688924241968.476, "dur": 1.750, + "args": { + "External id": 758318,"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": 688924241972.006, "dur": 1.320, + "args": { + "External id": 758319,"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": 688924241974.993, "dur": 1.205, + "args": { + "External id": 758320,"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": 688924241977.894, "dur": 1.388, + "args": { + "External id": 758321,"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": 688924241980.891, "dur": 1.234, + "args": { + "External id": 758322,"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": 688924241984.158, "dur": 1.218, + "args": { + "External id": 758323,"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": 688924241987.044, "dur": 2.503, + "args": { + "External id": 758324,"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": 688924241991.778, "dur": 1.047, + "args": { + "External id": 758325,"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": 688924241994.879, "dur": 0.851, + "args": { + "External id": 758326,"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": 688924242013.335, "dur": 7254.445, + "args": { + "External id": 758327,"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": 688924242028.992, "dur": 7231.929, + "args": { + "External id": 758328,"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": 688924242045.967, "dur": 14.859, + "args": { + "External id": 758329,"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": 688924242064.239, "dur": 7165.182, + "args": { + "External id": 758330,"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": 688924242067.386, "dur": 7161.628, + "args": { + "External id": 758331,"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": 688924242073.597, "dur": 7.498, + "args": { + "External id": 758332,"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": 688924242083.032, "dur": 7142.913, + "args": { + "External id": 758333,"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": 688924249443.121, "dur": 28.722, + "args": { + "External id": 758334,"Sequence number": 8961995, "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": 688924249443.121, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924249459.274, "dur": 7.442, + "args": { + "External id": 758335,"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": 688924249462.354, "dur": 4.129, + "args": { + "External id": 758336,"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": 688924249536.896, "dur": 86.872, + "args": { + "External id": 758337,"Record function id": 0, "Ev Idx": 6192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924249625.456, "dur": 1134.436, + "args": { + "External id": 758338,"Record function id": 0, "Ev Idx": 6193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924249694.876, "dur": 1048.447, + "args": { + "External id": 758339,"Sequence number": 8961996, "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": 688924249694.876, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924249772.620, "dur": 56.591, + "args": { + "External id": 758340,"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": 688924249845.485, "dur": 95.431, + "args": { + "External id": 758341,"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": 688924249950.057, "dur": 35.426, + "args": { + "External id": 758342,"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": 688924249994.332, "dur": 30.184, + "args": { + "External id": 758343,"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": 688924250050.572, "dur": 28.333, + "args": { + "External id": 758344,"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": 688924250098.640, "dur": 15.209, + "args": { + "External id": 758345,"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": 688924250133.119, "dur": 137.197, + "args": { + "External id": 758346,"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": 688924250189.465, "dur": 12.419, + "args": { + "External id": 758347,"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": 688924250194.575, "dur": 6.495, + "args": { + "External id": 758348,"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": 688924250205.104, "dur": 6.218, + "args": { + "External id": 758349,"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": 688924250212.833, "dur": 1.639, + "args": { + "External id": 758350,"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": 688924250216.812, "dur": 2.967, + "args": { + "External id": 758351,"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": 688924250281.665, "dur": 45.320, + "args": { + "External id": 758352,"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": 688924250358.658, "dur": 30.128, + "args": { + "External id": 758353,"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": 688924250397.545, "dur": 38.428, + "args": { + "External id": 758354,"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": 688924250444.670, "dur": 32.420, + "args": { + "External id": 758355,"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": 688924250498.537, "dur": 27.206, + "args": { + "External id": 758356,"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": 688924250531.882, "dur": 49.831, + "args": { + "External id": 758357,"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": 688924250601.026, "dur": 17.623, + "args": { + "External id": 758358,"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": 688924250845.455, "dur": 82.831, + "args": { + "External id": 758359,"Record function id": 0, "Ev Idx": 6214 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924251006.338, "dur": 49.021, + "args": { + "External id": 758360,"Record function id": 0, "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 4183436, "tid": 4183436, + "ts": 688924251065.229, "dur": 8481.676, + "args": { + "External id": 758361,"Record function id": 0, "Ev Idx": 6216 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 4183436, "tid": 4183436, + "ts": 688924251073.336, "dur": 982.680, + "args": { + "External id": 758362,"Record function id": 0, "Ev Idx": 6217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924251159.166, "dur": 9.812, + "args": { + "External id": 758363,"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": 688924251182.691, "dur": 38.187, + "args": { + "External id": 758364,"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": 688924251188.530, "dur": 2.368, + "args": { + "External id": 758365,"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": 688924251196.544, "dur": 0.433, + "args": { + "External id": 758366,"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": 688924251198.132, "dur": 0.663, + "args": { + "External id": 758367,"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": 688924251199.862, "dur": 0.836, + "args": { + "External id": 758368,"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": 688924251204.749, "dur": 0.469, + "args": { + "External id": 758369,"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": 688924251206.502, "dur": 0.546, + "args": { + "External id": 758370,"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": 688924251207.938, "dur": 2.386, + "args": { + "External id": 758371,"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": 688924251212.051, "dur": 0.495, + "args": { + "External id": 758372,"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": 688924251213.752, "dur": 0.516, + "args": { + "External id": 758373,"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": 688924251233.383, "dur": 45.387, + "args": { + "External id": 758374,"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": 688924251311.908, "dur": 116.097, + "args": { + "External id": 758375,"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": 688924251326.786, "dur": 6.496, + "args": { + "External id": 758376,"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": 688924251338.915, "dur": 10.673, + "args": { + "External id": 758377,"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": 688924251343.927, "dur": 5.260, + "args": { + "External id": 758378,"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": 688924251347.111, "dur": 0.719, + "args": { + "External id": 758379,"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": 688924251356.878, "dur": 29.533, + "args": { + "External id": 758380,"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": 688924251358.994, "dur": 0.796, + "args": { + "External id": 758381,"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": 688924251361.112, "dur": 2.657, + "args": { + "External id": 758382,"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": 688924251365.435, "dur": 0.485, + "args": { + "External id": 758383,"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": 688924251367.076, "dur": 0.655, + "args": { + "External id": 758384,"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": 688924251371.568, "dur": 0.381, + "args": { + "External id": 758385,"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": 688924251373.475, "dur": 0.310, + "args": { + "External id": 758386,"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": 688924251375.307, "dur": 0.293, + "args": { + "External id": 758387,"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": 688924251378.397, "dur": 0.368, + "args": { + "External id": 758388,"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": 688924251380.383, "dur": 0.399, + "args": { + "External id": 758389,"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": 688924251396.885, "dur": 23.444, + "args": { + "External id": 758390,"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": 688924251481.779, "dur": 463.270, + "args": { + "External id": 758391,"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": 688924251510.275, "dur": 427.976, + "args": { + "External id": 758392,"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": 688924251520.725, "dur": 410.037, + "args": { + "External id": 758393,"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": 688924251970.866, "dur": 3.053, + "args": { + "External id": 758394,"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": 688924252078.483, "dur": 7269.144, + "args": { + "External id": 758395,"Record function id": 0, "Ev Idx": 6250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924252186.546, "dur": 7.273, + "args": { + "External id": 758396,"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": 688924252197.290, "dur": 2.129, + "args": { + "External id": 758397,"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": 688924252201.289, "dur": 1.529, + "args": { + "External id": 758398,"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": 688924252204.462, "dur": 1.403, + "args": { + "External id": 758399,"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": 688924252207.524, "dur": 1.350, + "args": { + "External id": 758400,"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": 688924252210.695, "dur": 0.992, + "args": { + "External id": 758401,"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": 688924252213.536, "dur": 1.341, + "args": { + "External id": 758402,"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": 688924252217.071, "dur": 2.271, + "args": { + "External id": 758403,"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": 688924252221.342, "dur": 1.041, + "args": { + "External id": 758404,"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": 688924252224.325, "dur": 0.938, + "args": { + "External id": 758405,"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": 688924252243.598, "dur": 7066.978, + "args": { + "External id": 758406,"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": 688924252260.140, "dur": 7043.958, + "args": { + "External id": 758407,"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": 688924252275.410, "dur": 14.869, + "args": { + "External id": 758408,"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": 688924252293.346, "dur": 6978.232, + "args": { + "External id": 758409,"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": 688924252296.503, "dur": 6974.470, + "args": { + "External id": 758410,"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": 688924252302.994, "dur": 5.303, + "args": { + "External id": 758411,"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": 688924252310.157, "dur": 6957.830, + "args": { + "External id": 758412,"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": 688924259490.820, "dur": 30.047, + "args": { + "External id": 758413,"Sequence number": 8961997, "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": 688924259490.820, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924259508.000, "dur": 7.772, + "args": { + "External id": 758414,"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": 688924259511.170, "dur": 4.342, + "args": { + "External id": 758415,"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": 688924259586.562, "dur": 119.146, + "args": { + "External id": 758416,"Record function id": 0, "Ev Idx": 6271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924259709.237, "dur": 1062.795, + "args": { + "External id": 758417,"Record function id": 0, "Ev Idx": 6272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924259751.889, "dur": 1005.472, + "args": { + "External id": 758418,"Sequence number": 8961998, "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": 688924259751.889, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924259840.598, "dur": 46.030, + "args": { + "External id": 758419,"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": 688924259902.997, "dur": 93.681, + "args": { + "External id": 758420,"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": 688924260005.635, "dur": 34.450, + "args": { + "External id": 758421,"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": 688924260046.778, "dur": 29.464, + "args": { + "External id": 758422,"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": 688924260102.237, "dur": 25.305, + "args": { + "External id": 758423,"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": 688924260143.330, "dur": 17.364, + "args": { + "External id": 758424,"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": 688924260177.109, "dur": 128.938, + "args": { + "External id": 758425,"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": 688924260227.713, "dur": 12.128, + "args": { + "External id": 758426,"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": 688924260233.246, "dur": 5.794, + "args": { + "External id": 758427,"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": 688924260242.200, "dur": 4.839, + "args": { + "External id": 758428,"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": 688924260248.425, "dur": 3.331, + "args": { + "External id": 758429,"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": 688924260254.454, "dur": 2.643, + "args": { + "External id": 758430,"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": 688924260316.661, "dur": 42.903, + "args": { + "External id": 758431,"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": 688924260390.580, "dur": 29.236, + "args": { + "External id": 758432,"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": 688924260428.188, "dur": 36.949, + "args": { + "External id": 758433,"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": 688924260472.066, "dur": 31.585, + "args": { + "External id": 758434,"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": 688924260527.883, "dur": 26.988, + "args": { + "External id": 758435,"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": 688924260560.701, "dur": 46.679, + "args": { + "External id": 758436,"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": 688924260625.574, "dur": 23.937, + "args": { + "External id": 758437,"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": 688924260856.447, "dur": 85.015, + "args": { + "External id": 758438,"Record function id": 0, "Ev Idx": 6293 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183436, "tid": 4183436, + "ts": 688924261019.673, "dur": 49.734, + "args": { + "External id": 758439,"Record function id": 0, "Ev Idx": 6294 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 4183436, "tid": 4183436, + "ts": 688924261078.953, "dur": 8794.542, + "args": { + "External id": 758440,"Record function id": 0, "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 4183436, "tid": 4183436, + "ts": 688924261088.589, "dur": 927.436, + "args": { + "External id": 758441,"Record function id": 0, "Ev Idx": 6296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924261177.459, "dur": 9.442, + "args": { + "External id": 758442,"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": 688924261200.617, "dur": 38.533, + "args": { + "External id": 758443,"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": 688924261206.272, "dur": 2.323, + "args": { + "External id": 758444,"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": 688924261213.825, "dur": 0.459, + "args": { + "External id": 758445,"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": 688924261215.432, "dur": 0.854, + "args": { + "External id": 758446,"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": 688924261217.590, "dur": 1.042, + "args": { + "External id": 758447,"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": 688924261222.107, "dur": 0.923, + "args": { + "External id": 758448,"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": 688924261224.190, "dur": 1.200, + "args": { + "External id": 758449,"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": 688924261226.367, "dur": 2.148, + "args": { + "External id": 758450,"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": 688924261229.783, "dur": 0.565, + "args": { + "External id": 758451,"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": 688924261231.496, "dur": 0.826, + "args": { + "External id": 758452,"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": 688924261252.481, "dur": 46.157, + "args": { + "External id": 758453,"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": 688924261330.640, "dur": 114.835, + "args": { + "External id": 758454,"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": 688924261341.155, "dur": 4.653, + "args": { + "External id": 758455,"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": 688924261350.814, "dur": 11.048, + "args": { + "External id": 758456,"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": 688924261355.700, "dur": 5.776, + "args": { + "External id": 758457,"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": 688924261359.370, "dur": 0.972, + "args": { + "External id": 758458,"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": 688924261368.353, "dur": 31.563, + "args": { + "External id": 758459,"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": 688924261370.044, "dur": 2.627, + "args": { + "External id": 758460,"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": 688924261373.826, "dur": 0.830, + "args": { + "External id": 758461,"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": 688924261375.926, "dur": 0.615, + "args": { + "External id": 758462,"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": 688924261380.131, "dur": 0.723, + "args": { + "External id": 758463,"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": 688924261382.075, "dur": 0.887, + "args": { + "External id": 758464,"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": 688924261384.679, "dur": 0.988, + "args": { + "External id": 758465,"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": 688924261388.444, "dur": 1.012, + "args": { + "External id": 758466,"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": 688924261390.726, "dur": 0.712, + "args": { + "External id": 758467,"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": 688924261392.446, "dur": 2.763, + "args": { + "External id": 758468,"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": 688924261412.533, "dur": 25.064, + "args": { + "External id": 758469,"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": 688924261500.264, "dur": 412.642, + "args": { + "External id": 758470,"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": 688924261527.771, "dur": 379.012, + "args": { + "External id": 758471,"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": 688924261538.709, "dur": 362.375, + "args": { + "External id": 758472,"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": 688924261936.808, "dur": 2.928, + "args": { + "External id": 758473,"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": 688924262039.217, "dur": 7584.297, + "args": { + "External id": 758474,"Record function id": 0, "Ev Idx": 6329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924262147.635, "dur": 6.593, + "args": { + "External id": 758475,"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": 688924262181.253, "dur": 8.070, + "args": { + "External id": 758476,"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": 688924262191.492, "dur": 1.103, + "args": { + "External id": 758477,"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": 688924262194.205, "dur": 1.687, + "args": { + "External id": 758478,"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": 688924262197.506, "dur": 1.326, + "args": { + "External id": 758479,"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": 688924262200.505, "dur": 0.982, + "args": { + "External id": 758480,"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": 688924262203.361, "dur": 0.984, + "args": { + "External id": 758481,"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": 688924262206.520, "dur": 2.626, + "args": { + "External id": 758482,"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": 688924262210.740, "dur": 1.351, + "args": { + "External id": 758483,"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": 688924262214.153, "dur": 1.105, + "args": { + "External id": 758484,"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": 688924262235.695, "dur": 7348.939, + "args": { + "External id": 758485,"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": 688924262251.915, "dur": 7325.422, + "args": { + "External id": 758486,"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": 688924262265.738, "dur": 14.884, + "args": { + "External id": 758487,"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": 688924262283.530, "dur": 7260.049, + "args": { + "External id": 758488,"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": 688924262286.408, "dur": 7256.625, + "args": { + "External id": 758489,"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": 688924262292.505, "dur": 5.800, + "args": { + "External id": 758490,"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": 688924262300.608, "dur": 7239.567, + "args": { + "External id": 758491,"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": 688924269807.345, "dur": 37.763, + "args": { + "External id": 758492,"Sequence number": 8961999, "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": 688924269807.345, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183436, "tid": 4183436, + "ts": 688924269830.883, "dur": 8.990, + "args": { + "External id": 758493,"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": 688924269834.578, "dur": 4.885, + "args": { + "External id": 758494,"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": 688924269914.670, "dur": 89.033, + "args": { + "External id": 758495,"Record function id": 0, "Ev Idx": 6350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183436, "tid": 4183436, + "ts": 688924270005.438, "dur": 1109.786, + "args": { + "External id": 758496,"Record function id": 0, "Ev Idx": 6351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924270045.756, "dur": 1054.508, + "args": { + "External id": 758497,"Sequence number": 8962000, "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": 688924270045.756, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924270118.073, "dur": 46.644, + "args": { + "External id": 758498,"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": 688924270179.577, "dur": 97.704, + "args": { + "External id": 758499,"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": 688924270286.156, "dur": 35.541, + "args": { + "External id": 758500,"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": 688924270331.394, "dur": 29.953, + "args": { + "External id": 758501,"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": 688924270385.031, "dur": 26.553, + "args": { + "External id": 758502,"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": 688924270430.183, "dur": 14.258, + "args": { + "External id": 758503,"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": 688924270462.724, "dur": 125.658, + "args": { + "External id": 758504,"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": 688924270512.528, "dur": 11.257, + "args": { + "External id": 758505,"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": 688924270517.280, "dur": 5.726, + "args": { + "External id": 758506,"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": 688924270526.520, "dur": 4.621, + "args": { + "External id": 758507,"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": 688924270532.480, "dur": 1.521, + "args": { + "External id": 758508,"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": 688924270536.376, "dur": 2.973, + "args": { + "External id": 758509,"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": 688924270598.768, "dur": 42.541, + "args": { + "External id": 758510,"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": 688924270718.032, "dur": 32.886, + "args": { + "External id": 758511,"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": 688924270760.319, "dur": 58.323, + "args": { + "External id": 758512,"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": 688924270831.462, "dur": 39.928, + "args": { + "External id": 758513,"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": 688924270896.228, "dur": 28.995, + "args": { + "External id": 758514,"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": 688924270931.315, "dur": 54.985, + "args": { + "External id": 758515,"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": 688924271007.343, "dur": 18.680, + "args": { + "External id": 758516,"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": 688924271184.830, "dur": 34.048, + "args": { + "External id": 758517,"Record function id": 0, "Ev Idx": 6372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924271304.408, "dur": 278.427, + "args": { + "External id": 758518,"Sequence number": 8962001, "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": 688924271304.408, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924271336.416, "dur": 8.223, + "args": { + "External id": 758519,"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": 688924271338.531, "dur": 5.831, + "args": { + "External id": 758520,"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": 688924271353.723, "dur": 11.076, + "args": { + "External id": 758521,"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": 688924271356.813, "dur": 7.400, + "args": { + "External id": 758522,"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": 688924271372.557, "dur": 5.036, + "args": { + "External id": 758523,"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": 688924271563.220, "dur": 7.234, + "args": { + "External id": 758524,"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": 688924271567.094, "dur": 3.031, + "args": { + "External id": 758525,"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": 688924271612.477, "dur": 197.030, + "args": { + "External id": 758526,"Sequence number": 8962002, "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": 688924271615.294, "dur": 13.535, + "args": { + "External id": 758527,"Sequence number": 8962002, "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": 688924271615.294, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924271621.093, "dur": 5.898, + "args": { + "External id": 758528,"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": 688924271624.598, "dur": 2.065, + "args": { + "External id": 758529,"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": 688924271632.009, "dur": 176.863, + "args": { + "External id": 758530,"Sequence number": 8962003, "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": 688924271634.615, "dur": 5.527, + "args": { + "External id": 758531,"Sequence number": 8962003, "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": 688924271636.212, "dur": 3.773, + "args": { + "External id": 758532,"Sequence number": 8962003, "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": 688924271636.212, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924271642.816, "dur": 136.584, + "args": { + "External id": 758533,"Sequence number": 8962004, "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": 688924271642.816, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924271783.883, "dur": 22.935, + "args": { + "External id": 758534,"Sequence number": 8962005, "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": 688924271783.883, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924271824.251, "dur": 79.764, + "args": { + "External id": 758535,"Sequence number": 8962006, "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": 688924271825.895, "dur": 9.434, + "args": { + "External id": 758536,"Sequence number": 8962006, "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": 688924271825.895, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924271829.666, "dur": 4.136, + "args": { + "External id": 758537,"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": 688924271832.115, "dur": 1.458, + "args": { + "External id": 758538,"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": 688924271836.740, "dur": 66.895, + "args": { + "External id": 758539,"Sequence number": 8962007, "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": 688924271838.491, "dur": 7.679, + "args": { + "External id": 758540,"Sequence number": 8962007, "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": 688924271840.337, "dur": 5.685, + "args": { + "External id": 758541,"Sequence number": 8962007, "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": 688924271840.337, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924271847.178, "dur": 48.787, + "args": { + "External id": 758542,"Sequence number": 8962008, "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": 688924271847.178, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924271897.796, "dur": 5.418, + "args": { + "External id": 758543,"Sequence number": 8962009, "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": 688924271897.796, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924271912.137, "dur": 63.832, + "args": { + "External id": 758544,"Sequence number": 8962010, "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": 688924271913.230, "dur": 6.718, + "args": { + "External id": 758545,"Sequence number": 8962010, "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": 688924271913.230, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924271915.241, "dur": 3.417, + "args": { + "External id": 758546,"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": 688924271917.726, "dur": 0.803, + "args": { + "External id": 758547,"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": 688924271920.748, "dur": 55.036, + "args": { + "External id": 758548,"Sequence number": 8962011, "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": 688924271922.245, "dur": 5.299, + "args": { + "External id": 758549,"Sequence number": 8962011, "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": 688924271923.439, "dur": 3.970, + "args": { + "External id": 758550,"Sequence number": 8962011, "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": 688924271923.439, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924271928.467, "dur": 40.806, + "args": { + "External id": 758551,"Sequence number": 8962012, "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": 688924271928.467, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924271970.967, "dur": 4.256, + "args": { + "External id": 758552,"Sequence number": 8962013, "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": 688924271970.967, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924271998.558, "dur": 4.364, + "args": { + "External id": 758553,"Sequence number": 8962014, "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": 688924271999.498, "dur": 3.288, + "args": { + "External id": 758554,"Sequence number": 8962014, "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": 688924271999.498, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924272013.457, "dur": 5.040, + "args": { + "External id": 758555,"Sequence number": 8962015, "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": 688924272014.461, "dur": 3.887, + "args": { + "External id": 758556,"Sequence number": 8962015, "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": 688924272014.461, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924272023.170, "dur": 3.816, + "args": { + "External id": 758557,"Sequence number": 8962016, "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": 688924272024.490, "dur": 2.047, + "args": { + "External id": 758558,"Sequence number": 8962016, "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": 688924272024.490, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924272065.651, "dur": 186.886, + "args": { + "External id": 758559,"Sequence number": 8962017, "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": 688924272065.651, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 688924272089.423, "dur": 9.779, + "args": { + "External id": 758560,"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": 688924272092.547, "dur": 6.181, + "args": { + "External id": 758561,"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": 688924272268.240, "dur": 107.976, + "args": { + "External id": 758562,"Sequence number": 8962018, "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": 688924272268.240, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 688924272282.263, "dur": 7.592, + "args": { + "External id": 758563,"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": 688924272284.265, "dur": 5.114, + "args": { + "External id": 758564,"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": 688924272407.268, "dur": 184.118, + "args": { + "External id": 758565,"Sequence number": 8962019, "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": 688924272407.268, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183436, "tid": 4183436, + "ts": 688924272436.115, "dur": 127.053, + "args": { + "External id": 758566,"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": 688924272488.582, "dur": 6.854, + "args": { + "External id": 758567,"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": 688924272491.005, "dur": 4.063, + "args": { + "External id": 758568,"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": 688924272498.118, "dur": 4.098, + "args": { + "External id": 758569,"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": 688924272503.382, "dur": 1.662, + "args": { + "External id": 758570,"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": 688924272507.778, "dur": 5.115, + "args": { + "External id": 758571,"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": 688924272576.806, "dur": 5.092, + "args": { + "External id": 758572,"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": 688924272596.998, "dur": 5.668, + "args": { + "External id": 758573,"Sequence number": 8962020, "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": 688924272598.635, "dur": 3.911, + "args": { + "External id": 758574,"Sequence number": 8962020, "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": 688924272598.635, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924272615.428, "dur": 153.750, + "args": { + "External id": 758575,"Sequence number": 8962021, "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": 688924272616.762, "dur": 8.958, + "args": { + "External id": 758576,"Sequence number": 8962021, "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": 688924272616.762, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924272619.760, "dur": 4.597, + "args": { + "External id": 758577,"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": 688924272622.655, "dur": 1.461, + "args": { + "External id": 758578,"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": 688924272627.151, "dur": 141.692, + "args": { + "External id": 758579,"Sequence number": 8962022, "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": 688924272629.250, "dur": 5.708, + "args": { + "External id": 758580,"Sequence number": 8962022, "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": 688924272630.523, "dur": 4.314, + "args": { + "External id": 758581,"Sequence number": 8962022, "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": 688924272630.523, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924272635.873, "dur": 123.361, + "args": { + "External id": 758582,"Sequence number": 8962023, "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": 688924272635.873, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924272763.385, "dur": 4.584, + "args": { + "External id": 758583,"Sequence number": 8962024, "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": 688924272763.385, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924272827.002, "dur": 244.456, + "args": { + "External id": 758584,"Sequence number": 8962025, "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": 688924272827.002, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924272848.596, "dur": 4.790, + "args": { + "External id": 758585,"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": 688924272850.355, "dur": 2.713, + "args": { + "External id": 758586,"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": 688924272859.582, "dur": 4.580, + "args": { + "External id": 758587,"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": 688924272861.597, "dur": 2.449, + "args": { + "External id": 758588,"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": 688924272862.799, "dur": 1.142, + "args": { + "External id": 758589,"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": 688924272872.172, "dur": 9.086, + "args": { + "External id": 758590,"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": 688924272874.751, "dur": 6.180, + "args": { + "External id": 758591,"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": 688924272889.151, "dur": 3.726, + "args": { + "External id": 758592,"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": 688924272896.869, "dur": 5.455, + "args": { + "External id": 758593,"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": 688924273046.647, "dur": 5.527, + "args": { + "External id": 758594,"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": 688924273047.761, "dur": 4.165, + "args": { + "External id": 758595,"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": 688924273054.757, "dur": 2.806, + "args": { + "External id": 758596,"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": 688924273056.266, "dur": 1.170, + "args": { + "External id": 758597,"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": 688924273092.235, "dur": 102.282, + "args": { + "External id": 758598,"Sequence number": 8962026, "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": 688924273093.639, "dur": 9.120, + "args": { + "External id": 758599,"Sequence number": 8962026, "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": 688924273093.639, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924273096.822, "dur": 4.765, + "args": { + "External id": 758600,"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": 688924273099.538, "dur": 1.827, + "args": { + "External id": 758601,"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": 688924273103.820, "dur": 90.457, + "args": { + "External id": 758602,"Sequence number": 8962027, "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": 688924273105.887, "dur": 6.086, + "args": { + "External id": 758603,"Sequence number": 8962027, "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": 688924273106.818, "dur": 5.017, + "args": { + "External id": 758604,"Sequence number": 8962027, "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": 688924273106.818, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924273113.207, "dur": 74.439, + "args": { + "External id": 758605,"Sequence number": 8962028, "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": 688924273113.207, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924273190.008, "dur": 3.504, + "args": { + "External id": 758606,"Sequence number": 8962029, "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": 688924273190.008, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924273203.124, "dur": 70.483, + "args": { + "External id": 758607,"Sequence number": 8962030, "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": 688924273204.072, "dur": 8.876, + "args": { + "External id": 758608,"Sequence number": 8962030, "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": 688924273204.072, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924273205.681, "dur": 6.250, + "args": { + "External id": 758609,"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": 688924273210.643, "dur": 1.139, + "args": { + "External id": 758610,"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": 688924273213.899, "dur": 59.461, + "args": { + "External id": 758611,"Sequence number": 8962031, "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": 688924273215.244, "dur": 5.863, + "args": { + "External id": 758612,"Sequence number": 8962031, "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": 688924273216.493, "dur": 4.470, + "args": { + "External id": 758613,"Sequence number": 8962031, "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": 688924273216.493, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924273221.804, "dur": 44.263, + "args": { + "External id": 758614,"Sequence number": 8962032, "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": 688924273221.804, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924273267.979, "dur": 5.045, + "args": { + "External id": 758615,"Sequence number": 8962033, "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": 688924273267.979, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924273295.144, "dur": 153.720, + "args": { + "External id": 758616,"Sequence number": 8962034, "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": 688924273295.144, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924273339.726, "dur": 4.435, + "args": { + "External id": 758617,"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": 688924273378.729, "dur": 56.638, + "args": { + "External id": 758618,"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": 688924273379.686, "dur": 4.933, + "args": { + "External id": 758619,"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": 688924273380.913, "dur": 2.810, + "args": { + "External id": 758620,"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": 688924273382.752, "dur": 0.781, + "args": { + "External id": 758621,"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": 688924273385.429, "dur": 49.660, + "args": { + "External id": 758622,"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": 688924273387.333, "dur": 2.733, + "args": { + "External id": 758623,"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": 688924273388.606, "dur": 1.350, + "args": { + "External id": 758624,"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": 688924273390.786, "dur": 40.555, + "args": { + "External id": 758625,"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": 688924273433.195, "dur": 1.286, + "args": { + "External id": 758626,"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": 688924273459.257, "dur": 29.907, + "args": { + "External id": 758627,"Sequence number": 8962035, "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": 688924273459.257, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924273524.203, "dur": 235.584, + "args": { + "External id": 758628,"Sequence number": 8962036, "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": 688924273524.203, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924273545.113, "dur": 3.781, + "args": { + "External id": 758629,"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": 688924273546.480, "dur": 2.249, + "args": { + "External id": 758630,"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": 688924273556.548, "dur": 7.547, + "args": { + "External id": 758631,"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": 688924273559.365, "dur": 4.415, + "args": { + "External id": 758632,"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": 688924273569.257, "dur": 3.618, + "args": { + "External id": 758633,"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": 688924273740.104, "dur": 7.546, + "args": { + "External id": 758634,"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": 688924273744.069, "dur": 3.250, + "args": { + "External id": 758635,"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": 688924273781.524, "dur": 112.594, + "args": { + "External id": 758636,"Sequence number": 8962037, "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": 688924273783.072, "dur": 24.793, + "args": { + "External id": 758637,"Sequence number": 8962037, "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": 688924273783.072, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924273800.203, "dur": 5.842, + "args": { + "External id": 758638,"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": 688924273803.446, "dur": 2.217, + "args": { + "External id": 758639,"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": 688924273809.190, "dur": 84.618, + "args": { + "External id": 758640,"Sequence number": 8962038, "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": 688924273811.658, "dur": 5.507, + "args": { + "External id": 758641,"Sequence number": 8962038, "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": 688924273813.083, "dur": 3.955, + "args": { + "External id": 758642,"Sequence number": 8962038, "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": 688924273813.083, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924273818.070, "dur": 70.334, + "args": { + "External id": 758643,"Sequence number": 8962039, "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": 688924273818.070, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924273890.402, "dur": 2.770, + "args": { + "External id": 758644,"Sequence number": 8962040, "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": 688924273890.402, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924273905.218, "dur": 66.444, + "args": { + "External id": 758645,"Sequence number": 8962041, "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": 688924273905.790, "dur": 9.104, + "args": { + "External id": 758646,"Sequence number": 8962041, "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": 688924273905.790, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924273910.611, "dur": 3.135, + "args": { + "External id": 758647,"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": 688924273912.576, "dur": 1.014, + "args": { + "External id": 758648,"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": 688924273915.442, "dur": 55.993, + "args": { + "External id": 758649,"Sequence number": 8962042, "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": 688924273917.226, "dur": 6.220, + "args": { + "External id": 758650,"Sequence number": 8962042, "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": 688924273918.190, "dur": 5.117, + "args": { + "External id": 758651,"Sequence number": 8962042, "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": 688924273918.190, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924273924.039, "dur": 40.421, + "args": { + "External id": 758652,"Sequence number": 8962043, "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": 688924273924.039, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924273966.155, "dur": 4.865, + "args": { + "External id": 758653,"Sequence number": 8962044, "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": 688924273966.155, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924273979.654, "dur": 59.034, + "args": { + "External id": 758654,"Sequence number": 8962045, "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": 688924273980.544, "dur": 6.104, + "args": { + "External id": 758655,"Sequence number": 8962045, "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": 688924273980.544, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924273982.370, "dur": 3.083, + "args": { + "External id": 758656,"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": 688924273984.280, "dur": 1.045, + "args": { + "External id": 758657,"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": 688924273987.334, "dur": 51.160, + "args": { + "External id": 758658,"Sequence number": 8962046, "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": 688924273989.014, "dur": 5.336, + "args": { + "External id": 758659,"Sequence number": 8962046, "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": 688924273990.085, "dur": 4.112, + "args": { + "External id": 758660,"Sequence number": 8962046, "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": 688924273990.085, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924273994.828, "dur": 37.931, + "args": { + "External id": 758661,"Sequence number": 8962047, "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": 688924273994.828, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924274034.642, "dur": 3.326, + "args": { + "External id": 758662,"Sequence number": 8962048, "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": 688924274034.642, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924274055.882, "dur": 5.132, + "args": { + "External id": 758663,"Sequence number": 8962049, "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": 688924274057.309, "dur": 3.554, + "args": { + "External id": 758664,"Sequence number": 8962049, "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": 688924274057.309, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924274067.413, "dur": 6.243, + "args": { + "External id": 758665,"Sequence number": 8962050, "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": 688924274068.625, "dur": 4.892, + "args": { + "External id": 758666,"Sequence number": 8962050, "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": 688924274068.625, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924274077.685, "dur": 5.104, + "args": { + "External id": 758667,"Sequence number": 8962051, "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": 688924274078.772, "dur": 3.877, + "args": { + "External id": 758668,"Sequence number": 8962051, "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": 688924274078.772, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924274113.144, "dur": 167.659, + "args": { + "External id": 758669,"Sequence number": 8962052, "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": 688924274113.144, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 688924274133.958, "dur": 9.251, + "args": { + "External id": 758670,"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": 688924274137.269, "dur": 5.601, + "args": { + "External id": 758671,"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": 688924274292.997, "dur": 100.588, + "args": { + "External id": 758672,"Sequence number": 8962053, "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": 688924274292.997, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 688924274306.086, "dur": 7.219, + "args": { + "External id": 758673,"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": 688924274308.521, "dur": 4.310, + "args": { + "External id": 758674,"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": 688924274421.800, "dur": 177.921, + "args": { + "External id": 758675,"Sequence number": 8962054, "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": 688924274421.800, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183436, "tid": 4183436, + "ts": 688924274448.431, "dur": 127.836, + "args": { + "External id": 758676,"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": 688924274499.399, "dur": 7.384, + "args": { + "External id": 758677,"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": 688924274501.801, "dur": 4.508, + "args": { + "External id": 758678,"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": 688924274509.192, "dur": 3.765, + "args": { + "External id": 758679,"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": 688924274514.338, "dur": 1.486, + "args": { + "External id": 758680,"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": 688924274520.740, "dur": 3.225, + "args": { + "External id": 758681,"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": 688924274587.418, "dur": 4.589, + "args": { + "External id": 758682,"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": 688924274604.667, "dur": 5.817, + "args": { + "External id": 758683,"Sequence number": 8962055, "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": 688924274606.049, "dur": 4.275, + "args": { + "External id": 758684,"Sequence number": 8962055, "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": 688924274606.049, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924274622.069, "dur": 158.915, + "args": { + "External id": 758685,"Sequence number": 8962056, "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": 688924274623.749, "dur": 8.847, + "args": { + "External id": 758686,"Sequence number": 8962056, "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": 688924274623.749, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924274626.384, "dur": 4.847, + "args": { + "External id": 758687,"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": 688924274629.489, "dur": 1.482, + "args": { + "External id": 758688,"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": 688924274634.240, "dur": 146.426, + "args": { + "External id": 758689,"Sequence number": 8962057, "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": 688924274636.067, "dur": 3.722, + "args": { + "External id": 758690,"Sequence number": 8962057, "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": 688924274637.276, "dur": 2.375, + "args": { + "External id": 758691,"Sequence number": 8962057, "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": 688924274637.276, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924274640.875, "dur": 130.428, + "args": { + "External id": 758692,"Sequence number": 8962058, "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": 688924274640.875, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924274775.290, "dur": 4.436, + "args": { + "External id": 758693,"Sequence number": 8962059, "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": 688924274775.290, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924274838.217, "dur": 229.892, + "args": { + "External id": 758694,"Sequence number": 8962060, "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": 688924274838.217, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924274860.578, "dur": 4.953, + "args": { + "External id": 758695,"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": 688924274862.355, "dur": 2.556, + "args": { + "External id": 758696,"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": 688924274869.756, "dur": 4.100, + "args": { + "External id": 758697,"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": 688924274871.255, "dur": 2.492, + "args": { + "External id": 758698,"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": 688924274872.493, "dur": 1.153, + "args": { + "External id": 758699,"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": 688924274881.722, "dur": 8.569, + "args": { + "External id": 758700,"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": 688924274884.258, "dur": 5.681, + "args": { + "External id": 758701,"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": 688924274897.565, "dur": 3.741, + "args": { + "External id": 758702,"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": 688924274905.456, "dur": 3.080, + "args": { + "External id": 758703,"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": 688924275043.748, "dur": 6.237, + "args": { + "External id": 758704,"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": 688924275047.204, "dur": 2.507, + "args": { + "External id": 758705,"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": 688924275052.533, "dur": 2.693, + "args": { + "External id": 758706,"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": 688924275053.870, "dur": 1.229, + "args": { + "External id": 758707,"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": 688924275086.414, "dur": 142.178, + "args": { + "External id": 758708,"Sequence number": 8962061, "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": 688924275088.050, "dur": 8.982, + "args": { + "External id": 758709,"Sequence number": 8962061, "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": 688924275088.050, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924275091.390, "dur": 4.423, + "args": { + "External id": 758710,"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": 688924275093.832, "dur": 1.730, + "args": { + "External id": 758711,"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": 688924275098.011, "dur": 130.258, + "args": { + "External id": 758712,"Sequence number": 8962062, "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": 688924275100.320, "dur": 6.461, + "args": { + "External id": 758713,"Sequence number": 8962062, "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": 688924275101.492, "dur": 5.114, + "args": { + "External id": 758714,"Sequence number": 8962062, "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": 688924275101.492, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924275107.957, "dur": 73.194, + "args": { + "External id": 758715,"Sequence number": 8962063, "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": 688924275107.957, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924275220.713, "dur": 6.717, + "args": { + "External id": 758716,"Sequence number": 8962064, "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": 688924275220.713, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924275238.218, "dur": 70.543, + "args": { + "External id": 758717,"Sequence number": 8962065, "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": 688924275238.837, "dur": 6.669, + "args": { + "External id": 758718,"Sequence number": 8962065, "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": 688924275238.837, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924275240.662, "dur": 3.639, + "args": { + "External id": 758719,"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": 688924275243.047, "dur": 1.089, + "args": { + "External id": 758720,"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": 688924275246.242, "dur": 62.216, + "args": { + "External id": 758721,"Sequence number": 8962066, "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": 688924275247.888, "dur": 5.456, + "args": { + "External id": 758722,"Sequence number": 8962066, "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": 688924275248.821, "dur": 4.357, + "args": { + "External id": 758723,"Sequence number": 8962066, "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": 688924275248.821, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924275253.963, "dur": 49.809, + "args": { + "External id": 758724,"Sequence number": 8962067, "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": 688924275253.963, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924275305.709, "dur": 2.361, + "args": { + "External id": 758725,"Sequence number": 8962068, "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": 688924275305.709, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924275332.876, "dur": 152.390, + "args": { + "External id": 758726,"Sequence number": 8962069, "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": 688924275332.876, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924275373.385, "dur": 4.209, + "args": { + "External id": 758727,"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": 688924275410.335, "dur": 60.098, + "args": { + "External id": 758728,"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": 688924275411.002, "dur": 7.552, + "args": { + "External id": 758729,"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": 688924275412.117, "dur": 5.379, + "args": { + "External id": 758730,"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": 688924275416.617, "dur": 0.692, + "args": { + "External id": 758731,"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": 688924275419.318, "dur": 50.756, + "args": { + "External id": 758732,"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": 688924275421.593, "dur": 2.855, + "args": { + "External id": 758733,"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": 688924275422.728, "dur": 1.595, + "args": { + "External id": 758734,"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": 688924275425.343, "dur": 41.274, + "args": { + "External id": 758735,"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": 688924275468.390, "dur": 1.071, + "args": { + "External id": 758736,"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": 688924275494.186, "dur": 27.217, + "args": { + "External id": 758737,"Sequence number": 8962070, "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": 688924275494.186, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924275555.714, "dur": 260.638, + "args": { + "External id": 758738,"Sequence number": 8962071, "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": 688924275555.714, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924275574.020, "dur": 4.509, + "args": { + "External id": 758739,"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": 688924275575.237, "dur": 2.849, + "args": { + "External id": 758740,"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": 688924275586.535, "dur": 8.053, + "args": { + "External id": 758741,"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": 688924275589.574, "dur": 4.548, + "args": { + "External id": 758742,"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": 688924275600.520, "dur": 3.631, + "args": { + "External id": 758743,"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": 688924275778.245, "dur": 5.132, + "args": { + "External id": 758744,"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": 688924275779.670, "dur": 3.268, + "args": { + "External id": 758745,"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": 688924275838.701, "dur": 106.036, + "args": { + "External id": 758746,"Sequence number": 8962072, "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": 688924275840.129, "dur": 10.498, + "args": { + "External id": 758747,"Sequence number": 8962072, "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": 688924275840.129, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924275844.380, "dur": 4.805, + "args": { + "External id": 758748,"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": 688924275846.860, "dur": 2.137, + "args": { + "External id": 758749,"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": 688924275852.028, "dur": 92.470, + "args": { + "External id": 758750,"Sequence number": 8962073, "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": 688924275854.481, "dur": 6.006, + "args": { + "External id": 758751,"Sequence number": 8962073, "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": 688924275856.119, "dur": 4.215, + "args": { + "External id": 758752,"Sequence number": 8962073, "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": 688924275856.119, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924275861.823, "dur": 71.534, + "args": { + "External id": 758753,"Sequence number": 8962074, "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": 688924275861.823, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924275935.691, "dur": 7.904, + "args": { + "External id": 758754,"Sequence number": 8962075, "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": 688924275935.691, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924275953.864, "dur": 62.609, + "args": { + "External id": 758755,"Sequence number": 8962076, "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": 688924275954.443, "dur": 8.095, + "args": { + "External id": 758756,"Sequence number": 8962076, "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": 688924275954.443, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924275957.414, "dur": 3.759, + "args": { + "External id": 758757,"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": 688924275959.787, "dur": 1.244, + "args": { + "External id": 758758,"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": 688924275963.301, "dur": 52.916, + "args": { + "External id": 758759,"Sequence number": 8962077, "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": 688924275964.815, "dur": 4.133, + "args": { + "External id": 758760,"Sequence number": 8962077, "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": 688924275966.073, "dur": 2.738, + "args": { + "External id": 758761,"Sequence number": 8962077, "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": 688924275966.073, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924275969.693, "dur": 42.239, + "args": { + "External id": 758762,"Sequence number": 8962078, "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": 688924275969.693, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924276013.752, "dur": 2.118, + "args": { + "External id": 758763,"Sequence number": 8962079, "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": 688924276013.752, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924276024.336, "dur": 60.545, + "args": { + "External id": 758764,"Sequence number": 8962080, "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": 688924276025.200, "dur": 6.491, + "args": { + "External id": 758765,"Sequence number": 8962080, "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": 688924276025.200, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924276027.656, "dur": 2.825, + "args": { + "External id": 758766,"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": 688924276029.443, "dur": 0.896, + "args": { + "External id": 758767,"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": 688924276032.334, "dur": 52.359, + "args": { + "External id": 758768,"Sequence number": 8962081, "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": 688924276034.043, "dur": 5.859, + "args": { + "External id": 758769,"Sequence number": 8962081, "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": 688924276035.384, "dur": 4.368, + "args": { + "External id": 758770,"Sequence number": 8962081, "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": 688924276035.384, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924276040.625, "dur": 38.992, + "args": { + "External id": 758771,"Sequence number": 8962082, "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": 688924276040.625, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924276081.712, "dur": 2.699, + "args": { + "External id": 758772,"Sequence number": 8962083, "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": 688924276081.712, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924276101.641, "dur": 4.003, + "args": { + "External id": 758773,"Sequence number": 8962084, "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": 688924276102.811, "dur": 2.694, + "args": { + "External id": 758774,"Sequence number": 8962084, "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": 688924276102.811, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924276112.252, "dur": 5.548, + "args": { + "External id": 758775,"Sequence number": 8962085, "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": 688924276113.400, "dur": 4.260, + "args": { + "External id": 758776,"Sequence number": 8962085, "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": 688924276113.400, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924276121.943, "dur": 3.460, + "args": { + "External id": 758777,"Sequence number": 8962086, "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": 688924276123.263, "dur": 2.018, + "args": { + "External id": 758778,"Sequence number": 8962086, "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": 688924276123.263, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924276156.381, "dur": 151.560, + "args": { + "External id": 758779,"Sequence number": 8962087, "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": 688924276156.381, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 688924276176.300, "dur": 8.384, + "args": { + "External id": 758780,"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": 688924276178.876, "dur": 5.401, + "args": { + "External id": 758781,"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": 688924276319.410, "dur": 98.837, + "args": { + "External id": 758782,"Sequence number": 8962088, "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": 688924276319.410, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 688924276331.343, "dur": 6.572, + "args": { + "External id": 758783,"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": 688924276333.063, "dur": 4.395, + "args": { + "External id": 758784,"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": 688924276522.183, "dur": 251.109, + "args": { + "External id": 758785,"Sequence number": 8962089, "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": 688924276522.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183436, "tid": 4183436, + "ts": 688924276551.861, "dur": 187.911, + "args": { + "External id": 758786,"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": 688924276603.021, "dur": 10.680, + "args": { + "External id": 758787,"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": 688924276605.453, "dur": 7.712, + "args": { + "External id": 758788,"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": 688924276618.834, "dur": 3.997, + "args": { + "External id": 758789,"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": 688924276624.351, "dur": 1.627, + "args": { + "External id": 758790,"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": 688924276628.548, "dur": 3.597, + "args": { + "External id": 758791,"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": 688924276754.105, "dur": 5.959, + "args": { + "External id": 758792,"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": 688924276779.836, "dur": 21.680, + "args": { + "External id": 758793,"Sequence number": 8962090, "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": 688924276781.579, "dur": 19.434, + "args": { + "External id": 758794,"Sequence number": 8962090, "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": 688924276781.579, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924276819.092, "dur": 132.029, + "args": { + "External id": 758795,"Sequence number": 8962091, "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": 688924276820.930, "dur": 14.191, + "args": { + "External id": 758796,"Sequence number": 8962091, "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": 688924276820.930, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924276827.950, "dur": 5.797, + "args": { + "External id": 758797,"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": 688924276831.389, "dur": 2.055, + "args": { + "External id": 758798,"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": 688924276836.709, "dur": 114.063, + "args": { + "External id": 758799,"Sequence number": 8962092, "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": 688924276839.320, "dur": 4.471, + "args": { + "External id": 758800,"Sequence number": 8962092, "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": 688924276840.199, "dur": 3.423, + "args": { + "External id": 758801,"Sequence number": 8962092, "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": 688924276840.199, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924276845.335, "dur": 94.810, + "args": { + "External id": 758802,"Sequence number": 8962093, "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": 688924276845.335, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924276943.085, "dur": 6.803, + "args": { + "External id": 758803,"Sequence number": 8962094, "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": 688924276943.085, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924276992.523, "dur": 236.791, + "args": { + "External id": 758804,"Sequence number": 8962095, "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": 688924276992.523, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924277014.595, "dur": 3.264, + "args": { + "External id": 758805,"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": 688924277015.915, "dur": 1.779, + "args": { + "External id": 758806,"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": 688924277022.377, "dur": 3.873, + "args": { + "External id": 758807,"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": 688924277023.907, "dur": 2.237, + "args": { + "External id": 758808,"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": 688924277025.009, "dur": 0.975, + "args": { + "External id": 758809,"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": 688924277034.567, "dur": 8.893, + "args": { + "External id": 758810,"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": 688924277037.602, "dur": 5.499, + "args": { + "External id": 758811,"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": 688924277050.732, "dur": 3.631, + "args": { + "External id": 758812,"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": 688924277058.108, "dur": 3.493, + "args": { + "External id": 758813,"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": 688924277206.376, "dur": 3.504, + "args": { + "External id": 758814,"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": 688924277207.524, "dur": 2.148, + "args": { + "External id": 758815,"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": 688924277212.397, "dur": 2.463, + "args": { + "External id": 758816,"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": 688924277213.501, "dur": 1.249, + "args": { + "External id": 758817,"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": 688924277248.281, "dur": 94.205, + "args": { + "External id": 758818,"Sequence number": 8962096, "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": 688924277249.349, "dur": 7.332, + "args": { + "External id": 758819,"Sequence number": 8962096, "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": 688924277249.349, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924277252.013, "dur": 3.646, + "args": { + "External id": 758820,"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": 688924277254.197, "dur": 1.204, + "args": { + "External id": 758821,"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": 688924277257.989, "dur": 84.176, + "args": { + "External id": 758822,"Sequence number": 8962097, "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": 688924277260.017, "dur": 4.291, + "args": { + "External id": 758823,"Sequence number": 8962097, "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": 688924277261.290, "dur": 2.882, + "args": { + "External id": 758824,"Sequence number": 8962097, "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": 688924277261.290, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924277265.627, "dur": 67.997, + "args": { + "External id": 758825,"Sequence number": 8962098, "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": 688924277265.627, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924277336.399, "dur": 5.146, + "args": { + "External id": 758826,"Sequence number": 8962099, "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": 688924277336.399, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924277350.790, "dur": 67.566, + "args": { + "External id": 758827,"Sequence number": 8962100, "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": 688924277351.700, "dur": 5.960, + "args": { + "External id": 758828,"Sequence number": 8962100, "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": 688924277351.700, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924277353.009, "dur": 3.452, + "args": { + "External id": 758829,"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": 688924277355.409, "dur": 0.905, + "args": { + "External id": 758830,"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": 688924277358.354, "dur": 59.770, + "args": { + "External id": 758831,"Sequence number": 8962101, "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": 688924277359.852, "dur": 7.874, + "args": { + "External id": 758832,"Sequence number": 8962101, "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": 688924277361.534, "dur": 5.956, + "args": { + "External id": 758833,"Sequence number": 8962101, "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": 688924277361.534, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924277368.315, "dur": 42.459, + "args": { + "External id": 758834,"Sequence number": 8962102, "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": 688924277368.315, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924277413.072, "dur": 4.653, + "args": { + "External id": 758835,"Sequence number": 8962103, "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": 688924277413.072, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924277440.770, "dur": 143.791, + "args": { + "External id": 758836,"Sequence number": 8962104, "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": 688924277440.770, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924277480.703, "dur": 4.109, + "args": { + "External id": 758837,"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": 688924277515.159, "dur": 56.684, + "args": { + "External id": 758838,"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": 688924277516.166, "dur": 5.384, + "args": { + "External id": 758839,"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": 688924277517.513, "dur": 3.142, + "args": { + "External id": 758840,"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": 688924277519.388, "dur": 0.987, + "args": { + "External id": 758841,"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": 688924277522.566, "dur": 48.968, + "args": { + "External id": 758842,"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": 688924277524.524, "dur": 2.446, + "args": { + "External id": 758843,"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": 688924277525.330, "dur": 1.517, + "args": { + "External id": 758844,"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": 688924277527.906, "dur": 39.962, + "args": { + "External id": 758845,"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": 688924277569.840, "dur": 1.169, + "args": { + "External id": 758846,"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": 688924277592.580, "dur": 25.981, + "args": { + "External id": 758847,"Sequence number": 8962105, "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": 688924277592.580, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924277651.248, "dur": 266.590, + "args": { + "External id": 758848,"Sequence number": 8962106, "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": 688924277651.248, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924277713.596, "dur": 5.400, + "args": { + "External id": 758849,"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": 688924277715.077, "dur": 3.507, + "args": { + "External id": 758850,"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": 688924277728.273, "dur": 8.534, + "args": { + "External id": 758851,"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": 688924277731.353, "dur": 5.094, + "args": { + "External id": 758852,"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": 688924277743.375, "dur": 3.437, + "args": { + "External id": 758853,"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": 688924277899.761, "dur": 4.175, + "args": { + "External id": 758854,"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": 688924277900.896, "dur": 2.734, + "args": { + "External id": 758855,"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": 688924277939.302, "dur": 98.704, + "args": { + "External id": 758856,"Sequence number": 8962107, "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": 688924277940.489, "dur": 8.424, + "args": { + "External id": 758857,"Sequence number": 8962107, "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": 688924277940.489, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924277943.029, "dur": 4.176, + "args": { + "External id": 758858,"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": 688924277945.435, "dur": 1.496, + "args": { + "External id": 758859,"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": 688924277950.215, "dur": 87.460, + "args": { + "External id": 758860,"Sequence number": 8962108, "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": 688924277952.015, "dur": 5.048, + "args": { + "External id": 758861,"Sequence number": 8962108, "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": 688924277953.682, "dur": 3.252, + "args": { + "External id": 758862,"Sequence number": 8962108, "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": 688924277953.682, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924277958.434, "dur": 71.936, + "args": { + "External id": 758863,"Sequence number": 8962109, "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": 688924277958.434, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924278032.996, "dur": 3.912, + "args": { + "External id": 758864,"Sequence number": 8962110, "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": 688924278032.996, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924278046.568, "dur": 65.124, + "args": { + "External id": 758865,"Sequence number": 8962111, "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": 688924278047.239, "dur": 7.080, + "args": { + "External id": 758866,"Sequence number": 8962111, "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": 688924278047.239, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924278049.667, "dur": 3.590, + "args": { + "External id": 758867,"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": 688924278051.775, "dur": 1.340, + "args": { + "External id": 758868,"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": 688924278055.296, "dur": 56.166, + "args": { + "External id": 758869,"Sequence number": 8962112, "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": 688924278056.834, "dur": 3.813, + "args": { + "External id": 758870,"Sequence number": 8962112, "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": 688924278058.201, "dur": 2.299, + "args": { + "External id": 758871,"Sequence number": 8962112, "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": 688924278058.201, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924278061.231, "dur": 43.263, + "args": { + "External id": 758872,"Sequence number": 8962113, "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": 688924278061.231, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924278106.565, "dur": 4.575, + "args": { + "External id": 758873,"Sequence number": 8962114, "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": 688924278106.565, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924278118.194, "dur": 62.131, + "args": { + "External id": 758874,"Sequence number": 8962115, "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": 688924278119.243, "dur": 9.133, + "args": { + "External id": 758875,"Sequence number": 8962115, "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": 688924278119.243, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924278121.578, "dur": 5.334, + "args": { + "External id": 758876,"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": 688924278123.585, "dur": 3.134, + "args": { + "External id": 758877,"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": 688924278129.148, "dur": 50.864, + "args": { + "External id": 758878,"Sequence number": 8962116, "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": 688924278130.403, "dur": 5.999, + "args": { + "External id": 758879,"Sequence number": 8962116, "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": 688924278131.569, "dur": 4.674, + "args": { + "External id": 758880,"Sequence number": 8962116, "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": 688924278131.569, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924278137.179, "dur": 36.044, + "args": { + "External id": 758881,"Sequence number": 8962117, "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": 688924278137.179, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924278174.833, "dur": 4.850, + "args": { + "External id": 758882,"Sequence number": 8962118, "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": 688924278174.833, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924278196.623, "dur": 4.495, + "args": { + "External id": 758883,"Sequence number": 8962119, "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": 688924278198.058, "dur": 2.903, + "args": { + "External id": 758884,"Sequence number": 8962119, "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": 688924278198.058, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924278207.712, "dur": 3.810, + "args": { + "External id": 758885,"Sequence number": 8962120, "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": 688924278209.293, "dur": 2.091, + "args": { + "External id": 758886,"Sequence number": 8962120, "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": 688924278209.293, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924278215.441, "dur": 3.177, + "args": { + "External id": 758887,"Sequence number": 8962121, "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": 688924278216.558, "dur": 1.928, + "args": { + "External id": 758888,"Sequence number": 8962121, "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": 688924278216.558, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924278248.782, "dur": 157.111, + "args": { + "External id": 758889,"Sequence number": 8962122, "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": 688924278248.782, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 688924278268.417, "dur": 10.927, + "args": { + "External id": 758890,"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": 688924278271.316, "dur": 7.610, + "args": { + "External id": 758891,"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": 688924278425.657, "dur": 103.727, + "args": { + "External id": 758892,"Sequence number": 8962123, "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": 688924278425.657, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183436, "tid": 4183436, + "ts": 688924278438.510, "dur": 7.238, + "args": { + "External id": 758893,"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": 688924278440.658, "dur": 4.693, + "args": { + "External id": 758894,"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": 688924278555.451, "dur": 258.571, + "args": { + "External id": 758895,"Sequence number": 8962124, "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": 688924278555.451, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183436, "tid": 4183436, + "ts": 688924278583.601, "dur": 186.470, + "args": { + "External id": 758896,"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": 688924278631.539, "dur": 6.582, + "args": { + "External id": 758897,"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": 688924278633.481, "dur": 4.255, + "args": { + "External id": 758898,"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": 688924278640.767, "dur": 4.029, + "args": { + "External id": 758899,"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": 688924278646.196, "dur": 2.000, + "args": { + "External id": 758900,"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": 688924278651.236, "dur": 59.017, + "args": { + "External id": 758901,"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": 688924278782.118, "dur": 19.255, + "args": { + "External id": 758902,"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": 688924278820.677, "dur": 7.067, + "args": { + "External id": 758903,"Sequence number": 8962125, "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": 688924278822.450, "dur": 5.154, + "args": { + "External id": 758904,"Sequence number": 8962125, "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": 688924278822.450, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924278839.552, "dur": 110.630, + "args": { + "External id": 758905,"Sequence number": 8962126, "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": 688924278840.970, "dur": 9.363, + "args": { + "External id": 758906,"Sequence number": 8962126, "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": 688924278840.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924278844.962, "dur": 4.274, + "args": { + "External id": 758907,"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": 688924278847.482, "dur": 1.512, + "args": { + "External id": 758908,"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": 688924278851.861, "dur": 98.051, + "args": { + "External id": 758909,"Sequence number": 8962127, "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": 688924278854.210, "dur": 3.951, + "args": { + "External id": 758910,"Sequence number": 8962127, "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": 688924278855.521, "dur": 2.518, + "args": { + "External id": 758911,"Sequence number": 8962127, "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": 688924278855.521, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924278859.379, "dur": 83.527, + "args": { + "External id": 758912,"Sequence number": 8962128, "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": 688924278859.379, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924278945.234, "dur": 3.978, + "args": { + "External id": 758913,"Sequence number": 8962129, "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": 688924278945.234, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924278986.249, "dur": 213.705, + "args": { + "External id": 758914,"Sequence number": 8962130, "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": 688924278986.249, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183436, "tid": 4183436, + "ts": 688924279005.506, "dur": 3.251, + "args": { + "External id": 758915,"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": 688924279006.782, "dur": 1.795, + "args": { + "External id": 758916,"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": 688924279012.979, "dur": 3.784, + "args": { + "External id": 758917,"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": 688924279014.246, "dur": 2.389, + "args": { + "External id": 758918,"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": 688924279015.429, "dur": 1.093, + "args": { + "External id": 758919,"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": 688924279023.983, "dur": 7.703, + "args": { + "External id": 758920,"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": 688924279026.422, "dur": 4.878, + "args": { + "External id": 758921,"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": 688924279038.386, "dur": 3.049, + "args": { + "External id": 758922,"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": 688924279045.121, "dur": 3.366, + "args": { + "External id": 758923,"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": 688924279177.750, "dur": 5.914, + "args": { + "External id": 758924,"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": 688924279179.220, "dur": 4.253, + "args": { + "External id": 758925,"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": 688924279186.520, "dur": 2.359, + "args": { + "External id": 758926,"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": 688924279187.328, "dur": 1.419, + "args": { + "External id": 758927,"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": 688924279217.294, "dur": 88.219, + "args": { + "External id": 758928,"Sequence number": 8962131, "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": 688924279218.210, "dur": 7.441, + "args": { + "External id": 758929,"Sequence number": 8962131, "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": 688924279218.210, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924279220.669, "dur": 3.834, + "args": { + "External id": 758930,"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": 688924279223.150, "dur": 1.130, + "args": { + "External id": 758931,"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": 688924279226.590, "dur": 78.634, + "args": { + "External id": 758932,"Sequence number": 8962132, "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": 688924279228.583, "dur": 6.120, + "args": { + "External id": 758933,"Sequence number": 8962132, "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": 688924279229.854, "dur": 4.673, + "args": { + "External id": 758934,"Sequence number": 8962132, "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": 688924279229.854, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924279235.644, "dur": 63.295, + "args": { + "External id": 758935,"Sequence number": 8962133, "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": 688924279235.644, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924279301.241, "dur": 3.358, + "args": { + "External id": 758936,"Sequence number": 8962134, "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": 688924279301.241, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183436, "tid": 4183436, + "ts": 688924279313.744, "dur": 74.437, + "args": { + "External id": 758937,"Sequence number": 8962135, "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": 688924279314.473, "dur": 11.756, + "args": { + "External id": 758938,"Sequence number": 8962135, "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": 688924279314.473, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183436, "tid": 4183436, + "ts": 688924279319.243, "dur": 5.706, + "args": { + "External id": 758939,"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": 688924279323.695, "dur": 1.069, + "args": { + "External id": 758940,"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": 688924279327.377, "dur": 60.528, + "args": { + "External id": 758941,"Sequence number": 8962136, "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": 688924279329.129, "dur": 5.543, + "args": { + "External id": 758942,"Sequence number": 8962136, "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": 688924279330.254, "dur": 4.063, + "args": { + "External id": 758943,"Sequence number": 8962136, "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": 688924279330.254, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183436, "tid": 4183436, + "ts": 688924279335.197, "dur": 44.464, + "args": { + "External id": 758944,"Sequence number": 8962137, "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": 688924279335.197, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183436, "tid": 4183436, + "ts": 688924279381.617, "dur": 6.002, + "args": { + "External id": 758945,"Sequence number": 8962138, "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": 688924279381.617, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924279407.771, "dur": 147.084, + "args": { + "External id": 758946,"Sequence number": 8962139, "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": 688924279407.771, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183436, "tid": 4183436, + "ts": 688924279448.045, "dur": 4.111, + "args": { + "External id": 758947,"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": 688924279484.493, "dur": 57.474, + "args": { + "External id": 758948,"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": 688924279485.151, "dur": 4.778, + "args": { + "External id": 758949,"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": 688924279486.492, "dur": 2.546, + "args": { + "External id": 758950,"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": 688924279488.179, "dur": 0.646, + "args": { + "External id": 758951,"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": 688924279490.979, "dur": 50.622, + "args": { + "External id": 758952,"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": 688924279492.523, "dur": 2.787, + "args": { + "External id": 758953,"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": 688924279493.639, "dur": 1.542, + "args": { + "External id": 758954,"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": 688924279496.192, "dur": 41.394, + "args": { + "External id": 758955,"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": 688924279539.693, "dur": 1.328, + "args": { + "External id": 758956,"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": 688924279563.435, "dur": 27.029, + "args": { + "External id": 758957,"Sequence number": 8962140, "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": 688924279563.435, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 4183436, "tid": 4183436, + "ts": 688924279608.599, "dur": 39.837, + "args": { + "External id": 758958,"Sequence number": 8962141, "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": 688924279608.599, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 4183436, "tid": 4183436, + "ts": 688924279617.243, "dur": 26.705, + "args": { + "External id": 758959,"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": 688924279645.436, "dur": 1.352, + "args": { + "External id": 758960,"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": 688924279730.396, "dur": 48.211, + "args": { + "External id": 758961,"Record function id": 0, "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 4183436, "tid": 4183436, + "ts": 688924279780.035, "dur": 222.521, + "args": { + "External id": 758962,"Record function id": 0, "Ev Idx": 6817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183436, "tid": 4183436, + "ts": 688924279835.729, "dur": 157.690, + "args": { + "External id": 758963,"Sequence number": 8962142, "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": 688924279835.729, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183436, "tid": 4183436, + "ts": 688924279906.581, "dur": 45.947, + "args": { + "External id": 758964,"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": 688924280081.813, "dur": 42.389, + "args": { + "External id": 758965,"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": 688924280085.108, "dur": 5.647, + "args": { + "External id": 758966,"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": 688924280093.316, "dur": 30.559, + "args": { + "External id": 758967,"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": 688924280096.371, "dur": 26.911, + "args": { + "External id": 758968,"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": 688924280128.843, "dur": 21.124, + "args": { + "External id": 758969,"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": 688924280130.067, "dur": 2.899, + "args": { + "External id": 758970,"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": 688924280134.032, "dur": 15.677, + "args": { + "External id": 758971,"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": 688924280134.877, "dur": 14.481, + "args": { + "External id": 758972,"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": 688924280152.977, "dur": 17.597, + "args": { + "External id": 758973,"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": 688924280153.950, "dur": 2.891, + "args": { + "External id": 758974,"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": 688924280157.922, "dur": 12.401, + "args": { + "External id": 758975,"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": 688924280158.467, "dur": 11.425, + "args": { + "External id": 758976,"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": 688924280181.074, "dur": 0.904, + "args": { + "External id": 758977,"Sequence number": 8962143, "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": 688924280190.638, "dur": 9.673, + "args": { + "External id": 758978,"Sequence number": 8962143, "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": 688924280196.276, "dur": 2.222, + "args": { + "External id": 758979,"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": 688924280207.017, "dur": 7.166, + "args": { + "External id": 758980,"Sequence number": 8962143, "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": 688924280210.946, "dur": 1.166, + "args": { + "External id": 758981,"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": 688924280215.297, "dur": 3.457, + "args": { + "External id": 758982,"Sequence number": 8962143, "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": 688924280217.144, "dur": 0.827, + "args": { + "External id": 758983,"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": 688924280220.004, "dur": 3.560, + "args": { + "External id": 758984,"Sequence number": 8962143, "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": 688924280222.210, "dur": 0.821, + "args": { + "External id": 758985,"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": 688924280226.714, "dur": 3.095, + "args": { + "External id": 758986,"Sequence number": 8962143, "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": 688924280228.574, "dur": 0.695, + "args": { + "External id": 758987,"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": 688924280230.755, "dur": 3.787, + "args": { + "External id": 758988,"Sequence number": 8962143, "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": 688924280233.003, "dur": 0.775, + "args": { + "External id": 758989,"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": 688924280235.638, "dur": 3.271, + "args": { + "External id": 758990,"Sequence number": 8962143, "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": 688924280237.444, "dur": 0.953, + "args": { + "External id": 758991,"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": 688924280243.972, "dur": 5.241, + "args": { + "External id": 758992,"Sequence number": 8962143, "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": 688924280247.633, "dur": 0.784, + "args": { + "External id": 758993,"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": 688924280253.309, "dur": 3.450, + "args": { + "External id": 758994,"Sequence number": 8962143, "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": 688924280255.328, "dur": 0.863, + "args": { + "External id": 758995,"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": 688924280259.729, "dur": 7.413, + "args": { + "External id": 758996,"Sequence number": 8962143, "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": 688924280265.234, "dur": 0.886, + "args": { + "External id": 758997,"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": 688924280268.315, "dur": 3.228, + "args": { + "External id": 758998,"Sequence number": 8962143, "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": 688924280270.329, "dur": 0.660, + "args": { + "External id": 758999,"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": 688924280274.193, "dur": 6.053, + "args": { + "External id": 759000,"Sequence number": 8962143, "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": 688924280274.193, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924280277.855, "dur": 0.858, + "args": { + "External id": 759001,"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": 688924280281.271, "dur": 5.500, + "args": { + "External id": 759002,"Sequence number": 8962144, "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": 688924280281.271, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924280285.099, "dur": 0.862, + "args": { + "External id": 759003,"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": 688924280287.833, "dur": 5.817, + "args": { + "External id": 759004,"Sequence number": 8962145, "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": 688924280287.833, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924280292.082, "dur": 0.755, + "args": { + "External id": 759005,"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": 688924280294.869, "dur": 4.346, + "args": { + "External id": 759006,"Sequence number": 8962146, "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": 688924280294.869, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924280297.842, "dur": 0.641, + "args": { + "External id": 759007,"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": 688924280303.560, "dur": 40.515, + "args": { + "External id": 759008,"Sequence number": 8962147, "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": 688924280306.048, "dur": 37.764, + "args": { + "External id": 759009,"Sequence number": 8962147, "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": 688924280308.857, "dur": 8.527, + "args": { + "External id": 759010,"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": 688924280311.057, "dur": 5.649, + "args": { + "External id": 759011,"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": 688924280319.347, "dur": 23.988, + "args": { + "External id": 759012,"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": 688924280367.107, "dur": 4.703, + "args": { + "External id": 759013,"Sequence number": 8962147, "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": 688924280367.107, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924280374.176, "dur": 1.542, + "args": { + "External id": 759014,"Sequence number": 8962148, "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": 688924280400.021, "dur": 21403.071, + "args": { + "External id": 759015,"Sequence number": 8962148, "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": 688924280400.021, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 4183436, + "ts": 688924280413.764, "dur": 27.508, + "args": { + "External id": 759016,"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": 688924280414.570, "dur": 26.521, + "args": { + "External id": 759017,"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": 688924280416.350, "dur": 4.945, + "args": { + "External id": 759018,"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": 688924280417.457, "dur": 3.370, + "args": { + "External id": 759019,"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": 688924280422.433, "dur": 18.293, + "args": { + "External id": 759020,"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": 688924280456.856, "dur": 33.980, + "args": { + "External id": 759021,"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": 688924280466.318, "dur": 7.497, + "args": { + "External id": 759022,"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": 688924280468.887, "dur": 4.580, + "args": { + "External id": 759023,"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": 688924280475.119, "dur": 15.500, + "args": { + "External id": 759024,"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": 688924280476.120, "dur": 14.119, + "args": { + "External id": 759025,"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": 688924280494.598, "dur": 22.085, + "args": { + "External id": 759026,"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": 688924280495.574, "dur": 5.077, + "args": { + "External id": 759027,"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": 688924280497.125, "dur": 3.284, + "args": { + "External id": 759028,"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": 688924280501.305, "dur": 15.145, + "args": { + "External id": 759029,"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": 688924280502.195, "dur": 13.818, + "args": { + "External id": 759030,"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": 688924280521.076, "dur": 16.951, + "args": { + "External id": 759031,"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": 688924280522.313, "dur": 3.072, + "args": { + "External id": 759032,"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": 688924280525.917, "dur": 11.822, + "args": { + "External id": 759033,"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": 688924280527.151, "dur": 10.226, + "args": { + "External id": 759034,"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": 688924280543.832, "dur": 26.035, + "args": { + "External id": 759035,"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": 688924280575.406, "dur": 59.539, + "args": { + "External id": 759036,"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": 688924280578.928, "dur": 55.546, + "args": { + "External id": 759037,"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": 688924280585.675, "dur": 1.208, + "args": { + "External id": 759038,"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": 688924280588.904, "dur": 27.819, + "args": { + "External id": 759039,"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": 688924280592.905, "dur": 23.624, + "args": { + "External id": 759040,"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": 688924280595.924, "dur": 3.114, + "args": { + "External id": 759041,"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": 688924280599.898, "dur": 16.311, + "args": { + "External id": 759042,"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": 688924280639.334, "dur": 15087.619, + "args": { + "External id": 759043,"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": 688924280641.269, "dur": 15084.477, + "args": { + "External id": 759044,"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": 688924295738.062, "dur": 6.873, + "args": { + "External id": 759045,"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": 688924295742.219, "dur": 1.257, + "args": { + "External id": 759046,"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": 688924295750.247, "dur": 125.160, + "args": { + "External id": 759047,"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": 688924295752.374, "dur": 7.488, + "args": { + "External id": 759048,"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": 688924295754.908, "dur": 3.952, + "args": { + "External id": 759049,"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": 688924295757.277, "dur": 1.359, + "args": { + "External id": 759050,"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": 688924295761.292, "dur": 113.394, + "args": { + "External id": 759051,"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": 688924295763.555, "dur": 109.738, + "args": { + "External id": 759052,"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": 688924295880.824, "dur": 5.954, + "args": { + "External id": 759053,"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": 688924295883.793, "dur": 0.913, + "args": { + "External id": 759054,"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": 688924295896.295, "dur": 4.356, + "args": { + "External id": 759055,"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": 688924295912.124, "dur": 7.489, + "args": { + "External id": 759056,"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": 688924295914.711, "dur": 4.584, + "args": { + "External id": 759057,"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": 688924296067.743, "dur": 237.591, + "args": { + "External id": 759058,"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": 688924296071.325, "dur": 4.627, + "args": { + "External id": 759059,"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": 688924296078.825, "dur": 225.677, + "args": { + "External id": 759060,"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": 688924296081.994, "dur": 0.498, + "args": { + "External id": 759061,"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": 688924296085.528, "dur": 28.929, + "args": { + "External id": 759062,"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": 688924296117.293, "dur": 6.511, + "args": { + "External id": 759063,"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": 688924296122.602, "dur": 0.917, + "args": { + "External id": 759064,"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": 688924296126.450, "dur": 26.391, + "args": { + "External id": 759065,"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": 688924296127.756, "dur": 1.600, + "args": { + "External id": 759066,"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": 688924296131.670, "dur": 20.727, + "args": { + "External id": 759067,"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": 688924296136.522, "dur": 3.404, + "args": { + "External id": 759068,"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": 688924296155.291, "dur": 23.849, + "args": { + "External id": 759069,"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": 688924296182.215, "dur": 17.225, + "args": { + "External id": 759070,"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": 688924296203.425, "dur": 16.860, + "args": { + "External id": 759071,"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": 688924296223.422, "dur": 16.306, + "args": { + "External id": 759072,"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": 688924296242.230, "dur": 27.141, + "args": { + "External id": 759073,"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": 688924296247.408, "dur": 1.917, + "args": { + "External id": 759074,"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": 688924296252.233, "dur": 1.036, + "args": { + "External id": 759075,"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": 688924296272.165, "dur": 16.585, + "args": { + "External id": 759076,"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": 688924296290.928, "dur": 12.663, + "args": { + "External id": 759077,"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": 688924296312.427, "dur": 2.350, + "args": { + "External id": 759078,"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": 688924296321.934, "dur": 4.666, + "args": { + "External id": 759079,"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": 688924296324.739, "dur": 0.924, + "args": { + "External id": 759080,"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": 688924296411.995, "dur": 64.777, + "args": { + "External id": 759081,"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": 688924296482.595, "dur": 5.495, + "args": { + "External id": 759082,"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": 688924296485.865, "dur": 1.025, + "args": { + "External id": 759083,"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": 688924296490.180, "dur": 29.792, + "args": { + "External id": 759084,"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": 688924296525.751, "dur": 6.935, + "args": { + "External id": 759085,"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": 688924296527.710, "dur": 4.139, + "args": { + "External id": 759086,"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": 688924296530.138, "dur": 1.428, + "args": { + "External id": 759087,"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": 688924296537.649, "dur": 53.402, + "args": { + "External id": 759088,"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": 688924296539.017, "dur": 51.422, + "args": { + "External id": 759089,"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": 688924296596.252, "dur": 17.890, + "args": { + "External id": 759090,"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": 688924296619.760, "dur": 4.597, + "args": { + "External id": 759091,"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": 688924296622.558, "dur": 0.999, + "args": { + "External id": 759092,"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": 688924296628.548, "dur": 107.230, + "args": { + "External id": 759093,"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": 688924296630.027, "dur": 12.109, + "args": { + "External id": 759094,"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": 688924296631.083, "dur": 10.437, + "args": { + "External id": 759095,"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": 688924296640.463, "dur": 0.926, + "args": { + "External id": 759096,"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": 688924296642.781, "dur": 92.425, + "args": { + "External id": 759097,"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": 688924296643.593, "dur": 90.435, + "args": { + "External id": 759098,"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": 688924296742.371, "dur": 5.327, + "args": { + "External id": 759099,"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": 688924296745.265, "dur": 1.041, + "args": { + "External id": 759100,"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": 688924296755.207, "dur": 2.065, + "args": { + "External id": 759101,"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": 688924296766.787, "dur": 9.636, + "args": { + "External id": 759102,"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": 688924296769.307, "dur": 6.757, + "args": { + "External id": 759103,"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": 688924296913.192, "dur": 272.814, + "args": { + "External id": 759104,"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": 688924296915.864, "dur": 2.980, + "args": { + "External id": 759105,"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": 688924296920.807, "dur": 264.635, + "args": { + "External id": 759106,"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": 688924296923.150, "dur": 0.495, + "args": { + "External id": 759107,"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": 688924296925.453, "dur": 39.315, + "args": { + "External id": 759108,"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": 688924296966.758, "dur": 3.976, + "args": { + "External id": 759109,"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": 688924296969.440, "dur": 0.988, + "args": { + "External id": 759110,"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": 688924296972.900, "dur": 36.438, + "args": { + "External id": 759111,"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": 688924296974.293, "dur": 1.697, + "args": { + "External id": 759112,"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": 688924296977.464, "dur": 31.493, + "args": { + "External id": 759113,"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": 688924296983.675, "dur": 2.910, + "args": { + "External id": 759114,"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": 688924297011.352, "dur": 37.736, + "args": { + "External id": 759115,"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": 688924297050.988, "dur": 26.161, + "args": { + "External id": 759116,"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": 688924297080.425, "dur": 27.984, + "args": { + "External id": 759117,"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": 688924297110.589, "dur": 18.175, + "args": { + "External id": 759118,"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": 688924297130.650, "dur": 23.819, + "args": { + "External id": 759119,"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": 688924297132.891, "dur": 2.282, + "args": { + "External id": 759120,"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": 688924297138.116, "dur": 0.817, + "args": { + "External id": 759121,"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": 688924297156.421, "dur": 14.039, + "args": { + "External id": 759122,"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": 688924297172.081, "dur": 12.301, + "args": { + "External id": 759123,"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": 688924297193.358, "dur": 2.757, + "args": { + "External id": 759124,"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": 688924297206.045, "dur": 3.713, + "args": { + "External id": 759125,"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": 688924297208.394, "dur": 0.503, + "args": { + "External id": 759126,"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": 688924297283.172, "dur": 55.357, + "args": { + "External id": 759127,"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": 688924297343.427, "dur": 5.969, + "args": { + "External id": 759128,"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": 688924297346.815, "dur": 1.384, + "args": { + "External id": 759129,"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": 688924297350.884, "dur": 27.036, + "args": { + "External id": 759130,"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": 688924297382.487, "dur": 15.015, + "args": { + "External id": 759131,"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": 688924297390.266, "dur": 6.457, + "args": { + "External id": 759132,"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": 688924297395.378, "dur": 1.122, + "args": { + "External id": 759133,"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": 688924297400.506, "dur": 46.942, + "args": { + "External id": 759134,"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": 688924297401.779, "dur": 45.016, + "args": { + "External id": 759135,"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": 688924297451.806, "dur": 17.850, + "args": { + "External id": 759136,"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": 688924297475.505, "dur": 4.147, + "args": { + "External id": 759137,"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": 688924297477.969, "dur": 0.841, + "args": { + "External id": 759138,"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": 688924297483.984, "dur": 53.561, + "args": { + "External id": 759139,"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": 688924297484.843, "dur": 6.766, + "args": { + "External id": 759140,"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": 688924297485.795, "dur": 5.142, + "args": { + "External id": 759141,"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": 688924297487.632, "dur": 3.100, + "args": { + "External id": 759142,"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": 688924297492.826, "dur": 44.111, + "args": { + "External id": 759143,"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": 688924297493.680, "dur": 42.716, + "args": { + "External id": 759144,"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": 688924297542.579, "dur": 4.646, + "args": { + "External id": 759145,"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": 688924297544.722, "dur": 1.320, + "args": { + "External id": 759146,"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": 688924297553.085, "dur": 1.744, + "args": { + "External id": 759147,"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": 688924297563.270, "dur": 6.230, + "args": { + "External id": 759148,"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": 688924297565.614, "dur": 3.602, + "args": { + "External id": 759149,"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": 688924297701.053, "dur": 217.933, + "args": { + "External id": 759150,"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": 688924297704.390, "dur": 3.645, + "args": { + "External id": 759151,"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": 688924297710.298, "dur": 208.019, + "args": { + "External id": 759152,"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": 688924297711.958, "dur": 0.453, + "args": { + "External id": 759153,"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": 688924297716.663, "dur": 25.640, + "args": { + "External id": 759154,"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": 688924297744.089, "dur": 4.474, + "args": { + "External id": 759155,"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": 688924297746.844, "dur": 1.426, + "args": { + "External id": 759156,"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": 688924297749.574, "dur": 24.363, + "args": { + "External id": 759157,"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": 688924297750.717, "dur": 3.946, + "args": { + "External id": 759158,"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": 688924297756.323, "dur": 17.223, + "args": { + "External id": 759159,"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": 688924297759.255, "dur": 2.466, + "args": { + "External id": 759160,"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": 688924297775.640, "dur": 37.650, + "args": { + "External id": 759161,"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": 688924297815.686, "dur": 19.380, + "args": { + "External id": 759162,"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": 688924297838.422, "dur": 15.950, + "args": { + "External id": 759163,"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": 688924297856.121, "dur": 12.326, + "args": { + "External id": 759164,"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": 688924297870.633, "dur": 20.669, + "args": { + "External id": 759165,"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": 688924297872.832, "dur": 1.868, + "args": { + "External id": 759166,"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": 688924297877.461, "dur": 0.938, + "args": { + "External id": 759167,"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": 688924297893.133, "dur": 12.007, + "args": { + "External id": 759168,"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": 688924297906.371, "dur": 10.849, + "args": { + "External id": 759169,"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": 688924297927.259, "dur": 2.581, + "args": { + "External id": 759170,"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": 688924297941.490, "dur": 4.301, + "args": { + "External id": 759171,"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": 688924297944.172, "dur": 0.819, + "args": { + "External id": 759172,"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": 688924298020.211, "dur": 52.941, + "args": { + "External id": 759173,"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": 688924298078.106, "dur": 5.034, + "args": { + "External id": 759174,"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": 688924298081.047, "dur": 0.946, + "args": { + "External id": 759175,"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": 688924298084.973, "dur": 23.525, + "args": { + "External id": 759176,"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": 688924298112.985, "dur": 6.705, + "args": { + "External id": 759177,"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": 688924298114.924, "dur": 4.018, + "args": { + "External id": 759178,"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": 688924298117.498, "dur": 1.243, + "args": { + "External id": 759179,"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": 688924298123.072, "dur": 44.979, + "args": { + "External id": 759180,"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": 688924298123.994, "dur": 43.433, + "args": { + "External id": 759181,"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": 688924298172.178, "dur": 16.404, + "args": { + "External id": 759182,"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": 688924298194.360, "dur": 4.364, + "args": { + "External id": 759183,"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": 688924298196.789, "dur": 1.023, + "args": { + "External id": 759184,"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": 688924298202.898, "dur": 62.249, + "args": { + "External id": 759185,"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": 688924298204.398, "dur": 6.599, + "args": { + "External id": 759186,"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": 688924298205.064, "dur": 5.058, + "args": { + "External id": 759187,"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": 688924298209.178, "dur": 0.795, + "args": { + "External id": 759188,"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": 688924298211.697, "dur": 53.013, + "args": { + "External id": 759189,"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": 688924298212.706, "dur": 51.392, + "args": { + "External id": 759190,"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": 688924298269.497, "dur": 4.198, + "args": { + "External id": 759191,"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": 688924298271.361, "dur": 1.132, + "args": { + "External id": 759192,"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": 688924298279.473, "dur": 1.580, + "args": { + "External id": 759193,"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": 688924298288.910, "dur": 6.683, + "args": { + "External id": 759194,"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": 688924298291.248, "dur": 4.080, + "args": { + "External id": 759195,"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": 688924298382.229, "dur": 186.065, + "args": { + "External id": 759196,"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": 688924298384.520, "dur": 2.158, + "args": { + "External id": 759197,"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": 688924298388.187, "dur": 179.683, + "args": { + "External id": 759198,"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": 688924298392.085, "dur": 0.374, + "args": { + "External id": 759199,"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": 688924298393.945, "dur": 21.429, + "args": { + "External id": 759200,"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": 688924298417.109, "dur": 3.391, + "args": { + "External id": 759201,"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": 688924298419.141, "dur": 1.094, + "args": { + "External id": 759202,"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": 688924298421.937, "dur": 23.979, + "args": { + "External id": 759203,"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": 688924298425.687, "dur": 1.599, + "args": { + "External id": 759204,"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": 688924298428.605, "dur": 17.072, + "args": { + "External id": 759205,"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": 688924298430.929, "dur": 2.427, + "args": { + "External id": 759206,"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": 688924298447.468, "dur": 22.755, + "args": { + "External id": 759207,"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": 688924298471.818, "dur": 13.062, + "args": { + "External id": 759208,"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": 688924298487.628, "dur": 15.267, + "args": { + "External id": 759209,"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": 688924298504.616, "dur": 13.372, + "args": { + "External id": 759210,"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": 688924298519.735, "dur": 21.181, + "args": { + "External id": 759211,"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": 688924298521.783, "dur": 1.811, + "args": { + "External id": 759212,"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": 688924298526.097, "dur": 0.822, + "args": { + "External id": 759213,"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": 688924298542.526, "dur": 11.336, + "args": { + "External id": 759214,"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": 688924298555.085, "dur": 11.581, + "args": { + "External id": 759215,"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": 688924298573.833, "dur": 1.977, + "args": { + "External id": 759216,"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": 688924298583.566, "dur": 3.747, + "args": { + "External id": 759217,"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": 688924298586.052, "dur": 0.397, + "args": { + "External id": 759218,"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": 688924298649.769, "dur": 92.546, + "args": { + "External id": 759219,"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": 688924298749.326, "dur": 6.684, + "args": { + "External id": 759220,"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": 688924298753.288, "dur": 1.071, + "args": { + "External id": 759221,"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": 688924298758.070, "dur": 26.758, + "args": { + "External id": 759222,"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": 688924298806.045, "dur": 8.559, + "args": { + "External id": 759223,"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": 688924298808.064, "dur": 5.600, + "args": { + "External id": 759224,"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": 688924298810.181, "dur": 3.159, + "args": { + "External id": 759225,"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": 688924298817.974, "dur": 47.660, + "args": { + "External id": 759226,"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": 688924298819.466, "dur": 45.587, + "args": { + "External id": 759227,"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": 688924298869.932, "dur": 16.330, + "args": { + "External id": 759228,"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": 688924298892.627, "dur": 5.056, + "args": { + "External id": 759229,"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": 688924298895.633, "dur": 0.939, + "args": { + "External id": 759230,"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": 688924298901.573, "dur": 49.515, + "args": { + "External id": 759231,"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": 688924298902.753, "dur": 4.342, + "args": { + "External id": 759232,"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": 688924298903.651, "dur": 2.798, + "args": { + "External id": 759233,"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": 688924298905.526, "dur": 0.794, + "args": { + "External id": 759234,"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": 688924298907.931, "dur": 42.637, + "args": { + "External id": 759235,"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": 688924298908.924, "dur": 41.017, + "args": { + "External id": 759236,"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": 688924298955.500, "dur": 3.509, + "args": { + "External id": 759237,"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": 688924298957.161, "dur": 0.738, + "args": { + "External id": 759238,"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": 688924298965.993, "dur": 1.588, + "args": { + "External id": 759239,"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": 688924298975.495, "dur": 6.955, + "args": { + "External id": 759240,"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": 688924298977.975, "dur": 4.201, + "args": { + "External id": 759241,"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": 688924299071.663, "dur": 176.037, + "args": { + "External id": 759242,"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": 688924299073.926, "dur": 2.857, + "args": { + "External id": 759243,"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": 688924299080.720, "dur": 166.433, + "args": { + "External id": 759244,"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": 688924299082.126, "dur": 0.411, + "args": { + "External id": 759245,"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": 688924299084.230, "dur": 20.763, + "args": { + "External id": 759246,"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": 688924299106.973, "dur": 5.514, + "args": { + "External id": 759247,"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": 688924299109.161, "dur": 3.074, + "args": { + "External id": 759248,"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": 688924299113.771, "dur": 20.653, + "args": { + "External id": 759249,"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": 688924299114.982, "dur": 1.750, + "args": { + "External id": 759250,"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": 688924299117.886, "dur": 16.282, + "args": { + "External id": 759251,"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": 688924299120.296, "dur": 2.545, + "args": { + "External id": 759252,"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": 688924299136.133, "dur": 19.726, + "args": { + "External id": 759253,"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": 688924299157.280, "dur": 13.299, + "args": { + "External id": 759254,"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": 688924299173.358, "dur": 13.075, + "args": { + "External id": 759255,"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": 688924299187.895, "dur": 11.881, + "args": { + "External id": 759256,"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": 688924299201.471, "dur": 19.666, + "args": { + "External id": 759257,"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": 688924299203.758, "dur": 1.728, + "args": { + "External id": 759258,"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": 688924299207.979, "dur": 0.928, + "args": { + "External id": 759259,"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": 688924299222.933, "dur": 10.674, + "args": { + "External id": 759260,"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": 688924299234.728, "dur": 10.995, + "args": { + "External id": 759261,"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": 688924299253.518, "dur": 2.025, + "args": { + "External id": 759262,"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": 688924299276.708, "dur": 3.393, + "args": { + "External id": 759263,"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": 688924299278.815, "dur": 0.452, + "args": { + "External id": 759264,"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": 688924299341.945, "dur": 39.773, + "args": { + "External id": 759265,"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": 688924299386.430, "dur": 6.838, + "args": { + "External id": 759266,"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": 688924299389.332, "dur": 2.969, + "args": { + "External id": 759267,"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": 688924299394.732, "dur": 22.163, + "args": { + "External id": 759268,"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": 688924299421.044, "dur": 6.530, + "args": { + "External id": 759269,"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": 688924299422.776, "dur": 4.025, + "args": { + "External id": 759270,"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": 688924299425.214, "dur": 1.409, + "args": { + "External id": 759271,"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": 688924299430.061, "dur": 42.026, + "args": { + "External id": 759272,"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": 688924299431.383, "dur": 40.131, + "args": { + "External id": 759273,"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": 688924299475.922, "dur": 14.597, + "args": { + "External id": 759274,"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": 688924299495.752, "dur": 4.107, + "args": { + "External id": 759275,"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": 688924299498.232, "dur": 0.760, + "args": { + "External id": 759276,"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": 688924299503.886, "dur": 48.229, + "args": { + "External id": 759277,"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": 688924299504.759, "dur": 4.266, + "args": { + "External id": 759278,"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": 688924299505.777, "dur": 2.614, + "args": { + "External id": 759279,"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": 688924299507.533, "dur": 0.735, + "args": { + "External id": 759280,"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": 688924299510.166, "dur": 41.589, + "args": { + "External id": 759281,"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": 688924299510.891, "dur": 40.414, + "args": { + "External id": 759282,"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": 688924299556.121, "dur": 3.905, + "args": { + "External id": 759283,"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": 688924299558.288, "dur": 0.789, + "args": { + "External id": 759284,"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": 688924299565.054, "dur": 1.420, + "args": { + "External id": 759285,"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": 688924299573.695, "dur": 5.957, + "args": { + "External id": 759286,"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": 688924299575.765, "dur": 3.607, + "args": { + "External id": 759287,"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": 688924299700.919, "dur": 325.983, + "args": { + "External id": 759288,"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": 688924299703.420, "dur": 5.811, + "args": { + "External id": 759289,"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": 688924299711.429, "dur": 314.754, + "args": { + "External id": 759290,"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": 688924299713.451, "dur": 0.396, + "args": { + "External id": 759291,"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": 688924299715.217, "dur": 26.849, + "args": { + "External id": 759292,"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": 688924299743.869, "dur": 6.467, + "args": { + "External id": 759293,"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": 688924299748.756, "dur": 1.308, + "args": { + "External id": 759294,"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": 688924299751.469, "dur": 134.490, + "args": { + "External id": 759295,"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": 688924299752.686, "dur": 1.842, + "args": { + "External id": 759296,"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": 688924299859.248, "dur": 26.006, + "args": { + "External id": 759297,"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": 688924299865.443, "dur": 3.126, + "args": { + "External id": 759298,"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": 688924299887.665, "dur": 27.718, + "args": { + "External id": 759299,"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": 688924299916.714, "dur": 15.194, + "args": { + "External id": 759300,"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": 688924299935.122, "dur": 17.995, + "args": { + "External id": 759301,"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": 688924299954.644, "dur": 13.656, + "args": { + "External id": 759302,"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": 688924299970.060, "dur": 25.833, + "args": { + "External id": 759303,"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": 688924299974.215, "dur": 1.602, + "args": { + "External id": 759304,"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": 688924299978.708, "dur": 0.932, + "args": { + "External id": 759305,"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": 688924299997.773, "dur": 13.485, + "args": { + "External id": 759306,"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": 688924300012.527, "dur": 12.063, + "args": { + "External id": 759307,"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": 688924300036.851, "dur": 2.824, + "args": { + "External id": 759308,"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": 688924300051.390, "dur": 4.845, + "args": { + "External id": 759309,"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": 688924300054.664, "dur": 0.341, + "args": { + "External id": 759310,"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": 688924300137.905, "dur": 61.884, + "args": { + "External id": 759311,"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": 688924300204.762, "dur": 5.574, + "args": { + "External id": 759312,"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": 688924300208.058, "dur": 0.968, + "args": { + "External id": 759313,"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": 688924300211.736, "dur": 27.640, + "args": { + "External id": 759314,"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": 688924300244.177, "dur": 7.111, + "args": { + "External id": 759315,"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": 688924300245.982, "dur": 4.546, + "args": { + "External id": 759316,"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": 688924300248.663, "dur": 1.647, + "args": { + "External id": 759317,"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": 688924300254.275, "dur": 44.474, + "args": { + "External id": 759318,"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": 688924300255.509, "dur": 42.616, + "args": { + "External id": 759319,"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": 688924300302.911, "dur": 15.917, + "args": { + "External id": 759320,"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": 688924300324.672, "dur": 4.259, + "args": { + "External id": 759321,"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": 688924300327.452, "dur": 0.614, + "args": { + "External id": 759322,"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": 688924300333.491, "dur": 50.269, + "args": { + "External id": 759323,"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": 688924300334.436, "dur": 4.547, + "args": { + "External id": 759324,"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": 688924300335.516, "dur": 2.856, + "args": { + "External id": 759325,"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": 688924300337.302, "dur": 0.839, + "args": { + "External id": 759326,"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": 688924300340.163, "dur": 43.241, + "args": { + "External id": 759327,"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": 688924300341.038, "dur": 41.815, + "args": { + "External id": 759328,"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": 688924300388.289, "dur": 4.262, + "args": { + "External id": 759329,"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": 688924300390.652, "dur": 0.820, + "args": { + "External id": 759330,"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": 688924300398.390, "dur": 1.446, + "args": { + "External id": 759331,"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": 688924300408.559, "dur": 6.665, + "args": { + "External id": 759332,"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": 688924300411.226, "dur": 3.762, + "args": { + "External id": 759333,"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": 688924300507.138, "dur": 239.024, + "args": { + "External id": 759334,"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": 688924300511.754, "dur": 2.270, + "args": { + "External id": 759335,"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": 688924300515.991, "dur": 229.551, + "args": { + "External id": 759336,"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": 688924300517.676, "dur": 0.453, + "args": { + "External id": 759337,"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": 688924300519.606, "dur": 21.403, + "args": { + "External id": 759338,"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": 688924300542.643, "dur": 5.699, + "args": { + "External id": 759339,"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": 688924300546.936, "dur": 1.097, + "args": { + "External id": 759340,"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": 688924300549.443, "dur": 21.845, + "args": { + "External id": 759341,"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": 688924300550.947, "dur": 1.476, + "args": { + "External id": 759342,"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": 688924300554.201, "dur": 16.832, + "args": { + "External id": 759343,"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": 688924300556.464, "dur": 2.519, + "args": { + "External id": 759344,"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": 688924300572.959, "dur": 20.990, + "args": { + "External id": 759345,"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": 688924300595.559, "dur": 14.339, + "args": { + "External id": 759346,"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": 688924300618.632, "dur": 16.106, + "args": { + "External id": 759347,"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": 688924300635.972, "dur": 14.308, + "args": { + "External id": 759348,"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": 688924300690.422, "dur": 26.375, + "args": { + "External id": 759349,"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": 688924300694.201, "dur": 2.143, + "args": { + "External id": 759350,"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": 688924300698.885, "dur": 0.834, + "args": { + "External id": 759351,"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": 688924300718.702, "dur": 12.915, + "args": { + "External id": 759352,"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": 688924300732.592, "dur": 11.123, + "args": { + "External id": 759353,"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": 688924300753.908, "dur": 2.529, + "args": { + "External id": 759354,"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": 688924300766.434, "dur": 3.809, + "args": { + "External id": 759355,"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": 688924300768.733, "dur": 0.401, + "args": { + "External id": 759356,"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": 688924300857.418, "dur": 51.413, + "args": { + "External id": 759357,"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": 688924300914.611, "dur": 6.287, + "args": { + "External id": 759358,"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": 688924300918.071, "dur": 1.209, + "args": { + "External id": 759359,"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": 688924300922.323, "dur": 24.773, + "args": { + "External id": 759360,"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": 688924300951.948, "dur": 7.978, + "args": { + "External id": 759361,"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": 688924300953.598, "dur": 5.667, + "args": { + "External id": 759362,"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": 688924300955.797, "dur": 3.201, + "args": { + "External id": 759363,"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": 688924300962.670, "dur": 42.295, + "args": { + "External id": 759364,"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": 688924300963.856, "dur": 40.409, + "args": { + "External id": 759365,"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": 688924301009.049, "dur": 14.334, + "args": { + "External id": 759366,"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": 688924301029.010, "dur": 4.379, + "args": { + "External id": 759367,"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": 688924301031.233, "dur": 1.260, + "args": { + "External id": 759368,"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": 688924301037.765, "dur": 48.369, + "args": { + "External id": 759369,"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": 688924301038.582, "dur": 4.700, + "args": { + "External id": 759370,"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": 688924301039.723, "dur": 2.914, + "args": { + "External id": 759371,"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": 688924301041.812, "dur": 0.645, + "args": { + "External id": 759372,"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": 688924301044.107, "dur": 41.683, + "args": { + "External id": 759373,"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": 688924301044.755, "dur": 40.404, + "args": { + "External id": 759374,"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": 688924301090.364, "dur": 4.104, + "args": { + "External id": 759375,"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": 688924301092.525, "dur": 0.760, + "args": { + "External id": 759376,"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": 688924301100.787, "dur": 1.757, + "args": { + "External id": 759377,"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": 688924301110.851, "dur": 7.750, + "args": { + "External id": 759378,"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": 688924301113.405, "dur": 4.945, + "args": { + "External id": 759379,"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": 688924301200.858, "dur": 184.168, + "args": { + "External id": 759380,"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": 688924301203.185, "dur": 2.598, + "args": { + "External id": 759381,"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": 688924301209.725, "dur": 174.597, + "args": { + "External id": 759382,"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": 688924301211.703, "dur": 0.424, + "args": { + "External id": 759383,"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": 688924301213.869, "dur": 19.766, + "args": { + "External id": 759384,"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": 688924301235.193, "dur": 6.058, + "args": { + "External id": 759385,"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": 688924301237.769, "dur": 3.064, + "args": { + "External id": 759386,"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": 688924301242.289, "dur": 21.678, + "args": { + "External id": 759387,"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": 688924301243.660, "dur": 1.880, + "args": { + "External id": 759388,"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": 688924301247.217, "dur": 16.521, + "args": { + "External id": 759389,"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": 688924301249.834, "dur": 2.656, + "args": { + "External id": 759390,"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": 688924301265.462, "dur": 19.497, + "args": { + "External id": 759391,"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": 688924301286.626, "dur": 12.733, + "args": { + "External id": 759392,"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": 688924301302.044, "dur": 13.685, + "args": { + "External id": 759393,"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": 688924301317.150, "dur": 11.714, + "args": { + "External id": 759394,"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": 688924301330.606, "dur": 22.597, + "args": { + "External id": 759395,"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": 688924301332.290, "dur": 1.916, + "args": { + "External id": 759396,"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": 688924301336.621, "dur": 3.073, + "args": { + "External id": 759397,"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": 688924301354.665, "dur": 13.057, + "args": { + "External id": 759398,"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": 688924301368.823, "dur": 14.456, + "args": { + "External id": 759399,"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": 688924301390.842, "dur": 1.563, + "args": { + "External id": 759400,"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": 688924301401.140, "dur": 4.305, + "args": { + "External id": 759401,"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": 688924301403.630, "dur": 0.489, + "args": { + "External id": 759402,"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": 688924301463.508, "dur": 43.678, + "args": { + "External id": 759403,"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": 688924301511.638, "dur": 4.557, + "args": { + "External id": 759404,"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": 688924301514.115, "dur": 0.880, + "args": { + "External id": 759405,"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": 688924301517.990, "dur": 23.852, + "args": { + "External id": 759406,"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": 688924301545.885, "dur": 6.297, + "args": { + "External id": 759407,"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": 688924301547.453, "dur": 4.061, + "args": { + "External id": 759408,"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": 688924301549.677, "dur": 1.627, + "args": { + "External id": 759409,"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": 688924301554.961, "dur": 41.233, + "args": { + "External id": 759410,"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": 688924301556.084, "dur": 39.586, + "args": { + "External id": 759411,"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": 688924301600.062, "dur": 15.994, + "args": { + "External id": 759412,"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": 688924301621.100, "dur": 25.265, + "args": { + "External id": 759413,"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": 688924301623.519, "dur": 22.462, + "args": { + "External id": 759414,"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": 688924301628.712, "dur": 1.283, + "args": { + "External id": 759415,"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": 688924301703.065, "dur": 34.264, + "args": { + "External id": 759416,"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": 688924301706.443, "dur": 30.718, + "args": { + "External id": 759417,"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": 688924301712.111, "dur": 5.107, + "args": { + "External id": 759418,"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": 688924301718.858, "dur": 17.799, + "args": { + "External id": 759419,"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": 688924301754.870, "dur": 6.187, + "args": { + "External id": 759420,"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": 688924301757.300, "dur": 3.412, + "args": { + "External id": 759421,"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": 688924301762.371, "dur": 1.384, + "args": { + "External id": 759422,"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": 688924301763.109, "dur": 0.551, + "args": { + "External id": 759423,"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": 688924301825.076, "dur": 27.076, + "args": { + "External id": 759424,"Sequence number": 8962149, "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": 688924301825.076, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183436, "tid": 4183436, + "ts": 688924301859.258, "dur": 7.337, + "args": { + "External id": 759425,"Sequence number": 8962150, "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": 688924301863.453, "dur": 1.494, + "args": { + "External id": 759426,"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": 688924301869.567, "dur": 6.745, + "args": { + "External id": 759427,"Sequence number": 8962150, "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": 688924301874.335, "dur": 0.721, + "args": { + "External id": 759428,"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": 688924301877.842, "dur": 3.264, + "args": { + "External id": 759429,"Sequence number": 8962150, "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": 688924301879.830, "dur": 0.686, + "args": { + "External id": 759430,"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": 688924301885.759, "dur": 6.661, + "args": { + "External id": 759431,"Sequence number": 8962150, "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": 688924301885.759, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924301890.026, "dur": 1.148, + "args": { + "External id": 759432,"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": 688924301893.489, "dur": 5.483, + "args": { + "External id": 759433,"Sequence number": 8962151, "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": 688924301893.489, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924301897.545, "dur": 0.667, + "args": { + "External id": 759434,"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": 688924301900.190, "dur": 6.159, + "args": { + "External id": 759435,"Sequence number": 8962152, "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": 688924301900.190, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924301904.714, "dur": 0.781, + "args": { + "External id": 759436,"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": 688924301907.350, "dur": 4.313, + "args": { + "External id": 759437,"Sequence number": 8962153, "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": 688924301907.350, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924301909.886, "dur": 1.025, + "args": { + "External id": 759438,"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": 688924301915.831, "dur": 31.707, + "args": { + "External id": 759439,"Sequence number": 8962154, "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": 688924301917.734, "dur": 29.548, + "args": { + "External id": 759440,"Sequence number": 8962154, "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": 688924301920.297, "dur": 7.451, + "args": { + "External id": 759441,"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": 688924301923.208, "dur": 3.901, + "args": { + "External id": 759442,"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": 688924301928.623, "dur": 18.211, + "args": { + "External id": 759443,"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": 688924301976.370, "dur": 7.239, + "args": { + "External id": 759444,"Sequence number": 8962154, "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": 688924301976.370, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924301986.298, "dur": 1.119, + "args": { + "External id": 759445,"Sequence number": 8962155, "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": 688924302020.046, "dur": 22727.351, + "args": { + "External id": 759446,"Sequence number": 8962155, "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": 688924302020.046, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 4183436, + "ts": 688924302035.444, "dur": 27.206, + "args": { + "External id": 759447,"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": 688924302036.510, "dur": 25.958, + "args": { + "External id": 759448,"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": 688924302037.707, "dur": 6.197, + "args": { + "External id": 759449,"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": 688924302039.316, "dur": 4.178, + "args": { + "External id": 759450,"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": 688924302044.800, "dur": 17.266, + "args": { + "External id": 759451,"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": 688924302078.411, "dur": 28.027, + "args": { + "External id": 759452,"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": 688924302079.880, "dur": 6.519, + "args": { + "External id": 759453,"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": 688924302082.315, "dur": 3.651, + "args": { + "External id": 759454,"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": 688924302087.929, "dur": 18.288, + "args": { + "External id": 759455,"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": 688924302090.070, "dur": 15.744, + "args": { + "External id": 759456,"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": 688924302109.761, "dur": 21.213, + "args": { + "External id": 759457,"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": 688924302110.711, "dur": 5.080, + "args": { + "External id": 759458,"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": 688924302112.388, "dur": 3.160, + "args": { + "External id": 759459,"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": 688924302116.459, "dur": 14.323, + "args": { + "External id": 759460,"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": 688924302117.093, "dur": 13.342, + "args": { + "External id": 759461,"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": 688924302136.984, "dur": 20.247, + "args": { + "External id": 759462,"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": 688924302141.096, "dur": 2.643, + "args": { + "External id": 759463,"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": 688924302144.462, "dur": 12.518, + "args": { + "External id": 759464,"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": 688924302145.516, "dur": 11.085, + "args": { + "External id": 759465,"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": 688924302162.132, "dur": 21.427, + "args": { + "External id": 759466,"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": 688924302186.803, "dur": 49.725, + "args": { + "External id": 759467,"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": 688924302189.306, "dur": 46.744, + "args": { + "External id": 759468,"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": 688924302193.499, "dur": 1.235, + "args": { + "External id": 759469,"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": 688924302196.290, "dur": 22.437, + "args": { + "External id": 759470,"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": 688924302198.178, "dur": 20.362, + "args": { + "External id": 759471,"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": 688924302201.921, "dur": 2.832, + "args": { + "External id": 759472,"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": 688924302205.968, "dur": 12.254, + "args": { + "External id": 759473,"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": 688924302240.463, "dur": 16502.274, + "args": { + "External id": 759474,"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": 688924302241.909, "dur": 16499.619, + "args": { + "External id": 759475,"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": 688924318754.622, "dur": 8.419, + "args": { + "External id": 759476,"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": 688924318760.530, "dur": 0.960, + "args": { + "External id": 759477,"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": 688924318768.388, "dur": 118.604, + "args": { + "External id": 759478,"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": 688924318770.060, "dur": 6.811, + "args": { + "External id": 759479,"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": 688924318772.472, "dur": 3.406, + "args": { + "External id": 759480,"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": 688924318774.709, "dur": 0.911, + "args": { + "External id": 759481,"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": 688924318778.706, "dur": 107.378, + "args": { + "External id": 759482,"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": 688924318780.605, "dur": 103.933, + "args": { + "External id": 759483,"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": 688924318892.259, "dur": 5.269, + "args": { + "External id": 759484,"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": 688924318895.050, "dur": 1.013, + "args": { + "External id": 759485,"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": 688924318905.656, "dur": 2.671, + "args": { + "External id": 759486,"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": 688924318917.843, "dur": 7.387, + "args": { + "External id": 759487,"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": 688924318920.213, "dur": 4.666, + "args": { + "External id": 759488,"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": 688924319058.005, "dur": 214.702, + "args": { + "External id": 759489,"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": 688924319061.354, "dur": 2.850, + "args": { + "External id": 759490,"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": 688924319068.632, "dur": 203.562, + "args": { + "External id": 759491,"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": 688924319070.668, "dur": 0.490, + "args": { + "External id": 759492,"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": 688924319073.220, "dur": 26.007, + "args": { + "External id": 759493,"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": 688924319101.113, "dur": 5.870, + "args": { + "External id": 759494,"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": 688924319103.532, "dur": 3.012, + "args": { + "External id": 759495,"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": 688924319108.594, "dur": 37.033, + "args": { + "External id": 759496,"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": 688924319123.297, "dur": 1.643, + "args": { + "External id": 759497,"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": 688924319126.492, "dur": 18.824, + "args": { + "External id": 759498,"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": 688924319130.239, "dur": 3.417, + "args": { + "External id": 759499,"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": 688924319147.533, "dur": 22.212, + "args": { + "External id": 759500,"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": 688924319171.888, "dur": 17.458, + "args": { + "External id": 759501,"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": 688924319192.634, "dur": 14.184, + "args": { + "External id": 759502,"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": 688924319208.469, "dur": 13.535, + "args": { + "External id": 759503,"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": 688924319224.157, "dur": 20.485, + "args": { + "External id": 759504,"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": 688924319226.371, "dur": 1.755, + "args": { + "External id": 759505,"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": 688924319230.712, "dur": 0.750, + "args": { + "External id": 759506,"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": 688924319246.128, "dur": 12.541, + "args": { + "External id": 759507,"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": 688924319260.232, "dur": 11.004, + "args": { + "External id": 759508,"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": 688924319280.074, "dur": 2.064, + "args": { + "External id": 759509,"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": 688924319288.099, "dur": 4.547, + "args": { + "External id": 759510,"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": 688924319290.689, "dur": 1.037, + "args": { + "External id": 759511,"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": 688924319368.591, "dur": 56.104, + "args": { + "External id": 759512,"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": 688924319430.240, "dur": 6.400, + "args": { + "External id": 759513,"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": 688924319433.084, "dur": 0.968, + "args": { + "External id": 759514,"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": 688924319438.672, "dur": 26.292, + "args": { + "External id": 759515,"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": 688924319470.182, "dur": 7.225, + "args": { + "External id": 759516,"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": 688924319472.453, "dur": 4.098, + "args": { + "External id": 759517,"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": 688924319474.837, "dur": 1.471, + "args": { + "External id": 759518,"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": 688924319481.092, "dur": 46.268, + "args": { + "External id": 759519,"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": 688924319482.340, "dur": 44.294, + "args": { + "External id": 759520,"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": 688924319531.835, "dur": 14.743, + "args": { + "External id": 759521,"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": 688924319552.572, "dur": 4.243, + "args": { + "External id": 759522,"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": 688924319554.948, "dur": 0.921, + "args": { + "External id": 759523,"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": 688924319561.268, "dur": 51.426, + "args": { + "External id": 759524,"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": 688924319562.515, "dur": 4.535, + "args": { + "External id": 759525,"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": 688924319563.429, "dur": 2.965, + "args": { + "External id": 759526,"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": 688924319565.194, "dur": 0.853, + "args": { + "External id": 759527,"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": 688924319567.832, "dur": 44.357, + "args": { + "External id": 759528,"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": 688924319568.872, "dur": 42.687, + "args": { + "External id": 759529,"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": 688924319617.023, "dur": 3.281, + "args": { + "External id": 759530,"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": 688924319618.802, "dur": 0.505, + "args": { + "External id": 759531,"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": 688924319626.484, "dur": 1.518, + "args": { + "External id": 759532,"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": 688924319635.870, "dur": 8.961, + "args": { + "External id": 759533,"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": 688924319638.091, "dur": 6.358, + "args": { + "External id": 759534,"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": 688924319799.470, "dur": 333.131, + "args": { + "External id": 759535,"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": 688924319803.369, "dur": 3.121, + "args": { + "External id": 759536,"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": 688924319808.805, "dur": 323.299, + "args": { + "External id": 759537,"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": 688924319810.716, "dur": 0.348, + "args": { + "External id": 759538,"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": 688924319812.649, "dur": 26.077, + "args": { + "External id": 759539,"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": 688924319840.845, "dur": 4.153, + "args": { + "External id": 759540,"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": 688924319843.322, "dur": 1.364, + "args": { + "External id": 759541,"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": 688924319846.313, "dur": 24.898, + "args": { + "External id": 759542,"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": 688924319847.311, "dur": 2.187, + "args": { + "External id": 759543,"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": 688924319851.125, "dur": 19.790, + "args": { + "External id": 759544,"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": 688924319856.529, "dur": 3.168, + "args": { + "External id": 759545,"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": 688924319872.922, "dur": 26.310, + "args": { + "External id": 759546,"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": 688924319900.965, "dur": 31.999, + "args": { + "External id": 759547,"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": 688924319935.669, "dur": 41.475, + "args": { + "External id": 759548,"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": 688924319979.098, "dur": 41.746, + "args": { + "External id": 759549,"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": 688924320022.870, "dur": 41.568, + "args": { + "External id": 759550,"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": 688924320024.879, "dur": 1.611, + "args": { + "External id": 759551,"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": 688924320029.557, "dur": 1.050, + "args": { + "External id": 759552,"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": 688924320066.176, "dur": 37.622, + "args": { + "External id": 759553,"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": 688924320105.143, "dur": 26.026, + "args": { + "External id": 759554,"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": 688924320140.949, "dur": 2.513, + "args": { + "External id": 759555,"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": 688924320153.107, "dur": 3.807, + "args": { + "External id": 759556,"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": 688924320155.602, "dur": 0.476, + "args": { + "External id": 759557,"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": 688924320227.379, "dur": 51.162, + "args": { + "External id": 759558,"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": 688924320283.366, "dur": 5.339, + "args": { + "External id": 759559,"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": 688924320286.349, "dur": 1.279, + "args": { + "External id": 759560,"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": 688924320290.618, "dur": 24.939, + "args": { + "External id": 759561,"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": 688924320320.028, "dur": 6.320, + "args": { + "External id": 759562,"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": 688924320322.066, "dur": 3.604, + "args": { + "External id": 759563,"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": 688924320324.443, "dur": 1.047, + "args": { + "External id": 759564,"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": 688924320329.427, "dur": 42.804, + "args": { + "External id": 759565,"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": 688924320330.741, "dur": 40.790, + "args": { + "External id": 759566,"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": 688924320376.431, "dur": 14.192, + "args": { + "External id": 759567,"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": 688924320395.985, "dur": 4.073, + "args": { + "External id": 759568,"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": 688924320398.386, "dur": 0.771, + "args": { + "External id": 759569,"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": 688924320404.405, "dur": 99.695, + "args": { + "External id": 759570,"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": 688924320405.516, "dur": 5.923, + "args": { + "External id": 759571,"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": 688924320406.531, "dur": 4.284, + "args": { + "External id": 759572,"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": 688924320408.287, "dur": 2.376, + "args": { + "External id": 759573,"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": 688924320458.588, "dur": 44.897, + "args": { + "External id": 759574,"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": 688924320460.115, "dur": 42.715, + "args": { + "External id": 759575,"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": 688924320508.734, "dur": 4.548, + "args": { + "External id": 759576,"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": 688924320511.015, "dur": 1.126, + "args": { + "External id": 759577,"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": 688924320519.666, "dur": 1.830, + "args": { + "External id": 759578,"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": 688924320529.765, "dur": 6.411, + "args": { + "External id": 759579,"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": 688924320532.230, "dur": 3.701, + "args": { + "External id": 759580,"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": 688924320622.917, "dur": 252.959, + "args": { + "External id": 759581,"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": 688924320627.337, "dur": 2.303, + "args": { + "External id": 759582,"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": 688924320631.632, "dur": 243.477, + "args": { + "External id": 759583,"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": 688924320633.400, "dur": 0.580, + "args": { + "External id": 759584,"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": 688924320635.656, "dur": 58.657, + "args": { + "External id": 759585,"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": 688924320697.570, "dur": 6.174, + "args": { + "External id": 759586,"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": 688924320702.345, "dur": 1.134, + "args": { + "External id": 759587,"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": 688924320705.276, "dur": 24.519, + "args": { + "External id": 759588,"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": 688924320706.846, "dur": 2.377, + "args": { + "External id": 759589,"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": 688924320710.482, "dur": 18.989, + "args": { + "External id": 759590,"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": 688924320713.974, "dur": 3.439, + "args": { + "External id": 759591,"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": 688924320731.638, "dur": 21.185, + "args": { + "External id": 759592,"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": 688924320754.111, "dur": 15.889, + "args": { + "External id": 759593,"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": 688924320772.953, "dur": 28.933, + "args": { + "External id": 759594,"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": 688924320804.426, "dur": 13.992, + "args": { + "External id": 759595,"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": 688924320820.509, "dur": 23.425, + "args": { + "External id": 759596,"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": 688924320822.897, "dur": 1.938, + "args": { + "External id": 759597,"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": 688924320827.470, "dur": 1.111, + "args": { + "External id": 759598,"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": 688924320845.803, "dur": 15.598, + "args": { + "External id": 759599,"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": 688924320862.531, "dur": 11.153, + "args": { + "External id": 759600,"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": 688924320887.939, "dur": 2.436, + "args": { + "External id": 759601,"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": 688924320900.629, "dur": 4.237, + "args": { + "External id": 759602,"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": 688924320903.259, "dur": 0.538, + "args": { + "External id": 759603,"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": 688924320978.431, "dur": 51.720, + "args": { + "External id": 759604,"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": 688924321034.972, "dur": 5.719, + "args": { + "External id": 759605,"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": 688924321038.358, "dur": 1.215, + "args": { + "External id": 759606,"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": 688924321042.740, "dur": 23.672, + "args": { + "External id": 759607,"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": 688924321070.614, "dur": 8.409, + "args": { + "External id": 759608,"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": 688924321072.779, "dur": 5.348, + "args": { + "External id": 759609,"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": 688924321074.956, "dur": 2.986, + "args": { + "External id": 759610,"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": 688924321082.034, "dur": 44.246, + "args": { + "External id": 759611,"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": 688924321083.385, "dur": 42.072, + "args": { + "External id": 759612,"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": 688924321130.394, "dur": 15.921, + "args": { + "External id": 759613,"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": 688924321152.023, "dur": 4.611, + "args": { + "External id": 759614,"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": 688924321154.768, "dur": 0.950, + "args": { + "External id": 759615,"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": 688924321160.794, "dur": 47.862, + "args": { + "External id": 759616,"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": 688924321161.834, "dur": 4.288, + "args": { + "External id": 759617,"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": 688924321162.734, "dur": 2.747, + "args": { + "External id": 759618,"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": 688924321164.759, "dur": 0.592, + "args": { + "External id": 759619,"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": 688924321166.824, "dur": 41.406, + "args": { + "External id": 759620,"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": 688924321167.584, "dur": 40.055, + "args": { + "External id": 759621,"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": 688924321212.724, "dur": 3.755, + "args": { + "External id": 759622,"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": 688924321214.416, "dur": 0.957, + "args": { + "External id": 759623,"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": 688924321222.090, "dur": 1.603, + "args": { + "External id": 759624,"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": 688924321231.599, "dur": 7.794, + "args": { + "External id": 759625,"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": 688924321233.952, "dur": 5.117, + "args": { + "External id": 759626,"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": 688924321320.679, "dur": 181.333, + "args": { + "External id": 759627,"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": 688924321323.074, "dur": 2.124, + "args": { + "External id": 759628,"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": 688924321329.364, "dur": 172.078, + "args": { + "External id": 759629,"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": 688924321330.700, "dur": 0.493, + "args": { + "External id": 759630,"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": 688924321332.740, "dur": 22.397, + "args": { + "External id": 759631,"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": 688924321357.026, "dur": 5.429, + "args": { + "External id": 759632,"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": 688924321359.362, "dur": 2.852, + "args": { + "External id": 759633,"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": 688924321363.565, "dur": 21.538, + "args": { + "External id": 759634,"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": 688924321364.808, "dur": 1.315, + "args": { + "External id": 759635,"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": 688924321367.549, "dur": 17.276, + "args": { + "External id": 759636,"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": 688924321370.109, "dur": 2.498, + "args": { + "External id": 759637,"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": 688924321386.721, "dur": 22.235, + "args": { + "External id": 759638,"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": 688924321410.296, "dur": 13.935, + "args": { + "External id": 759639,"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": 688924321427.096, "dur": 14.497, + "args": { + "External id": 759640,"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": 688924321442.913, "dur": 11.887, + "args": { + "External id": 759641,"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": 688924321456.531, "dur": 19.176, + "args": { + "External id": 759642,"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": 688924321458.914, "dur": 1.479, + "args": { + "External id": 759643,"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": 688924321462.751, "dur": 1.022, + "args": { + "External id": 759644,"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": 688924321477.002, "dur": 11.273, + "args": { + "External id": 759645,"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": 688924321489.537, "dur": 10.996, + "args": { + "External id": 759646,"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": 688924321507.574, "dur": 1.858, + "args": { + "External id": 759647,"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": 688924321517.519, "dur": 4.009, + "args": { + "External id": 759648,"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": 688924321519.977, "dur": 0.616, + "args": { + "External id": 759649,"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": 688924321583.635, "dur": 39.006, + "args": { + "External id": 759650,"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": 688924321627.272, "dur": 7.791, + "args": { + "External id": 759651,"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": 688924321630.507, "dur": 3.313, + "args": { + "External id": 759652,"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": 688924321636.794, "dur": 60.486, + "args": { + "External id": 759653,"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": 688924321704.465, "dur": 6.186, + "args": { + "External id": 759654,"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": 688924321705.982, "dur": 3.840, + "args": { + "External id": 759655,"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": 688924321708.387, "dur": 1.258, + "args": { + "External id": 759656,"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": 688924321713.497, "dur": 48.884, + "args": { + "External id": 759657,"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": 688924321714.740, "dur": 46.706, + "args": { + "External id": 759658,"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": 688924321766.001, "dur": 15.112, + "args": { + "External id": 759659,"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": 688924321801.301, "dur": 5.561, + "args": { + "External id": 759660,"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": 688924321804.452, "dur": 1.104, + "args": { + "External id": 759661,"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": 688924321812.097, "dur": 53.011, + "args": { + "External id": 759662,"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": 688924321813.228, "dur": 4.642, + "args": { + "External id": 759663,"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": 688924321814.439, "dur": 2.833, + "args": { + "External id": 759664,"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": 688924321816.451, "dur": 0.684, + "args": { + "External id": 759665,"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": 688924321818.758, "dur": 45.882, + "args": { + "External id": 759666,"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": 688924321819.325, "dur": 44.562, + "args": { + "External id": 759667,"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": 688924321869.920, "dur": 3.929, + "args": { + "External id": 759668,"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": 688924321871.858, "dur": 0.922, + "args": { + "External id": 759669,"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": 688924321879.923, "dur": 1.608, + "args": { + "External id": 759670,"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": 688924321889.609, "dur": 6.621, + "args": { + "External id": 759671,"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": 688924321891.732, "dur": 4.211, + "args": { + "External id": 759672,"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": 688924321986.631, "dur": 181.767, + "args": { + "External id": 759673,"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": 688924321988.834, "dur": 4.809, + "args": { + "External id": 759674,"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": 688924321995.406, "dur": 172.475, + "args": { + "External id": 759675,"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": 688924321996.951, "dur": 0.454, + "args": { + "External id": 759676,"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": 688924321998.928, "dur": 22.167, + "args": { + "External id": 759677,"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": 688924322022.704, "dur": 5.644, + "args": { + "External id": 759678,"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": 688924322027.328, "dur": 0.739, + "args": { + "External id": 759679,"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": 688924322029.360, "dur": 21.406, + "args": { + "External id": 759680,"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": 688924322030.632, "dur": 1.607, + "args": { + "External id": 759681,"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": 688924322033.575, "dur": 16.894, + "args": { + "External id": 759682,"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": 688924322036.832, "dur": 2.665, + "args": { + "External id": 759683,"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": 688924322052.416, "dur": 19.978, + "args": { + "External id": 759684,"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": 688924322073.894, "dur": 12.749, + "args": { + "External id": 759685,"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": 688924322089.320, "dur": 13.427, + "args": { + "External id": 759686,"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": 688924322104.107, "dur": 11.743, + "args": { + "External id": 759687,"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": 688924322117.621, "dur": 22.495, + "args": { + "External id": 759688,"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": 688924322119.831, "dur": 1.236, + "args": { + "External id": 759689,"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": 688924322123.474, "dur": 2.911, + "args": { + "External id": 759690,"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": 688924322141.444, "dur": 12.831, + "args": { + "External id": 759691,"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": 688924322155.558, "dur": 11.243, + "args": { + "External id": 759692,"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": 688924322174.460, "dur": 2.395, + "args": { + "External id": 759693,"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": 688924322185.960, "dur": 4.150, + "args": { + "External id": 759694,"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": 688924322188.576, "dur": 0.519, + "args": { + "External id": 759695,"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": 688924322257.940, "dur": 46.478, + "args": { + "External id": 759696,"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": 688924322309.349, "dur": 5.468, + "args": { + "External id": 759697,"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": 688924322312.631, "dur": 1.023, + "args": { + "External id": 759698,"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": 688924322316.221, "dur": 24.536, + "args": { + "External id": 759699,"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": 688924322345.480, "dur": 6.421, + "args": { + "External id": 759700,"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": 688924322346.957, "dur": 4.188, + "args": { + "External id": 759701,"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": 688924322349.540, "dur": 1.419, + "args": { + "External id": 759702,"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": 688924322354.831, "dur": 44.881, + "args": { + "External id": 759703,"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": 688924322356.061, "dur": 43.009, + "args": { + "External id": 759704,"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": 688924322403.477, "dur": 15.508, + "args": { + "External id": 759705,"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": 688924322425.289, "dur": 4.361, + "args": { + "External id": 759706,"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": 688924322427.783, "dur": 1.066, + "args": { + "External id": 759707,"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": 688924322433.370, "dur": 51.459, + "args": { + "External id": 759708,"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": 688924322434.631, "dur": 3.740, + "args": { + "External id": 759709,"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": 688924322435.251, "dur": 2.581, + "args": { + "External id": 759710,"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": 688924322436.991, "dur": 0.712, + "args": { + "External id": 759711,"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": 688924322438.904, "dur": 45.399, + "args": { + "External id": 759712,"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": 688924322439.644, "dur": 44.072, + "args": { + "External id": 759713,"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": 688924322488.718, "dur": 3.846, + "args": { + "External id": 759714,"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": 688924322490.750, "dur": 0.808, + "args": { + "External id": 759715,"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": 688924322498.278, "dur": 1.501, + "args": { + "External id": 759716,"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": 688924322507.178, "dur": 6.088, + "args": { + "External id": 759717,"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": 688924322509.029, "dur": 3.922, + "args": { + "External id": 759718,"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": 688924322589.109, "dur": 346.709, + "args": { + "External id": 759719,"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": 688924322593.862, "dur": 2.079, + "args": { + "External id": 759720,"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": 688924322597.421, "dur": 337.803, + "args": { + "External id": 759721,"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": 688924322598.777, "dur": 0.436, + "args": { + "External id": 759722,"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": 688924322600.428, "dur": 18.890, + "args": { + "External id": 759723,"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": 688924322620.612, "dur": 5.902, + "args": { + "External id": 759724,"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": 688924322625.563, "dur": 0.714, + "args": { + "External id": 759725,"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": 688924322627.532, "dur": 18.318, + "args": { + "External id": 759726,"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": 688924322628.418, "dur": 1.509, + "args": { + "External id": 759727,"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": 688924322631.160, "dur": 14.339, + "args": { + "External id": 759728,"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": 688924322633.581, "dur": 2.256, + "args": { + "External id": 759729,"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": 688924322647.181, "dur": 70.212, + "args": { + "External id": 759730,"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": 688924322719.858, "dur": 39.941, + "args": { + "External id": 759731,"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": 688924322762.661, "dur": 42.022, + "args": { + "External id": 759732,"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": 688924322806.948, "dur": 42.192, + "args": { + "External id": 759733,"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": 688924322851.099, "dur": 30.326, + "args": { + "External id": 759734,"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": 688924322853.442, "dur": 2.405, + "args": { + "External id": 759735,"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": 688924322858.451, "dur": 1.070, + "args": { + "External id": 759736,"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": 688924322883.115, "dur": 25.039, + "args": { + "External id": 759737,"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": 688924322909.465, "dur": 24.650, + "args": { + "External id": 759738,"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": 688924322943.759, "dur": 2.759, + "args": { + "External id": 759739,"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": 688924322956.379, "dur": 4.869, + "args": { + "External id": 759740,"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": 688924322959.401, "dur": 0.746, + "args": { + "External id": 759741,"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": 688924323046.367, "dur": 51.294, + "args": { + "External id": 759742,"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": 688924323103.003, "dur": 5.036, + "args": { + "External id": 759743,"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": 688924323105.930, "dur": 1.027, + "args": { + "External id": 759744,"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": 688924323109.335, "dur": 23.970, + "args": { + "External id": 759745,"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": 688924323138.105, "dur": 7.462, + "args": { + "External id": 759746,"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": 688924323139.590, "dur": 5.274, + "args": { + "External id": 759747,"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": 688924323141.955, "dur": 2.674, + "args": { + "External id": 759748,"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": 688924323148.391, "dur": 43.279, + "args": { + "External id": 759749,"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": 688924323149.676, "dur": 41.303, + "args": { + "External id": 759750,"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": 688924323195.389, "dur": 13.929, + "args": { + "External id": 759751,"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": 688924323215.111, "dur": 3.980, + "args": { + "External id": 759752,"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": 688924323217.375, "dur": 0.781, + "args": { + "External id": 759753,"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": 688924323223.381, "dur": 48.283, + "args": { + "External id": 759754,"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": 688924323224.712, "dur": 3.904, + "args": { + "External id": 759755,"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": 688924323225.622, "dur": 2.439, + "args": { + "External id": 759756,"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": 688924323227.205, "dur": 0.711, + "args": { + "External id": 759757,"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": 688924323229.327, "dur": 41.993, + "args": { + "External id": 759758,"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": 688924323230.177, "dur": 40.438, + "args": { + "External id": 759759,"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": 688924323275.766, "dur": 4.121, + "args": { + "External id": 759760,"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": 688924323277.906, "dur": 0.768, + "args": { + "External id": 759761,"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": 688924323285.286, "dur": 1.510, + "args": { + "External id": 759762,"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": 688924323294.799, "dur": 18.536, + "args": { + "External id": 759763,"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": 688924323302.237, "dur": 10.757, + "args": { + "External id": 759764,"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": 688924323392.729, "dur": 165.481, + "args": { + "External id": 759765,"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": 688924323394.647, "dur": 2.000, + "args": { + "External id": 759766,"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": 688924323398.533, "dur": 159.275, + "args": { + "External id": 759767,"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": 688924323400.117, "dur": 0.387, + "args": { + "External id": 759768,"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": 688924323401.752, "dur": 21.812, + "args": { + "External id": 759769,"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": 688924323425.236, "dur": 3.167, + "args": { + "External id": 759770,"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": 688924323427.414, "dur": 0.747, + "args": { + "External id": 759771,"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": 688924323429.247, "dur": 22.077, + "args": { + "External id": 759772,"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": 688924323430.347, "dur": 1.553, + "args": { + "External id": 759773,"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": 688924323432.852, "dur": 18.142, + "args": { + "External id": 759774,"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": 688924323437.608, "dur": 2.416, + "args": { + "External id": 759775,"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": 688924323452.952, "dur": 18.695, + "args": { + "External id": 759776,"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": 688924323472.814, "dur": 12.646, + "args": { + "External id": 759777,"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": 688924323487.967, "dur": 12.032, + "args": { + "External id": 759778,"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": 688924323501.146, "dur": 11.773, + "args": { + "External id": 759779,"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": 688924323514.707, "dur": 18.179, + "args": { + "External id": 759780,"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": 688924323516.577, "dur": 1.275, + "args": { + "External id": 759781,"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": 688924323520.240, "dur": 0.688, + "args": { + "External id": 759782,"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": 688924323534.160, "dur": 10.934, + "args": { + "External id": 759783,"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": 688924323546.169, "dur": 10.597, + "args": { + "External id": 759784,"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": 688924323564.297, "dur": 1.664, + "args": { + "External id": 759785,"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": 688924323573.817, "dur": 3.578, + "args": { + "External id": 759786,"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": 688924323576.179, "dur": 0.411, + "args": { + "External id": 759787,"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": 688924323637.789, "dur": 96.853, + "args": { + "External id": 759788,"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": 688924323741.422, "dur": 7.145, + "args": { + "External id": 759789,"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": 688924323745.375, "dur": 1.727, + "args": { + "External id": 759790,"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": 688924323749.952, "dur": 24.402, + "args": { + "External id": 759791,"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": 688924323779.647, "dur": 5.924, + "args": { + "External id": 759792,"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": 688924323781.088, "dur": 3.770, + "args": { + "External id": 759793,"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": 688924323783.704, "dur": 0.958, + "args": { + "External id": 759794,"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": 688924323803.240, "dur": 49.255, + "args": { + "External id": 759795,"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": 688924323804.657, "dur": 47.160, + "args": { + "External id": 759796,"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": 688924323856.927, "dur": 21.353, + "args": { + "External id": 759797,"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": 688924323884.723, "dur": 4.876, + "args": { + "External id": 759798,"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": 688924323887.824, "dur": 0.706, + "args": { + "External id": 759799,"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": 688924323893.758, "dur": 50.949, + "args": { + "External id": 759800,"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": 688924323894.943, "dur": 6.431, + "args": { + "External id": 759801,"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": 688924323896.040, "dur": 4.700, + "args": { + "External id": 759802,"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": 688924323897.807, "dur": 2.798, + "args": { + "External id": 759803,"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": 688924323902.229, "dur": 41.991, + "args": { + "External id": 759804,"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": 688924323902.755, "dur": 40.655, + "args": { + "External id": 759805,"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": 688924323948.954, "dur": 4.511, + "args": { + "External id": 759806,"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": 688924323951.621, "dur": 0.733, + "args": { + "External id": 759807,"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": 688924323960.336, "dur": 1.827, + "args": { + "External id": 759808,"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": 688924324055.266, "dur": 8.384, + "args": { + "External id": 759809,"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": 688924324058.535, "dur": 4.765, + "args": { + "External id": 759810,"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": 688924324160.103, "dur": 185.625, + "args": { + "External id": 759811,"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": 688924324165.530, "dur": 2.745, + "args": { + "External id": 759812,"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": 688924324169.701, "dur": 175.448, + "args": { + "External id": 759813,"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": 688924324171.636, "dur": 0.402, + "args": { + "External id": 759814,"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": 688924324173.498, "dur": 22.076, + "args": { + "External id": 759815,"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": 688924324196.981, "dur": 6.090, + "args": { + "External id": 759816,"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": 688924324201.667, "dur": 1.107, + "args": { + "External id": 759817,"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": 688924324204.087, "dur": 20.340, + "args": { + "External id": 759818,"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": 688924324204.928, "dur": 1.572, + "args": { + "External id": 759819,"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": 688924324207.687, "dur": 16.433, + "args": { + "External id": 759820,"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": 688924324210.748, "dur": 2.688, + "args": { + "External id": 759821,"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": 688924324226.252, "dur": 21.517, + "args": { + "External id": 759822,"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": 688924324248.913, "dur": 12.536, + "args": { + "External id": 759823,"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": 688924324264.294, "dur": 14.117, + "args": { + "External id": 759824,"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": 688924324279.899, "dur": 12.024, + "args": { + "External id": 759825,"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": 688924324293.758, "dur": 22.559, + "args": { + "External id": 759826,"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": 688924324298.084, "dur": 1.788, + "args": { + "External id": 759827,"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": 688924324302.159, "dur": 0.772, + "args": { + "External id": 759828,"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": 688924324318.177, "dur": 13.001, + "args": { + "External id": 759829,"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": 688924324332.119, "dur": 11.741, + "args": { + "External id": 759830,"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": 688924324351.843, "dur": 2.141, + "args": { + "External id": 759831,"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": 688924324362.687, "dur": 3.422, + "args": { + "External id": 759832,"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": 688924324364.808, "dur": 0.278, + "args": { + "External id": 759833,"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": 688924324430.541, "dur": 47.730, + "args": { + "External id": 759834,"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": 688924324482.823, "dur": 5.114, + "args": { + "External id": 759835,"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": 688924324485.949, "dur": 0.913, + "args": { + "External id": 759836,"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": 688924324489.516, "dur": 25.569, + "args": { + "External id": 759837,"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": 688924324519.238, "dur": 6.130, + "args": { + "External id": 759838,"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": 688924324521.070, "dur": 3.642, + "args": { + "External id": 759839,"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": 688924324523.140, "dur": 1.422, + "args": { + "External id": 759840,"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": 688924324527.990, "dur": 43.438, + "args": { + "External id": 759841,"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": 688924324529.336, "dur": 41.512, + "args": { + "External id": 759842,"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": 688924324575.426, "dur": 15.353, + "args": { + "External id": 759843,"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": 688924324596.037, "dur": 24.142, + "args": { + "External id": 759844,"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": 688924324598.175, "dur": 21.609, + "args": { + "External id": 759845,"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": 688924324603.889, "dur": 1.019, + "args": { + "External id": 759846,"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": 688924324625.284, "dur": 75.910, + "args": { + "External id": 759847,"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": 688924324632.213, "dur": 68.727, + "args": { + "External id": 759848,"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": 688924324636.798, "dur": 3.834, + "args": { + "External id": 759849,"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": 688924324642.141, "dur": 57.806, + "args": { + "External id": 759850,"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": 688924324716.607, "dur": 5.832, + "args": { + "External id": 759851,"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": 688924324718.857, "dur": 3.307, + "args": { + "External id": 759852,"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": 688924324723.605, "dur": 1.580, + "args": { + "External id": 759853,"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": 688924324724.584, "dur": 0.524, + "args": { + "External id": 759854,"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": 688924324764.734, "dur": 39.063, + "args": { + "External id": 759855,"Sequence number": 8962156, "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": 688924324807.708, "dur": 17.230, + "args": { + "External id": 759856,"Sequence number": 8962157, "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": 688924324807.708, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183436, "tid": 4183436, + "ts": 688924324832.190, "dur": 7.146, + "args": { + "External id": 759857,"Sequence number": 8962158, "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": 688924324836.017, "dur": 1.499, + "args": { + "External id": 759858,"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": 688924324842.049, "dur": 7.694, + "args": { + "External id": 759859,"Sequence number": 8962158, "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": 688924324847.039, "dur": 1.224, + "args": { + "External id": 759860,"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": 688924324850.955, "dur": 3.284, + "args": { + "External id": 759861,"Sequence number": 8962158, "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": 688924324852.872, "dur": 0.788, + "args": { + "External id": 759862,"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": 688924324858.681, "dur": 5.641, + "args": { + "External id": 759863,"Sequence number": 8962158, "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": 688924324858.681, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924324862.172, "dur": 0.851, + "args": { + "External id": 759864,"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": 688924324865.668, "dur": 5.359, + "args": { + "External id": 759865,"Sequence number": 8962159, "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": 688924324865.668, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924324869.573, "dur": 0.721, + "args": { + "External id": 759866,"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": 688924324871.922, "dur": 5.581, + "args": { + "External id": 759867,"Sequence number": 8962160, "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": 688924324871.922, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924324875.697, "dur": 0.980, + "args": { + "External id": 759868,"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": 688924324878.530, "dur": 5.496, + "args": { + "External id": 759869,"Sequence number": 8962161, "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": 688924324878.530, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924324882.192, "dur": 1.077, + "args": { + "External id": 759870,"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": 688924324887.809, "dur": 31.969, + "args": { + "External id": 759871,"Sequence number": 8962162, "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": 688924324889.110, "dur": 30.464, + "args": { + "External id": 759872,"Sequence number": 8962162, "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": 688924324891.959, "dur": 9.142, + "args": { + "External id": 759873,"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": 688924324894.411, "dur": 6.134, + "args": { + "External id": 759874,"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": 688924324902.012, "dur": 17.091, + "args": { + "External id": 759875,"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": 688924324948.231, "dur": 4.710, + "args": { + "External id": 759876,"Sequence number": 8962162, "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": 688924324948.231, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924324955.367, "dur": 1.469, + "args": { + "External id": 759877,"Sequence number": 8962163, "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": 688924324990.256, "dur": 22496.673, + "args": { + "External id": 759878,"Sequence number": 8962163, "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": 688924324990.256, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 4183436, + "ts": 688924325007.351, "dur": 26.272, + "args": { + "External id": 759879,"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": 688924325007.986, "dur": 25.447, + "args": { + "External id": 759880,"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": 688924325009.589, "dur": 6.043, + "args": { + "External id": 759881,"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": 688924325011.060, "dur": 4.216, + "args": { + "External id": 759882,"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": 688924325016.402, "dur": 16.501, + "args": { + "External id": 759883,"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": 688924325049.819, "dur": 27.748, + "args": { + "External id": 759884,"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": 688924325050.990, "dur": 7.038, + "args": { + "External id": 759885,"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": 688924325053.672, "dur": 4.018, + "args": { + "External id": 759886,"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": 688924325059.433, "dur": 17.911, + "args": { + "External id": 759887,"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": 688924325061.354, "dur": 15.498, + "args": { + "External id": 759888,"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": 688924325081.382, "dur": 22.683, + "args": { + "External id": 759889,"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": 688924325082.309, "dur": 4.886, + "args": { + "External id": 759890,"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": 688924325084.135, "dur": 2.775, + "args": { + "External id": 759891,"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": 688924325088.117, "dur": 15.733, + "args": { + "External id": 759892,"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": 688924325088.581, "dur": 14.950, + "args": { + "External id": 759893,"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": 688924325110.173, "dur": 16.804, + "args": { + "External id": 759894,"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": 688924325111.732, "dur": 3.114, + "args": { + "External id": 759895,"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": 688924325115.725, "dur": 10.997, + "args": { + "External id": 759896,"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": 688924325116.220, "dur": 10.203, + "args": { + "External id": 759897,"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": 688924325132.231, "dur": 22.277, + "args": { + "External id": 759898,"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": 688924325157.369, "dur": 48.829, + "args": { + "External id": 759899,"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": 688924325159.515, "dur": 46.308, + "args": { + "External id": 759900,"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": 688924325164.541, "dur": 0.911, + "args": { + "External id": 759901,"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": 688924325167.179, "dur": 23.100, + "args": { + "External id": 759902,"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": 688924325171.179, "dur": 18.893, + "args": { + "External id": 759903,"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": 688924325173.680, "dur": 2.853, + "args": { + "External id": 759904,"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": 688924325177.692, "dur": 12.011, + "args": { + "External id": 759905,"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": 688924325210.756, "dur": 16414.490, + "args": { + "External id": 759906,"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": 688924325212.163, "dur": 16411.826, + "args": { + "External id": 759907,"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": 688924341638.638, "dur": 7.367, + "args": { + "External id": 759908,"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": 688924341643.150, "dur": 1.124, + "args": { + "External id": 759909,"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": 688924341651.116, "dur": 133.447, + "args": { + "External id": 759910,"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": 688924341674.314, "dur": 7.616, + "args": { + "External id": 759911,"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": 688924341676.834, "dur": 4.056, + "args": { + "External id": 759912,"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": 688924341679.246, "dur": 1.184, + "args": { + "External id": 759913,"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": 688924341683.280, "dur": 100.474, + "args": { + "External id": 759914,"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": 688924341685.140, "dur": 97.580, + "args": { + "External id": 759915,"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": 688924341799.972, "dur": 6.110, + "args": { + "External id": 759916,"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": 688924341802.960, "dur": 1.283, + "args": { + "External id": 759917,"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": 688924341814.458, "dur": 2.768, + "args": { + "External id": 759918,"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": 688924341827.418, "dur": 7.427, + "args": { + "External id": 759919,"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": 688924341829.961, "dur": 4.599, + "args": { + "External id": 759920,"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": 688924341975.201, "dur": 206.576, + "args": { + "External id": 759921,"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": 688924341979.138, "dur": 5.075, + "args": { + "External id": 759922,"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": 688924341986.029, "dur": 194.926, + "args": { + "External id": 759923,"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": 688924341988.562, "dur": 0.884, + "args": { + "External id": 759924,"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": 688924341991.593, "dur": 27.010, + "args": { + "External id": 759925,"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": 688924342021.254, "dur": 6.289, + "args": { + "External id": 759926,"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": 688924342026.270, "dur": 0.915, + "args": { + "External id": 759927,"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": 688924342029.047, "dur": 23.281, + "args": { + "External id": 759928,"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": 688924342030.554, "dur": 1.925, + "args": { + "External id": 759929,"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": 688924342033.805, "dur": 18.146, + "args": { + "External id": 759930,"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": 688924342037.559, "dur": 3.010, + "args": { + "External id": 759931,"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": 688924342054.232, "dur": 24.314, + "args": { + "External id": 759932,"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": 688924342080.550, "dur": 14.174, + "args": { + "External id": 759933,"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": 688924342098.192, "dur": 15.733, + "args": { + "External id": 759934,"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": 688924342115.940, "dur": 13.277, + "args": { + "External id": 759935,"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": 688924342130.963, "dur": 22.590, + "args": { + "External id": 759936,"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": 688924342133.569, "dur": 1.740, + "args": { + "External id": 759937,"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": 688924342137.936, "dur": 2.631, + "args": { + "External id": 759938,"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": 688924342155.322, "dur": 11.765, + "args": { + "External id": 759939,"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": 688924342168.907, "dur": 10.894, + "args": { + "External id": 759940,"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": 688924342189.033, "dur": 2.154, + "args": { + "External id": 759941,"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": 688924342198.067, "dur": 4.264, + "args": { + "External id": 759942,"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": 688924342200.484, "dur": 0.748, + "args": { + "External id": 759943,"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": 688924342279.026, "dur": 62.250, + "args": { + "External id": 759944,"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": 688924342346.743, "dur": 7.765, + "args": { + "External id": 759945,"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": 688924342350.509, "dur": 0.990, + "args": { + "External id": 759946,"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": 688924342356.379, "dur": 26.127, + "args": { + "External id": 759947,"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": 688924342388.346, "dur": 7.067, + "args": { + "External id": 759948,"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": 688924342390.246, "dur": 4.280, + "args": { + "External id": 759949,"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": 688924342392.713, "dur": 1.575, + "args": { + "External id": 759950,"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": 688924342398.725, "dur": 48.157, + "args": { + "External id": 759951,"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": 688924342400.030, "dur": 46.174, + "args": { + "External id": 759952,"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": 688924342451.219, "dur": 14.878, + "args": { + "External id": 759953,"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": 688924342472.463, "dur": 4.429, + "args": { + "External id": 759954,"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": 688924342475.429, "dur": 0.703, + "args": { + "External id": 759955,"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": 688924342481.042, "dur": 52.121, + "args": { + "External id": 759956,"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": 688924342482.326, "dur": 4.421, + "args": { + "External id": 759957,"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": 688924342483.419, "dur": 2.723, + "args": { + "External id": 759958,"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": 688924342485.300, "dur": 0.694, + "args": { + "External id": 759959,"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": 688924342487.372, "dur": 45.451, + "args": { + "External id": 759960,"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": 688924342487.971, "dur": 44.346, + "args": { + "External id": 759961,"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": 688924342536.869, "dur": 3.743, + "args": { + "External id": 759962,"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": 688924342538.762, "dur": 0.783, + "args": { + "External id": 759963,"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": 688924342546.952, "dur": 1.771, + "args": { + "External id": 759964,"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": 688924342556.712, "dur": 6.494, + "args": { + "External id": 759965,"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": 688924342558.998, "dur": 3.949, + "args": { + "External id": 759966,"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": 688924342699.099, "dur": 345.930, + "args": { + "External id": 759967,"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": 688924342704.465, "dur": 3.458, + "args": { + "External id": 759968,"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": 688924342710.126, "dur": 334.306, + "args": { + "External id": 759969,"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": 688924342712.232, "dur": 0.593, + "args": { + "External id": 759970,"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": 688924342714.740, "dur": 24.736, + "args": { + "External id": 759971,"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": 688924342741.104, "dur": 6.674, + "args": { + "External id": 759972,"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": 688924342746.136, "dur": 1.366, + "args": { + "External id": 759973,"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": 688924342748.896, "dur": 34.332, + "args": { + "External id": 759974,"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": 688924342750.082, "dur": 1.849, + "args": { + "External id": 759975,"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": 688924342763.908, "dur": 18.988, + "args": { + "External id": 759976,"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": 688924342766.971, "dur": 2.946, + "args": { + "External id": 759977,"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": 688924342785.121, "dur": 41.920, + "args": { + "External id": 759978,"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": 688924342829.404, "dur": 43.434, + "args": { + "External id": 759979,"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": 688924342875.841, "dur": 37.003, + "args": { + "External id": 759980,"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": 688924342914.416, "dur": 42.313, + "args": { + "External id": 759981,"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": 688924342958.715, "dur": 32.402, + "args": { + "External id": 759982,"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": 688924342963.361, "dur": 1.756, + "args": { + "External id": 759983,"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": 688924342967.926, "dur": 1.057, + "args": { + "External id": 759984,"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": 688924342992.705, "dur": 27.960, + "args": { + "External id": 759985,"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": 688924343022.144, "dur": 21.288, + "args": { + "External id": 759986,"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": 688924343053.575, "dur": 2.754, + "args": { + "External id": 759987,"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": 688924343066.376, "dur": 4.538, + "args": { + "External id": 759988,"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": 688924343069.265, "dur": 0.465, + "args": { + "External id": 759989,"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": 688924343150.873, "dur": 51.955, + "args": { + "External id": 759990,"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": 688924343207.794, "dur": 5.548, + "args": { + "External id": 759991,"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": 688924343211.258, "dur": 0.895, + "args": { + "External id": 759992,"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": 688924343214.737, "dur": 25.135, + "args": { + "External id": 759993,"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": 688924343244.854, "dur": 6.372, + "args": { + "External id": 759994,"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": 688924343246.672, "dur": 3.771, + "args": { + "External id": 759995,"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": 688924343248.690, "dur": 1.533, + "args": { + "External id": 759996,"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": 688924343253.950, "dur": 45.566, + "args": { + "External id": 759997,"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": 688924343255.923, "dur": 42.947, + "args": { + "External id": 759998,"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": 688924343303.692, "dur": 14.433, + "args": { + "External id": 759999,"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": 688924343323.897, "dur": 4.296, + "args": { + "External id": 760000,"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": 688924343326.748, "dur": 0.653, + "args": { + "External id": 760001,"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": 688924343332.167, "dur": 49.077, + "args": { + "External id": 760002,"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": 688924343333.391, "dur": 4.095, + "args": { + "External id": 760003,"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": 688924343334.351, "dur": 2.624, + "args": { + "External id": 760004,"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": 688924343336.147, "dur": 0.703, + "args": { + "External id": 760005,"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": 688924343338.209, "dur": 42.611, + "args": { + "External id": 760006,"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": 688924343339.300, "dur": 41.007, + "args": { + "External id": 760007,"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": 688924343385.506, "dur": 4.117, + "args": { + "External id": 760008,"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": 688924343387.510, "dur": 0.935, + "args": { + "External id": 760009,"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": 688924343395.713, "dur": 1.823, + "args": { + "External id": 760010,"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": 688924343405.311, "dur": 6.021, + "args": { + "External id": 760011,"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": 688924343407.978, "dur": 3.082, + "args": { + "External id": 760012,"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": 688924343499.317, "dur": 225.813, + "args": { + "External id": 760013,"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": 688924343503.726, "dur": 2.577, + "args": { + "External id": 760014,"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": 688924343507.652, "dur": 216.854, + "args": { + "External id": 760015,"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": 688924343509.725, "dur": 0.379, + "args": { + "External id": 760016,"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": 688924343512.064, "dur": 18.543, + "args": { + "External id": 760017,"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": 688924343532.067, "dur": 5.880, + "args": { + "External id": 760018,"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": 688924343536.708, "dur": 0.982, + "args": { + "External id": 760019,"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": 688924343538.921, "dur": 20.634, + "args": { + "External id": 760020,"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": 688924343540.331, "dur": 1.656, + "args": { + "External id": 760021,"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": 688924343543.329, "dur": 15.930, + "args": { + "External id": 760022,"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": 688924343545.697, "dur": 2.249, + "args": { + "External id": 760023,"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": 688924343561.201, "dur": 20.159, + "args": { + "External id": 760024,"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": 688924343583.203, "dur": 11.895, + "args": { + "External id": 760025,"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": 688924343597.805, "dur": 15.673, + "args": { + "External id": 760026,"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": 688924343614.714, "dur": 13.606, + "args": { + "External id": 760027,"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": 688924343630.157, "dur": 21.245, + "args": { + "External id": 760028,"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": 688924343631.880, "dur": 1.666, + "args": { + "External id": 760029,"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": 688924343636.049, "dur": 0.734, + "args": { + "External id": 760030,"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": 688924343692.378, "dur": 16.277, + "args": { + "External id": 760031,"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": 688924343710.401, "dur": 12.756, + "args": { + "External id": 760032,"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": 688924343732.869, "dur": 2.622, + "args": { + "External id": 760033,"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": 688924343745.289, "dur": 4.144, + "args": { + "External id": 760034,"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": 688924343747.900, "dur": 0.523, + "args": { + "External id": 760035,"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": 688924343839.087, "dur": 53.340, + "args": { + "External id": 760036,"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": 688924343897.325, "dur": 6.197, + "args": { + "External id": 760037,"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": 688924343900.999, "dur": 1.171, + "args": { + "External id": 760038,"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": 688924343905.040, "dur": 25.625, + "args": { + "External id": 760039,"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": 688924343935.213, "dur": 7.135, + "args": { + "External id": 760040,"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": 688924343937.245, "dur": 4.297, + "args": { + "External id": 760041,"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": 688924343939.748, "dur": 1.543, + "args": { + "External id": 760042,"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": 688924343945.104, "dur": 42.961, + "args": { + "External id": 760043,"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": 688924343946.376, "dur": 41.165, + "args": { + "External id": 760044,"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": 688924343991.953, "dur": 16.606, + "args": { + "External id": 760045,"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": 688924344014.717, "dur": 4.330, + "args": { + "External id": 760046,"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": 688924344017.243, "dur": 0.992, + "args": { + "External id": 760047,"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": 688924344023.054, "dur": 49.507, + "args": { + "External id": 760048,"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": 688924344024.250, "dur": 4.587, + "args": { + "External id": 760049,"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": 688924344025.077, "dur": 3.182, + "args": { + "External id": 760050,"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": 688924344027.355, "dur": 0.757, + "args": { + "External id": 760051,"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": 688924344029.430, "dur": 42.706, + "args": { + "External id": 760052,"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": 688924344030.276, "dur": 41.314, + "args": { + "External id": 760053,"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": 688924344076.190, "dur": 6.670, + "args": { + "External id": 760054,"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": 688924344078.611, "dur": 3.045, + "args": { + "External id": 760055,"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": 688924344089.037, "dur": 1.690, + "args": { + "External id": 760056,"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": 688924344098.100, "dur": 7.298, + "args": { + "External id": 760057,"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": 688924344100.869, "dur": 4.269, + "args": { + "External id": 760058,"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": 688924344191.582, "dur": 179.205, + "args": { + "External id": 760059,"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": 688924344193.591, "dur": 2.328, + "args": { + "External id": 760060,"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": 688924344197.852, "dur": 172.483, + "args": { + "External id": 760061,"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": 688924344199.358, "dur": 0.414, + "args": { + "External id": 760062,"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": 688924344201.186, "dur": 24.319, + "args": { + "External id": 760063,"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": 688924344227.324, "dur": 3.160, + "args": { + "External id": 760064,"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": 688924344229.310, "dur": 0.927, + "args": { + "External id": 760065,"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": 688924344231.503, "dur": 24.137, + "args": { + "External id": 760066,"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": 688924344232.973, "dur": 1.485, + "args": { + "External id": 760067,"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": 688924344235.965, "dur": 19.365, + "args": { + "External id": 760068,"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": 688924344240.525, "dur": 2.938, + "args": { + "External id": 760069,"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": 688924344257.314, "dur": 21.007, + "args": { + "External id": 760070,"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": 688924344280.098, "dur": 13.284, + "args": { + "External id": 760071,"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": 688924344296.108, "dur": 13.365, + "args": { + "External id": 760072,"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": 688924344310.751, "dur": 11.806, + "args": { + "External id": 760073,"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": 688924344324.454, "dur": 18.940, + "args": { + "External id": 760074,"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": 688924344326.238, "dur": 1.713, + "args": { + "External id": 760075,"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": 688924344330.177, "dur": 1.148, + "args": { + "External id": 760076,"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": 688924344345.199, "dur": 11.672, + "args": { + "External id": 760077,"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": 688924344358.196, "dur": 10.862, + "args": { + "External id": 760078,"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": 688924344377.059, "dur": 1.700, + "args": { + "External id": 760079,"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": 688924344386.976, "dur": 3.822, + "args": { + "External id": 760080,"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": 688924344389.632, "dur": 0.302, + "args": { + "External id": 760081,"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": 688924344452.357, "dur": 41.447, + "args": { + "External id": 760082,"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": 688924344498.038, "dur": 6.198, + "args": { + "External id": 760083,"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": 688924344501.208, "dur": 1.869, + "args": { + "External id": 760084,"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": 688924344505.772, "dur": 20.474, + "args": { + "External id": 760085,"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": 688924344530.442, "dur": 5.339, + "args": { + "External id": 760086,"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": 688924344532.021, "dur": 3.120, + "args": { + "External id": 760087,"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": 688924344533.900, "dur": 1.034, + "args": { + "External id": 760088,"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": 688924344538.055, "dur": 42.021, + "args": { + "External id": 760089,"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": 688924344539.069, "dur": 40.321, + "args": { + "External id": 760090,"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": 688924344583.527, "dur": 13.119, + "args": { + "External id": 760091,"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": 688924344602.025, "dur": 3.862, + "args": { + "External id": 760092,"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": 688924344604.329, "dur": 0.747, + "args": { + "External id": 760093,"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": 688924344609.212, "dur": 107.771, + "args": { + "External id": 760094,"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": 688924344609.832, "dur": 6.422, + "args": { + "External id": 760095,"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": 688924344610.947, "dur": 4.623, + "args": { + "External id": 760096,"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": 688924344614.581, "dur": 0.863, + "args": { + "External id": 760097,"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": 688924344630.761, "dur": 85.557, + "args": { + "External id": 760098,"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": 688924344632.034, "dur": 82.999, + "args": { + "External id": 760099,"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": 688924344724.108, "dur": 5.263, + "args": { + "External id": 760100,"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": 688924344726.953, "dur": 1.057, + "args": { + "External id": 760101,"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": 688924344735.727, "dur": 2.064, + "args": { + "External id": 760102,"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": 688924344745.789, "dur": 6.915, + "args": { + "External id": 760103,"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": 688924344748.506, "dur": 3.967, + "args": { + "External id": 760104,"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": 688924344866.907, "dur": 184.899, + "args": { + "External id": 760105,"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": 688924344872.074, "dur": 2.957, + "args": { + "External id": 760106,"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": 688924344877.040, "dur": 174.274, + "args": { + "External id": 760107,"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": 688924344878.650, "dur": 0.453, + "args": { + "External id": 760108,"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": 688924344880.556, "dur": 23.313, + "args": { + "External id": 760109,"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": 688924344905.565, "dur": 5.808, + "args": { + "External id": 760110,"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": 688924344910.165, "dur": 0.904, + "args": { + "External id": 760111,"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": 688924344912.407, "dur": 21.834, + "args": { + "External id": 760112,"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": 688924344913.647, "dur": 1.925, + "args": { + "External id": 760113,"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": 688924344916.747, "dur": 17.109, + "args": { + "External id": 760114,"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": 688924344920.063, "dur": 2.728, + "args": { + "External id": 760115,"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": 688924344936.100, "dur": 19.801, + "args": { + "External id": 760116,"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": 688924344957.547, "dur": 15.416, + "args": { + "External id": 760117,"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": 688924344975.390, "dur": 14.834, + "args": { + "External id": 760118,"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": 688924344991.650, "dur": 11.895, + "args": { + "External id": 760119,"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": 688924345005.398, "dur": 19.623, + "args": { + "External id": 760120,"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": 688924345007.352, "dur": 1.420, + "args": { + "External id": 760121,"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": 688924345011.292, "dur": 1.125, + "args": { + "External id": 760122,"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": 688924345026.610, "dur": 11.142, + "args": { + "External id": 760123,"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": 688924345039.099, "dur": 11.051, + "args": { + "External id": 760124,"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": 688924345058.956, "dur": 2.267, + "args": { + "External id": 760125,"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": 688924345070.352, "dur": 3.880, + "args": { + "External id": 760126,"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": 688924345072.955, "dur": 0.463, + "args": { + "External id": 760127,"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": 688924345140.419, "dur": 53.350, + "args": { + "External id": 760128,"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": 688924345199.011, "dur": 5.340, + "args": { + "External id": 760129,"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": 688924345201.913, "dur": 1.145, + "args": { + "External id": 760130,"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": 688924345205.852, "dur": 22.918, + "args": { + "External id": 760131,"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": 688924345233.501, "dur": 6.786, + "args": { + "External id": 760132,"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": 688924345235.190, "dur": 4.270, + "args": { + "External id": 760133,"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": 688924345237.421, "dur": 1.798, + "args": { + "External id": 760134,"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": 688924345243.251, "dur": 44.001, + "args": { + "External id": 760135,"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": 688924345244.630, "dur": 42.010, + "args": { + "External id": 760136,"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": 688924345291.251, "dur": 15.634, + "args": { + "External id": 760137,"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": 688924345312.946, "dur": 3.865, + "args": { + "External id": 760138,"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": 688924345315.197, "dur": 0.782, + "args": { + "External id": 760139,"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": 688924345320.684, "dur": 53.745, + "args": { + "External id": 760140,"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": 688924345322.223, "dur": 4.765, + "args": { + "External id": 760141,"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": 688924345323.391, "dur": 2.971, + "args": { + "External id": 760142,"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": 688924345325.074, "dur": 1.158, + "args": { + "External id": 760143,"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": 688924345328.010, "dur": 46.049, + "args": { + "External id": 760144,"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": 688924345328.829, "dur": 44.622, + "args": { + "External id": 760145,"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": 688924345378.403, "dur": 4.137, + "args": { + "External id": 760146,"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": 688924345380.507, "dur": 0.905, + "args": { + "External id": 760147,"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": 688924345388.196, "dur": 1.697, + "args": { + "External id": 760148,"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": 688924345397.244, "dur": 7.909, + "args": { + "External id": 760149,"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": 688924345399.383, "dur": 5.453, + "args": { + "External id": 760150,"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": 688924345488.686, "dur": 321.809, + "args": { + "External id": 760151,"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": 688924345490.842, "dur": 2.041, + "args": { + "External id": 760152,"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": 688924345494.280, "dur": 315.525, + "args": { + "External id": 760153,"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": 688924345495.995, "dur": 0.326, + "args": { + "External id": 760154,"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": 688924345497.784, "dur": 23.563, + "args": { + "External id": 760155,"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": 688924345523.017, "dur": 3.413, + "args": { + "External id": 760156,"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": 688924345524.951, "dur": 1.217, + "args": { + "External id": 760157,"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": 688924345527.306, "dur": 23.329, + "args": { + "External id": 760158,"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": 688924345528.139, "dur": 1.844, + "args": { + "External id": 760159,"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": 688924345531.271, "dur": 19.012, + "args": { + "External id": 760160,"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": 688924345535.975, "dur": 2.474, + "args": { + "External id": 760161,"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": 688924345552.410, "dur": 21.071, + "args": { + "External id": 760162,"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": 688924345574.783, "dur": 21.043, + "args": { + "External id": 760163,"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": 688924345598.715, "dur": 34.595, + "args": { + "External id": 760164,"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": 688924345634.534, "dur": 55.959, + "args": { + "External id": 760165,"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": 688924345693.899, "dur": 33.085, + "args": { + "External id": 760166,"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": 688924345696.100, "dur": 2.204, + "args": { + "External id": 760167,"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": 688924345701.235, "dur": 1.011, + "args": { + "External id": 760168,"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": 688924345728.871, "dur": 38.797, + "args": { + "External id": 760169,"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": 688924345769.353, "dur": 38.366, + "args": { + "External id": 760170,"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": 688924345819.781, "dur": 2.571, + "args": { + "External id": 760171,"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": 688924345831.702, "dur": 4.105, + "args": { + "External id": 760172,"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": 688924345834.432, "dur": 0.605, + "args": { + "External id": 760173,"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": 688924345910.655, "dur": 51.102, + "args": { + "External id": 760174,"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": 688924345968.109, "dur": 5.782, + "args": { + "External id": 760175,"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": 688924345971.441, "dur": 1.361, + "args": { + "External id": 760176,"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": 688924345975.544, "dur": 24.842, + "args": { + "External id": 760177,"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": 688924346004.706, "dur": 5.848, + "args": { + "External id": 760178,"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": 688924346006.418, "dur": 3.344, + "args": { + "External id": 760179,"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": 688924346008.471, "dur": 1.072, + "args": { + "External id": 760180,"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": 688924346013.355, "dur": 43.509, + "args": { + "External id": 760181,"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": 688924346014.324, "dur": 41.865, + "args": { + "External id": 760182,"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": 688924346060.365, "dur": 14.429, + "args": { + "External id": 760183,"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": 688924346080.719, "dur": 4.195, + "args": { + "External id": 760184,"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": 688924346083.453, "dur": 0.643, + "args": { + "External id": 760185,"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": 688924346088.866, "dur": 52.005, + "args": { + "External id": 760186,"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": 688924346090.277, "dur": 6.871, + "args": { + "External id": 760187,"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": 688924346091.063, "dur": 5.488, + "args": { + "External id": 760188,"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": 688924346092.987, "dur": 3.414, + "args": { + "External id": 760189,"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": 688924346098.007, "dur": 42.356, + "args": { + "External id": 760190,"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": 688924346098.787, "dur": 41.060, + "args": { + "External id": 760191,"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": 688924346144.980, "dur": 4.215, + "args": { + "External id": 760192,"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": 688924346147.031, "dur": 1.044, + "args": { + "External id": 760193,"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": 688924346154.349, "dur": 1.566, + "args": { + "External id": 760194,"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": 688924346163.701, "dur": 6.906, + "args": { + "External id": 760195,"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": 688924346166.234, "dur": 4.128, + "args": { + "External id": 760196,"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": 688924346252.662, "dur": 180.519, + "args": { + "External id": 760197,"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": 688924346254.933, "dur": 2.448, + "args": { + "External id": 760198,"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": 688924346259.084, "dur": 173.666, + "args": { + "External id": 760199,"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": 688924346260.460, "dur": 0.566, + "args": { + "External id": 760200,"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": 688924346264.727, "dur": 21.559, + "args": { + "External id": 760201,"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": 688924346287.820, "dur": 3.000, + "args": { + "External id": 760202,"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": 688924346289.801, "dur": 0.737, + "args": { + "External id": 760203,"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": 688924346291.932, "dur": 24.100, + "args": { + "External id": 760204,"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": 688924346293.206, "dur": 3.785, + "args": { + "External id": 760205,"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": 688924346298.281, "dur": 17.445, + "args": { + "External id": 760206,"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": 688924346300.770, "dur": 2.891, + "args": { + "External id": 760207,"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": 688924346317.821, "dur": 20.830, + "args": { + "External id": 760208,"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": 688924346339.910, "dur": 12.311, + "args": { + "External id": 760209,"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": 688924346354.316, "dur": 12.735, + "args": { + "External id": 760210,"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": 688924346368.361, "dur": 13.317, + "args": { + "External id": 760211,"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": 688924346383.327, "dur": 20.883, + "args": { + "External id": 760212,"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": 688924346385.190, "dur": 1.816, + "args": { + "External id": 760213,"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": 688924346389.423, "dur": 1.016, + "args": { + "External id": 760214,"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": 688924346405.838, "dur": 12.772, + "args": { + "External id": 760215,"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": 688924346419.818, "dur": 11.894, + "args": { + "External id": 760216,"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": 688924346438.743, "dur": 1.668, + "args": { + "External id": 760217,"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": 688924346447.612, "dur": 3.846, + "args": { + "External id": 760218,"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": 688924346450.195, "dur": 0.380, + "args": { + "External id": 760219,"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": 688924346511.660, "dur": 43.652, + "args": { + "External id": 760220,"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": 688924346572.194, "dur": 7.245, + "args": { + "External id": 760221,"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": 688924346575.246, "dur": 3.103, + "args": { + "External id": 760222,"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": 688924346580.832, "dur": 23.418, + "args": { + "External id": 760223,"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": 688924346608.265, "dur": 5.282, + "args": { + "External id": 760224,"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": 688924346609.592, "dur": 3.181, + "args": { + "External id": 760225,"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": 688924346611.704, "dur": 0.908, + "args": { + "External id": 760226,"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": 688924346615.942, "dur": 82.148, + "args": { + "External id": 760227,"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": 688924346616.923, "dur": 79.937, + "args": { + "External id": 760228,"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": 688924346703.890, "dur": 17.317, + "args": { + "External id": 760229,"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": 688924346728.513, "dur": 5.037, + "args": { + "External id": 760230,"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": 688924346731.333, "dur": 0.931, + "args": { + "External id": 760231,"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": 688924346737.283, "dur": 77.132, + "args": { + "External id": 760232,"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": 688924346738.333, "dur": 4.254, + "args": { + "External id": 760233,"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": 688924346739.332, "dur": 2.696, + "args": { + "External id": 760234,"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": 688924346741.149, "dur": 0.709, + "args": { + "External id": 760235,"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": 688924346743.269, "dur": 70.602, + "args": { + "External id": 760236,"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": 688924346744.031, "dur": 68.740, + "args": { + "External id": 760237,"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": 688924346820.274, "dur": 5.107, + "args": { + "External id": 760238,"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": 688924346822.879, "dur": 1.191, + "args": { + "External id": 760239,"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": 688924346831.977, "dur": 1.780, + "args": { + "External id": 760240,"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": 688924346841.999, "dur": 7.671, + "args": { + "External id": 760241,"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": 688924346844.023, "dur": 5.356, + "args": { + "External id": 760242,"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": 688924346941.516, "dur": 192.481, + "args": { + "External id": 760243,"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": 688924346944.199, "dur": 4.603, + "args": { + "External id": 760244,"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": 688924346950.363, "dur": 182.995, + "args": { + "External id": 760245,"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": 688924346952.205, "dur": 0.565, + "args": { + "External id": 760246,"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": 688924346954.515, "dur": 23.092, + "args": { + "External id": 760247,"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": 688924346979.175, "dur": 6.042, + "args": { + "External id": 760248,"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": 688924346984.112, "dur": 0.877, + "args": { + "External id": 760249,"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": 688924346986.231, "dur": 22.261, + "args": { + "External id": 760250,"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": 688924346987.139, "dur": 1.684, + "args": { + "External id": 760251,"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": 688924346990.280, "dur": 17.885, + "args": { + "External id": 760252,"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": 688924346993.069, "dur": 2.504, + "args": { + "External id": 760253,"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": 688924347010.064, "dur": 21.279, + "args": { + "External id": 760254,"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": 688924347032.859, "dur": 14.717, + "args": { + "External id": 760255,"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": 688924347050.226, "dur": 15.003, + "args": { + "External id": 760256,"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": 688924347066.446, "dur": 13.615, + "args": { + "External id": 760257,"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": 688924347081.811, "dur": 23.367, + "args": { + "External id": 760258,"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": 688924347083.686, "dur": 1.623, + "args": { + "External id": 760259,"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": 688924347087.793, "dur": 2.917, + "args": { + "External id": 760260,"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": 688924347107.058, "dur": 12.784, + "args": { + "External id": 760261,"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": 688924347121.144, "dur": 10.884, + "args": { + "External id": 760262,"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": 688924347140.100, "dur": 1.672, + "args": { + "External id": 760263,"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": 688924347149.937, "dur": 3.682, + "args": { + "External id": 760264,"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": 688924347152.428, "dur": 0.325, + "args": { + "External id": 760265,"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": 688924347218.666, "dur": 48.337, + "args": { + "External id": 760266,"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": 688924347271.214, "dur": 5.674, + "args": { + "External id": 760267,"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": 688924347274.008, "dur": 1.733, + "args": { + "External id": 760268,"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": 688924347278.291, "dur": 23.340, + "args": { + "External id": 760269,"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": 688924347306.296, "dur": 6.007, + "args": { + "External id": 760270,"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": 688924347307.951, "dur": 3.679, + "args": { + "External id": 760271,"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": 688924347310.188, "dur": 1.253, + "args": { + "External id": 760272,"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": 688924347314.995, "dur": 42.637, + "args": { + "External id": 760273,"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": 688924347316.359, "dur": 40.651, + "args": { + "External id": 760274,"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": 688924347361.530, "dur": 13.544, + "args": { + "External id": 760275,"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": 688924347380.706, "dur": 26.590, + "args": { + "External id": 760276,"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": 688924347382.981, "dur": 23.959, + "args": { + "External id": 760277,"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": 688924347388.212, "dur": 1.200, + "args": { + "External id": 760278,"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": 688924347411.818, "dur": 27.747, + "args": { + "External id": 760279,"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": 688924347413.839, "dur": 25.516, + "args": { + "External id": 760280,"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": 688924347418.448, "dur": 4.039, + "args": { + "External id": 760281,"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": 688924347423.944, "dur": 14.970, + "args": { + "External id": 760282,"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": 688924347451.603, "dur": 5.348, + "args": { + "External id": 760283,"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": 688924347453.774, "dur": 2.891, + "args": { + "External id": 760284,"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": 688924347457.995, "dur": 1.412, + "args": { + "External id": 760285,"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": 688924347458.871, "dur": 0.460, + "args": { + "External id": 760286,"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": 688924347505.325, "dur": 21.806, + "args": { + "External id": 760287,"Sequence number": 8962164, "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": 688924347529.042, "dur": 15.148, + "args": { + "External id": 760288,"Sequence number": 8962165, "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": 688924347529.042, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183436, "tid": 4183436, + "ts": 688924347549.583, "dur": 6.280, + "args": { + "External id": 760289,"Sequence number": 8962166, "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": 688924347553.424, "dur": 1.165, + "args": { + "External id": 760290,"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": 688924347558.494, "dur": 6.608, + "args": { + "External id": 760291,"Sequence number": 8962166, "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": 688924347563.074, "dur": 0.826, + "args": { + "External id": 760292,"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": 688924347566.294, "dur": 3.075, + "args": { + "External id": 760293,"Sequence number": 8962166, "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": 688924347568.110, "dur": 0.653, + "args": { + "External id": 760294,"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": 688924347573.513, "dur": 7.315, + "args": { + "External id": 760295,"Sequence number": 8962166, "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": 688924347573.513, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924347578.547, "dur": 1.012, + "args": { + "External id": 760296,"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": 688924347581.936, "dur": 5.699, + "args": { + "External id": 760297,"Sequence number": 8962167, "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": 688924347581.936, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924347586.220, "dur": 0.695, + "args": { + "External id": 760298,"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": 688924347588.566, "dur": 6.010, + "args": { + "External id": 760299,"Sequence number": 8962168, "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": 688924347588.566, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924347592.519, "dur": 0.891, + "args": { + "External id": 760300,"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": 688924347595.662, "dur": 4.199, + "args": { + "External id": 760301,"Sequence number": 8962169, "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": 688924347595.662, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183436, "tid": 4183436, + "ts": 688924347598.083, "dur": 1.061, + "args": { + "External id": 760302,"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": 688924347603.857, "dur": 29.188, + "args": { + "External id": 760303,"Sequence number": 8962170, "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": 688924347605.439, "dur": 27.404, + "args": { + "External id": 760304,"Sequence number": 8962170, "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": 688924347608.252, "dur": 6.238, + "args": { + "External id": 760305,"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": 688924347610.601, "dur": 3.438, + "args": { + "External id": 760306,"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": 688924347615.361, "dur": 16.910, + "args": { + "External id": 760307,"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": 688924347702.937, "dur": 8.249, + "args": { + "External id": 760308,"Sequence number": 8962170, "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": 688924347702.937, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183436, "tid": 4183436, + "ts": 688924347714.251, "dur": 1.307, + "args": { + "External id": 760309,"Sequence number": 8962171, "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": 688924347749.473, "dur": 23500.329, + "args": { + "External id": 760310,"Sequence number": 8962171, "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": 688924347749.473, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183436, "tid": 4183436, + "ts": 688924347765.775, "dur": 48.837, + "args": { + "External id": 760311,"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": 688924347767.204, "dur": 47.224, + "args": { + "External id": 760312,"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": 688924347768.748, "dur": 7.506, + "args": { + "External id": 760313,"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": 688924347771.096, "dur": 4.738, + "args": { + "External id": 760314,"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": 688924347777.054, "dur": 36.787, + "args": { + "External id": 760315,"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": 688924347832.752, "dur": 29.274, + "args": { + "External id": 760316,"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": 688924347833.675, "dur": 8.051, + "args": { + "External id": 760317,"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": 688924347836.399, "dur": 4.930, + "args": { + "External id": 760318,"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": 688924347843.010, "dur": 18.794, + "args": { + "External id": 760319,"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": 688924347845.170, "dur": 16.245, + "args": { + "External id": 760320,"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": 688924347945.658, "dur": 23.303, + "args": { + "External id": 760321,"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": 688924347946.646, "dur": 6.278, + "args": { + "External id": 760322,"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": 688924347948.460, "dur": 4.192, + "args": { + "External id": 760323,"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": 688924347953.555, "dur": 15.180, + "args": { + "External id": 760324,"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": 688924347954.145, "dur": 14.115, + "args": { + "External id": 760325,"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": 688924347976.146, "dur": 21.327, + "args": { + "External id": 760326,"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": 688924347980.405, "dur": 3.333, + "args": { + "External id": 760327,"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": 688924347984.355, "dur": 12.769, + "args": { + "External id": 760328,"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": 688924347984.980, "dur": 11.788, + "args": { + "External id": 760329,"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": 688924348002.543, "dur": 22.659, + "args": { + "External id": 760330,"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": 688924348027.816, "dur": 49.479, + "args": { + "External id": 760331,"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": 688924348030.337, "dur": 46.536, + "args": { + "External id": 760332,"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": 688924348035.240, "dur": 1.176, + "args": { + "External id": 760333,"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": 688924348037.671, "dur": 24.110, + "args": { + "External id": 760334,"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": 688924348038.990, "dur": 22.574, + "args": { + "External id": 760335,"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": 688924348043.267, "dur": 3.023, + "args": { + "External id": 760336,"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": 688924348047.306, "dur": 13.915, + "args": { + "External id": 760337,"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": 688924348082.263, "dur": 17282.334, + "args": { + "External id": 760338,"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": 688924348083.580, "dur": 17279.944, + "args": { + "External id": 760339,"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": 688924365375.620, "dur": 7.683, + "args": { + "External id": 760340,"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": 688924365380.334, "dur": 1.129, + "args": { + "External id": 760341,"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": 688924365388.435, "dur": 108.738, + "args": { + "External id": 760342,"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": 688924365390.364, "dur": 6.955, + "args": { + "External id": 760343,"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": 688924365392.789, "dur": 3.664, + "args": { + "External id": 760344,"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": 688924365395.075, "dur": 1.078, + "args": { + "External id": 760345,"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": 688924365398.657, "dur": 97.887, + "args": { + "External id": 760346,"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": 688924365400.299, "dur": 95.237, + "args": { + "External id": 760347,"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": 688924365500.679, "dur": 4.801, + "args": { + "External id": 760348,"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": 688924365502.947, "dur": 1.065, + "args": { + "External id": 760349,"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": 688924365513.192, "dur": 2.566, + "args": { + "External id": 760350,"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": 688924365529.770, "dur": 6.776, + "args": { + "External id": 760351,"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": 688924365532.130, "dur": 4.124, + "args": { + "External id": 760352,"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": 688924365710.797, "dur": 235.460, + "args": { + "External id": 760353,"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": 688924365716.890, "dur": 4.134, + "args": { + "External id": 760354,"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": 688924365723.346, "dur": 222.235, + "args": { + "External id": 760355,"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": 688924365725.493, "dur": 0.678, + "args": { + "External id": 760356,"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": 688924365728.077, "dur": 27.704, + "args": { + "External id": 760357,"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": 688924365758.088, "dur": 6.349, + "args": { + "External id": 760358,"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": 688924365762.982, "dur": 0.990, + "args": { + "External id": 760359,"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": 688924365765.766, "dur": 38.613, + "args": { + "External id": 760360,"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": 688924365767.235, "dur": 1.477, + "args": { + "External id": 760361,"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": 688924365770.086, "dur": 33.559, + "args": { + "External id": 760362,"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": 688924365774.081, "dur": 3.589, + "args": { + "External id": 760363,"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": 688924365806.956, "dur": 25.591, + "args": { + "External id": 760364,"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": 688924365834.430, "dur": 19.545, + "args": { + "External id": 760365,"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": 688924365857.374, "dur": 16.707, + "args": { + "External id": 760366,"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": 688924365875.988, "dur": 14.800, + "args": { + "External id": 760367,"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": 688924365892.729, "dur": 22.814, + "args": { + "External id": 760368,"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": 688924365895.068, "dur": 1.750, + "args": { + "External id": 760369,"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": 688924365899.535, "dur": 0.876, + "args": { + "External id": 760370,"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": 688924365917.208, "dur": 13.876, + "args": { + "External id": 760371,"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": 688924365932.770, "dur": 11.865, + "args": { + "External id": 760372,"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": 688924365955.114, "dur": 2.966, + "args": { + "External id": 760373,"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": 688924365965.650, "dur": 4.751, + "args": { + "External id": 760374,"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": 688924365968.386, "dur": 0.984, + "args": { + "External id": 760375,"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": 688924366056.182, "dur": 60.842, + "args": { + "External id": 760376,"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": 688924366122.653, "dur": 33.556, + "args": { + "External id": 760377,"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": 688924366151.991, "dur": 1.184, + "args": { + "External id": 760378,"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": 688924366158.066, "dur": 26.316, + "args": { + "External id": 760379,"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": 688924366189.775, "dur": 10.337, + "args": { + "External id": 760380,"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": 688924366192.226, "dur": 6.741, + "args": { + "External id": 760381,"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": 688924366194.624, "dur": 4.085, + "args": { + "External id": 760382,"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": 688924366203.832, "dur": 51.124, + "args": { + "External id": 760383,"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": 688924366205.699, "dur": 48.616, + "args": { + "External id": 760384,"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": 688924366259.771, "dur": 16.952, + "args": { + "External id": 760385,"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": 688924366283.233, "dur": 4.501, + "args": { + "External id": 760386,"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": 688924366285.906, "dur": 0.743, + "args": { + "External id": 760387,"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": 688924366292.307, "dur": 51.822, + "args": { + "External id": 760388,"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": 688924366293.471, "dur": 4.174, + "args": { + "External id": 760389,"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": 688924366294.358, "dur": 2.768, + "args": { + "External id": 760390,"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": 688924366295.833, "dur": 1.075, + "args": { + "External id": 760391,"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": 688924366298.279, "dur": 45.372, + "args": { + "External id": 760392,"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": 688924366299.483, "dur": 43.553, + "args": { + "External id": 760393,"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": 688924366348.784, "dur": 4.214, + "args": { + "External id": 760394,"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": 688924366351.067, "dur": 0.831, + "args": { + "External id": 760395,"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": 688924366359.080, "dur": 1.738, + "args": { + "External id": 760396,"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": 688924366368.898, "dur": 7.673, + "args": { + "External id": 760397,"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": 688924366371.312, "dur": 4.969, + "args": { + "External id": 760398,"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": 688924366477.170, "dur": 326.007, + "args": { + "External id": 760399,"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": 688924366479.296, "dur": 2.638, + "args": { + "External id": 760400,"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": 688924366486.179, "dur": 316.281, + "args": { + "External id": 760401,"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": 688924366487.441, "dur": 0.473, + "args": { + "External id": 760402,"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": 688924366489.375, "dur": 21.823, + "args": { + "External id": 760403,"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": 688924366512.949, "dur": 5.315, + "args": { + "External id": 760404,"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": 688924366515.254, "dur": 2.742, + "args": { + "External id": 760405,"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": 688924366519.674, "dur": 22.691, + "args": { + "External id": 760406,"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": 688924366521.004, "dur": 1.407, + "args": { + "External id": 760407,"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": 688924366523.833, "dur": 18.208, + "args": { + "External id": 760408,"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": 688924366527.113, "dur": 2.628, + "args": { + "External id": 760409,"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": 688924366543.741, "dur": 22.376, + "args": { + "External id": 760410,"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": 688924366567.493, "dur": 17.907, + "args": { + "External id": 760411,"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": 688924366588.292, "dur": 20.835, + "args": { + "External id": 760412,"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": 688924366610.468, "dur": 38.812, + "args": { + "External id": 760413,"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": 688924366650.862, "dur": 68.046, + "args": { + "External id": 760414,"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": 688924366690.129, "dur": 2.826, + "args": { + "External id": 760415,"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": 688924366695.913, "dur": 1.153, + "args": { + "External id": 760416,"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": 688924366720.758, "dur": 37.392, + "args": { + "External id": 760417,"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": 688924366759.550, "dur": 41.027, + "args": { + "External id": 760418,"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": 688924366813.254, "dur": 2.796, + "args": { + "External id": 760419,"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": 688924366826.917, "dur": 4.510, + "args": { + "External id": 760420,"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": 688924366829.749, "dur": 0.619, + "args": { + "External id": 760421,"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": 688924366911.486, "dur": 54.110, + "args": { + "External id": 760422,"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": 688924366970.858, "dur": 7.540, + "args": { + "External id": 760423,"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": 688924366974.206, "dur": 2.915, + "args": { + "External id": 760424,"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": 688924366980.229, "dur": 25.937, + "args": { + "External id": 760425,"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": 688924367045.093, "dur": 6.756, + "args": { + "External id": 760426,"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": 688924367047.396, "dur": 3.432, + "args": { + "External id": 760427,"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": 688924367049.550, "dur": 1.008, + "args": { + "External id": 760428,"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": 688924367054.969, "dur": 45.755, + "args": { + "External id": 760429,"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": 688924367056.187, "dur": 43.905, + "args": { + "External id": 760430,"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": 688924367104.398, "dur": 16.158, + "args": { + "External id": 760431,"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": 688924367126.836, "dur": 4.231, + "args": { + "External id": 760432,"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": 688924367129.416, "dur": 0.848, + "args": { + "External id": 760433,"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": 688924367135.079, "dur": 49.659, + "args": { + "External id": 760434,"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": 688924367136.283, "dur": 3.813, + "args": { + "External id": 760435,"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": 688924367137.311, "dur": 2.170, + "args": { + "External id": 760436,"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": 688924367138.691, "dur": 0.630, + "args": { + "External id": 760437,"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": 688924367140.984, "dur": 43.289, + "args": { + "External id": 760438,"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": 688924367141.839, "dur": 41.908, + "args": { + "External id": 760439,"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": 688924367189.093, "dur": 3.452, + "args": { + "External id": 760440,"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": 688924367190.743, "dur": 0.737, + "args": { + "External id": 760441,"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": 688924367198.604, "dur": 1.512, + "args": { + "External id": 760442,"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": 688924367208.698, "dur": 8.395, + "args": { + "External id": 760443,"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": 688924367210.955, "dur": 5.832, + "args": { + "External id": 760444,"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": 688924367312.938, "dur": 192.182, + "args": { + "External id": 760445,"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": 688924367315.055, "dur": 2.415, + "args": { + "External id": 760446,"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": 688924367319.275, "dur": 185.288, + "args": { + "External id": 760447,"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": 688924367321.298, "dur": 0.443, + "args": { + "External id": 760448,"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": 688924367323.274, "dur": 25.725, + "args": { + "External id": 760449,"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": 688924367350.686, "dur": 3.096, + "args": { + "External id": 760450,"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": 688924367352.800, "dur": 0.786, + "args": { + "External id": 760451,"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": 688924367354.758, "dur": 26.523, + "args": { + "External id": 760452,"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": 688924367356.035, "dur": 1.738, + "args": { + "External id": 760453,"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": 688924367359.415, "dur": 21.583, + "args": { + "External id": 760454,"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": 688924367364.865, "dur": 2.310, + "args": { + "External id": 760455,"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": 688924367386.582, "dur": 21.254, + "args": { + "External id": 760456,"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": 688924367409.412, "dur": 15.282, + "args": { + "External id": 760457,"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": 688924367427.271, "dur": 14.096, + "args": { + "External id": 760458,"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": 688924367442.943, "dur": 13.903, + "args": { + "External id": 760459,"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": 688924367458.607, "dur": 19.686, + "args": { + "External id": 760460,"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": 688924367460.875, "dur": 1.679, + "args": { + "External id": 760461,"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": 688924367465.054, "dur": 1.201, + "args": { + "External id": 760462,"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": 688924367479.728, "dur": 11.620, + "args": { + "External id": 760463,"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": 688924367492.760, "dur": 10.595, + "args": { + "External id": 760464,"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": 688924367511.588, "dur": 1.687, + "args": { + "External id": 760465,"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": 688924367522.322, "dur": 4.370, + "args": { + "External id": 760466,"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": 688924367524.993, "dur": 0.611, + "args": { + "External id": 760467,"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": 688924367595.108, "dur": 43.421, + "args": { + "External id": 760468,"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": 688924367643.441, "dur": 7.006, + "args": { + "External id": 760469,"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": 688924367646.069, "dur": 3.215, + "args": { + "External id": 760470,"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": 688924367690.005, "dur": 26.260, + "args": { + "External id": 760471,"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": 688924367722.269, "dur": 6.555, + "args": { + "External id": 760472,"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": 688924367724.045, "dur": 4.005, + "args": { + "External id": 760473,"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": 688924367726.334, "dur": 1.361, + "args": { + "External id": 760474,"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": 688924367731.685, "dur": 46.576, + "args": { + "External id": 760475,"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": 688924367733.149, "dur": 44.231, + "args": { + "External id": 760476,"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": 688924367782.277, "dur": 29.540, + "args": { + "External id": 760477,"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": 688924367820.324, "dur": 5.637, + "args": { + "External id": 760478,"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": 688924367823.837, "dur": 1.035, + "args": { + "External id": 760479,"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": 688924367830.137, "dur": 52.832, + "args": { + "External id": 760480,"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": 688924367831.390, "dur": 4.951, + "args": { + "External id": 760481,"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": 688924367832.581, "dur": 3.129, + "args": { + "External id": 760482,"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": 688924367834.710, "dur": 0.847, + "args": { + "External id": 760483,"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": 688924367836.963, "dur": 45.467, + "args": { + "External id": 760484,"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": 688924367837.898, "dur": 43.945, + "args": { + "External id": 760485,"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": 688924367887.199, "dur": 4.073, + "args": { + "External id": 760486,"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": 688924367889.066, "dur": 1.094, + "args": { + "External id": 760487,"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": 688924367897.898, "dur": 1.648, + "args": { + "External id": 760488,"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": 688924367908.061, "dur": 7.405, + "args": { + "External id": 760489,"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": 688924367910.195, "dur": 4.940, + "args": { + "External id": 760490,"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": 688924368004.802, "dur": 195.350, + "args": { + "External id": 760491,"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": 688924368007.078, "dur": 4.628, + "args": { + "External id": 760492,"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": 688924368013.604, "dur": 185.928, + "args": { + "External id": 760493,"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": 688924368015.006, "dur": 0.662, + "args": { + "External id": 760494,"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": 688924368017.062, "dur": 21.055, + "args": { + "External id": 760495,"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": 688924368039.601, "dur": 5.555, + "args": { + "External id": 760496,"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": 688924368044.043, "dur": 0.873, + "args": { + "External id": 760497,"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": 688924368046.136, "dur": 22.629, + "args": { + "External id": 760498,"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": 688924368047.756, "dur": 1.886, + "args": { + "External id": 760499,"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": 688924368050.975, "dur": 17.457, + "args": { + "External id": 760500,"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": 688924368054.089, "dur": 2.684, + "args": { + "External id": 760501,"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": 688924368070.644, "dur": 23.266, + "args": { + "External id": 760502,"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": 688924368095.525, "dur": 13.650, + "args": { + "External id": 760503,"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": 688924368111.826, "dur": 16.624, + "args": { + "External id": 760504,"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": 688924368129.654, "dur": 13.504, + "args": { + "External id": 760505,"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": 688924368145.400, "dur": 25.241, + "args": { + "External id": 760506,"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": 688924368147.907, "dur": 2.055, + "args": { + "External id": 760507,"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": 688924368152.140, "dur": 3.460, + "args": { + "External id": 760508,"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": 688924368172.196, "dur": 13.006, + "args": { + "External id": 760509,"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": 688924368186.645, "dur": 11.655, + "args": { + "External id": 760510,"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": 688924368206.923, "dur": 1.797, + "args": { + "External id": 760511,"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": 688924368217.432, "dur": 3.463, + "args": { + "External id": 760512,"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": 688924368219.519, "dur": 0.303, + "args": { + "External id": 760513,"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": 688924368285.587, "dur": 45.100, + "args": { + "External id": 760514,"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": 688924368335.209, "dur": 5.181, + "args": { + "External id": 760515,"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": 688924368338.239, "dur": 1.124, + "args": { + "External id": 760516,"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": 688924368341.845, "dur": 23.756, + "args": { + "External id": 760517,"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": 688924368369.685, "dur": 7.146, + "args": { + "External id": 760518,"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": 688924368371.958, "dur": 4.149, + "args": { + "External id": 760519,"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": 688924368374.228, "dur": 1.700, + "args": { + "External id": 760520,"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": 688924368379.426, "dur": 45.979, + "args": { + "External id": 760521,"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": 688924368381.089, "dur": 43.647, + "args": { + "External id": 760522,"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": 688924368429.268, "dur": 15.392, + "args": { + "External id": 760523,"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": 688924368450.380, "dur": 4.244, + "args": { + "External id": 760524,"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": 688924368452.572, "dur": 1.175, + "args": { + "External id": 760525,"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": 688924368458.176, "dur": 49.946, + "args": { + "External id": 760526,"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": 688924368459.313, "dur": 4.217, + "args": { + "External id": 760527,"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": 688924368460.320, "dur": 2.662, + "args": { + "External id": 760528,"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": 688924368462.007, "dur": 0.835, + "args": { + "External id": 760529,"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": 688924368464.399, "dur": 43.336, + "args": { + "External id": 760530,"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": 688924368465.276, "dur": 41.861, + "args": { + "External id": 760531,"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": 688924368511.974, "dur": 3.868, + "args": { + "External id": 760532,"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": 688924368513.848, "dur": 0.970, + "args": { + "External id": 760533,"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": 688924368521.813, "dur": 1.787, + "args": { + "External id": 760534,"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": 688924368530.804, "dur": 6.099, + "args": { + "External id": 760535,"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": 688924368532.766, "dur": 3.861, + "args": { + "External id": 760536,"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": 688924368624.227, "dur": 261.818, + "args": { + "External id": 760537,"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": 688924368628.497, "dur": 2.393, + "args": { + "External id": 760538,"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": 688924368632.507, "dur": 252.849, + "args": { + "External id": 760539,"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": 688924368633.835, "dur": 0.532, + "args": { + "External id": 760540,"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": 688924368635.797, "dur": 63.218, + "args": { + "External id": 760541,"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": 688924368702.099, "dur": 6.775, + "args": { + "External id": 760542,"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": 688924368707.464, "dur": 1.076, + "args": { + "External id": 760543,"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": 688924368709.913, "dur": 26.420, + "args": { + "External id": 760544,"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": 688924368711.286, "dur": 2.143, + "args": { + "External id": 760545,"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": 688924368714.836, "dur": 21.114, + "args": { + "External id": 760546,"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": 688924368718.566, "dur": 2.715, + "args": { + "External id": 760547,"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": 688924368737.732, "dur": 22.004, + "args": { + "External id": 760548,"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": 688924368761.308, "dur": 18.687, + "args": { + "External id": 760549,"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": 688924368782.535, "dur": 30.102, + "args": { + "External id": 760550,"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": 688924368815.480, "dur": 13.970, + "args": { + "External id": 760551,"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": 688924368831.512, "dur": 24.127, + "args": { + "External id": 760552,"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": 688924368833.758, "dur": 2.037, + "args": { + "External id": 760553,"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": 688924368838.605, "dur": 1.265, + "args": { + "External id": 760554,"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": 688924368857.382, "dur": 14.152, + "args": { + "External id": 760555,"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": 688924368872.783, "dur": 11.193, + "args": { + "External id": 760556,"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": 688924368893.944, "dur": 2.360, + "args": { + "External id": 760557,"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": 688924368907.188, "dur": 4.310, + "args": { + "External id": 760558,"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": 688924368909.789, "dur": 0.690, + "args": { + "External id": 760559,"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": 688924368988.764, "dur": 52.360, + "args": { + "External id": 760560,"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": 688924369045.829, "dur": 5.383, + "args": { + "External id": 760561,"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": 688924369049.022, "dur": 1.171, + "args": { + "External id": 760562,"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": 688924369052.789, "dur": 24.981, + "args": { + "External id": 760563,"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": 688924369081.974, "dur": 7.689, + "args": { + "External id": 760564,"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": 688924369083.915, "dur": 5.065, + "args": { + "External id": 760565,"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": 688924369085.867, "dur": 2.884, + "args": { + "External id": 760566,"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": 688924369092.719, "dur": 43.650, + "args": { + "External id": 760567,"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": 688924369094.572, "dur": 41.218, + "args": { + "External id": 760568,"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": 688924369140.243, "dur": 15.319, + "args": { + "External id": 760569,"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": 688924369161.634, "dur": 4.117, + "args": { + "External id": 760570,"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": 688924369164.105, "dur": 0.977, + "args": { + "External id": 760571,"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": 688924369169.166, "dur": 49.948, + "args": { + "External id": 760572,"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": 688924369170.341, "dur": 4.779, + "args": { + "External id": 760573,"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": 688924369171.351, "dur": 3.236, + "args": { + "External id": 760574,"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": 688924369173.578, "dur": 0.885, + "args": { + "External id": 760575,"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": 688924369176.024, "dur": 42.623, + "args": { + "External id": 760576,"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": 688924369177.009, "dur": 41.024, + "args": { + "External id": 760577,"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": 688924369223.064, "dur": 4.318, + "args": { + "External id": 760578,"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": 688924369225.217, "dur": 1.025, + "args": { + "External id": 760579,"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": 688924369232.937, "dur": 1.536, + "args": { + "External id": 760580,"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": 688924369241.683, "dur": 8.966, + "args": { + "External id": 760581,"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": 688924369243.876, "dur": 6.481, + "args": { + "External id": 760582,"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": 688924369338.428, "dur": 179.071, + "args": { + "External id": 760583,"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": 688924369340.456, "dur": 2.455, + "args": { + "External id": 760584,"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": 688924369344.821, "dur": 172.030, + "args": { + "External id": 760585,"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": 688924369346.171, "dur": 0.422, + "args": { + "External id": 760586,"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": 688924369348.043, "dur": 23.442, + "args": { + "External id": 760587,"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": 688924369373.072, "dur": 4.109, + "args": { + "External id": 760588,"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": 688924369375.364, "dur": 1.570, + "args": { + "External id": 760589,"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": 688924369378.366, "dur": 23.465, + "args": { + "External id": 760590,"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": 688924369379.782, "dur": 1.749, + "args": { + "External id": 760591,"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": 688924369382.624, "dur": 18.856, + "args": { + "External id": 760592,"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": 688924369387.452, "dur": 2.168, + "args": { + "External id": 760593,"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": 688924369403.221, "dur": 19.863, + "args": { + "External id": 760594,"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": 688924369424.716, "dur": 12.021, + "args": { + "External id": 760595,"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": 688924369439.623, "dur": 13.184, + "args": { + "External id": 760596,"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": 688924369454.747, "dur": 10.971, + "args": { + "External id": 760597,"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": 688924369467.648, "dur": 21.308, + "args": { + "External id": 760598,"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": 688924369470.066, "dur": 1.828, + "args": { + "External id": 760599,"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": 688924369474.501, "dur": 0.786, + "args": { + "External id": 760600,"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": 688924369490.643, "dur": 12.667, + "args": { + "External id": 760601,"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": 688924369504.359, "dur": 11.296, + "args": { + "External id": 760602,"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": 688924369523.210, "dur": 1.600, + "args": { + "External id": 760603,"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": 688924369547.947, "dur": 3.968, + "args": { + "External id": 760604,"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": 688924369550.595, "dur": 0.404, + "args": { + "External id": 760605,"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": 688924369613.370, "dur": 88.155, + "args": { + "External id": 760606,"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": 688924369708.715, "dur": 6.503, + "args": { + "External id": 760607,"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": 688924369712.206, "dur": 1.330, + "args": { + "External id": 760608,"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": 688924369716.772, "dur": 27.485, + "args": { + "External id": 760609,"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": 688924369749.116, "dur": 8.169, + "args": { + "External id": 760610,"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": 688924369750.876, "dur": 5.686, + "args": { + "External id": 760611,"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": 688924369753.024, "dur": 3.257, + "args": { + "External id": 760612,"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": 688924369760.021, "dur": 78.871, + "args": { + "External id": 760613,"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": 688924369761.181, "dur": 76.707, + "args": { + "External id": 760614,"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": 688924369844.547, "dur": 20.441, + "args": { + "External id": 760615,"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": 688924369871.591, "dur": 4.563, + "args": { + "External id": 760616,"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": 688924369874.223, "dur": 0.868, + "args": { + "External id": 760617,"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": 688924369880.210, "dur": 51.913, + "args": { + "External id": 760618,"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": 688924369881.308, "dur": 4.508, + "args": { + "External id": 760619,"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": 688924369882.333, "dur": 2.963, + "args": { + "External id": 760620,"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": 688924369884.240, "dur": 0.742, + "args": { + "External id": 760621,"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": 688924369886.590, "dur": 45.197, + "args": { + "External id": 760622,"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": 688924369887.633, "dur": 43.577, + "args": { + "External id": 760623,"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": 688924369936.694, "dur": 3.685, + "args": { + "External id": 760624,"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": 688924369938.680, "dur": 0.713, + "args": { + "External id": 760625,"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": 688924369946.809, "dur": 1.787, + "args": { + "External id": 760626,"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": 688924369956.931, "dur": 6.812, + "args": { + "External id": 760627,"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": 688924369958.907, "dur": 4.573, + "args": { + "External id": 760628,"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": 688924370052.112, "dur": 185.895, + "args": { + "External id": 760629,"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": 688924370054.317, "dur": 2.552, + "args": { + "External id": 760630,"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": 688924370061.087, "dur": 176.414, + "args": { + "External id": 760631,"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": 688924370062.453, "dur": 0.602, + "args": { + "External id": 760632,"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": 688924370064.610, "dur": 23.780, + "args": { + "External id": 760633,"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": 688924370090.240, "dur": 5.816, + "args": { + "External id": 760634,"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": 688924370091.982, "dur": 3.801, + "args": { + "External id": 760635,"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": 688924370097.186, "dur": 21.745, + "args": { + "External id": 760636,"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": 688924370098.500, "dur": 1.421, + "args": { + "External id": 760637,"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": 688924370101.206, "dur": 17.413, + "args": { + "External id": 760638,"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": 688924370103.971, "dur": 2.653, + "args": { + "External id": 760639,"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": 688924370120.862, "dur": 21.377, + "args": { + "External id": 760640,"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": 688924370143.556, "dur": 14.275, + "args": { + "External id": 760641,"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": 688924370160.408, "dur": 14.234, + "args": { + "External id": 760642,"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": 688924370175.965, "dur": 11.608, + "args": { + "External id": 760643,"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": 688924370189.506, "dur": 19.603, + "args": { + "External id": 760644,"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": 688924370191.710, "dur": 1.784, + "args": { + "External id": 760645,"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": 688924370195.990, "dur": 0.961, + "args": { + "External id": 760646,"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": 688924370211.127, "dur": 12.626, + "args": { + "External id": 760647,"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": 688924370224.944, "dur": 10.991, + "args": { + "External id": 760648,"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": 688924370243.681, "dur": 1.802, + "args": { + "External id": 760649,"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": 688924370255.170, "dur": 3.145, + "args": { + "External id": 760650,"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": 688924370257.267, "dur": 0.268, + "args": { + "External id": 760651,"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": 688924370320.454, "dur": 40.392, + "args": { + "External id": 760652,"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": 688924370365.241, "dur": 7.189, + "args": { + "External id": 760653,"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": 688924370368.192, "dur": 3.229, + "args": { + "External id": 760654,"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": 688924370374.170, "dur": 20.954, + "args": { + "External id": 760655,"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": 688924370398.933, "dur": 6.036, + "args": { + "External id": 760656,"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": 688924370400.850, "dur": 3.433, + "args": { + "External id": 760657,"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": 688924370402.925, "dur": 1.114, + "args": { + "External id": 760658,"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": 688924370407.171, "dur": 40.207, + "args": { + "External id": 760659,"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": 688924370408.493, "dur": 38.255, + "args": { + "External id": 760660,"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": 688924370450.805, "dur": 13.234, + "args": { + "External id": 760661,"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": 688924370469.429, "dur": 4.232, + "args": { + "External id": 760662,"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": 688924370472.042, "dur": 0.851, + "args": { + "External id": 760663,"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": 688924370477.021, "dur": 47.282, + "args": { + "External id": 760664,"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": 688924370478.151, "dur": 4.336, + "args": { + "External id": 760665,"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": 688924370478.972, "dur": 2.982, + "args": { + "External id": 760666,"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": 688924370480.954, "dur": 0.808, + "args": { + "External id": 760667,"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": 688924370483.027, "dur": 40.873, + "args": { + "External id": 760668,"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": 688924370484.269, "dur": 39.109, + "args": { + "External id": 760669,"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": 688924370527.971, "dur": 4.399, + "args": { + "External id": 760670,"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": 688924370530.306, "dur": 0.964, + "args": { + "External id": 760671,"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": 688924370537.197, "dur": 1.447, + "args": { + "External id": 760672,"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": 688924370545.955, "dur": 6.487, + "args": { + "External id": 760673,"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": 688924370547.973, "dur": 4.209, + "args": { + "External id": 760674,"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": 688924370627.419, "dur": 248.616, + "args": { + "External id": 760675,"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": 688924370629.244, "dur": 3.870, + "args": { + "External id": 760676,"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": 688924370634.785, "dur": 240.534, + "args": { + "External id": 760677,"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": 688924370635.878, "dur": 0.532, + "args": { + "External id": 760678,"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": 688924370637.798, "dur": 70.004, + "args": { + "External id": 760679,"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": 688924370710.895, "dur": 6.502, + "args": { + "External id": 760680,"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": 688924370716.088, "dur": 1.059, + "args": { + "External id": 760681,"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": 688924370718.370, "dur": 23.592, + "args": { + "External id": 760682,"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": 688924370719.758, "dur": 2.315, + "args": { + "External id": 760683,"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": 688924370723.509, "dur": 18.168, + "args": { + "External id": 760684,"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": 688924370726.756, "dur": 2.976, + "args": { + "External id": 760685,"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": 688924370743.431, "dur": 19.664, + "args": { + "External id": 760686,"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": 688924370764.651, "dur": 12.924, + "args": { + "External id": 760687,"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": 688924370780.318, "dur": 28.694, + "args": { + "External id": 760688,"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": 688924370811.568, "dur": 12.241, + "args": { + "External id": 760689,"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": 688924370825.826, "dur": 23.016, + "args": { + "External id": 760690,"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": 688924370828.203, "dur": 2.224, + "args": { + "External id": 760691,"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": 688924370832.995, "dur": 2.947, + "args": { + "External id": 760692,"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": 688924370850.430, "dur": 11.407, + "args": { + "External id": 760693,"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": 688924370863.026, "dur": 11.008, + "args": { + "External id": 760694,"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": 688924370884.703, "dur": 2.441, + "args": { + "External id": 760695,"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": 688924370897.080, "dur": 4.001, + "args": { + "External id": 760696,"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": 688924370899.441, "dur": 0.491, + "args": { + "External id": 760697,"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": 688924370968.769, "dur": 50.655, + "args": { + "External id": 760698,"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": 688924371024.473, "dur": 15.583, + "args": { + "External id": 760699,"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": 688924371037.453, "dur": 1.249, + "args": { + "External id": 760700,"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": 688924371041.863, "dur": 25.105, + "args": { + "External id": 760701,"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": 688924371072.244, "dur": 8.411, + "args": { + "External id": 760702,"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": 688924371073.982, "dur": 5.971, + "args": { + "External id": 760703,"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": 688924371076.570, "dur": 3.161, + "args": { + "External id": 760704,"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": 688924371083.301, "dur": 42.436, + "args": { + "External id": 760705,"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": 688924371084.573, "dur": 40.344, + "args": { + "External id": 760706,"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": 688924371129.362, "dur": 14.683, + "args": { + "External id": 760707,"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": 688924371149.705, "dur": 24.294, + "args": { + "External id": 760708,"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": 688924371151.978, "dur": 21.669, + "args": { + "External id": 760709,"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": 688924371157.060, "dur": 1.742, + "args": { + "External id": 760710,"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": 688924371179.020, "dur": 26.960, + "args": { + "External id": 760711,"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": 688924371181.088, "dur": 24.677, + "args": { + "External id": 760712,"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": 688924371186.345, "dur": 3.768, + "args": { + "External id": 760713,"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": 688924371191.413, "dur": 13.899, + "args": { + "External id": 760714,"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": 688924371217.543, "dur": 5.473, + "args": { + "External id": 760715,"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": 688924371219.980, "dur": 2.705, + "args": { + "External id": 760716,"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": 688924371224.419, "dur": 1.581, + "args": { + "External id": 760717,"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": 688924371225.180, "dur": 0.746, + "args": { + "External id": 760718,"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": 688924371268.301, "dur": 22.885, + "args": { + "External id": 760719,"Sequence number": 8962172, "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": 688924371293.728, "dur": 15.270, + "args": { + "External id": 760720,"Sequence number": 8962173, "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": 688924371293.728, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 4183436, "tid": 4183436, + "ts": 688924371419.906, "dur": 39.922, + "args": { + "External id": 760721,"Record function id": 0, "Ev Idx": 8576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 4183436, "tid": 4183436, + "ts": 688924371583.667, "dur": 37.257, + "args": { + "External id": 760722,"Sequence number": 8962174, "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": 688924371583.667, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 4183436, "tid": 4183436, + "ts": 688924371702.413, "dur": 33.731, + "args": { + "External id": 760723,"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": 688924371704.032, "dur": 10.986, + "args": { + "External id": 760724,"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": 688924371708.208, "dur": 5.928, + "args": { + "External id": 760725,"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": 688924371716.740, "dur": 19.097, + "args": { + "External id": 760726,"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": 688924815724.025, "dur": 47.621, + "args": { + "External id": 760727,"Sequence number": 8962175, "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": 688924815780.404, "dur": 36.973, + "args": { + "External id": 760728,"Sequence number": 8962176, "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": 688924815970.569, "dur": 27.202, + "args": { + "External id": 760729,"Sequence number": 8962177, "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": 688924816487.480, "dur": 20.346, + "args": { + "External id": 760730,"Sequence number": 8962178, "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": 688924816513.517, "dur": 12.744, + "args": { + "External id": 760731,"Sequence number": 8962179, "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": 688924818357.753, "dur": 2515.585, + "args": { + "External id": 760732,"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": 688924818903.392, "dur": 725.027, + "args": { + "External id": 760733,"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": 688924818921.766, "dur": 69.096, + "args": { + "External id": 760734,"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": 688924818925.436, "dur": 13.634, + "args": { + "External id": 760735,"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": 688924818941.906, "dur": 48.596, + "args": { + "External id": 760736,"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": 688924818944.606, "dur": 45.210, + "args": { + "External id": 760737,"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": 688924820901.629, "dur": 3.100, + "args": { + "External id": 760738,"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": 688924820906.991, "dur": 0.299, + "args": { + "External id": 760739,"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": 688924820908.606, "dur": 0.247, + "args": { + "External id": 760740,"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": 688924820909.901, "dur": 0.312, + "args": { + "External id": 760741,"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": 688924820911.139, "dur": 0.578, + "args": { + "External id": 760742,"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": 688924820913.113, "dur": 0.622, + "args": { + "External id": 760743,"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": 688924820914.695, "dur": 0.695, + "args": { + "External id": 760744,"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": 688924820917.196, "dur": 0.224, + "args": { + "External id": 760745,"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": 688924820918.367, "dur": 0.333, + "args": { + "External id": 760746,"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": 688924820919.703, "dur": 0.201, + "args": { + "External id": 760747,"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": 688924820920.649, "dur": 0.320, + "args": { + "External id": 760748,"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": 688924820921.737, "dur": 0.299, + "args": { + "External id": 760749,"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": 688924820922.779, "dur": 0.256, + "args": { + "External id": 760750,"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": 688924820923.779, "dur": 0.331, + "args": { + "External id": 760751,"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": 688924820925.055, "dur": 0.180, + "args": { + "External id": 760752,"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": 688924820927.555, "dur": 0.206, + "args": { + "External id": 760753,"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": 688924820928.545, "dur": 0.230, + "args": { + "External id": 760754,"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": 688924820929.675, "dur": 0.234, + "args": { + "External id": 760755,"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": 688924820930.919, "dur": 0.205, + "args": { + "External id": 760756,"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": 688924820932.249, "dur": 0.226, + "args": { + "External id": 760757,"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": 688924820933.223, "dur": 0.207, + "args": { + "External id": 760758,"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": 688924820934.372, "dur": 0.203, + "args": { + "External id": 760759,"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": 688924820935.384, "dur": 0.206, + "args": { + "External id": 760760,"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": 688924820938.148, "dur": 0.211, + "args": { + "External id": 760761,"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": 688924820939.091, "dur": 0.209, + "args": { + "External id": 760762,"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": 688924820940.255, "dur": 0.233, + "args": { + "External id": 760763,"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": 688924820941.410, "dur": 0.198, + "args": { + "External id": 760764,"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": 688924820942.548, "dur": 0.207, + "args": { + "External id": 760765,"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": 688924820943.481, "dur": 0.209, + "args": { + "External id": 760766,"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": 688924820944.570, "dur": 0.210, + "args": { + "External id": 760767,"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": 688924820945.613, "dur": 0.475, + "args": { + "External id": 760768,"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": 688924820948.684, "dur": 0.214, + "args": { + "External id": 760769,"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": 688924820949.926, "dur": 0.342, + "args": { + "External id": 760770,"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": 688924820951.231, "dur": 0.318, + "args": { + "External id": 760771,"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": 688924820952.675, "dur": 0.199, + "args": { + "External id": 760772,"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": 688924820953.617, "dur": 0.237, + "args": { + "External id": 760773,"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": 688924820954.605, "dur": 0.345, + "args": { + "External id": 760774,"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": 688924820955.857, "dur": 0.220, + "args": { + "External id": 760775,"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": 688924820956.847, "dur": 0.310, + "args": { + "External id": 760776,"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": 688924820959.207, "dur": 0.206, + "args": { + "External id": 760777,"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": 688924820960.159, "dur": 0.351, + "args": { + "External id": 760778,"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": 688924820961.634, "dur": 0.203, + "args": { + "External id": 760779,"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": 688924820962.571, "dur": 0.209, + "args": { + "External id": 760780,"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": 688924820963.666, "dur": 0.206, + "args": { + "External id": 760781,"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": 688924820964.874, "dur": 0.217, + "args": { + "External id": 760782,"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": 688924820965.953, "dur": 0.208, + "args": { + "External id": 760783,"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": 688924820967.166, "dur": 0.211, + "args": { + "External id": 760784,"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": 688924820970.673, "dur": 0.216, + "args": { + "External id": 760785,"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": 688924820971.817, "dur": 0.225, + "args": { + "External id": 760786,"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": 688924820972.857, "dur": 0.207, + "args": { + "External id": 760787,"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": 688924820973.881, "dur": 0.200, + "args": { + "External id": 760788,"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": 688924820974.953, "dur": 0.214, + "args": { + "External id": 760789,"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": 688924820975.990, "dur": 0.211, + "args": { + "External id": 760790,"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": 688924820977.397, "dur": 0.214, + "args": { + "External id": 760791,"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": 688924820978.447, "dur": 0.204, + "args": { + "External id": 760792,"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": 688924820980.568, "dur": 0.204, + "args": { + "External id": 760793,"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": 688924820981.541, "dur": 0.324, + "args": { + "External id": 760794,"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": 688924820982.582, "dur": 0.290, + "args": { + "External id": 760795,"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": 688924820983.624, "dur": 0.201, + "args": { + "External id": 760796,"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": 688924820984.556, "dur": 0.353, + "args": { + "External id": 760797,"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": 688924820985.628, "dur": 0.346, + "args": { + "External id": 760798,"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": 688924820986.864, "dur": 0.353, + "args": { + "External id": 760799,"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": 688924820987.950, "dur": 0.378, + "args": { + "External id": 760800,"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": 688924820990.957, "dur": 0.211, + "args": { + "External id": 760801,"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": 688924820991.894, "dur": 0.343, + "args": { + "External id": 760802,"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": 688924820993.182, "dur": 0.205, + "args": { + "External id": 760803,"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": 688924820994.116, "dur": 0.200, + "args": { + "External id": 760804,"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": 688924820995.064, "dur": 0.201, + "args": { + "External id": 760805,"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": 688924820996.017, "dur": 0.215, + "args": { + "External id": 760806,"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": 688924820996.954, "dur": 0.339, + "args": { + "External id": 760807,"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": 688924820998.108, "dur": 0.233, + "args": { + "External id": 760808,"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": 688924821000.504, "dur": 0.207, + "args": { + "External id": 760809,"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": 688924821001.474, "dur": 0.203, + "args": { + "External id": 760810,"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": 688924821002.388, "dur": 0.206, + "args": { + "External id": 760811,"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": 688924821003.317, "dur": 0.207, + "args": { + "External id": 760812,"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": 688924821004.234, "dur": 0.204, + "args": { + "External id": 760813,"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": 688924821005.165, "dur": 0.205, + "args": { + "External id": 760814,"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": 688924821006.970, "dur": 0.214, + "args": { + "External id": 760815,"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": 688924821007.937, "dur": 0.228, + "args": { + "External id": 760816,"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": 688924821010.537, "dur": 0.215, + "args": { + "External id": 760817,"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": 688924821011.494, "dur": 0.627, + "args": { + "External id": 760818,"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": 688924821012.903, "dur": 0.326, + "args": { + "External id": 760819,"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": 688924821013.982, "dur": 0.354, + "args": { + "External id": 760820,"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": 688924821015.069, "dur": 0.327, + "args": { + "External id": 760821,"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": 688924821016.179, "dur": 0.213, + "args": { + "External id": 760822,"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": 688924821017.229, "dur": 0.232, + "args": { + "External id": 760823,"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": 688924821018.452, "dur": 0.235, + "args": { + "External id": 760824,"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": 688924821020.556, "dur": 0.212, + "args": { + "External id": 760825,"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": 688924821021.721, "dur": 0.324, + "args": { + "External id": 760826,"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": 688924821022.885, "dur": 0.211, + "args": { + "External id": 760827,"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": 688924821024.165, "dur": 0.210, + "args": { + "External id": 760828,"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": 688924821025.289, "dur": 0.227, + "args": { + "External id": 760829,"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": 688924821026.276, "dur": 0.210, + "args": { + "External id": 760830,"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": 688924821028.125, "dur": 0.350, + "args": { + "External id": 760831,"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": 688924821029.457, "dur": 0.251, + "args": { + "External id": 760832,"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": 688924821089.498, "dur": 0.929, + "args": { + "External id": 765441,"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": 688924821092.255, "dur": 0.276, + "args": { + "External id": 765442,"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": 688924821093.431, "dur": 0.244, + "args": { + "External id": 765443,"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": 688924821094.696, "dur": 0.220, + "args": { + "External id": 765444,"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": 688924821095.727, "dur": 0.224, + "args": { + "External id": 765445,"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": 688924821096.783, "dur": 0.213, + "args": { + "External id": 765446,"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": 688924821097.926, "dur": 0.223, + "args": { + "External id": 765447,"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": 688924821099.037, "dur": 0.216, + "args": { + "External id": 765448,"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": 688924821101.544, "dur": 0.212, + "args": { + "External id": 765449,"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": 688924821102.695, "dur": 0.215, + "args": { + "External id": 765450,"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": 688924821103.670, "dur": 0.212, + "args": { + "External id": 765451,"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": 688924821104.718, "dur": 0.211, + "args": { + "External id": 765452,"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": 688924821105.745, "dur": 0.221, + "args": { + "External id": 765453,"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": 688924821106.762, "dur": 0.206, + "args": { + "External id": 765454,"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": 688924821109.311, "dur": 0.225, + "args": { + "External id": 765455,"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": 688924821110.499, "dur": 0.222, + "args": { + "External id": 765456,"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": 688924821112.761, "dur": 0.236, + "args": { + "External id": 765457,"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": 688924821113.840, "dur": 0.224, + "args": { + "External id": 765458,"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": 688924821114.811, "dur": 0.218, + "args": { + "External id": 765459,"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": 688924821115.840, "dur": 0.212, + "args": { + "External id": 765460,"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": 688924821116.858, "dur": 0.221, + "args": { + "External id": 765461,"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": 688924821117.843, "dur": 0.211, + "args": { + "External id": 765462,"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": 688924821118.897, "dur": 0.224, + "args": { + "External id": 765463,"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": 688924821133.161, "dur": 0.467, + "args": { + "External id": 765464,"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": 688924821136.606, "dur": 0.241, + "args": { + "External id": 765465,"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": 688924821138.033, "dur": 0.229, + "args": { + "External id": 765466,"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": 688924821139.061, "dur": 0.212, + "args": { + "External id": 765467,"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": 688924821140.197, "dur": 0.236, + "args": { + "External id": 765468,"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": 688924821141.279, "dur": 0.218, + "args": { + "External id": 765469,"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": 688924821142.269, "dur": 0.219, + "args": { + "External id": 765470,"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": 688924821143.335, "dur": 0.240, + "args": { + "External id": 765471,"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": 688924821144.436, "dur": 0.216, + "args": { + "External id": 765472,"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": 688924821146.872, "dur": 0.216, + "args": { + "External id": 765473,"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": 688924821147.848, "dur": 0.213, + "args": { + "External id": 765474,"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": 688924821152.460, "dur": 0.209, + "args": { + "External id": 765475,"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": 688924821153.507, "dur": 0.215, + "args": { + "External id": 765476,"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": 688924821154.603, "dur": 0.208, + "args": { + "External id": 765477,"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": 688924821155.671, "dur": 0.214, + "args": { + "External id": 765478,"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": 688924821156.718, "dur": 0.216, + "args": { + "External id": 765479,"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": 688924821157.808, "dur": 0.214, + "args": { + "External id": 765480,"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": 688924821160.291, "dur": 0.209, + "args": { + "External id": 765481,"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": 688924821161.497, "dur": 0.219, + "args": { + "External id": 765482,"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": 688924821162.554, "dur": 0.214, + "args": { + "External id": 765483,"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": 688924821163.571, "dur": 0.209, + "args": { + "External id": 765484,"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": 688924821164.658, "dur": 0.215, + "args": { + "External id": 765485,"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": 688924821165.726, "dur": 0.228, + "args": { + "External id": 765486,"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": 688924821166.815, "dur": 0.205, + "args": { + "External id": 765487,"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": 688924821167.943, "dur": 0.215, + "args": { + "External id": 765488,"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": 688924821170.017, "dur": 0.211, + "args": { + "External id": 765489,"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": 688924821171.097, "dur": 0.228, + "args": { + "External id": 765490,"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": 688924821172.122, "dur": 0.209, + "args": { + "External id": 765491,"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": 688924821173.099, "dur": 0.214, + "args": { + "External id": 765492,"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": 688924821174.084, "dur": 0.207, + "args": { + "External id": 765493,"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": 688924821175.075, "dur": 0.210, + "args": { + "External id": 765494,"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": 688924821176.504, "dur": 0.208, + "args": { + "External id": 765495,"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": 688924821177.591, "dur": 0.213, + "args": { + "External id": 765496,"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": 688924821180.353, "dur": 0.213, + "args": { + "External id": 765497,"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": 688924821181.317, "dur": 0.214, + "args": { + "External id": 765498,"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": 688924821182.342, "dur": 0.206, + "args": { + "External id": 765499,"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": 688924821183.300, "dur": 0.211, + "args": { + "External id": 765500,"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": 688924821184.279, "dur": 0.209, + "args": { + "External id": 765501,"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": 688924821185.222, "dur": 0.210, + "args": { + "External id": 765502,"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": 688924821186.223, "dur": 0.208, + "args": { + "External id": 765503,"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": 688924821187.171, "dur": 0.218, + "args": { + "External id": 765504,"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": 688924821189.974, "dur": 0.206, + "args": { + "External id": 765505,"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": 688924821190.966, "dur": 0.210, + "args": { + "External id": 765506,"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": 688924821193.442, "dur": 0.218, + "args": { + "External id": 765507,"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": 688924821194.482, "dur": 0.216, + "args": { + "External id": 765508,"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": 688924821195.536, "dur": 0.210, + "args": { + "External id": 765509,"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": 688924821196.522, "dur": 0.214, + "args": { + "External id": 765510,"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": 688924821197.508, "dur": 0.206, + "args": { + "External id": 765511,"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": 688924821198.585, "dur": 0.224, + "args": { + "External id": 765512,"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": 688924821201.077, "dur": 0.211, + "args": { + "External id": 765513,"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": 688924821202.082, "dur": 0.214, + "args": { + "External id": 765514,"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": 688924821203.131, "dur": 0.208, + "args": { + "External id": 765515,"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": 688924821204.166, "dur": 0.210, + "args": { + "External id": 765516,"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": 688924821205.248, "dur": 0.210, + "args": { + "External id": 765517,"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": 688924821206.199, "dur": 0.209, + "args": { + "External id": 765518,"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": 688924821207.475, "dur": 0.209, + "args": { + "External id": 765519,"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": 688924821208.590, "dur": 0.219, + "args": { + "External id": 765520,"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": 688924821210.843, "dur": 0.214, + "args": { + "External id": 765521,"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": 688924821211.837, "dur": 0.213, + "args": { + "External id": 765522,"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": 688924821212.810, "dur": 0.206, + "args": { + "External id": 765523,"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": 688924821213.854, "dur": 0.219, + "args": { + "External id": 765524,"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": 688924821214.850, "dur": 0.221, + "args": { + "External id": 765525,"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": 688924821215.797, "dur": 0.211, + "args": { + "External id": 765526,"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": 688924821216.855, "dur": 0.213, + "args": { + "External id": 765527,"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": 688924821217.946, "dur": 0.213, + "args": { + "External id": 765528,"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": 688924821220.429, "dur": 0.210, + "args": { + "External id": 765529,"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": 688924821221.487, "dur": 0.225, + "args": { + "External id": 765530,"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": 688924821222.669, "dur": 0.215, + "args": { + "External id": 765531,"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": 688924821223.712, "dur": 0.218, + "args": { + "External id": 765532,"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": 688924821224.788, "dur": 0.210, + "args": { + "External id": 765533,"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": 688924821225.795, "dur": 0.220, + "args": { + "External id": 765534,"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": 688924821226.764, "dur": 0.210, + "args": { + "External id": 765535,"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": 688924821227.692, "dur": 0.210, + "args": { + "External id": 765536,"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": 688924821229.909, "dur": 0.211, + "args": { + "External id": 765537,"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": 688924821230.942, "dur": 0.210, + "args": { + "External id": 765538,"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": 688924821231.939, "dur": 0.205, + "args": { + "External id": 765539,"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": 688924821232.939, "dur": 0.213, + "args": { + "External id": 765540,"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": 688924821233.888, "dur": 0.207, + "args": { + "External id": 765541,"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": 688924821234.979, "dur": 0.211, + "args": { + "External id": 765542,"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": 688924821235.988, "dur": 0.202, + "args": { + "External id": 765543,"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": 688924821237.041, "dur": 0.222, + "args": { + "External id": 765544,"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": 688924821239.523, "dur": 0.210, + "args": { + "External id": 765545,"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": 688924821240.551, "dur": 0.224, + "args": { + "External id": 765546,"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": 688924821241.894, "dur": 0.203, + "args": { + "External id": 765547,"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": 688924821242.894, "dur": 0.214, + "args": { + "External id": 765548,"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": 688924821266.250, "dur": 0.323, + "args": { + "External id": 765549,"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": 688924821267.723, "dur": 0.239, + "args": { + "External id": 765550,"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": 688924821268.823, "dur": 0.207, + "args": { + "External id": 765551,"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": 688924821269.851, "dur": 0.228, + "args": { + "External id": 765552,"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": 688924821272.150, "dur": 0.204, + "args": { + "External id": 765553,"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": 688924821273.162, "dur": 0.218, + "args": { + "External id": 765554,"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": 688924821274.143, "dur": 0.203, + "args": { + "External id": 765555,"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": 688924821275.094, "dur": 0.204, + "args": { + "External id": 765556,"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": 688924821276.036, "dur": 0.240, + "args": { + "External id": 765557,"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": 688924821277.008, "dur": 0.200, + "args": { + "External id": 765558,"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": 688924821278.034, "dur": 0.206, + "args": { + "External id": 765559,"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": 688924821279.005, "dur": 0.205, + "args": { + "External id": 765560,"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": 688924821281.421, "dur": 0.206, + "args": { + "External id": 765561,"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": 688924821282.410, "dur": 0.199, + "args": { + "External id": 765562,"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": 688924821283.397, "dur": 0.208, + "args": { + "External id": 765563,"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": 688924821284.407, "dur": 0.203, + "args": { + "External id": 765564,"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": 688924821330.547, "dur": 1201.901, + "args": { + "External id": 765565,"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": 688924821701.732, "dur": 761.011, + "args": { + "External id": 765566,"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": 688924821708.575, "dur": 7.980, + "args": { + "External id": 765567,"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": 688924821712.677, "dur": 3.178, + "args": { + "External id": 765568,"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": 688924821717.407, "dur": 3.232, + "args": { + "External id": 765569,"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": 688924821718.266, "dur": 2.266, + "args": { + "External id": 765570,"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": 688924821721.002, "dur": 2.800, + "args": { + "External id": 765571,"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": 688924821723.019, "dur": 0.718, + "args": { + "External id": 765572,"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": 688924821724.130, "dur": 1.209, + "args": { + "External id": 765573,"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": 688924821724.515, "dur": 0.751, + "args": { + "External id": 765574,"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": 688924821726.959, "dur": 5.034, + "args": { + "External id": 765575,"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": 688924821731.279, "dur": 0.650, + "args": { + "External id": 765576,"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": 688924821732.275, "dur": 0.958, + "args": { + "External id": 765577,"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": 688924821732.671, "dur": 0.498, + "args": { + "External id": 765578,"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": 688924821733.476, "dur": 1.353, + "args": { + "External id": 765579,"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": 688924821733.836, "dur": 0.926, + "args": { + "External id": 765580,"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": 688924821735.057, "dur": 5.004, + "args": { + "External id": 765581,"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": 688924821739.161, "dur": 0.836, + "args": { + "External id": 765582,"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": 688924821740.397, "dur": 1.180, + "args": { + "External id": 765583,"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": 688924821740.827, "dur": 0.690, + "args": { + "External id": 765584,"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": 688924821741.807, "dur": 2.390, + "args": { + "External id": 765585,"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": 688924821742.166, "dur": 1.958, + "args": { + "External id": 765586,"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": 688924821744.465, "dur": 2.289, + "args": { + "External id": 765587,"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": 688924821746.113, "dur": 0.579, + "args": { + "External id": 765588,"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": 688924821747.208, "dur": 0.837, + "args": { + "External id": 765589,"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": 688924821747.566, "dur": 0.412, + "args": { + "External id": 765590,"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": 688924821749.832, "dur": 5.325, + "args": { + "External id": 765591,"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": 688924821754.560, "dur": 0.530, + "args": { + "External id": 765592,"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": 688924821755.424, "dur": 1.423, + "args": { + "External id": 765593,"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": 688924821755.783, "dur": 1.000, + "args": { + "External id": 765594,"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": 688924821757.092, "dur": 1.409, + "args": { + "External id": 765595,"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": 688924821757.452, "dur": 0.981, + "args": { + "External id": 765596,"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": 688924821758.725, "dur": 3.228, + "args": { + "External id": 765597,"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": 688924821761.307, "dur": 0.581, + "args": { + "External id": 765598,"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": 688924821762.178, "dur": 1.083, + "args": { + "External id": 765599,"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": 688924821762.547, "dur": 0.647, + "args": { + "External id": 765600,"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": 688924821763.506, "dur": 2.456, + "args": { + "External id": 765601,"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": 688924821763.864, "dur": 2.024, + "args": { + "External id": 765602,"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": 688924821766.211, "dur": 2.070, + "args": { + "External id": 765603,"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": 688924821767.595, "dur": 0.625, + "args": { + "External id": 765604,"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": 688924821768.684, "dur": 0.933, + "args": { + "External id": 765605,"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": 688924821769.044, "dur": 0.507, + "args": { + "External id": 765606,"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": 688924821771.221, "dur": 5.004, + "args": { + "External id": 765607,"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": 688924821775.496, "dur": 0.661, + "args": { + "External id": 765608,"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": 688924821776.468, "dur": 1.114, + "args": { + "External id": 765609,"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": 688924821776.826, "dur": 0.680, + "args": { + "External id": 765610,"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": 688924821777.803, "dur": 1.008, + "args": { + "External id": 765611,"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": 688924821778.163, "dur": 0.579, + "args": { + "External id": 765612,"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": 688924821779.036, "dur": 3.398, + "args": { + "External id": 765613,"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": 688924821781.771, "dur": 0.600, + "args": { + "External id": 765614,"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": 688924821782.672, "dur": 0.944, + "args": { + "External id": 765615,"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": 688924821783.059, "dur": 0.487, + "args": { + "External id": 765616,"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": 688924821783.841, "dur": 13.154, + "args": { + "External id": 765617,"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": 688924821784.207, "dur": 12.240, + "args": { + "External id": 765618,"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": 688924821798.306, "dur": 3.093, + "args": { + "External id": 765619,"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": 688924821800.651, "dur": 0.684, + "args": { + "External id": 765620,"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": 688924821801.734, "dur": 1.452, + "args": { + "External id": 765621,"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": 688924821802.128, "dur": 0.996, + "args": { + "External id": 765622,"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": 688924821804.017, "dur": 4.594, + "args": { + "External id": 765623,"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": 688924821807.897, "dur": 0.649, + "args": { + "External id": 765624,"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": 688924821808.868, "dur": 1.032, + "args": { + "External id": 765625,"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": 688924821809.230, "dur": 0.607, + "args": { + "External id": 765626,"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": 688924821810.153, "dur": 1.521, + "args": { + "External id": 765627,"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": 688924821810.515, "dur": 1.098, + "args": { + "External id": 765628,"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": 688924821811.907, "dur": 4.189, + "args": { + "External id": 765629,"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": 688924821815.340, "dur": 0.692, + "args": { + "External id": 765630,"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": 688924821816.325, "dur": 1.185, + "args": { + "External id": 765631,"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": 688924821816.706, "dur": 0.742, + "args": { + "External id": 765632,"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": 688924821817.741, "dur": 2.593, + "args": { + "External id": 765633,"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": 688924821818.111, "dur": 2.127, + "args": { + "External id": 765634,"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": 688924821820.703, "dur": 3.048, + "args": { + "External id": 765635,"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": 688924821822.718, "dur": 0.971, + "args": { + "External id": 765636,"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": 688924821824.163, "dur": 1.162, + "args": { + "External id": 765637,"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": 688924821824.533, "dur": 0.729, + "args": { + "External id": 765638,"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": 688924821825.604, "dur": 4.473, + "args": { + "External id": 765639,"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": 688924821829.302, "dur": 0.700, + "args": { + "External id": 765640,"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": 688924821830.375, "dur": 1.018, + "args": { + "External id": 765641,"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": 688924821830.744, "dur": 0.586, + "args": { + "External id": 765642,"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": 688924821831.927, "dur": 1.592, + "args": { + "External id": 765643,"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": 688924821832.302, "dur": 1.151, + "args": { + "External id": 765644,"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": 688924821833.761, "dur": 3.772, + "args": { + "External id": 765645,"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": 688924821836.863, "dur": 0.604, + "args": { + "External id": 765646,"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": 688924821837.935, "dur": 1.253, + "args": { + "External id": 765647,"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": 688924821838.307, "dur": 0.818, + "args": { + "External id": 765648,"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": 688924821839.465, "dur": 2.463, + "args": { + "External id": 765649,"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": 688924821839.834, "dur": 1.947, + "args": { + "External id": 765650,"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": 688924821842.193, "dur": 1.661, + "args": { + "External id": 765651,"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": 688924821843.012, "dur": 0.782, + "args": { + "External id": 765652,"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": 688924821844.427, "dur": 1.371, + "args": { + "External id": 765653,"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": 688924821844.821, "dur": 0.914, + "args": { + "External id": 765654,"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": 688924821846.053, "dur": 3.250, + "args": { + "External id": 765655,"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": 688924821848.647, "dur": 0.597, + "args": { + "External id": 765656,"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": 688924821849.556, "dur": 1.155, + "args": { + "External id": 765657,"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": 688924821849.957, "dur": 0.694, + "args": { + "External id": 765658,"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": 688924821851.002, "dur": 1.136, + "args": { + "External id": 765659,"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": 688924821851.367, "dur": 0.707, + "args": { + "External id": 765660,"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": 688924821852.376, "dur": 3.382, + "args": { + "External id": 765661,"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": 688924821854.724, "dur": 0.972, + "args": { + "External id": 765662,"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": 688924821856.013, "dur": 0.996, + "args": { + "External id": 765663,"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": 688924821856.365, "dur": 0.584, + "args": { + "External id": 765664,"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": 688924821857.249, "dur": 2.343, + "args": { + "External id": 765665,"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": 688924821857.604, "dur": 1.916, + "args": { + "External id": 765666,"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": 688924821859.990, "dur": 1.837, + "args": { + "External id": 765667,"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": 688924821860.693, "dur": 1.061, + "args": { + "External id": 765668,"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": 688924821862.065, "dur": 1.041, + "args": { + "External id": 765669,"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": 688924821862.429, "dur": 0.611, + "args": { + "External id": 765670,"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": 688924821863.456, "dur": 2.810, + "args": { + "External id": 765671,"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": 688924821865.701, "dur": 0.498, + "args": { + "External id": 765672,"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": 688924821866.530, "dur": 1.016, + "args": { + "External id": 765673,"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": 688924821866.900, "dur": 0.581, + "args": { + "External id": 765674,"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": 688924821867.828, "dur": 0.950, + "args": { + "External id": 765675,"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": 688924821868.198, "dur": 0.519, + "args": { + "External id": 765676,"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": 688924821869.018, "dur": 3.086, + "args": { + "External id": 765677,"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": 688924821871.520, "dur": 0.518, + "args": { + "External id": 765678,"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": 688924821872.355, "dur": 1.214, + "args": { + "External id": 765679,"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": 688924821872.706, "dur": 0.796, + "args": { + "External id": 765680,"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": 688924821874.009, "dur": 2.921, + "args": { + "External id": 765681,"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": 688924821874.358, "dur": 2.393, + "args": { + "External id": 765682,"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": 688924821877.175, "dur": 1.698, + "args": { + "External id": 765683,"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": 688924821877.740, "dur": 1.069, + "args": { + "External id": 765684,"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": 688924821879.119, "dur": 1.169, + "args": { + "External id": 765685,"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": 688924821879.483, "dur": 0.739, + "args": { + "External id": 765686,"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": 688924821880.629, "dur": 3.625, + "args": { + "External id": 765687,"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": 688924821883.285, "dur": 0.907, + "args": { + "External id": 765688,"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": 688924821884.527, "dur": 1.258, + "args": { + "External id": 765689,"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": 688924821884.890, "dur": 0.830, + "args": { + "External id": 765690,"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": 688924821886.073, "dur": 1.352, + "args": { + "External id": 765691,"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": 688924821886.437, "dur": 0.923, + "args": { + "External id": 765692,"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": 688924821887.665, "dur": 2.997, + "args": { + "External id": 765693,"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": 688924821890.004, "dur": 0.596, + "args": { + "External id": 765694,"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": 688924821890.918, "dur": 1.070, + "args": { + "External id": 765695,"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": 688924821891.318, "dur": 0.607, + "args": { + "External id": 765696,"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": 688924821892.244, "dur": 3.038, + "args": { + "External id": 765697,"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": 688924821892.615, "dur": 2.479, + "args": { + "External id": 765698,"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": 688924821895.537, "dur": 1.095, + "args": { + "External id": 765699,"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": 688924821896.018, "dur": 0.554, + "args": { + "External id": 765700,"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": 688924821896.871, "dur": 1.217, + "args": { + "External id": 765701,"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": 688924821897.239, "dur": 0.786, + "args": { + "External id": 765702,"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": 688924821898.344, "dur": 3.016, + "args": { + "External id": 765703,"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": 688924821900.871, "dur": 0.429, + "args": { + "External id": 765704,"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": 688924821901.615, "dur": 1.315, + "args": { + "External id": 765705,"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": 688924821901.977, "dur": 0.889, + "args": { + "External id": 765706,"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": 688924821903.279, "dur": 1.146, + "args": { + "External id": 765707,"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": 688924821903.645, "dur": 0.712, + "args": { + "External id": 765708,"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": 688924821904.664, "dur": 3.130, + "args": { + "External id": 765709,"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": 688924821906.910, "dur": 0.820, + "args": { + "External id": 765710,"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": 688924821908.049, "dur": 1.544, + "args": { + "External id": 765711,"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": 688924821908.433, "dur": 1.097, + "args": { + "External id": 765712,"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": 688924821909.843, "dur": 2.756, + "args": { + "External id": 765713,"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": 688924821910.210, "dur": 2.322, + "args": { + "External id": 765714,"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": 688924821912.862, "dur": 1.461, + "args": { + "External id": 765715,"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": 688924821913.808, "dur": 0.452, + "args": { + "External id": 765716,"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": 688924821914.561, "dur": 1.309, + "args": { + "External id": 765717,"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": 688924821914.913, "dur": 0.894, + "args": { + "External id": 765718,"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": 688924821916.126, "dur": 3.934, + "args": { + "External id": 765719,"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": 688924821919.089, "dur": 0.910, + "args": { + "External id": 765720,"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": 688924821920.319, "dur": 1.607, + "args": { + "External id": 765721,"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": 688924821920.718, "dur": 1.144, + "args": { + "External id": 765722,"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": 688924821922.183, "dur": 1.339, + "args": { + "External id": 765723,"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": 688924821922.549, "dur": 0.907, + "args": { + "External id": 765724,"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": 688924821923.776, "dur": 2.677, + "args": { + "External id": 765725,"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": 688924821925.842, "dur": 0.549, + "args": { + "External id": 765726,"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": 688924821926.708, "dur": 1.195, + "args": { + "External id": 765727,"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": 688924821927.067, "dur": 0.771, + "args": { + "External id": 765728,"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": 688924821928.155, "dur": 2.767, + "args": { + "External id": 765729,"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": 688924821928.516, "dur": 2.320, + "args": { + "External id": 765730,"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": 688924821931.198, "dur": 1.364, + "args": { + "External id": 765731,"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": 688924821931.673, "dur": 0.828, + "args": { + "External id": 765732,"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": 688924821932.893, "dur": 1.339, + "args": { + "External id": 765733,"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": 688924821933.266, "dur": 0.902, + "args": { + "External id": 765734,"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": 688924821934.702, "dur": 3.596, + "args": { + "External id": 765735,"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": 688924821937.490, "dur": 0.745, + "args": { + "External id": 765736,"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": 688924821938.553, "dur": 1.032, + "args": { + "External id": 765737,"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": 688924821938.928, "dur": 0.580, + "args": { + "External id": 765738,"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": 688924821939.854, "dur": 1.018, + "args": { + "External id": 765739,"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": 688924821940.225, "dur": 0.583, + "args": { + "External id": 765740,"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": 688924821941.126, "dur": 3.264, + "args": { + "External id": 765741,"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": 688924821943.667, "dur": 0.661, + "args": { + "External id": 765742,"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": 688924821944.645, "dur": 0.977, + "args": { + "External id": 765743,"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": 688924821944.999, "dur": 0.560, + "args": { + "External id": 765744,"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": 688924821945.874, "dur": 2.571, + "args": { + "External id": 765745,"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": 688924821946.266, "dur": 2.115, + "args": { + "External id": 765746,"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": 688924821948.697, "dur": 1.517, + "args": { + "External id": 765747,"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": 688924821949.533, "dur": 0.620, + "args": { + "External id": 765748,"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": 688924821950.453, "dur": 1.127, + "args": { + "External id": 765749,"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": 688924821950.809, "dur": 0.705, + "args": { + "External id": 765750,"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": 688924821951.834, "dur": 2.926, + "args": { + "External id": 765751,"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": 688924821954.321, "dur": 0.312, + "args": { + "External id": 765752,"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": 688924821955.041, "dur": 1.017, + "args": { + "External id": 765753,"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": 688924821955.447, "dur": 0.550, + "args": { + "External id": 765754,"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": 688924821956.323, "dur": 1.183, + "args": { + "External id": 765755,"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": 688924821956.727, "dur": 0.714, + "args": { + "External id": 765756,"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": 688924821957.757, "dur": 3.447, + "args": { + "External id": 765757,"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": 688924821960.283, "dur": 0.851, + "args": { + "External id": 765758,"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": 688924821961.500, "dur": 1.421, + "args": { + "External id": 765759,"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": 688924821962.323, "dur": 0.537, + "args": { + "External id": 765760,"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": 688924821963.200, "dur": 2.750, + "args": { + "External id": 765761,"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": 688924821963.819, "dur": 2.064, + "args": { + "External id": 765762,"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": 688924821966.238, "dur": 1.515, + "args": { + "External id": 765763,"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": 688924821966.708, "dur": 0.973, + "args": { + "External id": 765764,"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": 688924821968.016, "dur": 1.582, + "args": { + "External id": 765765,"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": 688924821968.646, "dur": 0.889, + "args": { + "External id": 765766,"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": 688924821970.016, "dur": 2.643, + "args": { + "External id": 765767,"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": 688924821972.218, "dur": 0.377, + "args": { + "External id": 765768,"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": 688924821972.975, "dur": 1.295, + "args": { + "External id": 765769,"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": 688924821973.690, "dur": 0.516, + "args": { + "External id": 765770,"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": 688924821974.550, "dur": 1.396, + "args": { + "External id": 765771,"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": 688924821975.335, "dur": 0.532, + "args": { + "External id": 765772,"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": 688924821976.221, "dur": 3.189, + "args": { + "External id": 765773,"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": 688924821978.796, "dur": 0.550, + "args": { + "External id": 765774,"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": 688924821979.789, "dur": 1.353, + "args": { + "External id": 765775,"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": 688924821980.591, "dur": 0.490, + "args": { + "External id": 765776,"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": 688924821981.440, "dur": 2.583, + "args": { + "External id": 765777,"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": 688924821982.001, "dur": 1.864, + "args": { + "External id": 765778,"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": 688924821984.299, "dur": 1.289, + "args": { + "External id": 765779,"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": 688924821984.841, "dur": 0.684, + "args": { + "External id": 765780,"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": 688924821985.944, "dur": 1.039, + "args": { + "External id": 765781,"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": 688924821986.351, "dur": 0.568, + "args": { + "External id": 765782,"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": 688924821987.441, "dur": 3.641, + "args": { + "External id": 765783,"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": 688924821990.084, "dur": 0.935, + "args": { + "External id": 765784,"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": 688924821991.375, "dur": 1.132, + "args": { + "External id": 765785,"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": 688924821991.988, "dur": 0.456, + "args": { + "External id": 765786,"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": 688924821992.797, "dur": 1.228, + "args": { + "External id": 765787,"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": 688924821993.268, "dur": 0.694, + "args": { + "External id": 765788,"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": 688924821994.390, "dur": 2.959, + "args": { + "External id": 765789,"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": 688924821996.684, "dur": 0.595, + "args": { + "External id": 765790,"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": 688924821997.639, "dur": 1.078, + "args": { + "External id": 765791,"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": 688924821998.065, "dur": 0.590, + "args": { + "External id": 765792,"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": 688924821998.998, "dur": 2.953, + "args": { + "External id": 765793,"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": 688924821999.584, "dur": 2.299, + "args": { + "External id": 765794,"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": 688924822002.220, "dur": 1.237, + "args": { + "External id": 765795,"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": 688924822002.799, "dur": 0.598, + "args": { + "External id": 765796,"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": 688924822004.037, "dur": 1.400, + "args": { + "External id": 765797,"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": 688924822004.610, "dur": 0.547, + "args": { + "External id": 765798,"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": 688924822005.724, "dur": 3.188, + "args": { + "External id": 765799,"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": 688924822008.357, "dur": 0.492, + "args": { + "External id": 765800,"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": 688924822009.199, "dur": 0.953, + "args": { + "External id": 765801,"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": 688924822009.657, "dur": 0.433, + "args": { + "External id": 765802,"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": 688924822010.523, "dur": 1.087, + "args": { + "External id": 765803,"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": 688924822011.020, "dur": 0.528, + "args": { + "External id": 765804,"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": 688924822011.886, "dur": 3.273, + "args": { + "External id": 765805,"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": 688924822014.666, "dur": 0.433, + "args": { + "External id": 765806,"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": 688924822015.572, "dur": 1.171, + "args": { + "External id": 765807,"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": 688924822016.077, "dur": 0.603, + "args": { + "External id": 765808,"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": 688924822017.046, "dur": 2.486, + "args": { + "External id": 765809,"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": 688924822017.578, "dur": 1.886, + "args": { + "External id": 765810,"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": 688924822019.804, "dur": 1.503, + "args": { + "External id": 765811,"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": 688924822020.303, "dur": 0.929, + "args": { + "External id": 765812,"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": 688924822021.763, "dur": 1.527, + "args": { + "External id": 765813,"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": 688924822022.288, "dur": 0.937, + "args": { + "External id": 765814,"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": 688924822023.571, "dur": 3.382, + "args": { + "External id": 765815,"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": 688924822026.003, "dur": 0.888, + "args": { + "External id": 765816,"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": 688924822027.261, "dur": 1.308, + "args": { + "External id": 765817,"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": 688924822028.052, "dur": 0.454, + "args": { + "External id": 765818,"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": 688924822028.973, "dur": 1.242, + "args": { + "External id": 765819,"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": 688924822029.535, "dur": 0.616, + "args": { + "External id": 765820,"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": 688924822030.500, "dur": 2.549, + "args": { + "External id": 765821,"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": 688924822032.651, "dur": 0.331, + "args": { + "External id": 765822,"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": 688924822033.328, "dur": 1.003, + "args": { + "External id": 765823,"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": 688924822033.750, "dur": 0.518, + "args": { + "External id": 765824,"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": 688924822034.662, "dur": 2.794, + "args": { + "External id": 765825,"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": 688924822035.162, "dur": 2.223, + "args": { + "External id": 765826,"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": 688924822037.729, "dur": 1.576, + "args": { + "External id": 765827,"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": 688924822038.259, "dur": 0.984, + "args": { + "External id": 765828,"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": 688924822039.836, "dur": 1.185, + "args": { + "External id": 765829,"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": 688924822040.241, "dur": 0.713, + "args": { + "External id": 765830,"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": 688924822041.301, "dur": 3.213, + "args": { + "External id": 765831,"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": 688924822043.720, "dur": 0.729, + "args": { + "External id": 765832,"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": 688924822044.826, "dur": 1.081, + "args": { + "External id": 765833,"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": 688924822045.365, "dur": 0.478, + "args": { + "External id": 765834,"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": 688924822046.187, "dur": 1.171, + "args": { + "External id": 765835,"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": 688924822046.772, "dur": 0.522, + "args": { + "External id": 765836,"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": 688924822047.639, "dur": 4.102, + "args": { + "External id": 765837,"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": 688924822051.079, "dur": 0.593, + "args": { + "External id": 765838,"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": 688924822052.021, "dur": 1.377, + "args": { + "External id": 765839,"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": 688924822052.588, "dur": 0.746, + "args": { + "External id": 765840,"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": 688924822053.800, "dur": 2.814, + "args": { + "External id": 765841,"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": 688924822054.395, "dur": 2.154, + "args": { + "External id": 765842,"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": 688924822056.896, "dur": 0.755, + "args": { + "External id": 765843,"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": 688924822057.333, "dur": 0.255, + "args": { + "External id": 765844,"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": 688924822058.151, "dur": 0.994, + "args": { + "External id": 765845,"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": 688924822058.560, "dur": 0.521, + "args": { + "External id": 765846,"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": 688924822059.444, "dur": 2.945, + "args": { + "External id": 765847,"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": 688924822061.749, "dur": 0.578, + "args": { + "External id": 765848,"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": 688924822062.672, "dur": 0.957, + "args": { + "External id": 765849,"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": 688924822063.168, "dur": 0.392, + "args": { + "External id": 765850,"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": 688924822063.909, "dur": 1.419, + "args": { + "External id": 765851,"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": 688924822064.313, "dur": 0.952, + "args": { + "External id": 765852,"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": 688924822065.680, "dur": 2.816, + "args": { + "External id": 765853,"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": 688924822068.060, "dur": 0.371, + "args": { + "External id": 765854,"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": 688924822068.787, "dur": 0.753, + "args": { + "External id": 765855,"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": 688924822069.218, "dur": 0.258, + "args": { + "External id": 765856,"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": 688924822069.818, "dur": 2.351, + "args": { + "External id": 765857,"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": 688924822070.315, "dur": 1.788, + "args": { + "External id": 765858,"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": 688924822072.439, "dur": 0.955, + "args": { + "External id": 765859,"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": 688924822072.858, "dur": 0.470, + "args": { + "External id": 765860,"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": 688924822073.752, "dur": 1.588, + "args": { + "External id": 765861,"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": 688924822074.276, "dur": 0.996, + "args": { + "External id": 765862,"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": 688924822075.620, "dur": 3.473, + "args": { + "External id": 765863,"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": 688924822077.840, "dur": 1.189, + "args": { + "External id": 765864,"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": 688924822079.381, "dur": 0.902, + "args": { + "External id": 765865,"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": 688924822079.852, "dur": 0.367, + "args": { + "External id": 765866,"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": 688924822080.564, "dur": 1.669, + "args": { + "External id": 765867,"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": 688924822081.070, "dur": 1.099, + "args": { + "External id": 765868,"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": 688924822082.512, "dur": 2.682, + "args": { + "External id": 765869,"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": 688924822084.712, "dur": 0.420, + "args": { + "External id": 765870,"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": 688924822085.478, "dur": 0.811, + "args": { + "External id": 765871,"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": 688924822085.898, "dur": 0.327, + "args": { + "External id": 765872,"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": 688924822086.563, "dur": 2.559, + "args": { + "External id": 765873,"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": 688924822086.964, "dur": 2.089, + "args": { + "External id": 765874,"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": 688924822089.391, "dur": 1.020, + "args": { + "External id": 765875,"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": 688924822089.930, "dur": 0.420, + "args": { + "External id": 765876,"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": 688924822090.698, "dur": 1.258, + "args": { + "External id": 765877,"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": 688924822091.223, "dur": 0.668, + "args": { + "External id": 765878,"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": 688924822092.360, "dur": 3.076, + "args": { + "External id": 765879,"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": 688924822095.043, "dur": 0.324, + "args": { + "External id": 765880,"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": 688924822095.747, "dur": 0.777, + "args": { + "External id": 765881,"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": 688924822096.177, "dur": 0.283, + "args": { + "External id": 765882,"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": 688924822096.889, "dur": 1.134, + "args": { + "External id": 765883,"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": 688924822097.518, "dur": 0.441, + "args": { + "External id": 765884,"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": 688924822098.304, "dur": 2.991, + "args": { + "External id": 765885,"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": 688924822100.804, "dur": 0.430, + "args": { + "External id": 765886,"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": 688924822101.816, "dur": 1.034, + "args": { + "External id": 765887,"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": 688924822102.255, "dur": 0.531, + "args": { + "External id": 765888,"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": 688924822103.124, "dur": 2.380, + "args": { + "External id": 765889,"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": 688924822103.543, "dur": 1.894, + "args": { + "External id": 765890,"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": 688924822105.783, "dur": 0.929, + "args": { + "External id": 765891,"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": 688924822106.216, "dur": 0.435, + "args": { + "External id": 765892,"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": 688924822107.008, "dur": 0.916, + "args": { + "External id": 765893,"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": 688924822107.457, "dur": 0.402, + "args": { + "External id": 765894,"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": 688924822108.362, "dur": 3.435, + "args": { + "External id": 765895,"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": 688924822111.163, "dur": 0.565, + "args": { + "External id": 765896,"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": 688924822112.080, "dur": 0.956, + "args": { + "External id": 765897,"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": 688924822112.550, "dur": 0.419, + "args": { + "External id": 765898,"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": 688924822113.432, "dur": 1.235, + "args": { + "External id": 765899,"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": 688924822113.884, "dur": 0.719, + "args": { + "External id": 765900,"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": 688924822114.943, "dur": 3.885, + "args": { + "External id": 765901,"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": 688924822118.284, "dur": 0.478, + "args": { + "External id": 765902,"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": 688924822119.291, "dur": 1.160, + "args": { + "External id": 765903,"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": 688924822119.805, "dur": 0.584, + "args": { + "External id": 765904,"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": 688924822120.739, "dur": 3.110, + "args": { + "External id": 765905,"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": 688924822121.238, "dur": 2.200, + "args": { + "External id": 765906,"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": 688924822124.134, "dur": 0.930, + "args": { + "External id": 765907,"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": 688924822124.640, "dur": 0.363, + "args": { + "External id": 765908,"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": 688924822125.329, "dur": 1.295, + "args": { + "External id": 765909,"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": 688924822125.881, "dur": 0.674, + "args": { + "External id": 765910,"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": 688924822126.904, "dur": 2.916, + "args": { + "External id": 765911,"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": 688924822129.390, "dur": 0.365, + "args": { + "External id": 765912,"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": 688924822130.182, "dur": 1.140, + "args": { + "External id": 765913,"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": 688924822130.680, "dur": 0.577, + "args": { + "External id": 765914,"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": 688924822132.101, "dur": 1.215, + "args": { + "External id": 765915,"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": 688924822132.619, "dur": 0.632, + "args": { + "External id": 765916,"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": 688924822133.594, "dur": 3.411, + "args": { + "External id": 765917,"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": 688924822136.502, "dur": 0.438, + "args": { + "External id": 765918,"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": 688924822137.398, "dur": 1.137, + "args": { + "External id": 765919,"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": 688924822138.029, "dur": 0.441, + "args": { + "External id": 765920,"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": 688924822138.823, "dur": 2.258, + "args": { + "External id": 765921,"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": 688924822139.344, "dur": 1.664, + "args": { + "External id": 765922,"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": 688924822141.386, "dur": 1.015, + "args": { + "External id": 765923,"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": 688924822141.918, "dur": 0.417, + "args": { + "External id": 765924,"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": 688924822142.769, "dur": 0.882, + "args": { + "External id": 765925,"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": 688924822143.274, "dur": 0.314, + "args": { + "External id": 765926,"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": 688924822143.946, "dur": 2.915, + "args": { + "External id": 765927,"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": 688924822146.365, "dur": 0.433, + "args": { + "External id": 765928,"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": 688924822147.148, "dur": 1.274, + "args": { + "External id": 765929,"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": 688924822147.695, "dur": 0.665, + "args": { + "External id": 765930,"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": 688924822148.703, "dur": 1.249, + "args": { + "External id": 765931,"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": 688924822149.294, "dur": 0.590, + "args": { + "External id": 765932,"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": 688924822150.232, "dur": 3.565, + "args": { + "External id": 765933,"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": 688924822152.741, "dur": 0.993, + "args": { + "External id": 765934,"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": 688924822154.214, "dur": 1.047, + "args": { + "External id": 765935,"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": 688924822154.788, "dur": 0.412, + "args": { + "External id": 765936,"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": 688924822155.546, "dur": 2.629, + "args": { + "External id": 765937,"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": 688924822156.054, "dur": 2.054, + "args": { + "External id": 765938,"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": 688924822158.449, "dur": 0.964, + "args": { + "External id": 765939,"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": 688924822159.101, "dur": 0.246, + "args": { + "External id": 765940,"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": 688924822159.678, "dur": 1.126, + "args": { + "External id": 765941,"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": 688924822160.327, "dur": 0.413, + "args": { + "External id": 765942,"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": 688924822161.087, "dur": 2.496, + "args": { + "External id": 765943,"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": 688924822163.215, "dur": 0.307, + "args": { + "External id": 765944,"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": 688924822163.884, "dur": 1.289, + "args": { + "External id": 765945,"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": 688924822164.580, "dur": 0.526, + "args": { + "External id": 765946,"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": 688924822165.564, "dur": 0.992, + "args": { + "External id": 765947,"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": 688924822166.004, "dur": 0.490, + "args": { + "External id": 765948,"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": 688924822166.831, "dur": 2.969, + "args": { + "External id": 765949,"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": 688924822169.259, "dur": 0.479, + "args": { + "External id": 765950,"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": 688924822170.080, "dur": 0.731, + "args": { + "External id": 765951,"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": 688924822170.499, "dur": 0.247, + "args": { + "External id": 765952,"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": 688924822241.428, "dur": 4.526, + "args": { + "External id": 765953,"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": 688924822244.048, "dur": 1.726, + "args": { + "External id": 765954,"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": 688924822246.543, "dur": 1.322, + "args": { + "External id": 765955,"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": 688924822247.120, "dur": 0.683, + "args": { + "External id": 765956,"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": 688924822248.157, "dur": 1.133, + "args": { + "External id": 765957,"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": 688924822248.741, "dur": 0.480, + "args": { + "External id": 765958,"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": 688924822249.595, "dur": 2.619, + "args": { + "External id": 765959,"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": 688924822251.747, "dur": 0.398, + "args": { + "External id": 765960,"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": 688924822252.551, "dur": 1.199, + "args": { + "External id": 765961,"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": 688924822253.059, "dur": 0.624, + "args": { + "External id": 765962,"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": 688924822254.047, "dur": 1.074, + "args": { + "External id": 765963,"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": 688924822254.627, "dur": 0.427, + "args": { + "External id": 765964,"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": 688924822255.437, "dur": 2.962, + "args": { + "External id": 765965,"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": 688924822257.970, "dur": 0.365, + "args": { + "External id": 765966,"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": 688924822258.695, "dur": 1.325, + "args": { + "External id": 765967,"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": 688924822259.200, "dur": 0.759, + "args": { + "External id": 765968,"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": 688924822260.309, "dur": 2.868, + "args": { + "External id": 765969,"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": 688924822261.041, "dur": 2.064, + "args": { + "External id": 765970,"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": 688924822263.491, "dur": 0.854, + "args": { + "External id": 765971,"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": 688924822263.982, "dur": 0.298, + "args": { + "External id": 765972,"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": 688924822264.757, "dur": 1.757, + "args": { + "External id": 765973,"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": 688924822265.545, "dur": 0.901, + "args": { + "External id": 765974,"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": 688924822266.888, "dur": 3.402, + "args": { + "External id": 765975,"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": 688924822269.684, "dur": 0.509, + "args": { + "External id": 765976,"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": 688924822270.618, "dur": 1.219, + "args": { + "External id": 765977,"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": 688924822271.071, "dur": 0.694, + "args": { + "External id": 765978,"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": 688924822272.174, "dur": 8.737, + "args": { + "External id": 765979,"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": 688924822277.044, "dur": 3.742, + "args": { + "External id": 765980,"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": 688924822281.223, "dur": 1.079, + "args": { + "External id": 765981,"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": 688924822281.901, "dur": 0.326, + "args": { + "External id": 765982,"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": 688924822282.603, "dur": 1.131, + "args": { + "External id": 765983,"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": 688924822283.134, "dur": 0.529, + "args": { + "External id": 765984,"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": 688924822284.039, "dur": 2.911, + "args": { + "External id": 765985,"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": 688924822286.558, "dur": 0.317, + "args": { + "External id": 765986,"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": 688924822287.256, "dur": 1.003, + "args": { + "External id": 765987,"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": 688924822287.947, "dur": 0.238, + "args": { + "External id": 765988,"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": 688924822288.585, "dur": 0.813, + "args": { + "External id": 765989,"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": 688924822289.025, "dur": 0.303, + "args": { + "External id": 765990,"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": 688924822289.718, "dur": 2.977, + "args": { + "External id": 765991,"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": 688924822292.057, "dur": 0.566, + "args": { + "External id": 765992,"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": 688924822293.011, "dur": 1.586, + "args": { + "External id": 765993,"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": 688924822294.032, "dur": 0.492, + "args": { + "External id": 765994,"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": 688924822295.026, "dur": 3.138, + "args": { + "External id": 765995,"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": 688924822295.851, "dur": 2.242, + "args": { + "External id": 765996,"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": 688924822298.463, "dur": 0.854, + "args": { + "External id": 765997,"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": 688924822298.923, "dur": 0.320, + "args": { + "External id": 765998,"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": 688924822299.937, "dur": 0.815, + "args": { + "External id": 765999,"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": 688924822300.374, "dur": 0.304, + "args": { + "External id": 766000,"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": 688924822301.054, "dur": 2.423, + "args": { + "External id": 766001,"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": 688924822303.102, "dur": 0.299, + "args": { + "External id": 766002,"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": 688924822303.781, "dur": 0.813, + "args": { + "External id": 766003,"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": 688924822304.231, "dur": 0.289, + "args": { + "External id": 766004,"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": 688924822343.461, "dur": 109.964, + "args": { + "External id": 766005,"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": 688924822545.948, "dur": 164.359, + "args": { + "External id": 766006,"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": 688924822607.297, "dur": 80.128, + "args": { + "External id": 766007,"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": 688924822620.354, "dur": 1.229, + "args": { + "External id": 766008,"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": 688924823055.985, "dur": 914.546, + "args": { + "External id": 766009,"Sequence number": 8962180, "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": 688924823106.917, "dur": 49.499, + "args": { + "External id": 766010,"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": 688924823111.607, "dur": 1.398, + "args": { + "External id": 766011,"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": 688924823114.950, "dur": 0.753, + "args": { + "External id": 766012,"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": 688924823180.104, "dur": 426.882, + "args": { + "External id": 766013,"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": 688924823183.848, "dur": 46.536, + "args": { + "External id": 766014,"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": 688924823187.073, "dur": 8.701, + "args": { + "External id": 766015,"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": 688924823191.083, "dur": 3.917, + "args": { + "External id": 766016,"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": 688924823197.311, "dur": 32.573, + "args": { + "External id": 766017,"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": 688924823239.937, "dur": 363.267, + "args": { + "External id": 766018,"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": 688924823269.736, "dur": 327.122, + "args": { + "External id": 766019,"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": 688924823286.824, "dur": 304.785, + "args": { + "External id": 766020,"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": 688924823705.383, "dur": 226.335, + "args": { + "External id": 766021,"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": 688924823812.403, "dur": 33.918, + "args": { + "External id": 766022,"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": 688924823830.577, "dur": 5.932, + "args": { + "External id": 766023,"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": 688924823877.879, "dur": 47.694, + "args": { + "External id": 766024,"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": 688924823880.676, "dur": 1.313, + "args": { + "External id": 766025,"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": 688924823883.573, "dur": 0.603, + "args": { + "External id": 766026,"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": 688924823988.525, "dur": 22.607, + "args": { + "External id": 766027,"Sequence number": 8962181, "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": 688924823999.345, "dur": 8.850, + "args": { + "External id": 766028,"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": 688924824001.936, "dur": 6.078, + "args": { + "External id": 766029,"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": 688924824417.451, "dur": 31.231, + "args": { + "External id": 766030,"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": 688924824457.794, "dur": 21.032, + "args": { + "External id": 766031,"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": 688924824492.140, "dur": 30.562, + "args": { + "External id": 766032,"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": 688924824535.730, "dur": 26.567, + "args": { + "External id": 766033,"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": 688924824539.566, "dur": 0.514, + "args": { + "External id": 766034,"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": 688924824580.137, "dur": 0.428, + "args": { + "External id": 766035,"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": 688924824714.877, "dur": 533.067, + "args": { + "External id": 766036,"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": 688924825142.034, "dur": 77.370, + "args": { + "External id": 766037,"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": 688924825289.366, "dur": 31.120, + "args": { + "External id": 766038,"Sequence number": 8962182, "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": 688924825293.157, "dur": 26.826, + "args": { + "External id": 766039,"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": 688924825324.861, "dur": 64.203, + "args": { + "External id": 766040,"Sequence number": 8962182, "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": 688924825326.627, "dur": 62.228, + "args": { + "External id": 766041,"Sequence number": 8962182, "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": 688924825328.383, "dur": 60.017, + "args": { + "External id": 766042,"Sequence number": 8962182, "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": 688924825394.654, "dur": 59.661, + "args": { + "External id": 766043,"Sequence number": 8962182, "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": 688924825397.696, "dur": 33.216, + "args": { + "External id": 766044,"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": 688924825403.841, "dur": 2.977, + "args": { + "External id": 766045,"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": 688924825408.414, "dur": 22.178, + "args": { + "External id": 766046,"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": 688924825412.808, "dur": 2.356, + "args": { + "External id": 766047,"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": 688924825432.618, "dur": 20.804, + "args": { + "External id": 766048,"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": 688924825456.645, "dur": 36.077, + "args": { + "External id": 766049,"Sequence number": 8962182, "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": 688924825457.343, "dur": 35.229, + "args": { + "External id": 766050,"Sequence number": 8962182, "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": 688924825458.188, "dur": 34.154, + "args": { + "External id": 766051,"Sequence number": 8962182, "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": 688924825520.696, "dur": 4701.873, + "args": { + "External id": 766052,"Record function id": 0, "Ev Idx": 9299 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 4183436, "tid": 4183436, + "ts": 688924825555.230, "dur": 4645.969, + "args": { + "External id": 766053,"Record function id": 0, "Ev Idx": 9300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 4183436, "tid": 4183436, + "ts": 688924826578.174, "dur": 237.876, + "args": { + "External id": 766054,"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": 688924826594.755, "dur": 1.084, + "args": { + "External id": 766055,"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": 688924826597.048, "dur": 0.243, + "args": { + "External id": 766056,"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": 688924826597.830, "dur": 0.199, + "args": { + "External id": 766057,"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": 688924826598.479, "dur": 0.110, + "args": { + "External id": 766058,"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": 688924826599.086, "dur": 0.053, + "args": { + "External id": 766059,"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": 688924826599.577, "dur": 0.207, + "args": { + "External id": 766060,"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": 688924826600.113, "dur": 0.091, + "args": { + "External id": 766061,"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": 688924826600.584, "dur": 0.137, + "args": { + "External id": 766062,"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": 688924826601.075, "dur": 0.090, + "args": { + "External id": 766063,"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": 688924826601.639, "dur": 0.198, + "args": { + "External id": 766064,"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": 688924826602.210, "dur": 0.102, + "args": { + "External id": 766065,"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": 688924826602.723, "dur": 0.066, + "args": { + "External id": 766066,"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": 688924826603.048, "dur": 0.065, + "args": { + "External id": 766067,"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": 688924826603.504, "dur": 0.051, + "args": { + "External id": 766068,"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": 688924826603.984, "dur": 0.066, + "args": { + "External id": 766069,"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": 688924826604.581, "dur": 0.069, + "args": { + "External id": 766070,"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": 688924826605.017, "dur": 0.070, + "args": { + "External id": 766071,"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": 688924826605.484, "dur": 0.066, + "args": { + "External id": 766072,"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": 688924826605.845, "dur": 0.063, + "args": { + "External id": 766073,"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": 688924826606.317, "dur": 0.067, + "args": { + "External id": 766074,"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": 688924826606.823, "dur": 0.052, + "args": { + "External id": 766075,"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": 688924826607.277, "dur": 0.067, + "args": { + "External id": 766076,"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": 688924826607.712, "dur": 0.068, + "args": { + "External id": 766077,"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": 688924826608.110, "dur": 0.069, + "args": { + "External id": 766078,"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": 688924826608.559, "dur": 0.067, + "args": { + "External id": 766079,"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": 688924826608.985, "dur": 0.066, + "args": { + "External id": 766080,"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": 688924826609.448, "dur": 0.062, + "args": { + "External id": 766081,"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": 688924826609.945, "dur": 0.062, + "args": { + "External id": 766082,"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": 688924826610.383, "dur": 0.060, + "args": { + "External id": 766083,"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": 688924826610.796, "dur": 0.067, + "args": { + "External id": 766084,"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": 688924826611.368, "dur": 0.099, + "args": { + "External id": 766085,"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": 688924826611.852, "dur": 0.060, + "args": { + "External id": 766086,"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": 688924826612.312, "dur": 0.056, + "args": { + "External id": 766087,"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": 688924826612.767, "dur": 0.065, + "args": { + "External id": 766088,"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": 688924826613.184, "dur": 0.063, + "args": { + "External id": 766089,"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": 688924826613.661, "dur": 0.062, + "args": { + "External id": 766090,"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": 688924826614.104, "dur": 0.064, + "args": { + "External id": 766091,"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": 688924826614.573, "dur": 0.066, + "args": { + "External id": 766092,"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": 688924826614.996, "dur": 0.063, + "args": { + "External id": 766093,"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": 688924826615.428, "dur": 0.064, + "args": { + "External id": 766094,"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": 688924826615.908, "dur": 0.067, + "args": { + "External id": 766095,"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": 688924826616.345, "dur": 0.065, + "args": { + "External id": 766096,"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": 688924826616.857, "dur": 0.066, + "args": { + "External id": 766097,"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": 688924826617.284, "dur": 0.062, + "args": { + "External id": 766098,"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": 688924826617.693, "dur": 0.062, + "args": { + "External id": 766099,"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": 688924826618.128, "dur": 0.064, + "args": { + "External id": 766100,"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": 688924826618.623, "dur": 0.062, + "args": { + "External id": 766101,"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": 688924826619.009, "dur": 0.067, + "args": { + "External id": 766102,"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": 688924826619.529, "dur": 0.062, + "args": { + "External id": 766103,"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": 688924826619.858, "dur": 0.062, + "args": { + "External id": 766104,"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": 688924826620.279, "dur": 0.063, + "args": { + "External id": 766105,"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": 688924826620.883, "dur": 0.063, + "args": { + "External id": 766106,"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": 688924826621.263, "dur": 0.062, + "args": { + "External id": 766107,"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": 688924826621.637, "dur": 0.066, + "args": { + "External id": 766108,"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": 688924826622.069, "dur": 0.067, + "args": { + "External id": 766109,"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": 688924826622.468, "dur": 0.066, + "args": { + "External id": 766110,"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": 688924826623.199, "dur": 0.066, + "args": { + "External id": 766111,"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": 688924826623.636, "dur": 0.066, + "args": { + "External id": 766112,"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": 688924826624.073, "dur": 0.065, + "args": { + "External id": 766113,"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": 688924826624.586, "dur": 0.067, + "args": { + "External id": 766114,"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": 688924826624.969, "dur": 0.066, + "args": { + "External id": 766115,"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": 688924826625.526, "dur": 0.056, + "args": { + "External id": 766116,"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": 688924826626.065, "dur": 0.064, + "args": { + "External id": 766117,"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": 688924826626.489, "dur": 0.066, + "args": { + "External id": 766118,"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": 688924826627.003, "dur": 0.088, + "args": { + "External id": 766119,"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": 688924826627.439, "dur": 0.089, + "args": { + "External id": 766120,"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": 688924826627.972, "dur": 0.091, + "args": { + "External id": 766121,"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": 688924826628.492, "dur": 0.089, + "args": { + "External id": 766122,"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": 688924826629.074, "dur": 0.067, + "args": { + "External id": 766123,"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": 688924826629.495, "dur": 0.069, + "args": { + "External id": 766124,"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": 688924826629.931, "dur": 0.069, + "args": { + "External id": 766125,"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": 688924826630.387, "dur": 0.185, + "args": { + "External id": 766126,"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": 688924826630.980, "dur": 0.109, + "args": { + "External id": 766127,"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": 688924826631.537, "dur": 0.106, + "args": { + "External id": 766128,"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": 688924826631.992, "dur": 0.210, + "args": { + "External id": 766129,"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": 688924826632.539, "dur": 0.100, + "args": { + "External id": 766130,"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": 688924826633.019, "dur": 0.066, + "args": { + "External id": 766131,"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": 688924826633.459, "dur": 0.065, + "args": { + "External id": 766132,"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": 688924826633.895, "dur": 0.065, + "args": { + "External id": 766133,"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": 688924826634.320, "dur": 0.067, + "args": { + "External id": 766134,"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": 688924826634.757, "dur": 0.066, + "args": { + "External id": 766135,"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": 688924826635.318, "dur": 0.051, + "args": { + "External id": 766136,"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": 688924826635.725, "dur": 0.064, + "args": { + "External id": 766137,"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": 688924826636.300, "dur": 0.062, + "args": { + "External id": 766138,"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": 688924826636.723, "dur": 0.065, + "args": { + "External id": 766139,"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": 688924826637.202, "dur": 0.062, + "args": { + "External id": 766140,"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": 688924826637.655, "dur": 0.063, + "args": { + "External id": 766141,"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": 688924826638.051, "dur": 0.064, + "args": { + "External id": 766142,"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": 688924826638.495, "dur": 0.060, + "args": { + "External id": 766143,"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": 688924826638.888, "dur": 0.064, + "args": { + "External id": 766144,"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": 688924826639.309, "dur": 0.066, + "args": { + "External id": 766145,"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": 688924826639.673, "dur": 0.065, + "args": { + "External id": 766146,"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": 688924826640.121, "dur": 0.065, + "args": { + "External id": 766147,"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": 688924826640.454, "dur": 0.064, + "args": { + "External id": 766148,"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": 688924826640.905, "dur": 0.203, + "args": { + "External id": 766149,"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": 688924826641.471, "dur": 0.074, + "args": { + "External id": 766150,"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": 688924826641.916, "dur": 0.085, + "args": { + "External id": 766151,"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": 688924826642.415, "dur": 0.097, + "args": { + "External id": 766152,"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": 688924826642.785, "dur": 0.083, + "args": { + "External id": 766153,"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": 688924826643.370, "dur": 0.200, + "args": { + "External id": 766154,"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": 688924826643.849, "dur": 0.065, + "args": { + "External id": 766155,"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": 688924826644.543, "dur": 0.056, + "args": { + "External id": 766156,"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": 688924826645.027, "dur": 0.066, + "args": { + "External id": 766157,"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": 688924826645.423, "dur": 0.069, + "args": { + "External id": 766158,"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": 688924826645.841, "dur": 0.221, + "args": { + "External id": 766159,"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": 688924826646.362, "dur": 0.066, + "args": { + "External id": 766160,"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": 688924826646.859, "dur": 0.069, + "args": { + "External id": 766161,"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": 688924826647.317, "dur": 0.070, + "args": { + "External id": 766162,"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": 688924826647.770, "dur": 0.065, + "args": { + "External id": 766163,"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": 688924826648.280, "dur": 0.066, + "args": { + "External id": 766164,"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": 688924826648.727, "dur": 0.067, + "args": { + "External id": 766165,"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": 688924826649.089, "dur": 0.065, + "args": { + "External id": 766166,"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": 688924826649.512, "dur": 0.056, + "args": { + "External id": 766167,"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": 688924826650.061, "dur": 0.053, + "args": { + "External id": 766168,"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": 688924826650.676, "dur": 0.065, + "args": { + "External id": 766169,"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": 688924826651.127, "dur": 0.067, + "args": { + "External id": 766170,"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": 688924826651.531, "dur": 0.068, + "args": { + "External id": 766171,"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": 688924826651.904, "dur": 0.064, + "args": { + "External id": 766172,"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": 688924826652.390, "dur": 0.055, + "args": { + "External id": 766173,"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": 688924826652.839, "dur": 0.066, + "args": { + "External id": 766174,"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": 688924826653.456, "dur": 0.065, + "args": { + "External id": 766175,"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": 688924826653.854, "dur": 0.067, + "args": { + "External id": 766176,"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": 688924826680.660, "dur": 0.605, + "args": { + "External id": 766177,"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": 688924826682.479, "dur": 0.055, + "args": { + "External id": 766178,"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": 688924826683.166, "dur": 0.055, + "args": { + "External id": 766179,"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": 688924826683.678, "dur": 0.051, + "args": { + "External id": 766180,"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": 688924826684.285, "dur": 0.060, + "args": { + "External id": 766181,"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": 688924826684.752, "dur": 0.064, + "args": { + "External id": 766182,"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": 688924826685.312, "dur": 0.083, + "args": { + "External id": 766183,"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": 688924826685.798, "dur": 0.209, + "args": { + "External id": 766184,"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": 688924826686.447, "dur": 0.195, + "args": { + "External id": 766185,"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": 688924826687.022, "dur": 0.086, + "args": { + "External id": 766186,"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": 688924826687.383, "dur": 0.066, + "args": { + "External id": 766187,"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": 688924826687.800, "dur": 0.076, + "args": { + "External id": 766188,"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": 688924826688.325, "dur": 0.085, + "args": { + "External id": 766189,"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": 688924826688.776, "dur": 0.213, + "args": { + "External id": 766190,"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": 688924826689.383, "dur": 0.151, + "args": { + "External id": 766191,"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": 688924826689.964, "dur": 0.087, + "args": { + "External id": 766192,"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": 688924826690.345, "dur": 0.080, + "args": { + "External id": 766193,"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": 688924826690.825, "dur": 0.089, + "args": { + "External id": 766194,"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": 688924826691.311, "dur": 0.067, + "args": { + "External id": 766195,"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": 688924826691.707, "dur": 0.080, + "args": { + "External id": 766196,"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": 688924826692.140, "dur": 0.076, + "args": { + "External id": 766197,"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": 688924826692.489, "dur": 0.072, + "args": { + "External id": 766198,"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": 688924826692.854, "dur": 0.262, + "args": { + "External id": 766199,"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": 688924826693.698, "dur": 0.080, + "args": { + "External id": 766200,"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": 688924826694.317, "dur": 0.099, + "args": { + "External id": 766201,"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": 688924826694.860, "dur": 0.066, + "args": { + "External id": 766202,"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": 688924826695.356, "dur": 0.051, + "args": { + "External id": 766203,"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": 688924826696.097, "dur": 0.058, + "args": { + "External id": 766204,"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": 688924826696.441, "dur": 0.060, + "args": { + "External id": 766205,"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": 688924826697.116, "dur": 0.062, + "args": { + "External id": 766206,"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": 688924826697.427, "dur": 0.064, + "args": { + "External id": 766207,"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": 688924826698.040, "dur": 0.069, + "args": { + "External id": 766208,"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": 688924826698.413, "dur": 0.050, + "args": { + "External id": 766209,"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": 688924826699.175, "dur": 0.068, + "args": { + "External id": 766210,"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": 688924826699.493, "dur": 0.051, + "args": { + "External id": 766211,"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": 688924826700.272, "dur": 0.062, + "args": { + "External id": 766212,"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": 688924826700.588, "dur": 0.048, + "args": { + "External id": 766213,"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": 688924826701.313, "dur": 0.062, + "args": { + "External id": 766214,"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": 688924826701.627, "dur": 0.054, + "args": { + "External id": 766215,"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": 688924826702.340, "dur": 0.051, + "args": { + "External id": 766216,"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": 688924826702.648, "dur": 0.051, + "args": { + "External id": 766217,"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": 688924826703.180, "dur": 0.067, + "args": { + "External id": 766218,"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": 688924826703.498, "dur": 0.055, + "args": { + "External id": 766219,"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": 688924826704.047, "dur": 0.065, + "args": { + "External id": 766220,"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": 688924826704.504, "dur": 0.057, + "args": { + "External id": 766221,"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": 688924826705.070, "dur": 0.074, + "args": { + "External id": 766222,"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": 688924826705.563, "dur": 0.066, + "args": { + "External id": 766223,"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": 688924826706.358, "dur": 0.065, + "args": { + "External id": 766224,"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": 688924826706.781, "dur": 0.063, + "args": { + "External id": 766225,"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": 688924826707.681, "dur": 0.064, + "args": { + "External id": 766226,"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": 688924826707.995, "dur": 0.054, + "args": { + "External id": 766227,"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": 688924826708.634, "dur": 0.065, + "args": { + "External id": 766228,"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": 688924826708.950, "dur": 0.053, + "args": { + "External id": 766229,"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": 688924826709.517, "dur": 0.063, + "args": { + "External id": 766230,"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": 688924826709.833, "dur": 0.052, + "args": { + "External id": 766231,"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": 688924826710.269, "dur": 0.065, + "args": { + "External id": 766232,"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": 688924826710.584, "dur": 0.053, + "args": { + "External id": 766233,"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": 688924826711.402, "dur": 0.088, + "args": { + "External id": 766234,"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": 688924826711.739, "dur": 0.051, + "args": { + "External id": 766235,"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": 688924826712.753, "dur": 0.063, + "args": { + "External id": 766236,"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": 688924826713.066, "dur": 0.054, + "args": { + "External id": 766237,"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": 688924826713.829, "dur": 0.053, + "args": { + "External id": 766238,"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": 688924826714.131, "dur": 0.054, + "args": { + "External id": 766239,"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": 688924826714.816, "dur": 0.067, + "args": { + "External id": 766240,"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": 688924826715.131, "dur": 0.053, + "args": { + "External id": 766241,"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": 688924826715.870, "dur": 0.064, + "args": { + "External id": 766242,"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": 688924826716.183, "dur": 0.053, + "args": { + "External id": 766243,"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": 688924826716.894, "dur": 0.064, + "args": { + "External id": 766244,"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": 688924826717.204, "dur": 0.055, + "args": { + "External id": 766245,"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": 688924826717.736, "dur": 0.061, + "args": { + "External id": 766246,"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": 688924826718.043, "dur": 0.057, + "args": { + "External id": 766247,"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": 688924826718.553, "dur": 0.065, + "args": { + "External id": 766248,"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": 688924826718.863, "dur": 0.058, + "args": { + "External id": 766249,"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": 688924826719.594, "dur": 0.062, + "args": { + "External id": 766250,"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": 688924826719.906, "dur": 0.052, + "args": { + "External id": 766251,"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": 688924826720.730, "dur": 0.066, + "args": { + "External id": 766252,"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": 688924826721.043, "dur": 0.080, + "args": { + "External id": 766253,"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": 688924826721.977, "dur": 0.066, + "args": { + "External id": 766254,"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": 688924826722.291, "dur": 0.054, + "args": { + "External id": 766255,"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": 688924826722.985, "dur": 0.062, + "args": { + "External id": 766256,"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": 688924826723.300, "dur": 0.051, + "args": { + "External id": 766257,"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": 688924826723.977, "dur": 0.065, + "args": { + "External id": 766258,"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": 688924826724.285, "dur": 0.053, + "args": { + "External id": 766259,"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": 688924826724.829, "dur": 0.067, + "args": { + "External id": 766260,"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": 688924826725.139, "dur": 0.055, + "args": { + "External id": 766261,"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": 688924826725.851, "dur": 0.065, + "args": { + "External id": 766262,"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": 688924826726.303, "dur": 0.063, + "args": { + "External id": 766263,"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": 688924826727.050, "dur": 0.066, + "args": { + "External id": 766264,"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": 688924826727.377, "dur": 0.092, + "args": { + "External id": 766265,"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": 688924826728.080, "dur": 0.090, + "args": { + "External id": 766266,"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": 688924826728.543, "dur": 0.064, + "args": { + "External id": 766267,"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": 688924826729.129, "dur": 0.068, + "args": { + "External id": 766268,"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": 688924826729.442, "dur": 0.053, + "args": { + "External id": 766269,"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": 688924826729.882, "dur": 0.074, + "args": { + "External id": 766270,"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": 688924826730.242, "dur": 0.070, + "args": { + "External id": 766271,"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": 688924826730.829, "dur": 0.082, + "args": { + "External id": 766272,"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": 688924826731.153, "dur": 0.093, + "args": { + "External id": 766273,"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": 688924827265.337, "dur": 2846.529, + "args": { + "External id": 766274,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "0.00020941477080254028", "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": 688924829745.434, "dur": 234.270, + "args": { + "External id": 766275,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "0.00020941477080254028", "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": 688924052396.578, "pid": 4183436, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 688924052396.578, "pid": 4183436, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 688924052396.578, "pid": 4183436, "tid": 0, + "args": { + "sort_index": 4183436 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 688924052396.578, "pid": 4183436, "tid": 31338, + "args": { + "name": "thread 31338 (pt_autograd_0)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 688924052396.578, "pid": 4183436, "tid": 31338, + "args": { + "sort_index": 31338 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 688924052396.578, "pid": 4183436, "tid": 4183436, + "args": { + "name": "thread 4183436 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 688924052396.578, "pid": 4183436, "tid": 4183436, + "args": { + "sort_index": 4183436 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 688924052396.578, "pid": 4183436, "tid": 31338, + "args": { + "name": "thread 31338 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 688924052396.578, "pid": 4183436, "tid": 31338, + "args": { + "sort_index": 31338 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 688924052330.363, "dur": 778176.781, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 688924052330.363, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 688924052330.363 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 688924880040.277 + } + ], + "traceName": "exp/mtp.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine/profile_trace/iteration_39936/rank0_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file