diff --git "a/profile_trace/iteration_2048/rank1_trace.json" "b/profile_trace/iteration_2048/rank1_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_2048/rank1_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": 1, "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": "CC02532804304DDC9B84CB50F9C07336", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 4183437, "tid": 31318, + "ts": 658971989257.474, "dur": 126.704, + "args": { + "External id": 33281,"Record function id": 0, "Sequence number": 460102, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 4183437, "tid": 31318, + "ts": 658971989288.851, "dur": 86.167, + "args": { + "External id": 33282,"Sequence number": 460102, "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": 4183437, "tid": 31318, "ts": 658971989288.851, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 4183437, "tid": 31318, + "ts": 658971989296.349, "dur": 76.752, + "args": { + "External id": 33283,"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": 4183437, "tid": 31318, + "ts": 658971989396.948, "dur": 205.001, + "args": { + "External id": 33284,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 4183437, "tid": 31318, + "ts": 658971989447.860, "dur": 87.279, + "args": { + "External id": 33285,"Record function id": 0, "Ev Idx": 4 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.19", "pid": 4183437, "tid": 31318, + "ts": 658971989480.432, "dur": 44.346, + "args": { + "External id": 33286,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183437, "tid": 31318, + "ts": 658971989539.927, "dur": 1.442, + "args": { + "External id": 33287,"Sequence number": 460101, "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": 4183437, "tid": 31318, "ts": 658971989539.927, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183437, "tid": 31318, + "ts": 658971989545.094, "dur": 51.995, + "args": { + "External id": 33288,"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": 4183437, "tid": 31318, + "ts": 658971989553.283, "dur": 43.232, + "args": { + "External id": 33289,"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": 4183437, "tid": 31318, + "ts": 658971989562.459, "dur": 3.411, + "args": { + "External id": 33290,"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": 4183437, "tid": 31318, + "ts": 658971989610.023, "dur": 17218.521, + "args": { + "External id": 33291,"Record function id": 0, "Sequence number": 460099, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658971989611.924, "dur": 17207.875, + "args": { + "External id": 33292,"Sequence number": 460099, "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": 4183437, "tid": 31318, "ts": 658971989611.924, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658971989689.519, "dur": 4.054, + "args": { + "External id": 33293,"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": 4183437, "tid": 31318, + "ts": 658971989699.112, "dur": 17010.474, + "args": { + "External id": 33294,"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": 4183437, "tid": 31318, + "ts": 658971989701.101, "dur": 17008.162, + "args": { + "External id": 33295,"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": 4183437, "tid": 31318, + "ts": 658971989705.434, "dur": 9.086, + "args": { + "External id": 33296,"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": 4183437, "tid": 31318, + "ts": 658971989716.114, "dur": 16991.910, + "args": { + "External id": 33297,"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": 4183437, "tid": 31318, + "ts": 658972006714.098, "dur": 0.585, + "args": { + "External id": 33298,"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": 4183437, "tid": 31318, + "ts": 658972006716.784, "dur": 2.634, + "args": { + "External id": 33299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 18 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 4183437, "tid": 31318, + "ts": 658972006718.205, "dur": 1.070, + "args": { + "External id": 33300,"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": 4183437, "tid": 31318, + "ts": 658972006725.388, "dur": 32.365, + "args": { + "External id": 33301,"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": 4183437, "tid": 31318, + "ts": 658972006765.672, "dur": 45.310, + "args": { + "External id": 33302,"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": 4183437, "tid": 31318, + "ts": 658972006767.183, "dur": 43.611, + "args": { + "External id": 33303,"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": 4183437, "tid": 31318, + "ts": 658972006769.054, "dur": 41.469, + "args": { + "External id": 33304,"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": 4183437, "tid": 31318, + "ts": 658972006839.452, "dur": 14.590, + "args": { + "External id": 33305,"Record function id": 0, "Sequence number": 460098, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972006840.630, "dur": 10.839, + "args": { + "External id": 33306,"Sequence number": 460098, "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": 4183437, "tid": 31318, "ts": 658972006840.630, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972006843.952, "dur": 7.280, + "args": { + "External id": 33307,"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": 4183437, "tid": 31318, + "ts": 658972006846.525, "dur": 4.547, + "args": { + "External id": 33308,"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": 4183437, "tid": 31318, + "ts": 658972006858.157, "dur": 88.384, + "args": { + "External id": 33309,"Record function id": 0, "Sequence number": 460097, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972006858.964, "dur": 81.005, + "args": { + "External id": 33310,"Sequence number": 460097, "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": 4183437, "tid": 31318, "ts": 658972006858.964, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972006862.220, "dur": 77.307, + "args": { + "External id": 33311,"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": 4183437, "tid": 31318, + "ts": 658972006866.429, "dur": 30.855, + "args": { + "External id": 33312,"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": 4183437, "tid": 31318, + "ts": 658972006868.634, "dur": 5.045, + "args": { + "External id": 33313,"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": 4183437, "tid": 31318, + "ts": 658972006875.152, "dur": 21.830, + "args": { + "External id": 33314,"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": 4183437, "tid": 31318, + "ts": 658972006877.493, "dur": 19.019, + "args": { + "External id": 33315,"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": 4183437, "tid": 31318, + "ts": 658972006901.584, "dur": 6.220, + "args": { + "External id": 33316,"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": 4183437, "tid": 31318, + "ts": 658972006905.903, "dur": 1.566, + "args": { + "External id": 33317,"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": 4183437, "tid": 31318, + "ts": 658972006908.908, "dur": 29.844, + "args": { + "External id": 33318,"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": 4183437, "tid": 31318, + "ts": 658972006950.678, "dur": 62.397, + "args": { + "External id": 33319,"Record function id": 0, "Sequence number": 460096, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972006951.686, "dur": 57.798, + "args": { + "External id": 33320,"Sequence number": 460096, "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": 4183437, "tid": 31318, "ts": 658972006951.686, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183437, "tid": 31318, + "ts": 658972006955.225, "dur": 53.953, + "args": { + "External id": 33321,"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": 4183437, "tid": 31318, + "ts": 658972006958.127, "dur": 21.718, + "args": { + "External id": 33322,"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": 4183437, "tid": 31318, + "ts": 658972006959.530, "dur": 2.564, + "args": { + "External id": 33323,"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": 4183437, "tid": 31318, + "ts": 658972006962.806, "dur": 16.756, + "args": { + "External id": 33324,"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": 4183437, "tid": 31318, + "ts": 658972006964.958, "dur": 14.207, + "args": { + "External id": 33325,"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": 4183437, "tid": 31318, + "ts": 658972006983.204, "dur": 6.003, + "args": { + "External id": 33326,"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": 4183437, "tid": 31318, + "ts": 658972006987.557, "dur": 0.939, + "args": { + "External id": 33327,"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": 4183437, "tid": 31318, + "ts": 658972006989.968, "dur": 18.661, + "args": { + "External id": 33328,"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": 4183437, "tid": 31318, + "ts": 658972007017.560, "dur": 104.036, + "args": { + "External id": 33329,"Record function id": 0, "Sequence number": 460095, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972007018.866, "dur": 98.707, + "args": { + "External id": 33330,"Sequence number": 460095, "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": 4183437, "tid": 31318, "ts": 658972007018.866, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972007020.940, "dur": 96.309, + "args": { + "External id": 33331,"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": 4183437, "tid": 31318, + "ts": 658972007024.866, "dur": 16.926, + "args": { + "External id": 33332,"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": 4183437, "tid": 31318, + "ts": 658972007025.906, "dur": 2.255, + "args": { + "External id": 33333,"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": 4183437, "tid": 31318, + "ts": 658972007028.771, "dur": 12.758, + "args": { + "External id": 33334,"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": 4183437, "tid": 31318, + "ts": 658972007029.406, "dur": 11.832, + "args": { + "External id": 33335,"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": 4183437, "tid": 31318, + "ts": 658972007044.538, "dur": 4.622, + "args": { + "External id": 33336,"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": 4183437, "tid": 31318, + "ts": 658972007046.420, "dur": 2.535, + "args": { + "External id": 33337,"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": 4183437, "tid": 31318, + "ts": 658972007050.171, "dur": 66.377, + "args": { + "External id": 33338,"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": 4183437, "tid": 31318, + "ts": 658972007126.845, "dur": 69.186, + "args": { + "External id": 33339,"Record function id": 0, "Sequence number": 460094, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972007127.901, "dur": 65.095, + "args": { + "External id": 33340,"Sequence number": 460094, "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": 4183437, "tid": 31318, "ts": 658972007127.901, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972007129.324, "dur": 63.322, + "args": { + "External id": 33341,"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": 4183437, "tid": 31318, + "ts": 658972007130.864, "dur": 16.627, + "args": { + "External id": 33342,"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": 4183437, "tid": 31318, + "ts": 658972007131.968, "dur": 1.823, + "args": { + "External id": 33343,"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": 4183437, "tid": 31318, + "ts": 658972007134.670, "dur": 12.578, + "args": { + "External id": 33344,"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": 4183437, "tid": 31318, + "ts": 658972007135.171, "dur": 11.791, + "args": { + "External id": 33345,"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": 4183437, "tid": 31318, + "ts": 658972007148.424, "dur": 4.345, + "args": { + "External id": 33346,"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": 4183437, "tid": 31318, + "ts": 658972007152.109, "dur": 0.485, + "args": { + "External id": 33347,"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": 4183437, "tid": 31318, + "ts": 658972007154.877, "dur": 37.171, + "args": { + "External id": 33348,"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": 4183437, "tid": 31318, + "ts": 658972007199.896, "dur": 35.733, + "args": { + "External id": 33349,"Record function id": 0, "Sequence number": 460093, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972007201.302, "dur": 0.732, + "args": { + "External id": 33350,"Sequence number": 460093, "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": 4183437, "tid": 31318, "ts": 658972007201.302, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183437, "tid": 31318, + "ts": 658972007204.442, "dur": 28.180, + "args": { + "External id": 33351,"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": 4183437, "tid": 31318, + "ts": 658972007206.586, "dur": 25.596, + "args": { + "External id": 33352,"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": 4183437, "tid": 31318, + "ts": 658972007213.164, "dur": 0.473, + "args": { + "External id": 33353,"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": 4183437, "tid": 31318, + "ts": 658972007240.186, "dur": 1085.786, + "args": { + "External id": 33354,"Record function id": 0, "Sequence number": 460091, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972007241.474, "dur": 1050.493, + "args": { + "External id": 33355,"Sequence number": 460091, "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": 4183437, "tid": 31318, "ts": 658972007241.474, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972007289.454, "dur": 3.402, + "args": { + "External id": 33356,"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": 4183437, "tid": 31318, + "ts": 658972007295.657, "dur": 905.617, + "args": { + "External id": 33357,"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": 4183437, "tid": 31318, + "ts": 658972007297.475, "dur": 903.595, + "args": { + "External id": 33358,"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": 4183437, "tid": 31318, + "ts": 658972007300.315, "dur": 4.083, + "args": { + "External id": 33359,"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": 4183437, "tid": 31318, + "ts": 658972007305.377, "dur": 894.394, + "args": { + "External id": 33360,"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": 4183437, "tid": 31318, + "ts": 658972008204.893, "dur": 0.398, + "args": { + "External id": 33361,"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": 4183437, "tid": 31318, + "ts": 658972008206.700, "dur": 4.257, + "args": { + "External id": 33362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 81 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 4183437, "tid": 31318, + "ts": 658972008210.011, "dur": 0.829, + "args": { + "External id": 33363,"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": 4183437, "tid": 31318, + "ts": 658972008214.948, "dur": 21.578, + "args": { + "External id": 33364,"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": 4183437, "tid": 31318, + "ts": 658972008241.639, "dur": 42.164, + "args": { + "External id": 33365,"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": 4183437, "tid": 31318, + "ts": 658972008242.962, "dur": 40.628, + "args": { + "External id": 33366,"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": 4183437, "tid": 31318, + "ts": 658972008244.160, "dur": 38.845, + "args": { + "External id": 33367,"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": 4183437, "tid": 31318, + "ts": 658972008300.782, "dur": 21.374, + "args": { + "External id": 33368,"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": 4183437, "tid": 31318, + "ts": 658972008334.381, "dur": 13.096, + "args": { + "External id": 33369,"Record function id": 0, "Sequence number": 460090, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972008335.721, "dur": 9.732, + "args": { + "External id": 33370,"Sequence number": 460090, "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": 4183437, "tid": 31318, "ts": 658972008335.721, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972008338.217, "dur": 7.023, + "args": { + "External id": 33371,"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": 4183437, "tid": 31318, + "ts": 658972008341.611, "dur": 3.491, + "args": { + "External id": 33372,"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": 4183437, "tid": 31318, + "ts": 658972008350.909, "dur": 63.080, + "args": { + "External id": 33373,"Record function id": 0, "Sequence number": 460089, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972008351.702, "dur": 58.060, + "args": { + "External id": 33374,"Sequence number": 460089, "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": 4183437, "tid": 31318, "ts": 658972008351.702, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972008354.097, "dur": 55.227, + "args": { + "External id": 33375,"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": 4183437, "tid": 31318, + "ts": 658972008356.606, "dur": 24.125, + "args": { + "External id": 33376,"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": 4183437, "tid": 31318, + "ts": 658972008358.393, "dur": 5.096, + "args": { + "External id": 33377,"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": 4183437, "tid": 31318, + "ts": 658972008364.398, "dur": 16.088, + "args": { + "External id": 33378,"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": 4183437, "tid": 31318, + "ts": 658972008365.778, "dur": 14.378, + "args": { + "External id": 33379,"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": 4183437, "tid": 31318, + "ts": 658972008382.304, "dur": 3.535, + "args": { + "External id": 33380,"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": 4183437, "tid": 31318, + "ts": 658972008384.736, "dur": 0.860, + "args": { + "External id": 33381,"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": 4183437, "tid": 31318, + "ts": 658972008386.869, "dur": 21.720, + "args": { + "External id": 33382,"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": 4183437, "tid": 31318, + "ts": 658972008419.889, "dur": 53.827, + "args": { + "External id": 33383,"Record function id": 0, "Sequence number": 460088, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972008420.778, "dur": 50.072, + "args": { + "External id": 33384,"Sequence number": 460088, "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": 4183437, "tid": 31318, "ts": 658972008420.778, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183437, "tid": 31318, + "ts": 658972008422.743, "dur": 47.825, + "args": { + "External id": 33385,"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": 4183437, "tid": 31318, + "ts": 658972008424.735, "dur": 18.968, + "args": { + "External id": 33386,"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": 4183437, "tid": 31318, + "ts": 658972008425.359, "dur": 2.068, + "args": { + "External id": 33387,"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": 4183437, "tid": 31318, + "ts": 658972008427.915, "dur": 15.530, + "args": { + "External id": 33388,"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": 4183437, "tid": 31318, + "ts": 658972008428.582, "dur": 14.480, + "args": { + "External id": 33389,"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": 4183437, "tid": 31318, + "ts": 658972008445.189, "dur": 6.800, + "args": { + "External id": 33390,"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": 4183437, "tid": 31318, + "ts": 658972008450.584, "dur": 0.771, + "args": { + "External id": 33391,"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": 4183437, "tid": 31318, + "ts": 658972008452.589, "dur": 17.441, + "args": { + "External id": 33392,"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": 4183437, "tid": 31318, + "ts": 658972008477.281, "dur": 88.222, + "args": { + "External id": 33393,"Record function id": 0, "Sequence number": 460087, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972008478.336, "dur": 84.407, + "args": { + "External id": 33394,"Sequence number": 460087, "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": 4183437, "tid": 31318, "ts": 658972008478.336, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972008480.153, "dur": 82.365, + "args": { + "External id": 33395,"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": 4183437, "tid": 31318, + "ts": 658972008481.340, "dur": 16.101, + "args": { + "External id": 33396,"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": 4183437, "tid": 31318, + "ts": 658972008482.166, "dur": 2.076, + "args": { + "External id": 33397,"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": 4183437, "tid": 31318, + "ts": 658972008484.888, "dur": 12.301, + "args": { + "External id": 33398,"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": 4183437, "tid": 31318, + "ts": 658972008485.521, "dur": 11.278, + "args": { + "External id": 33399,"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": 4183437, "tid": 31318, + "ts": 658972008498.489, "dur": 4.409, + "args": { + "External id": 33400,"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": 4183437, "tid": 31318, + "ts": 658972008501.927, "dur": 0.764, + "args": { + "External id": 33401,"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": 4183437, "tid": 31318, + "ts": 658972008503.579, "dur": 58.195, + "args": { + "External id": 33402,"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": 4183437, "tid": 31318, + "ts": 658972008571.075, "dur": 107.618, + "args": { + "External id": 33403,"Record function id": 0, "Sequence number": 460086, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972008572.013, "dur": 60.210, + "args": { + "External id": 33404,"Sequence number": 460086, "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": 4183437, "tid": 31318, "ts": 658972008572.013, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972008573.632, "dur": 58.347, + "args": { + "External id": 33405,"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": 4183437, "tid": 31318, + "ts": 658972008574.543, "dur": 15.638, + "args": { + "External id": 33406,"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": 4183437, "tid": 31318, + "ts": 658972008575.203, "dur": 1.716, + "args": { + "External id": 33407,"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": 4183437, "tid": 31318, + "ts": 658972008577.395, "dur": 12.543, + "args": { + "External id": 33408,"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": 4183437, "tid": 31318, + "ts": 658972008578.022, "dur": 11.632, + "args": { + "External id": 33409,"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": 4183437, "tid": 31318, + "ts": 658972008591.063, "dur": 2.384, + "args": { + "External id": 33410,"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": 4183437, "tid": 31318, + "ts": 658972008592.787, "dur": 0.482, + "args": { + "External id": 33411,"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": 4183437, "tid": 31318, + "ts": 658972008594.055, "dur": 37.304, + "args": { + "External id": 33412,"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": 4183437, "tid": 31318, + "ts": 658972008635.703, "dur": 14.318, + "args": { + "External id": 33413,"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": 4183437, "tid": 31318, + "ts": 658972008686.136, "dur": 40.046, + "args": { + "External id": 33414,"Record function id": 0, "Sequence number": 460085, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972008689.248, "dur": 0.851, + "args": { + "External id": 33415,"Sequence number": 460085, "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": 4183437, "tid": 31318, "ts": 658972008689.248, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183437, "tid": 31318, + "ts": 658972008692.203, "dur": 31.183, + "args": { + "External id": 33416,"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": 4183437, "tid": 31318, + "ts": 658972008694.358, "dur": 28.555, + "args": { + "External id": 33417,"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": 4183437, "tid": 31318, + "ts": 658972008701.757, "dur": 0.614, + "args": { + "External id": 33418,"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": 4183437, "tid": 31318, + "ts": 658972008731.071, "dur": 1436.662, + "args": { + "External id": 33419,"Record function id": 0, "Sequence number": 460083, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972008734.334, "dur": 1408.497, + "args": { + "External id": 33420,"Sequence number": 460083, "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": 4183437, "tid": 31318, "ts": 658972008734.334, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972008762.441, "dur": 1.963, + "args": { + "External id": 33421,"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": 4183437, "tid": 31318, + "ts": 658972008766.396, "dur": 1291.372, + "args": { + "External id": 33422,"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": 4183437, "tid": 31318, + "ts": 658972008767.614, "dur": 1289.922, + "args": { + "External id": 33423,"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": 4183437, "tid": 31318, + "ts": 658972008770.116, "dur": 3.056, + "args": { + "External id": 33424,"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": 4183437, "tid": 31318, + "ts": 658972008773.963, "dur": 1282.303, + "args": { + "External id": 33425,"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": 4183437, "tid": 31318, + "ts": 658972010060.908, "dur": 0.299, + "args": { + "External id": 33426,"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": 4183437, "tid": 31318, + "ts": 658972010062.289, "dur": 2.218, + "args": { + "External id": 33427,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 4183437, "tid": 31318, + "ts": 658972010063.503, "dur": 0.898, + "args": { + "External id": 33428,"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": 4183437, "tid": 31318, + "ts": 658972010068.088, "dur": 24.812, + "args": { + "External id": 33429,"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": 4183437, "tid": 31318, + "ts": 658972010099.835, "dur": 36.429, + "args": { + "External id": 33430,"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": 4183437, "tid": 31318, + "ts": 658972010100.999, "dur": 35.054, + "args": { + "External id": 33431,"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": 4183437, "tid": 31318, + "ts": 658972010102.112, "dur": 33.717, + "args": { + "External id": 33432,"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": 4183437, "tid": 31318, + "ts": 658972010149.525, "dur": 15.287, + "args": { + "External id": 33433,"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": 4183437, "tid": 31318, + "ts": 658972010176.252, "dur": 10.082, + "args": { + "External id": 33434,"Record function id": 0, "Sequence number": 460082, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972010177.674, "dur": 7.011, + "args": { + "External id": 33435,"Sequence number": 460082, "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": 4183437, "tid": 31318, "ts": 658972010177.674, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972010180.220, "dur": 4.244, + "args": { + "External id": 33436,"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": 4183437, "tid": 31318, + "ts": 658972010181.614, "dur": 2.681, + "args": { + "External id": 33437,"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": 4183437, "tid": 31318, + "ts": 658972010189.633, "dur": 57.578, + "args": { + "External id": 33438,"Record function id": 0, "Sequence number": 460081, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972010190.442, "dur": 53.124, + "args": { + "External id": 33439,"Sequence number": 460081, "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": 4183437, "tid": 31318, "ts": 658972010190.442, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972010192.493, "dur": 50.656, + "args": { + "External id": 33440,"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": 4183437, "tid": 31318, + "ts": 658972010196.469, "dur": 19.465, + "args": { + "External id": 33441,"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": 4183437, "tid": 31318, + "ts": 658972010198.027, "dur": 2.559, + "args": { + "External id": 33442,"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": 4183437, "tid": 31318, + "ts": 658972010201.239, "dur": 14.435, + "args": { + "External id": 33443,"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": 4183437, "tid": 31318, + "ts": 658972010202.545, "dur": 12.741, + "args": { + "External id": 33444,"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": 4183437, "tid": 31318, + "ts": 658972010217.465, "dur": 3.346, + "args": { + "External id": 33445,"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": 4183437, "tid": 31318, + "ts": 658972010219.881, "dur": 0.754, + "args": { + "External id": 33446,"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": 4183437, "tid": 31318, + "ts": 658972010221.768, "dur": 20.587, + "args": { + "External id": 33447,"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": 4183437, "tid": 31318, + "ts": 658972010251.083, "dur": 69.534, + "args": { + "External id": 33448,"Record function id": 0, "Sequence number": 460080, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972010252.026, "dur": 65.064, + "args": { + "External id": 33449,"Sequence number": 460080, "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": 4183437, "tid": 31318, "ts": 658972010252.026, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183437, "tid": 31318, + "ts": 658972010254.211, "dur": 62.504, + "args": { + "External id": 33450,"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": 4183437, "tid": 31318, + "ts": 658972010255.767, "dur": 34.277, + "args": { + "External id": 33451,"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": 4183437, "tid": 31318, + "ts": 658972010258.379, "dur": 2.340, + "args": { + "External id": 33452,"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": 4183437, "tid": 31318, + "ts": 658972010261.415, "dur": 28.391, + "args": { + "External id": 33453,"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": 4183437, "tid": 31318, + "ts": 658972010273.101, "dur": 16.130, + "args": { + "External id": 33454,"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": 4183437, "tid": 31318, + "ts": 658972010291.547, "dur": 6.862, + "args": { + "External id": 33455,"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": 4183437, "tid": 31318, + "ts": 658972010295.138, "dur": 2.739, + "args": { + "External id": 33456,"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": 4183437, "tid": 31318, + "ts": 658972010299.112, "dur": 16.905, + "args": { + "External id": 33457,"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": 4183437, "tid": 31318, + "ts": 658972010325.475, "dur": 75.497, + "args": { + "External id": 33458,"Record function id": 0, "Sequence number": 460079, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972010326.496, "dur": 72.168, + "args": { + "External id": 33459,"Sequence number": 460079, "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": 4183437, "tid": 31318, "ts": 658972010326.496, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972010327.908, "dur": 70.346, + "args": { + "External id": 33460,"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": 4183437, "tid": 31318, + "ts": 658972010329.386, "dur": 21.870, + "args": { + "External id": 33461,"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": 4183437, "tid": 31318, + "ts": 658972010332.504, "dur": 2.480, + "args": { + "External id": 33462,"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": 4183437, "tid": 31318, + "ts": 658972010335.599, "dur": 15.378, + "args": { + "External id": 33463,"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": 4183437, "tid": 31318, + "ts": 658972010336.272, "dur": 14.314, + "args": { + "External id": 33464,"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": 4183437, "tid": 31318, + "ts": 658972010352.193, "dur": 2.804, + "args": { + "External id": 33465,"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": 4183437, "tid": 31318, + "ts": 658972010353.955, "dur": 0.763, + "args": { + "External id": 33466,"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": 4183437, "tid": 31318, + "ts": 658972010355.724, "dur": 41.764, + "args": { + "External id": 33467,"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": 4183437, "tid": 31318, + "ts": 658972010404.684, "dur": 76.325, + "args": { + "External id": 33468,"Record function id": 0, "Sequence number": 460078, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972010405.717, "dur": 59.950, + "args": { + "External id": 33469,"Sequence number": 460078, "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": 4183437, "tid": 31318, "ts": 658972010405.717, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972010408.297, "dur": 57.080, + "args": { + "External id": 33470,"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": 4183437, "tid": 31318, + "ts": 658972010409.533, "dur": 16.655, + "args": { + "External id": 33471,"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": 4183437, "tid": 31318, + "ts": 658972010412.414, "dur": 1.864, + "args": { + "External id": 33472,"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": 4183437, "tid": 31318, + "ts": 658972010414.726, "dur": 11.184, + "args": { + "External id": 33473,"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": 4183437, "tid": 31318, + "ts": 658972010415.767, "dur": 9.728, + "args": { + "External id": 33474,"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": 4183437, "tid": 31318, + "ts": 658972010426.884, "dur": 1.966, + "args": { + "External id": 33475,"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": 4183437, "tid": 31318, + "ts": 658972010428.251, "dur": 0.391, + "args": { + "External id": 33476,"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": 4183437, "tid": 31318, + "ts": 658972010429.458, "dur": 35.333, + "args": { + "External id": 33477,"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": 4183437, "tid": 31318, + "ts": 658972010468.813, "dur": 11.041, + "args": { + "External id": 33478,"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": 4183437, "tid": 31318, + "ts": 658972010485.026, "dur": 32.571, + "args": { + "External id": 33479,"Record function id": 0, "Sequence number": 460077, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972010486.014, "dur": 1.102, + "args": { + "External id": 33480,"Sequence number": 460077, "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": 4183437, "tid": 31318, "ts": 658972010486.014, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183437, "tid": 31318, + "ts": 658972010488.713, "dur": 24.498, + "args": { + "External id": 33481,"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": 4183437, "tid": 31318, + "ts": 658972010490.486, "dur": 22.347, + "args": { + "External id": 33482,"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": 4183437, "tid": 31318, + "ts": 658972010495.088, "dur": 0.751, + "args": { + "External id": 33483,"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": 4183437, "tid": 31318, + "ts": 658972010521.724, "dur": 1483.419, + "args": { + "External id": 33484,"Record function id": 0, "Sequence number": 460076, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972010532.802, "dur": 1444.740, + "args": { + "External id": 33485,"Sequence number": 460076, "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": 4183437, "tid": 31318, "ts": 658972010532.802, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972010558.170, "dur": 1.900, + "args": { + "External id": 33486,"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": 4183437, "tid": 31318, + "ts": 658972010562.197, "dur": 1330.291, + "args": { + "External id": 33487,"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": 4183437, "tid": 31318, + "ts": 658972010563.357, "dur": 1328.897, + "args": { + "External id": 33488,"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": 4183437, "tid": 31318, + "ts": 658972010565.870, "dur": 3.026, + "args": { + "External id": 33489,"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": 4183437, "tid": 31318, + "ts": 658972010569.804, "dur": 1321.192, + "args": { + "External id": 33490,"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": 4183437, "tid": 31318, + "ts": 658972011895.748, "dur": 0.513, + "args": { + "External id": 33491,"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": 4183437, "tid": 31318, + "ts": 658972011897.456, "dur": 2.080, + "args": { + "External id": 33492,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 4183437, "tid": 31318, + "ts": 658972011898.607, "dur": 0.789, + "args": { + "External id": 33493,"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": 4183437, "tid": 31318, + "ts": 658972011903.216, "dur": 20.430, + "args": { + "External id": 33494,"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": 4183437, "tid": 31318, + "ts": 658972011928.261, "dur": 42.738, + "args": { + "External id": 33495,"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": 4183437, "tid": 31318, + "ts": 658972011929.054, "dur": 41.727, + "args": { + "External id": 33496,"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": 4183437, "tid": 31318, + "ts": 658972011930.269, "dur": 40.187, + "args": { + "External id": 33497,"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": 4183437, "tid": 31318, + "ts": 658972011987.337, "dur": 14.148, + "args": { + "External id": 33498,"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": 4183437, "tid": 31318, + "ts": 658972012015.708, "dur": 12.220, + "args": { + "External id": 33499,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972012018.361, "dur": 7.767, + "args": { + "External id": 33500,"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": 4183437, "tid": 31318, + "ts": 658972012021.358, "dur": 3.803, + "args": { + "External id": 33501,"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": 4183437, "tid": 31318, + "ts": 658972012022.282, "dur": 2.773, + "args": { + "External id": 33502,"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": 4183437, "tid": 31318, + "ts": 658972012031.312, "dur": 9.555, + "args": { + "External id": 33503,"Record function id": 0, "Sequence number": 460075, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972012032.135, "dur": 6.720, + "args": { + "External id": 33504,"Sequence number": 460075, "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": 4183437, "tid": 31318, "ts": 658972012032.135, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972012034.540, "dur": 4.128, + "args": { + "External id": 33505,"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": 4183437, "tid": 31318, + "ts": 658972012036.136, "dur": 2.406, + "args": { + "External id": 33506,"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": 4183437, "tid": 31318, + "ts": 658972012044.380, "dur": 61.132, + "args": { + "External id": 33507,"Record function id": 0, "Sequence number": 460074, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972012045.423, "dur": 56.224, + "args": { + "External id": 33508,"Sequence number": 460074, "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": 4183437, "tid": 31318, "ts": 658972012045.423, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972012048.237, "dur": 53.176, + "args": { + "External id": 33509,"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": 4183437, "tid": 31318, + "ts": 658972012052.357, "dur": 21.568, + "args": { + "External id": 33510,"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": 4183437, "tid": 31318, + "ts": 658972012054.359, "dur": 2.626, + "args": { + "External id": 33511,"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": 4183437, "tid": 31318, + "ts": 658972012058.135, "dur": 15.463, + "args": { + "External id": 33512,"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": 4183437, "tid": 31318, + "ts": 658972012059.729, "dur": 13.439, + "args": { + "External id": 33513,"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": 4183437, "tid": 31318, + "ts": 658972012075.237, "dur": 4.390, + "args": { + "External id": 33514,"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": 4183437, "tid": 31318, + "ts": 658972012078.266, "dur": 1.172, + "args": { + "External id": 33515,"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": 4183437, "tid": 31318, + "ts": 658972012080.471, "dur": 20.288, + "args": { + "External id": 33516,"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": 4183437, "tid": 31318, + "ts": 658972012110.945, "dur": 52.295, + "args": { + "External id": 33517,"Record function id": 0, "Sequence number": 460073, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972012111.900, "dur": 48.813, + "args": { + "External id": 33518,"Sequence number": 460073, "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": 4183437, "tid": 31318, "ts": 658972012111.900, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183437, "tid": 31318, + "ts": 658972012114.315, "dur": 46.081, + "args": { + "External id": 33519,"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": 4183437, "tid": 31318, + "ts": 658972012115.813, "dur": 18.218, + "args": { + "External id": 33520,"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": 4183437, "tid": 31318, + "ts": 658972012118.296, "dur": 2.716, + "args": { + "External id": 33521,"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": 4183437, "tid": 31318, + "ts": 658972012121.619, "dur": 12.159, + "args": { + "External id": 33522,"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": 4183437, "tid": 31318, + "ts": 658972012122.719, "dur": 10.671, + "args": { + "External id": 33523,"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": 4183437, "tid": 31318, + "ts": 658972012135.073, "dur": 5.565, + "args": { + "External id": 33524,"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": 4183437, "tid": 31318, + "ts": 658972012139.184, "dur": 0.949, + "args": { + "External id": 33525,"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": 4183437, "tid": 31318, + "ts": 658972012141.574, "dur": 18.368, + "args": { + "External id": 33526,"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": 4183437, "tid": 31318, + "ts": 658972012166.863, "dur": 71.286, + "args": { + "External id": 33527,"Record function id": 0, "Sequence number": 460072, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972012167.859, "dur": 67.764, + "args": { + "External id": 33528,"Sequence number": 460072, "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": 4183437, "tid": 31318, "ts": 658972012167.859, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972012169.528, "dur": 65.762, + "args": { + "External id": 33529,"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": 4183437, "tid": 31318, + "ts": 658972012172.351, "dur": 16.671, + "args": { + "External id": 33530,"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": 4183437, "tid": 31318, + "ts": 658972012175.198, "dur": 1.837, + "args": { + "External id": 33531,"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": 4183437, "tid": 31318, + "ts": 658972012177.707, "dur": 11.071, + "args": { + "External id": 33532,"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": 4183437, "tid": 31318, + "ts": 658972012178.486, "dur": 9.927, + "args": { + "External id": 33533,"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": 4183437, "tid": 31318, + "ts": 658972012189.751, "dur": 4.369, + "args": { + "External id": 33534,"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": 4183437, "tid": 31318, + "ts": 658972012191.517, "dur": 2.366, + "args": { + "External id": 33535,"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": 4183437, "tid": 31318, + "ts": 658972012194.898, "dur": 39.651, + "args": { + "External id": 33536,"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": 4183437, "tid": 31318, + "ts": 658972012241.893, "dur": 102.196, + "args": { + "External id": 33537,"Record function id": 0, "Sequence number": 460071, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972012242.680, "dur": 82.980, + "args": { + "External id": 33538,"Sequence number": 460071, "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": 4183437, "tid": 31318, "ts": 658972012242.680, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183437, "tid": 31318, + "ts": 658972012244.637, "dur": 80.733, + "args": { + "External id": 33539,"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": 4183437, "tid": 31318, + "ts": 658972012245.754, "dur": 33.995, + "args": { + "External id": 33540,"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": 4183437, "tid": 31318, + "ts": 658972012248.731, "dur": 1.748, + "args": { + "External id": 33541,"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": 4183437, "tid": 31318, + "ts": 658972012253.865, "dur": 25.600, + "args": { + "External id": 33542,"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": 4183437, "tid": 31318, + "ts": 658972012255.890, "dur": 22.940, + "args": { + "External id": 33543,"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": 4183437, "tid": 31318, + "ts": 658972012281.415, "dur": 4.983, + "args": { + "External id": 33544,"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": 4183437, "tid": 31318, + "ts": 658972012285.388, "dur": 0.778, + "args": { + "External id": 33545,"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": 4183437, "tid": 31318, + "ts": 658972012287.204, "dur": 37.412, + "args": { + "External id": 33546,"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": 4183437, "tid": 31318, + "ts": 658972012329.760, "dur": 12.541, + "args": { + "External id": 33547,"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": 4183437, "tid": 31318, + "ts": 658972012351.088, "dur": 388.339, + "args": { + "External id": 33548,"Record function id": 0, "Sequence number": 460070, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972012352.953, "dur": 377.052, + "args": { + "External id": 33549,"Sequence number": 460070, "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": 4183437, "tid": 31318, "ts": 658972012352.953, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183437, "tid": 31318, + "ts": 658972012522.066, "dur": 41.592, + "args": { + "External id": 33550,"kernel_hash": "ciouqosvw2sjmbrdwkhbaqxz7nskiaugkfnyhquptr5auanulqq6", "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/io/ciouqosvw2sjmbrdwkhbaqxz7nskiaugkfnyhquptr5auanulqq6.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": 4183437, "tid": 31318, + "ts": 658972012593.446, "dur": 26.394, + "args": { + "External id": 33551,"kernel_hash": "ck4kxmj6itojvwysygotvlksvmolpqx52nbiyx5ivctli2nco42c", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4kxmj6itojvwysygotvlksvmolpqx52nbiyx5ivctli2nco42c.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": 4183437, "tid": 31318, + "ts": 658972012637.974, "dur": 63.997, + "args": { + "External id": 33552,"kernel_hash": "cw37dis4epeet5w4vumkmze46zkdtqaxu7thnazyfte3ifl3t4rz", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw37dis4epeet5w4vumkmze46zkdtqaxu7thnazyfte3ifl3t4rz.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": 4183437, "tid": 31318, + "ts": 658972012751.336, "dur": 13.999, + "args": { + "External id": 33553,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972012753.852, "dur": 10.625, + "args": { + "External id": 33554,"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": 4183437, "tid": 31318, + "ts": 658972012756.917, "dur": 6.671, + "args": { + "External id": 33555,"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": 4183437, "tid": 31318, + "ts": 658972012760.021, "dur": 3.459, + "args": { + "External id": 33556,"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": 4183437, "tid": 31318, + "ts": 658972012771.284, "dur": 31.022, + "args": { + "External id": 33557,"Record function id": 0, "Sequence number": 460069, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972012772.396, "dur": 23.776, + "args": { + "External id": 33558,"Sequence number": 460069, "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": 4183437, "tid": 31318, "ts": 658972012772.396, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183437, "tid": 31318, + "ts": 658972012774.521, "dur": 8.891, + "args": { + "External id": 33559,"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": 4183437, "tid": 31318, + "ts": 658972012780.236, "dur": 1.461, + "args": { + "External id": 33560,"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": 4183437, "tid": 31318, + "ts": 658972012783.951, "dur": 3.890, + "args": { + "External id": 33561,"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": 4183437, "tid": 31318, + "ts": 658972012786.455, "dur": 0.622, + "args": { + "External id": 33562,"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": 4183437, "tid": 31318, + "ts": 658972012788.294, "dur": 3.335, + "args": { + "External id": 33563,"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": 4183437, "tid": 31318, + "ts": 658972012790.420, "dur": 0.400, + "args": { + "External id": 33564,"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": 4183437, "tid": 31318, + "ts": 658972012792.073, "dur": 3.475, + "args": { + "External id": 33565,"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": 4183437, "tid": 31318, + "ts": 658972012794.004, "dur": 0.523, + "args": { + "External id": 33566,"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": 4183437, "tid": 31318, + "ts": 658972012806.033, "dur": 5.231, + "args": { + "External id": 33567,"Record function id": 0, "Sequence number": 460068, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972012806.814, "dur": 1.169, + "args": { + "External id": 33568,"Sequence number": 460068, "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": 4183437, "tid": 31318, "ts": 658972012806.814, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972012815.471, "dur": 490.634, + "args": { + "External id": 33569,"Record function id": 0, "Sequence number": 460067, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972012816.954, "dur": 475.994, + "args": { + "External id": 33570,"Sequence number": 460067, "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": 4183437, "tid": 31318, "ts": 658972012816.954, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972012856.916, "dur": 9.743, + "args": { + "External id": 33571,"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": 4183437, "tid": 31318, + "ts": 658972012862.445, "dur": 3.876, + "args": { + "External id": 33572,"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": 4183437, "tid": 31318, + "ts": 658972012870.364, "dur": 9.412, + "args": { + "External id": 33573,"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": 4183437, "tid": 31318, + "ts": 658972012872.792, "dur": 6.127, + "args": { + "External id": 33574,"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": 4183437, "tid": 31318, + "ts": 658972012876.489, "dur": 2.204, + "args": { + "External id": 33575,"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": 4183437, "tid": 31318, + "ts": 658972012883.554, "dur": 118.525, + "args": { + "External id": 33576,"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": 4183437, "tid": 31318, + "ts": 658972012884.702, "dur": 3.713, + "args": { + "External id": 33577,"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": 4183437, "tid": 31318, + "ts": 658972012885.319, "dur": 2.121, + "args": { + "External id": 33578,"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": 4183437, "tid": 31318, + "ts": 658972012886.928, "dur": 0.398, + "args": { + "External id": 33579,"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": 4183437, "tid": 31318, + "ts": 658972012889.593, "dur": 111.805, + "args": { + "External id": 33580,"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": 4183437, "tid": 31318, + "ts": 658972012891.749, "dur": 108.737, + "args": { + "External id": 33581,"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": 4183437, "tid": 31318, + "ts": 658972013009.438, "dur": 4.570, + "args": { + "External id": 33582,"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": 4183437, "tid": 31318, + "ts": 658972013011.281, "dur": 2.562, + "args": { + "External id": 33583,"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": 4183437, "tid": 31318, + "ts": 658972013048.141, "dur": 6.707, + "args": { + "External id": 33584,"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": 4183437, "tid": 31318, + "ts": 658972013056.154, "dur": 2.235, + "args": { + "External id": 33585,"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": 4183437, "tid": 31318, + "ts": 658972013059.661, "dur": 1.761, + "args": { + "External id": 33586,"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": 4183437, "tid": 31318, + "ts": 658972013097.811, "dur": 2.456, + "args": { + "External id": 33587,"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": 4183437, "tid": 31318, + "ts": 658972013098.841, "dur": 1.292, + "args": { + "External id": 33588,"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": 4183437, "tid": 31318, + "ts": 658972013127.211, "dur": 125.949, + "args": { + "External id": 33589,"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": 4183437, "tid": 31318, + "ts": 658972013134.054, "dur": 9.090, + "args": { + "External id": 33590,"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": 4183437, "tid": 31318, + "ts": 658972013137.963, "dur": 2.887, + "args": { + "External id": 33591,"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": 4183437, "tid": 31318, + "ts": 658972013145.815, "dur": 6.773, + "args": { + "External id": 33592,"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": 4183437, "tid": 31318, + "ts": 658972013151.228, "dur": 0.630, + "args": { + "External id": 33593,"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": 4183437, "tid": 31318, + "ts": 658972013154.261, "dur": 2.497, + "args": { + "External id": 33594,"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": 4183437, "tid": 31318, + "ts": 658972013155.993, "dur": 0.368, + "args": { + "External id": 33595,"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": 4183437, "tid": 31318, + "ts": 658972013157.719, "dur": 2.916, + "args": { + "External id": 33596,"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": 4183437, "tid": 31318, + "ts": 658972013159.660, "dur": 0.575, + "args": { + "External id": 33597,"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": 4183437, "tid": 31318, + "ts": 658972013166.846, "dur": 2.934, + "args": { + "External id": 33598,"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": 4183437, "tid": 31318, + "ts": 658972013168.918, "dur": 0.540, + "args": { + "External id": 33599,"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": 4183437, "tid": 31318, + "ts": 658972013171.239, "dur": 5.800, + "args": { + "External id": 33600,"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": 4183437, "tid": 31318, + "ts": 658972013175.132, "dur": 1.707, + "args": { + "External id": 33601,"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": 4183437, "tid": 31318, + "ts": 658972013177.992, "dur": 2.861, + "args": { + "External id": 33602,"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": 4183437, "tid": 31318, + "ts": 658972013180.084, "dur": 0.446, + "args": { + "External id": 33603,"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": 4183437, "tid": 31318, + "ts": 658972013181.828, "dur": 2.323, + "args": { + "External id": 33604,"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": 4183437, "tid": 31318, + "ts": 658972013182.862, "dur": 1.188, + "args": { + "External id": 33605,"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": 4183437, "tid": 31318, + "ts": 658972013186.158, "dur": 55.526, + "args": { + "External id": 33606,"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": 4183437, "tid": 31318, + "ts": 658972013243.609, "dur": 0.853, + "args": { + "External id": 33607,"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": 4183437, "tid": 31318, + "ts": 658972013245.498, "dur": 3.360, + "args": { + "External id": 33608,"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": 4183437, "tid": 31318, + "ts": 658972013247.717, "dur": 0.615, + "args": { + "External id": 33609,"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": 4183437, "tid": 31318, + "ts": 658972013250.925, "dur": 1.130, + "args": { + "External id": 33610,"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": 4183437, "tid": 31318, + "ts": 658972013318.576, "dur": 10.351, + "args": { + "External id": 33611,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972013321.150, "dur": 7.004, + "args": { + "External id": 33612,"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": 4183437, "tid": 31318, + "ts": 658972013323.808, "dur": 3.406, + "args": { + "External id": 33613,"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": 4183437, "tid": 31318, + "ts": 658972013324.742, "dur": 2.349, + "args": { + "External id": 33614,"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": 4183437, "tid": 31318, + "ts": 658972013333.218, "dur": 8.447, + "args": { + "External id": 33615,"Record function id": 0, "Sequence number": 460066, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972013334.763, "dur": 4.822, + "args": { + "External id": 33616,"Sequence number": 460066, "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": 4183437, "tid": 31318, "ts": 658972013334.763, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972013336.432, "dur": 2.940, + "args": { + "External id": 33617,"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": 4183437, "tid": 31318, + "ts": 658972013337.638, "dur": 1.638, + "args": { + "External id": 33618,"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": 4183437, "tid": 31318, + "ts": 658972013345.598, "dur": 122.504, + "args": { + "External id": 33619,"Record function id": 0, "Sequence number": 460065, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972013347.991, "dur": 112.837, + "args": { + "External id": 33620,"Sequence number": 460065, "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": 4183437, "tid": 31318, "ts": 658972013347.991, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972013351.758, "dur": 4.113, + "args": { + "External id": 33621,"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": 4183437, "tid": 31318, + "ts": 658972013353.105, "dur": 2.189, + "args": { + "External id": 33622,"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": 4183437, "tid": 31318, + "ts": 658972013354.515, "dur": 0.596, + "args": { + "External id": 33623,"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": 4183437, "tid": 31318, + "ts": 658972013356.907, "dur": 46.237, + "args": { + "External id": 33624,"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": 4183437, "tid": 31318, + "ts": 658972013404.354, "dur": 5.093, + "args": { + "External id": 33625,"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": 4183437, "tid": 31318, + "ts": 658972013404.990, "dur": 3.846, + "args": { + "External id": 33626,"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": 4183437, "tid": 31318, + "ts": 658972013407.719, "dur": 0.920, + "args": { + "External id": 33627,"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": 4183437, "tid": 31318, + "ts": 658972013411.093, "dur": 4.666, + "args": { + "External id": 33628,"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": 4183437, "tid": 31318, + "ts": 658972013411.766, "dur": 3.511, + "args": { + "External id": 33629,"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": 4183437, "tid": 31318, + "ts": 658972013413.062, "dur": 2.090, + "args": { + "External id": 33630,"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": 4183437, "tid": 31318, + "ts": 658972013416.308, "dur": 43.822, + "args": { + "External id": 33631,"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": 4183437, "tid": 31318, + "ts": 658972013472.688, "dur": 9.130, + "args": { + "External id": 33632,"Record function id": 0, "Sequence number": 460064, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972013473.483, "dur": 6.705, + "args": { + "External id": 33633,"Sequence number": 460064, "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": 4183437, "tid": 31318, "ts": 658972013473.483, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972013475.330, "dur": 4.709, + "args": { + "External id": 33634,"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": 4183437, "tid": 31318, + "ts": 658972013478.603, "dur": 1.282, + "args": { + "External id": 33635,"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": 4183437, "tid": 31318, + "ts": 658972013485.427, "dur": 7.670, + "args": { + "External id": 33636,"Record function id": 0, "Sequence number": 460063, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972013486.457, "dur": 4.753, + "args": { + "External id": 33637,"Sequence number": 460063, "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": 4183437, "tid": 31318, "ts": 658972013486.457, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972013487.484, "dur": 3.526, + "args": { + "External id": 33638,"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": 4183437, "tid": 31318, + "ts": 658972013488.149, "dur": 2.351, + "args": { + "External id": 33639,"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": 4183437, "tid": 31318, + "ts": 658972013489.593, "dur": 0.782, + "args": { + "External id": 33640,"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": 4183437, "tid": 31318, + "ts": 658972013497.163, "dur": 5.485, + "args": { + "External id": 33641,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972013498.847, "dur": 3.217, + "args": { + "External id": 33642,"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": 4183437, "tid": 31318, + "ts": 658972013499.766, "dur": 1.977, + "args": { + "External id": 33643,"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": 4183437, "tid": 31318, + "ts": 658972013500.542, "dur": 1.101, + "args": { + "External id": 33644,"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": 4183437, "tid": 31318, + "ts": 658972013505.663, "dur": 8.624, + "args": { + "External id": 33645,"Record function id": 0, "Sequence number": 460062, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972013506.925, "dur": 4.958, + "args": { + "External id": 33646,"Sequence number": 460062, "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": 4183437, "tid": 31318, "ts": 658972013506.925, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972013509.979, "dur": 1.779, + "args": { + "External id": 33647,"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": 4183437, "tid": 31318, + "ts": 658972013511.008, "dur": 0.634, + "args": { + "External id": 33648,"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": 4183437, "tid": 31318, + "ts": 658972013517.415, "dur": 93.065, + "args": { + "External id": 33649,"Record function id": 0, "Sequence number": 460061, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972013518.169, "dur": 84.672, + "args": { + "External id": 33650,"Sequence number": 460061, "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": 4183437, "tid": 31318, "ts": 658972013518.169, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972013520.065, "dur": 5.661, + "args": { + "External id": 33651,"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": 4183437, "tid": 31318, + "ts": 658972013520.737, "dur": 4.538, + "args": { + "External id": 33652,"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": 4183437, "tid": 31318, + "ts": 658972013524.488, "dur": 0.669, + "args": { + "External id": 33653,"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": 4183437, "tid": 31318, + "ts": 658972013526.350, "dur": 25.208, + "args": { + "External id": 33654,"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": 4183437, "tid": 31318, + "ts": 658972013552.625, "dur": 5.725, + "args": { + "External id": 33655,"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": 4183437, "tid": 31318, + "ts": 658972013553.088, "dur": 4.627, + "args": { + "External id": 33656,"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": 4183437, "tid": 31318, + "ts": 658972013554.978, "dur": 2.621, + "args": { + "External id": 33657,"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": 4183437, "tid": 31318, + "ts": 658972013559.454, "dur": 4.854, + "args": { + "External id": 33658,"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": 4183437, "tid": 31318, + "ts": 658972013560.228, "dur": 3.649, + "args": { + "External id": 33659,"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": 4183437, "tid": 31318, + "ts": 658972013563.203, "dur": 0.556, + "args": { + "External id": 33660,"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": 4183437, "tid": 31318, + "ts": 658972013564.976, "dur": 37.141, + "args": { + "External id": 33661,"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": 4183437, "tid": 31318, + "ts": 658972013617.107, "dur": 33.292, + "args": { + "External id": 33662,"Record function id": 0, "Sequence number": 460060, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972013617.907, "dur": 4.293, + "args": { + "External id": 33663,"Sequence number": 460060, "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": 4183437, "tid": 31318, "ts": 658972013617.907, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972013619.467, "dur": 2.600, + "args": { + "External id": 33664,"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": 4183437, "tid": 31318, + "ts": 658972013620.760, "dur": 1.168, + "args": { + "External id": 33665,"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": 4183437, "tid": 31318, + "ts": 658972013625.436, "dur": 22.168, + "args": { + "External id": 33666,"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": 4183437, "tid": 31318, + "ts": 658972013693.433, "dur": 13.242, + "args": { + "External id": 33667,"Record function id": 0, "Sequence number": 460059, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972013695.017, "dur": 8.216, + "args": { + "External id": 33668,"Sequence number": 460059, "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": 4183437, "tid": 31318, "ts": 658972013695.017, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972013698.059, "dur": 4.948, + "args": { + "External id": 33669,"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": 4183437, "tid": 31318, + "ts": 658972013699.463, "dur": 2.776, + "args": { + "External id": 33670,"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": 4183437, "tid": 31318, + "ts": 658972013701.222, "dur": 0.823, + "args": { + "External id": 33671,"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": 4183437, "tid": 31318, + "ts": 658972013711.407, "dur": 6.512, + "args": { + "External id": 33672,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972013713.179, "dur": 4.255, + "args": { + "External id": 33673,"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": 4183437, "tid": 31318, + "ts": 658972013714.829, "dur": 2.228, + "args": { + "External id": 33674,"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": 4183437, "tid": 31318, + "ts": 658972013715.563, "dur": 1.418, + "args": { + "External id": 33675,"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": 4183437, "tid": 31318, + "ts": 658972013722.501, "dur": 418.952, + "args": { + "External id": 33676,"Record function id": 0, "Sequence number": 460058, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972013724.141, "dur": 403.555, + "args": { + "External id": 33677,"Sequence number": 460058, "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": 4183437, "tid": 31318, "ts": 658972013724.141, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183437, "tid": 31318, + "ts": 658972013748.961, "dur": 38.590, + "args": { + "External id": 33678,"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": 4183437, "tid": 31318, + "ts": 658972013750.702, "dur": 36.650, + "args": { + "External id": 33679,"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": 4183437, "tid": 31318, + "ts": 658972013753.708, "dur": 7.290, + "args": { + "External id": 33680,"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": 4183437, "tid": 31318, + "ts": 658972013756.907, "dur": 3.564, + "args": { + "External id": 33681,"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": 4183437, "tid": 31318, + "ts": 658972013762.337, "dur": 24.567, + "args": { + "External id": 33682,"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": 4183437, "tid": 31318, + "ts": 658972013800.518, "dur": 4.159, + "args": { + "External id": 33683,"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": 4183437, "tid": 31318, + "ts": 658972013801.648, "dur": 2.932, + "args": { + "External id": 33684,"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": 4183437, "tid": 31318, + "ts": 658972013808.449, "dur": 2.017, + "args": { + "External id": 33685,"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": 4183437, "tid": 31318, + "ts": 658972013809.534, "dur": 0.828, + "args": { + "External id": 33686,"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": 4183437, "tid": 31318, + "ts": 658972013825.844, "dur": 2.253, + "args": { + "External id": 33687,"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": 4183437, "tid": 31318, + "ts": 658972013839.489, "dur": 3.080, + "args": { + "External id": 33688,"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": 4183437, "tid": 31318, + "ts": 658972014018.759, "dur": 2.463, + "args": { + "External id": 33689,"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": 4183437, "tid": 31318, + "ts": 658972014026.336, "dur": 32.168, + "args": { + "External id": 33690,"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": 4183437, "tid": 31318, + "ts": 658972014036.044, "dur": 0.842, + "args": { + "External id": 33691,"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": 4183437, "tid": 31318, + "ts": 658972014064.253, "dur": 29.827, + "args": { + "External id": 33692,"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": 4183437, "tid": 31318, + "ts": 658972014066.119, "dur": 27.751, + "args": { + "External id": 33693,"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": 4183437, "tid": 31318, + "ts": 658972014071.022, "dur": 3.919, + "args": { + "External id": 33694,"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": 4183437, "tid": 31318, + "ts": 658972014078.151, "dur": 15.125, + "args": { + "External id": 33695,"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": 4183437, "tid": 31318, + "ts": 658972014098.901, "dur": 2.497, + "args": { + "External id": 33696,"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": 4183437, "tid": 31318, + "ts": 658972014100.159, "dur": 1.078, + "args": { + "External id": 33697,"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": 4183437, "tid": 31318, + "ts": 658972014107.994, "dur": 4.108, + "args": { + "External id": 33698,"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": 4183437, "tid": 31318, + "ts": 658972014109.262, "dur": 2.741, + "args": { + "External id": 33699,"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": 4183437, "tid": 31318, + "ts": 658972014114.672, "dur": 2.027, + "args": { + "External id": 33700,"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": 4183437, "tid": 31318, + "ts": 658972014115.680, "dur": 0.930, + "args": { + "External id": 33701,"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": 4183437, "tid": 31318, + "ts": 658972014151.922, "dur": 7.476, + "args": { + "External id": 33702,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972014153.865, "dur": 4.855, + "args": { + "External id": 33703,"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": 4183437, "tid": 31318, + "ts": 658972014155.450, "dur": 2.516, + "args": { + "External id": 33704,"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": 4183437, "tid": 31318, + "ts": 658972014156.224, "dur": 1.648, + "args": { + "External id": 33705,"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": 4183437, "tid": 31318, + "ts": 658972014163.286, "dur": 8.204, + "args": { + "External id": 33706,"Record function id": 0, "Sequence number": 460057, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972014164.785, "dur": 3.906, + "args": { + "External id": 33707,"Sequence number": 460057, "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": 4183437, "tid": 31318, "ts": 658972014164.785, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972014166.229, "dur": 2.287, + "args": { + "External id": 33708,"Record 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": 4183437, "tid": 31318, + "ts": 658972014167.237, "dur": 1.139, + "args": { + "External id": 33709,"Record 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": 4183437, "tid": 31318, + "ts": 658972014176.975, "dur": 172.324, + "args": { + "External id": 33710,"Record function id": 0, "Sequence number": 460056, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972014177.746, "dur": 165.810, + "args": { + "External id": 33711,"Sequence number": 460056, "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": 4183437, "tid": 31318, "ts": 658972014177.746, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972014180.701, "dur": 4.623, + "args": { + "External id": 33712,"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": 4183437, "tid": 31318, + "ts": 658972014181.838, "dur": 2.882, + "args": { + "External id": 33713,"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": 4183437, "tid": 31318, + "ts": 658972014183.664, "dur": 0.869, + "args": { + "External id": 33714,"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": 4183437, "tid": 31318, + "ts": 658972014186.624, "dur": 95.931, + "args": { + "External id": 33715,"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": 4183437, "tid": 31318, + "ts": 658972014285.295, "dur": 8.686, + "args": { + "External id": 33716,"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": 4183437, "tid": 31318, + "ts": 658972014288.416, "dur": 4.569, + "args": { + "External id": 33717,"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": 4183437, "tid": 31318, + "ts": 658972014290.766, "dur": 2.024, + "args": { + "External id": 33718,"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": 4183437, "tid": 31318, + "ts": 658972014295.781, "dur": 3.323, + "args": { + "External id": 33719,"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": 4183437, "tid": 31318, + "ts": 658972014296.575, "dur": 1.996, + "args": { + "External id": 33720,"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": 4183437, "tid": 31318, + "ts": 658972014298.080, "dur": 0.363, + "args": { + "External id": 33721,"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": 4183437, "tid": 31318, + "ts": 658972014299.837, "dur": 42.784, + "args": { + "External id": 33722,"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": 4183437, "tid": 31318, + "ts": 658972014356.441, "dur": 11.433, + "args": { + "External id": 33723,"Record function id": 0, "Sequence number": 460055, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972014357.592, "dur": 8.134, + "args": { + "External id": 33724,"Sequence number": 460055, "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": 4183437, "tid": 31318, "ts": 658972014357.592, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972014360.801, "dur": 4.774, + "args": { + "External id": 33725,"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": 4183437, "tid": 31318, + "ts": 658972014362.107, "dur": 3.359, + "args": { + "External id": 33726,"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": 4183437, "tid": 31318, + "ts": 658972014371.399, "dur": 7.369, + "args": { + "External id": 33727,"Record function id": 0, "Sequence number": 460054, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972014372.167, "dur": 4.643, + "args": { + "External id": 33728,"Sequence number": 460054, "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": 4183437, "tid": 31318, "ts": 658972014372.167, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972014372.757, "dur": 3.819, + "args": { + "External id": 33729,"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": 4183437, "tid": 31318, + "ts": 658972014373.420, "dur": 2.660, + "args": { + "External id": 33730,"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": 4183437, "tid": 31318, + "ts": 658972014375.335, "dur": 0.614, + "args": { + "External id": 33731,"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": 4183437, "tid": 31318, + "ts": 658972014383.033, "dur": 8.306, + "args": { + "External id": 33732,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972014384.750, "dur": 6.018, + "args": { + "External id": 33733,"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": 4183437, "tid": 31318, + "ts": 658972014386.179, "dur": 4.307, + "args": { + "External id": 33734,"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": 4183437, "tid": 31318, + "ts": 658972014388.990, "dur": 1.370, + "args": { + "External id": 33735,"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": 4183437, "tid": 31318, + "ts": 658972014394.490, "dur": 5.675, + "args": { + "External id": 33736,"Record function id": 0, "Sequence number": 460053, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972014395.315, "dur": 3.343, + "args": { + "External id": 33737,"Sequence number": 460053, "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": 4183437, "tid": 31318, "ts": 658972014395.315, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972014396.394, "dur": 2.112, + "args": { + "External id": 33738,"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": 4183437, "tid": 31318, + "ts": 658972014397.155, "dur": 1.223, + "args": { + "External id": 33739,"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": 4183437, "tid": 31318, + "ts": 658972014404.450, "dur": 348.966, + "args": { + "External id": 33740,"Record function id": 0, "Sequence number": 460052, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183437, "tid": 31318, + "ts": 658972014406.385, "dur": 329.989, + "args": { + "External id": 33741,"Sequence number": 460052, "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": 4183437, "tid": 31318, "ts": 658972014406.385, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 31318, + "ts": 658972014422.114, "dur": 7.341, + "args": { + "External id": 33742,"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": 4183437, "tid": 31318, + "ts": 658972014425.156, "dur": 3.850, + "args": { + "External id": 33743,"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": 4183437, "tid": 31318, + "ts": 658972014431.378, "dur": 4.274, + "args": { + "External id": 33744,"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": 4183437, "tid": 31318, + "ts": 658972014433.605, "dur": 1.829, + "args": { + "External id": 33745,"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": 4183437, "tid": 31318, + "ts": 658972014437.545, "dur": 5.359, + "args": { + "External id": 33746,"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": 4183437, "tid": 31318, + "ts": 658972014439.531, "dur": 3.184, + "args": { + "External id": 33747,"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": 4183437, "tid": 31318, + "ts": 658972014473.363, "dur": 233.272, + "args": { + "External id": 33748,"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": 4183437, "tid": 31318, + "ts": 658972014569.485, "dur": 4.536, + "args": { + "External id": 33749,"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": 4183437, "tid": 31318, + "ts": 658972014575.884, "dur": 4.037, + "args": { + "External id": 33750,"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": 4183437, "tid": 31318, + "ts": 658972014722.946, "dur": 4.147, + "args": { + "External id": 33751,"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": 4183437, "tid": 31318, + "ts": 658972014730.399, "dur": 0.669, + "args": { + "External id": 33752,"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": 4183437, "tid": 31318, + "ts": 658972014732.927, "dur": 0.821, + "args": { + "External id": 33753,"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": 4183437, "tid": 31318, + "ts": 658972014763.754, "dur": 228.615, + "args": { + "External id": 33754,"Record function id": 0, "Sequence number": 460051, "Fwd thread id": 1, "Ev Idx": 473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972014765.776, "dur": 219.918, + "args": { + "External id": 33755,"Sequence number": 460051, "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": 4183437, "tid": 31318, "ts": 658972014765.776, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183437, "tid": 31318, + "ts": 658972014787.680, "dur": 44.942, + "args": { + "External id": 33756,"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": 4183437, "tid": 31318, + "ts": 658972014791.892, "dur": 3.781, + "args": { + "External id": 33757,"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": 4183437, "tid": 31318, + "ts": 658972014796.983, "dur": 35.063, + "args": { + "External id": 33758,"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": 4183437, "tid": 31318, + "ts": 658972014843.007, "dur": 4.847, + "args": { + "External id": 33759,"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": 4183437, "tid": 31318, + "ts": 658972014845.340, "dur": 2.216, + "args": { + "External id": 33760,"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": 4183437, "tid": 31318, + "ts": 658972014999.187, "dur": 144.319, + "args": { + "External id": 33761,"Record function id": 0, "Sequence number": 460050, "Fwd thread id": 1, "Ev Idx": 480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972015001.471, "dur": 136.805, + "args": { + "External id": 33762,"Sequence number": 460050, "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": 4183437, "tid": 31318, "ts": 658972015001.471, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183437, "tid": 31318, + "ts": 658972015012.920, "dur": 26.606, + "args": { + "External id": 33763,"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": 4183437, "tid": 31318, + "ts": 658972015015.236, "dur": 2.689, + "args": { + "External id": 33764,"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": 4183437, "tid": 31318, + "ts": 658972015018.783, "dur": 20.360, + "args": { + "External id": 33765,"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": 4183437, "tid": 31318, + "ts": 658972015046.778, "dur": 5.724, + "args": { + "External id": 33766,"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": 4183437, "tid": 31318, + "ts": 658972015048.331, "dur": 3.860, + "args": { + "External id": 33767,"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": 4183437, "tid": 31318, + "ts": 658972015149.233, "dur": 13.689, + "args": { + "External id": 33768,"Record function id": 0, "Sequence number": 460049, "Fwd thread id": 1, "Ev Idx": 487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015150.732, "dur": 9.912, + "args": { + "External id": 33769,"Sequence number": 460049, "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": 4183437, "tid": 31318, "ts": 658972015150.732, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972015153.048, "dur": 7.306, + "args": { + "External id": 33770,"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": 4183437, "tid": 31318, + "ts": 658972015154.667, "dur": 5.520, + "args": { + "External id": 33771,"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": 4183437, "tid": 31318, + "ts": 658972015166.300, "dur": 6.608, + "args": { + "External id": 33772,"Record function id": 0, "Sequence number": 460048, "Fwd thread id": 1, "Ev Idx": 491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015167.054, "dur": 3.661, + "args": { + "External id": 33773,"Sequence number": 460048, "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": 4183437, "tid": 31318, "ts": 658972015167.054, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972015168.375, "dur": 2.204, + "args": { + "External id": 33774,"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": 4183437, "tid": 31318, + "ts": 658972015169.624, "dur": 0.802, + "args": { + "External id": 33775,"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": 4183437, "tid": 31318, + "ts": 658972015175.806, "dur": 8.581, + "args": { + "External id": 33776,"Record function id": 0, "Sequence number": 460047, "Fwd thread id": 1, "Ev Idx": 495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015178.596, "dur": 3.626, + "args": { + "External id": 33777,"Sequence number": 460047, "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": 4183437, "tid": 31318, "ts": 658972015178.596, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972015180.187, "dur": 1.902, + "args": { + "External id": 33778,"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": 4183437, "tid": 31318, + "ts": 658972015181.288, "dur": 0.687, + "args": { + "External id": 33779,"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": 4183437, "tid": 31318, + "ts": 658972015187.726, "dur": 6.207, + "args": { + "External id": 33780,"Record function id": 0, "Sequence number": 460046, "Fwd thread id": 1, "Ev Idx": 499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015189.005, "dur": 3.097, + "args": { + "External id": 33781,"Sequence number": 460046, "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": 4183437, "tid": 31318, "ts": 658972015189.005, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972015190.362, "dur": 1.611, + "args": { + "External id": 33782,"Record 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": 4183437, "tid": 31318, + "ts": 658972015191.110, "dur": 0.770, + "args": { + "External id": 33783,"Record 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": 4183437, "tid": 31318, + "ts": 658972015197.290, "dur": 204.309, + "args": { + "External id": 33784,"Record function id": 0, "Sequence number": 460045, "Fwd thread id": 1, "Ev Idx": 503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015198.259, "dur": 194.455, + "args": { + "External id": 33785,"Sequence number": 460045, "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": 4183437, "tid": 31318, "ts": 658972015198.259, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972015203.498, "dur": 6.298, + "args": { + "External id": 33786,"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": 4183437, "tid": 31318, + "ts": 658972015205.376, "dur": 3.841, + "args": { + "External id": 33787,"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": 4183437, "tid": 31318, + "ts": 658972015207.484, "dur": 1.494, + "args": { + "External id": 33788,"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": 4183437, "tid": 31318, + "ts": 658972015210.999, "dur": 99.621, + "args": { + "External id": 33789,"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": 4183437, "tid": 31318, + "ts": 658972015313.242, "dur": 8.076, + "args": { + "External id": 33790,"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": 4183437, "tid": 31318, + "ts": 658972015314.492, "dur": 5.938, + "args": { + "External id": 33791,"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": 4183437, "tid": 31318, + "ts": 658972015318.944, "dur": 1.260, + "args": { + "External id": 33792,"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": 4183437, "tid": 31318, + "ts": 658972015342.077, "dur": 3.376, + "args": { + "External id": 33793,"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": 4183437, "tid": 31318, + "ts": 658972015343.077, "dur": 1.827, + "args": { + "External id": 33794,"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": 4183437, "tid": 31318, + "ts": 658972015344.504, "dur": 0.311, + "args": { + "External id": 33795,"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": 4183437, "tid": 31318, + "ts": 658972015346.186, "dur": 45.656, + "args": { + "External id": 33796,"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": 4183437, "tid": 31318, + "ts": 658972015409.430, "dur": 7.159, + "args": { + "External id": 33797,"Record function id": 0, "Sequence number": 460044, "Fwd thread id": 1, "Ev Idx": 516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015410.480, "dur": 4.536, + "args": { + "External id": 33798,"Sequence number": 460044, "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": 4183437, "tid": 31318, "ts": 658972015410.480, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972015412.248, "dur": 2.626, + "args": { + "External id": 33799,"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": 4183437, "tid": 31318, + "ts": 658972015413.159, "dur": 1.523, + "args": { + "External id": 33800,"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": 4183437, "tid": 31318, + "ts": 658972015419.840, "dur": 8.986, + "args": { + "External id": 33801,"Record function id": 0, "Sequence number": 460043, "Fwd thread id": 1, "Ev Idx": 520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015422.278, "dur": 4.364, + "args": { + "External id": 33802,"Sequence number": 460043, "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": 4183437, "tid": 31318, "ts": 658972015422.278, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972015423.022, "dur": 3.401, + "args": { + "External id": 33803,"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": 4183437, "tid": 31318, + "ts": 658972015423.705, "dur": 2.275, + "args": { + "External id": 33804,"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": 4183437, "tid": 31318, + "ts": 658972015425.486, "dur": 0.371, + "args": { + "External id": 33805,"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": 4183437, "tid": 31318, + "ts": 658972015434.502, "dur": 9.255, + "args": { + "External id": 33806,"Record function id": 0, "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972015436.393, "dur": 6.542, + "args": { + "External id": 33807,"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": 4183437, "tid": 31318, + "ts": 658972015438.855, "dur": 3.680, + "args": { + "External id": 33808,"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": 4183437, "tid": 31318, + "ts": 658972015439.967, "dur": 2.459, + "args": { + "External id": 33809,"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": 4183437, "tid": 31318, + "ts": 658972015448.969, "dur": 6.986, + "args": { + "External id": 33810,"Record function id": 0, "Sequence number": 460042, "Fwd thread id": 1, "Ev Idx": 529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015450.150, "dur": 4.096, + "args": { + "External id": 33811,"Sequence number": 460042, "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": 4183437, "tid": 31318, "ts": 658972015450.150, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972015451.190, "dur": 2.902, + "args": { + "External id": 33812,"Record 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": 4183437, "tid": 31318, + "ts": 658972015453.274, "dur": 0.672, + "args": { + "External id": 33813,"Record 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": 4183437, "tid": 31318, + "ts": 658972015459.290, "dur": 92.991, + "args": { + "External id": 33814,"Record function id": 0, "Sequence number": 460041, "Fwd thread id": 1, "Ev Idx": 533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015460.160, "dur": 86.647, + "args": { + "External id": 33815,"Sequence number": 460041, "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": 4183437, "tid": 31318, "ts": 658972015460.160, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972015462.115, "dur": 2.893, + "args": { + "External id": 33816,"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": 4183437, "tid": 31318, + "ts": 658972015462.542, "dur": 2.017, + "args": { + "External id": 33817,"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": 4183437, "tid": 31318, + "ts": 658972015463.870, "dur": 0.592, + "args": { + "External id": 33818,"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": 4183437, "tid": 31318, + "ts": 658972015467.509, "dur": 35.592, + "args": { + "External id": 33819,"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": 4183437, "tid": 31318, + "ts": 658972015504.019, "dur": 3.516, + "args": { + "External id": 33820,"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": 4183437, "tid": 31318, + "ts": 658972015504.622, "dur": 2.317, + "args": { + "External id": 33821,"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": 4183437, "tid": 31318, + "ts": 658972015506.170, "dur": 0.638, + "args": { + "External id": 33822,"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": 4183437, "tid": 31318, + "ts": 658972015508.595, "dur": 4.372, + "args": { + "External id": 33823,"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": 4183437, "tid": 31318, + "ts": 658972015509.091, "dur": 3.479, + "args": { + "External id": 33824,"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": 4183437, "tid": 31318, + "ts": 658972015510.732, "dur": 1.728, + "args": { + "External id": 33825,"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": 4183437, "tid": 31318, + "ts": 658972015515.154, "dur": 31.012, + "args": { + "External id": 33826,"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": 4183437, "tid": 31318, + "ts": 658972015556.361, "dur": 36.023, + "args": { + "External id": 33827,"Record function id": 0, "Sequence number": 460040, "Fwd thread id": 1, "Ev Idx": 546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015557.180, "dur": 4.135, + "args": { + "External id": 33828,"Sequence number": 460040, "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": 4183437, "tid": 31318, "ts": 658972015557.180, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972015558.739, "dur": 2.420, + "args": { + "External id": 33829,"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": 4183437, "tid": 31318, + "ts": 658972015559.830, "dur": 1.207, + "args": { + "External id": 33830,"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": 4183437, "tid": 31318, + "ts": 658972015564.503, "dur": 25.916, + "args": { + "External id": 33831,"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": 4183437, "tid": 31318, + "ts": 658972015596.034, "dur": 9.794, + "args": { + "External id": 33832,"Record function id": 0, "Sequence number": 460039, "Fwd thread id": 1, "Ev Idx": 551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015597.013, "dur": 6.712, + "args": { + "External id": 33833,"Sequence number": 460039, "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": 4183437, "tid": 31318, "ts": 658972015597.013, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972015597.911, "dur": 5.602, + "args": { + "External id": 33834,"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": 4183437, "tid": 31318, + "ts": 658972015600.766, "dur": 2.229, + "args": { + "External id": 33835,"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": 4183437, "tid": 31318, + "ts": 658972015602.380, "dur": 0.485, + "args": { + "External id": 33836,"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": 4183437, "tid": 31318, + "ts": 658972015609.758, "dur": 5.026, + "args": { + "External id": 33837,"Record function id": 0, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972015611.486, "dur": 2.656, + "args": { + "External id": 33838,"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": 4183437, "tid": 31318, + "ts": 658972015612.261, "dur": 1.497, + "args": { + "External id": 33839,"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": 4183437, "tid": 31318, + "ts": 658972015612.687, "dur": 0.951, + "args": { + "External id": 33840,"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": 4183437, "tid": 31318, + "ts": 658972015618.430, "dur": 6.032, + "args": { + "External id": 33841,"Record function id": 0, "Sequence number": 460038, "Fwd thread id": 1, "Ev Idx": 560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015619.805, "dur": 3.068, + "args": { + "External id": 33842,"Sequence number": 460038, "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": 4183437, "tid": 31318, "ts": 658972015619.805, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972015620.914, "dur": 1.830, + "args": { + "External id": 33843,"Record 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": 4183437, "tid": 31318, + "ts": 658972015621.779, "dur": 0.832, + "args": { + "External id": 33844,"Record 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": 4183437, "tid": 31318, + "ts": 658972015629.266, "dur": 150.907, + "args": { + "External id": 33845,"Record function id": 0, "Sequence number": 460037, "Fwd thread id": 1, "Ev Idx": 564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015629.868, "dur": 141.749, + "args": { + "External id": 33846,"Sequence number": 460037, "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": 4183437, "tid": 31318, "ts": 658972015629.868, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972015631.356, "dur": 3.237, + "args": { + "External id": 33847,"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": 4183437, "tid": 31318, + "ts": 658972015631.815, "dur": 2.323, + "args": { + "External id": 33848,"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": 4183437, "tid": 31318, + "ts": 658972015633.563, "dur": 0.433, + "args": { + "External id": 33849,"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": 4183437, "tid": 31318, + "ts": 658972015635.138, "dur": 87.666, + "args": { + "External id": 33850,"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": 4183437, "tid": 31318, + "ts": 658972015725.262, "dur": 6.002, + "args": { + "External id": 33851,"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": 4183437, "tid": 31318, + "ts": 658972015727.827, "dur": 2.584, + "args": { + "External id": 33852,"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": 4183437, "tid": 31318, + "ts": 658972015729.538, "dur": 0.728, + "args": { + "External id": 33853,"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": 4183437, "tid": 31318, + "ts": 658972015732.472, "dur": 2.913, + "args": { + "External id": 33854,"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": 4183437, "tid": 31318, + "ts": 658972015733.172, "dur": 1.777, + "args": { + "External id": 33855,"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": 4183437, "tid": 31318, + "ts": 658972015734.531, "dur": 0.347, + "args": { + "External id": 33856,"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": 4183437, "tid": 31318, + "ts": 658972015735.851, "dur": 35.108, + "args": { + "External id": 33857,"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": 4183437, "tid": 31318, + "ts": 658972015786.124, "dur": 28.706, + "args": { + "External id": 33858,"Record function id": 0, "Sequence number": 460036, "Fwd thread id": 1, "Ev Idx": 577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015788.814, "dur": 4.607, + "args": { + "External id": 33859,"Sequence number": 460036, "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": 4183437, "tid": 31318, "ts": 658972015788.814, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972015790.399, "dur": 2.834, + "args": { + "External id": 33860,"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": 4183437, "tid": 31318, + "ts": 658972015791.485, "dur": 1.596, + "args": { + "External id": 33861,"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": 4183437, "tid": 31318, + "ts": 658972015795.950, "dur": 16.789, + "args": { + "External id": 33862,"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": 4183437, "tid": 31318, + "ts": 658972015818.576, "dur": 11.126, + "args": { + "External id": 33863,"Record function id": 0, "Sequence number": 460035, "Fwd thread id": 1, "Ev Idx": 582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972015819.510, "dur": 7.715, + "args": { + "External id": 33864,"Sequence number": 460035, "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": 4183437, "tid": 31318, "ts": 658972015819.510, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972015820.251, "dur": 6.736, + "args": { + "External id": 33865,"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": 4183437, "tid": 31318, + "ts": 658972015822.632, "dur": 3.793, + "args": { + "External id": 33866,"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": 4183437, "tid": 31318, + "ts": 658972015825.761, "dur": 0.550, + "args": { + "External id": 33867,"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": 4183437, "tid": 31318, + "ts": 658972015834.027, "dur": 6.055, + "args": { + "External id": 33868,"Record function id": 0, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972015835.905, "dur": 3.677, + "args": { + "External id": 33869,"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": 4183437, "tid": 31318, + "ts": 658972015836.866, "dur": 2.083, + "args": { + "External id": 33870,"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": 4183437, "tid": 31318, + "ts": 658972015837.402, "dur": 1.431, + "args": { + "External id": 33871,"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": 4183437, "tid": 31318, + "ts": 658972015844.170, "dur": 362.055, + "args": { + "External id": 33872,"Record function id": 0, "Sequence number": 460034, "Fwd thread id": 1, "Ev Idx": 591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972015845.655, "dur": 327.642, + "args": { + "External id": 33873,"Sequence number": 460034, "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": 4183437, "tid": 31318, "ts": 658972015845.655, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972015878.261, "dur": 2.026, + "args": { + "External id": 33874,"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": 4183437, "tid": 31318, + "ts": 658972015879.078, "dur": 1.032, + "args": { + "External id": 33875,"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": 4183437, "tid": 31318, + "ts": 658972015895.415, "dur": 5.437, + "args": { + "External id": 33876,"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": 4183437, "tid": 31318, + "ts": 658972015911.921, "dur": 4.833, + "args": { + "External id": 33877,"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": 4183437, "tid": 31318, + "ts": 658972016073.005, "dur": 1.821, + "args": { + "External id": 33878,"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": 4183437, "tid": 31318, + "ts": 658972016079.111, "dur": 32.860, + "args": { + "External id": 33879,"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": 4183437, "tid": 31318, + "ts": 658972016089.397, "dur": 0.737, + "args": { + "External id": 33880,"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": 4183437, "tid": 31318, + "ts": 658972016117.682, "dur": 31.488, + "args": { + "External id": 33881,"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": 4183437, "tid": 31318, + "ts": 658972016119.312, "dur": 29.654, + "args": { + "External id": 33882,"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": 4183437, "tid": 31318, + "ts": 658972016123.873, "dur": 3.631, + "args": { + "External id": 33883,"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": 4183437, "tid": 31318, + "ts": 658972016128.954, "dur": 19.365, + "args": { + "External id": 33884,"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": 4183437, "tid": 31318, + "ts": 658972016153.811, "dur": 4.629, + "args": { + "External id": 33885,"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": 4183437, "tid": 31318, + "ts": 658972016157.278, "dur": 1.017, + "args": { + "External id": 33886,"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": 4183437, "tid": 31318, + "ts": 658972016164.824, "dur": 2.076, + "args": { + "External id": 33887,"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": 4183437, "tid": 31318, + "ts": 658972016165.731, "dur": 1.033, + "args": { + "External id": 33888,"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": 4183437, "tid": 31318, + "ts": 658972016183.419, "dur": 17.306, + "args": { + "External id": 33889,"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": 4183437, "tid": 31318, + "ts": 658972016215.807, "dur": 7.662, + "args": { + "External id": 33890,"Record function id": 0, "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972016217.778, "dur": 4.902, + "args": { + "External id": 33891,"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": 4183437, "tid": 31318, + "ts": 658972016219.117, "dur": 2.576, + "args": { + "External id": 33892,"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": 4183437, "tid": 31318, + "ts": 658972016219.973, "dur": 1.586, + "args": { + "External id": 33893,"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": 4183437, "tid": 31318, + "ts": 658972016229.406, "dur": 4.617, + "args": { + "External id": 33894,"Record function id": 0, "Sequence number": 460033, "Fwd thread id": 1, "Ev Idx": 613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972016230.317, "dur": 1.061, + "args": { + "External id": 33895,"Sequence number": 460033, "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": 4183437, "tid": 31318, "ts": 658972016230.317, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972016238.113, "dur": 476.268, + "args": { + "External id": 33896,"Record function id": 0, "Sequence number": 460032, "Fwd thread id": 1, "Ev Idx": 615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972016239.677, "dur": 461.890, + "args": { + "External id": 33897,"Sequence number": 460032, "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": 4183437, "tid": 31318, "ts": 658972016239.677, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972016289.939, "dur": 10.280, + "args": { + "External id": 33898,"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": 4183437, "tid": 31318, + "ts": 658972016295.968, "dur": 3.771, + "args": { + "External id": 33899,"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": 4183437, "tid": 31318, + "ts": 658972016303.940, "dur": 7.581, + "args": { + "External id": 33900,"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": 4183437, "tid": 31318, + "ts": 658972016305.891, "dur": 4.925, + "args": { + "External id": 33901,"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": 4183437, "tid": 31318, + "ts": 658972016307.861, "dur": 2.758, + "args": { + "External id": 33902,"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": 4183437, "tid": 31318, + "ts": 658972016316.831, "dur": 102.804, + "args": { + "External id": 33903,"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": 4183437, "tid": 31318, + "ts": 658972016317.610, "dur": 2.671, + "args": { + "External id": 33904,"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": 4183437, "tid": 31318, + "ts": 658972016318.095, "dur": 1.721, + "args": { + "External id": 33905,"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": 4183437, "tid": 31318, + "ts": 658972016319.260, "dur": 0.468, + "args": { + "External id": 33906,"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": 4183437, "tid": 31318, + "ts": 658972016321.374, "dur": 97.651, + "args": { + "External id": 33907,"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": 4183437, "tid": 31318, + "ts": 658972016322.754, "dur": 95.327, + "args": { + "External id": 33908,"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": 4183437, "tid": 31318, + "ts": 658972016423.507, "dur": 5.484, + "args": { + "External id": 33909,"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": 4183437, "tid": 31318, + "ts": 658972016427.119, "dur": 1.736, + "args": { + "External id": 33910,"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": 4183437, "tid": 31318, + "ts": 658972016462.734, "dur": 6.000, + "args": { + "External id": 33911,"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": 4183437, "tid": 31318, + "ts": 658972016470.523, "dur": 1.581, + "args": { + "External id": 33912,"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": 4183437, "tid": 31318, + "ts": 658972016473.181, "dur": 1.867, + "args": { + "External id": 33913,"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": 4183437, "tid": 31318, + "ts": 658972016506.694, "dur": 2.217, + "args": { + "External id": 33914,"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": 4183437, "tid": 31318, + "ts": 658972016507.564, "dur": 1.143, + "args": { + "External id": 33915,"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": 4183437, "tid": 31318, + "ts": 658972016531.479, "dur": 108.177, + "args": { + "External id": 33916,"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": 4183437, "tid": 31318, + "ts": 658972016536.685, "dur": 7.449, + "args": { + "External id": 33917,"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": 4183437, "tid": 31318, + "ts": 658972016540.805, "dur": 2.636, + "args": { + "External id": 33918,"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": 4183437, "tid": 31318, + "ts": 658972016546.228, "dur": 5.078, + "args": { + "External id": 33919,"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": 4183437, "tid": 31318, + "ts": 658972016550.143, "dur": 0.568, + "args": { + "External id": 33920,"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": 4183437, "tid": 31318, + "ts": 658972016552.663, "dur": 2.348, + "args": { + "External id": 33921,"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": 4183437, "tid": 31318, + "ts": 658972016554.322, "dur": 0.324, + "args": { + "External id": 33922,"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": 4183437, "tid": 31318, + "ts": 658972016555.849, "dur": 2.617, + "args": { + "External id": 33923,"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": 4183437, "tid": 31318, + "ts": 658972016557.472, "dur": 0.576, + "args": { + "External id": 33924,"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": 4183437, "tid": 31318, + "ts": 658972016562.203, "dur": 2.967, + "args": { + "External id": 33925,"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": 4183437, "tid": 31318, + "ts": 658972016564.385, "dur": 0.491, + "args": { + "External id": 33926,"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": 4183437, "tid": 31318, + "ts": 658972016567.650, "dur": 6.426, + "args": { + "External id": 33927,"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": 4183437, "tid": 31318, + "ts": 658972016572.094, "dur": 1.755, + "args": { + "External id": 33928,"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": 4183437, "tid": 31318, + "ts": 658972016575.164, "dur": 3.092, + "args": { + "External id": 33929,"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": 4183437, "tid": 31318, + "ts": 658972016577.341, "dur": 0.607, + "args": { + "External id": 33930,"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": 4183437, "tid": 31318, + "ts": 658972016579.130, "dur": 4.141, + "args": { + "External id": 33931,"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": 4183437, "tid": 31318, + "ts": 658972016580.091, "dur": 3.086, + "args": { + "External id": 33932,"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": 4183437, "tid": 31318, + "ts": 658972016584.414, "dur": 44.008, + "args": { + "External id": 33933,"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": 4183437, "tid": 31318, + "ts": 658972016630.328, "dur": 1.177, + "args": { + "External id": 33934,"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": 4183437, "tid": 31318, + "ts": 658972016632.508, "dur": 2.753, + "args": { + "External id": 33935,"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": 4183437, "tid": 31318, + "ts": 658972016634.325, "dur": 0.364, + "args": { + "External id": 33936,"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": 4183437, "tid": 31318, + "ts": 658972016637.765, "dur": 0.824, + "args": { + "External id": 33937,"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": 4183437, "tid": 31318, + "ts": 658972016728.376, "dur": 10.405, + "args": { + "External id": 33938,"Record function id": 0, "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972016731.027, "dur": 7.023, + "args": { + "External id": 33939,"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": 4183437, "tid": 31318, + "ts": 658972016733.483, "dur": 3.449, + "args": { + "External id": 33940,"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": 4183437, "tid": 31318, + "ts": 658972016734.439, "dur": 2.371, + "args": { + "External id": 33941,"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": 4183437, "tid": 31318, + "ts": 658972016742.665, "dur": 8.471, + "args": { + "External id": 33942,"Record function id": 0, "Sequence number": 460031, "Fwd thread id": 1, "Ev Idx": 661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972016744.250, "dur": 4.422, + "args": { + "External id": 33943,"Sequence number": 460031, "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": 4183437, "tid": 31318, "ts": 658972016744.250, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972016745.860, "dur": 2.592, + "args": { + "External id": 33944,"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": 4183437, "tid": 31318, + "ts": 658972016746.963, "dur": 1.334, + "args": { + "External id": 33945,"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": 4183437, "tid": 31318, + "ts": 658972016754.499, "dur": 112.241, + "args": { + "External id": 33946,"Record function id": 0, "Sequence number": 460030, "Fwd thread id": 1, "Ev Idx": 665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972016755.239, "dur": 105.153, + "args": { + "External id": 33947,"Sequence number": 460030, "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": 4183437, "tid": 31318, "ts": 658972016755.239, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972016759.872, "dur": 4.961, + "args": { + "External id": 33948,"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": 4183437, "tid": 31318, + "ts": 658972016761.466, "dur": 2.810, + "args": { + "External id": 33949,"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": 4183437, "tid": 31318, + "ts": 658972016763.443, "dur": 0.664, + "args": { + "External id": 33950,"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": 4183437, "tid": 31318, + "ts": 658972016765.933, "dur": 41.867, + "args": { + "External id": 33951,"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": 4183437, "tid": 31318, + "ts": 658972016808.858, "dur": 5.421, + "args": { + "External id": 33952,"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": 4183437, "tid": 31318, + "ts": 658972016809.574, "dur": 3.951, + "args": { + "External id": 33953,"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": 4183437, "tid": 31318, + "ts": 658972016812.597, "dur": 0.782, + "args": { + "External id": 33954,"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": 4183437, "tid": 31318, + "ts": 658972016815.683, "dur": 4.749, + "args": { + "External id": 33955,"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": 4183437, "tid": 31318, + "ts": 658972016816.323, "dur": 3.604, + "args": { + "External id": 33956,"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": 4183437, "tid": 31318, + "ts": 658972016817.580, "dur": 2.282, + "args": { + "External id": 33957,"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": 4183437, "tid": 31318, + "ts": 658972016820.986, "dur": 38.494, + "args": { + "External id": 33958,"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": 4183437, "tid": 31318, + "ts": 658972016871.270, "dur": 7.087, + "args": { + "External id": 33959,"Record function id": 0, "Sequence number": 460029, "Fwd thread id": 1, "Ev Idx": 678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972016872.274, "dur": 4.623, + "args": { + "External id": 33960,"Sequence number": 460029, "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": 4183437, "tid": 31318, "ts": 658972016872.274, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972016874.318, "dur": 2.429, + "args": { + "External id": 33961,"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": 4183437, "tid": 31318, + "ts": 658972016875.195, "dur": 1.447, + "args": { + "External id": 33962,"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": 4183437, "tid": 31318, + "ts": 658972016881.931, "dur": 9.411, + "args": { + "External id": 33963,"Record function id": 0, "Sequence number": 460028, "Fwd thread id": 1, "Ev Idx": 682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972016884.530, "dur": 4.499, + "args": { + "External id": 33964,"Sequence number": 460028, "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": 4183437, "tid": 31318, "ts": 658972016884.530, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972016885.256, "dur": 3.562, + "args": { + "External id": 33965,"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": 4183437, "tid": 31318, + "ts": 658972016886.137, "dur": 2.213, + "args": { + "External id": 33966,"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": 4183437, "tid": 31318, + "ts": 658972016887.700, "dur": 0.550, + "args": { + "External id": 33967,"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": 4183437, "tid": 31318, + "ts": 658972016895.476, "dur": 5.620, + "args": { + "External id": 33968,"Record function id": 0, "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972016897.617, "dur": 2.961, + "args": { + "External id": 33969,"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": 4183437, "tid": 31318, + "ts": 658972016898.574, "dur": 1.718, + "args": { + "External id": 33970,"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": 4183437, "tid": 31318, + "ts": 658972016899.184, "dur": 1.024, + "args": { + "External id": 33971,"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": 4183437, "tid": 31318, + "ts": 658972016904.360, "dur": 7.363, + "args": { + "External id": 33972,"Record function id": 0, "Sequence number": 460027, "Fwd thread id": 1, "Ev Idx": 691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972016905.612, "dur": 4.299, + "args": { + "External id": 33973,"Sequence number": 460027, "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": 4183437, "tid": 31318, "ts": 658972016905.612, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972016906.620, "dur": 3.136, + "args": { + "External id": 33974,"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": 4183437, "tid": 31318, + "ts": 658972016908.910, "dur": 0.713, + "args": { + "External id": 33975,"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": 4183437, "tid": 31318, + "ts": 658972016914.857, "dur": 92.266, + "args": { + "External id": 33976,"Record function id": 0, "Sequence number": 460026, "Fwd thread id": 1, "Ev Idx": 695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972016915.774, "dur": 84.101, + "args": { + "External id": 33977,"Sequence number": 460026, "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": 4183437, "tid": 31318, "ts": 658972016915.774, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972016917.311, "dur": 6.432, + "args": { + "External id": 33978,"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": 4183437, "tid": 31318, + "ts": 658972016917.877, "dur": 5.421, + "args": { + "External id": 33979,"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": 4183437, "tid": 31318, + "ts": 658972016922.783, "dur": 0.408, + "args": { + "External id": 33980,"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": 4183437, "tid": 31318, + "ts": 658972016925.990, "dur": 27.322, + "args": { + "External id": 33981,"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": 4183437, "tid": 31318, + "ts": 658972016954.375, "dur": 6.350, + "args": { + "External id": 33982,"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": 4183437, "tid": 31318, + "ts": 658972016955.074, "dur": 5.189, + "args": { + "External id": 33983,"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": 4183437, "tid": 31318, + "ts": 658972016956.747, "dur": 3.356, + "args": { + "External id": 33984,"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": 4183437, "tid": 31318, + "ts": 658972016961.607, "dur": 4.812, + "args": { + "External id": 33985,"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": 4183437, "tid": 31318, + "ts": 658972016962.185, "dur": 3.822, + "args": { + "External id": 33986,"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": 4183437, "tid": 31318, + "ts": 658972016965.501, "dur": 0.403, + "args": { + "External id": 33987,"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": 4183437, "tid": 31318, + "ts": 658972016967.049, "dur": 32.147, + "args": { + "External id": 33988,"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": 4183437, "tid": 31318, + "ts": 658972017011.239, "dur": 30.270, + "args": { + "External id": 33989,"Record function id": 0, "Sequence number": 460025, "Fwd thread id": 1, "Ev Idx": 708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972017012.126, "dur": 4.262, + "args": { + "External id": 33990,"Sequence number": 460025, "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": 4183437, "tid": 31318, "ts": 658972017012.126, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972017013.675, "dur": 2.556, + "args": { + "External id": 33991,"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": 4183437, "tid": 31318, + "ts": 658972017014.714, "dur": 1.378, + "args": { + "External id": 33992,"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": 4183437, "tid": 31318, + "ts": 658972017018.778, "dur": 19.930, + "args": { + "External id": 33993,"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": 4183437, "tid": 31318, + "ts": 658972017045.075, "dur": 9.104, + "args": { + "External id": 33994,"Record function id": 0, "Sequence number": 460024, "Fwd thread id": 1, "Ev Idx": 713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972017046.323, "dur": 5.899, + "args": { + "External id": 33995,"Sequence number": 460024, "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": 4183437, "tid": 31318, "ts": 658972017046.323, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972017047.028, "dur": 4.978, + "args": { + "External id": 33996,"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": 4183437, "tid": 31318, + "ts": 658972017047.750, "dur": 3.760, + "args": { + "External id": 33997,"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": 4183437, "tid": 31318, + "ts": 658972017050.608, "dur": 0.783, + "args": { + "External id": 33998,"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": 4183437, "tid": 31318, + "ts": 658972017057.923, "dur": 4.716, + "args": { + "External id": 33999,"Record function id": 0, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972017059.633, "dur": 2.480, + "args": { + "External id": 34000,"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": 4183437, "tid": 31318, + "ts": 658972017060.394, "dur": 1.448, + "args": { + "External id": 34001,"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": 4183437, "tid": 31318, + "ts": 658972017060.895, "dur": 0.864, + "args": { + "External id": 34002,"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": 4183437, "tid": 31318, + "ts": 658972017069.068, "dur": 429.045, + "args": { + "External id": 34003,"Record function id": 0, "Sequence number": 460023, "Fwd thread id": 1, "Ev Idx": 722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972017070.415, "dur": 388.503, + "args": { + "External id": 34004,"Sequence number": 460023, "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": 4183437, "tid": 31318, "ts": 658972017070.415, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183437, "tid": 31318, + "ts": 658972017093.835, "dur": 33.216, + "args": { + "External id": 34005,"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": 4183437, "tid": 31318, + "ts": 658972017095.231, "dur": 31.620, + "args": { + "External id": 34006,"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": 4183437, "tid": 31318, + "ts": 658972017098.394, "dur": 5.911, + "args": { + "External id": 34007,"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": 4183437, "tid": 31318, + "ts": 658972017100.814, "dur": 2.975, + "args": { + "External id": 34008,"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": 4183437, "tid": 31318, + "ts": 658972017105.431, "dur": 20.969, + "args": { + "External id": 34009,"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": 4183437, "tid": 31318, + "ts": 658972017136.998, "dur": 5.293, + "args": { + "External id": 34010,"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": 4183437, "tid": 31318, + "ts": 658972017139.497, "dur": 2.665, + "args": { + "External id": 34011,"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": 4183437, "tid": 31318, + "ts": 658972017145.728, "dur": 1.587, + "args": { + "External id": 34012,"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": 4183437, "tid": 31318, + "ts": 658972017146.351, "dur": 0.862, + "args": { + "External id": 34013,"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": 4183437, "tid": 31318, + "ts": 658972017160.231, "dur": 2.061, + "args": { + "External id": 34014,"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": 4183437, "tid": 31318, + "ts": 658972017172.946, "dur": 3.091, + "args": { + "External id": 34015,"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": 4183437, "tid": 31318, + "ts": 658972017347.491, "dur": 3.165, + "args": { + "External id": 34016,"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": 4183437, "tid": 31318, + "ts": 658972017354.815, "dur": 36.719, + "args": { + "External id": 34017,"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": 4183437, "tid": 31318, + "ts": 658972017365.100, "dur": 0.737, + "args": { + "External id": 34018,"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": 4183437, "tid": 31318, + "ts": 658972017396.789, "dur": 29.843, + "args": { + "External id": 34019,"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": 4183437, "tid": 31318, + "ts": 658972017398.507, "dur": 27.921, + "args": { + "External id": 34020,"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": 4183437, "tid": 31318, + "ts": 658972017402.822, "dur": 4.604, + "args": { + "External id": 34021,"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": 4183437, "tid": 31318, + "ts": 658972017408.942, "dur": 16.929, + "args": { + "External id": 34022,"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": 4183437, "tid": 31318, + "ts": 658972017431.075, "dur": 4.259, + "args": { + "External id": 34023,"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": 4183437, "tid": 31318, + "ts": 658972017433.915, "dur": 1.272, + "args": { + "External id": 34024,"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": 4183437, "tid": 31318, + "ts": 658972017442.178, "dur": 4.207, + "args": { + "External id": 34025,"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": 4183437, "tid": 31318, + "ts": 658972017443.277, "dur": 3.002, + "args": { + "External id": 34026,"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": 4183437, "tid": 31318, + "ts": 658972017448.414, "dur": 2.107, + "args": { + "External id": 34027,"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": 4183437, "tid": 31318, + "ts": 658972017449.407, "dur": 1.028, + "args": { + "External id": 34028,"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": 4183437, "tid": 31318, + "ts": 658972017472.334, "dur": 24.158, + "args": { + "External id": 34029,"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": 4183437, "tid": 31318, + "ts": 658972017510.850, "dur": 9.869, + "args": { + "External id": 34030,"Record function id": 0, "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972017513.041, "dur": 7.017, + "args": { + "External id": 34031,"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": 4183437, "tid": 31318, + "ts": 658972017514.918, "dur": 4.270, + "args": { + "External id": 34032,"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": 4183437, "tid": 31318, + "ts": 658972017517.397, "dur": 1.705, + "args": { + "External id": 34033,"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": 4183437, "tid": 31318, + "ts": 658972017524.688, "dur": 7.626, + "args": { + "External id": 34034,"Record function id": 0, "Sequence number": 460022, "Fwd thread id": 1, "Ev Idx": 753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972017526.264, "dur": 3.956, + "args": { + "External id": 34035,"Sequence number": 460022, "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": 4183437, "tid": 31318, "ts": 658972017526.264, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972017527.626, "dur": 2.347, + "args": { + "External id": 34036,"Record 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": 4183437, "tid": 31318, + "ts": 658972017528.719, "dur": 1.094, + "args": { + "External id": 34037,"Record 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": 4183437, "tid": 31318, + "ts": 658972017535.493, "dur": 179.741, + "args": { + "External id": 34038,"Record function id": 0, "Sequence number": 460021, "Fwd thread id": 1, "Ev Idx": 757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972017536.460, "dur": 170.262, + "args": { + "External id": 34039,"Sequence number": 460021, "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": 4183437, "tid": 31318, "ts": 658972017536.460, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972017539.500, "dur": 7.122, + "args": { + "External id": 34040,"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": 4183437, "tid": 31318, + "ts": 658972017542.594, "dur": 3.498, + "args": { + "External id": 34041,"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": 4183437, "tid": 31318, + "ts": 658972017544.965, "dur": 0.931, + "args": { + "External id": 34042,"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": 4183437, "tid": 31318, + "ts": 658972017547.750, "dur": 64.933, + "args": { + "External id": 34043,"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": 4183437, "tid": 31318, + "ts": 658972017614.111, "dur": 5.529, + "args": { + "External id": 34044,"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": 4183437, "tid": 31318, + "ts": 658972017614.992, "dur": 4.004, + "args": { + "External id": 34045,"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": 4183437, "tid": 31318, + "ts": 658972017617.102, "dur": 1.716, + "args": { + "External id": 34046,"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": 4183437, "tid": 31318, + "ts": 658972017623.037, "dur": 2.935, + "args": { + "External id": 34047,"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": 4183437, "tid": 31318, + "ts": 658972017623.797, "dur": 1.720, + "args": { + "External id": 34048,"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": 4183437, "tid": 31318, + "ts": 658972017625.072, "dur": 0.374, + "args": { + "External id": 34049,"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": 4183437, "tid": 31318, + "ts": 658972017626.538, "dur": 78.596, + "args": { + "External id": 34050,"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": 4183437, "tid": 31318, + "ts": 658972017722.855, "dur": 9.732, + "args": { + "External id": 34051,"Record function id": 0, "Sequence number": 460020, "Fwd thread id": 1, "Ev Idx": 770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972017723.971, "dur": 6.874, + "args": { + "External id": 34052,"Sequence number": 460020, "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": 4183437, "tid": 31318, "ts": 658972017723.971, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972017726.210, "dur": 4.490, + "args": { + "External id": 34053,"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": 4183437, "tid": 31318, + "ts": 658972017727.042, "dur": 3.549, + "args": { + "External id": 34054,"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": 4183437, "tid": 31318, + "ts": 658972017735.909, "dur": 10.403, + "args": { + "External id": 34055,"Record function id": 0, "Sequence number": 460019, "Fwd thread id": 1, "Ev Idx": 774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972017738.999, "dur": 5.307, + "args": { + "External id": 34056,"Sequence number": 460019, "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": 4183437, "tid": 31318, "ts": 658972017738.999, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972017739.834, "dur": 4.294, + "args": { + "External id": 34057,"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": 4183437, "tid": 31318, + "ts": 658972017740.810, "dur": 2.786, + "args": { + "External id": 34058,"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": 4183437, "tid": 31318, + "ts": 658972017742.860, "dur": 0.616, + "args": { + "External id": 34059,"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": 4183437, "tid": 31318, + "ts": 658972017750.582, "dur": 6.142, + "args": { + "External id": 34060,"Record function id": 0, "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972017752.206, "dur": 4.025, + "args": { + "External id": 34061,"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": 4183437, "tid": 31318, + "ts": 658972017753.349, "dur": 2.577, + "args": { + "External id": 34062,"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": 4183437, "tid": 31318, + "ts": 658972017754.163, "dur": 1.673, + "args": { + "External id": 34063,"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": 4183437, "tid": 31318, + "ts": 658972017759.883, "dur": 7.066, + "args": { + "External id": 34064,"Record function id": 0, "Sequence number": 460018, "Fwd thread id": 1, "Ev Idx": 783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972017760.543, "dur": 4.578, + "args": { + "External id": 34065,"Sequence number": 460018, "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": 4183437, "tid": 31318, "ts": 658972017760.543, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972017763.009, "dur": 1.981, + "args": { + "External id": 34066,"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": 4183437, "tid": 31318, + "ts": 658972017763.645, "dur": 1.213, + "args": { + "External id": 34067,"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": 4183437, "tid": 31318, + "ts": 658972017771.596, "dur": 273.986, + "args": { + "External id": 34068,"Record function id": 0, "Sequence number": 460017, "Fwd thread id": 1, "Ev Idx": 787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183437, "tid": 31318, + "ts": 658972017773.312, "dur": 254.933, + "args": { + "External id": 34069,"Sequence number": 460017, "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": 4183437, "tid": 31318, "ts": 658972017773.312, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 31318, + "ts": 658972017788.602, "dur": 6.894, + "args": { + "External id": 34070,"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": 4183437, "tid": 31318, + "ts": 658972017791.211, "dur": 3.843, + "args": { + "External id": 34071,"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": 4183437, "tid": 31318, + "ts": 658972017797.461, "dur": 3.548, + "args": { + "External id": 34072,"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": 4183437, "tid": 31318, + "ts": 658972017798.731, "dur": 2.091, + "args": { + "External id": 34073,"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": 4183437, "tid": 31318, + "ts": 658972017802.685, "dur": 5.295, + "args": { + "External id": 34074,"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": 4183437, "tid": 31318, + "ts": 658972017804.789, "dur": 2.996, + "args": { + "External id": 34075,"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": 4183437, "tid": 31318, + "ts": 658972017832.835, "dur": 171.500, + "args": { + "External id": 34076,"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": 4183437, "tid": 31318, + "ts": 658972017910.569, "dur": 3.941, + "args": { + "External id": 34077,"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": 4183437, "tid": 31318, + "ts": 658972017916.649, "dur": 3.485, + "args": { + "External id": 34078,"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": 4183437, "tid": 31318, + "ts": 658972018016.592, "dur": 3.173, + "args": { + "External id": 34079,"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": 4183437, "tid": 31318, + "ts": 658972018022.533, "dur": 0.739, + "args": { + "External id": 34080,"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": 4183437, "tid": 31318, + "ts": 658972018025.202, "dur": 0.511, + "args": { + "External id": 34081,"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": 4183437, "tid": 31318, + "ts": 658972018052.791, "dur": 229.977, + "args": { + "External id": 34082,"Record function id": 0, "Sequence number": 460016, "Fwd thread id": 1, "Ev Idx": 801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972018054.420, "dur": 203.372, + "args": { + "External id": 34083,"Sequence number": 460016, "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": 4183437, "tid": 31318, "ts": 658972018054.420, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183437, "tid": 31318, + "ts": 658972018073.769, "dur": 43.236, + "args": { + "External id": 34084,"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": 4183437, "tid": 31318, + "ts": 658972018076.813, "dur": 2.598, + "args": { + "External id": 34085,"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": 4183437, "tid": 31318, + "ts": 658972018080.580, "dur": 36.002, + "args": { + "External id": 34086,"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": 4183437, "tid": 31318, + "ts": 658972018126.643, "dur": 4.393, + "args": { + "External id": 34087,"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": 4183437, "tid": 31318, + "ts": 658972018128.603, "dur": 2.178, + "args": { + "External id": 34088,"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": 4183437, "tid": 31318, + "ts": 658972018292.972, "dur": 151.628, + "args": { + "External id": 34089,"Record function id": 0, "Sequence number": 460015, "Fwd thread id": 1, "Ev Idx": 808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972018295.355, "dur": 143.260, + "args": { + "External id": 34090,"Sequence number": 460015, "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": 4183437, "tid": 31318, "ts": 658972018295.355, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183437, "tid": 31318, + "ts": 658972018308.961, "dur": 31.503, + "args": { + "External id": 34091,"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": 4183437, "tid": 31318, + "ts": 658972018311.884, "dur": 3.580, + "args": { + "External id": 34092,"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": 4183437, "tid": 31318, + "ts": 658972018316.353, "dur": 23.651, + "args": { + "External id": 34093,"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": 4183437, "tid": 31318, + "ts": 658972018347.929, "dur": 4.492, + "args": { + "External id": 34094,"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": 4183437, "tid": 31318, + "ts": 658972018349.761, "dur": 2.337, + "args": { + "External id": 34095,"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": 4183437, "tid": 31318, + "ts": 658972018450.355, "dur": 16.162, + "args": { + "External id": 34096,"Record function id": 0, "Sequence number": 460014, "Fwd thread id": 1, "Ev Idx": 815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018451.634, "dur": 12.029, + "args": { + "External id": 34097,"Sequence number": 460014, "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": 4183437, "tid": 31318, "ts": 658972018451.634, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972018454.241, "dur": 9.144, + "args": { + "External id": 34098,"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": 4183437, "tid": 31318, + "ts": 658972018457.508, "dur": 5.678, + "args": { + "External id": 34099,"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": 4183437, "tid": 31318, + "ts": 658972018470.177, "dur": 5.981, + "args": { + "External id": 34100,"Record function id": 0, "Sequence number": 460013, "Fwd thread id": 1, "Ev Idx": 819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018471.217, "dur": 3.186, + "args": { + "External id": 34101,"Sequence number": 460013, "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": 4183437, "tid": 31318, "ts": 658972018471.217, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972018472.331, "dur": 1.892, + "args": { + "External id": 34102,"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": 4183437, "tid": 31318, + "ts": 658972018473.218, "dur": 0.828, + "args": { + "External id": 34103,"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": 4183437, "tid": 31318, + "ts": 658972018481.463, "dur": 6.625, + "args": { + "External id": 34104,"Record function id": 0, "Sequence number": 460012, "Fwd thread id": 1, "Ev Idx": 823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018482.084, "dur": 3.648, + "args": { + "External id": 34105,"Sequence number": 460012, "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": 4183437, "tid": 31318, "ts": 658972018482.084, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972018483.468, "dur": 2.104, + "args": { + "External id": 34106,"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": 4183437, "tid": 31318, + "ts": 658972018484.757, "dur": 0.672, + "args": { + "External id": 34107,"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": 4183437, "tid": 31318, + "ts": 658972018491.661, "dur": 7.587, + "args": { + "External id": 34108,"Record function id": 0, "Sequence number": 460011, "Fwd thread id": 1, "Ev Idx": 827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018492.824, "dur": 4.578, + "args": { + "External id": 34109,"Sequence number": 460011, "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": 4183437, "tid": 31318, "ts": 658972018492.824, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972018494.108, "dur": 3.122, + "args": { + "External id": 34110,"Record 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": 4183437, "tid": 31318, + "ts": 658972018496.104, "dur": 1.012, + "args": { + "External id": 34111,"Record 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": 4183437, "tid": 31318, + "ts": 658972018502.634, "dur": 150.569, + "args": { + "External id": 34112,"Record function id": 0, "Sequence number": 460010, "Fwd thread id": 1, "Ev Idx": 831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018503.671, "dur": 142.039, + "args": { + "External id": 34113,"Sequence number": 460010, "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": 4183437, "tid": 31318, "ts": 658972018503.671, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972018507.123, "dur": 6.627, + "args": { + "External id": 34114,"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": 4183437, "tid": 31318, + "ts": 658972018508.891, "dur": 4.260, + "args": { + "External id": 34115,"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": 4183437, "tid": 31318, + "ts": 658972018511.484, "dur": 1.378, + "args": { + "External id": 34116,"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": 4183437, "tid": 31318, + "ts": 658972018517.181, "dur": 77.628, + "args": { + "External id": 34117,"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": 4183437, "tid": 31318, + "ts": 658972018596.148, "dur": 4.304, + "args": { + "External id": 34118,"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": 4183437, "tid": 31318, + "ts": 658972018596.950, "dur": 2.785, + "args": { + "External id": 34119,"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": 4183437, "tid": 31318, + "ts": 658972018598.670, "dur": 0.891, + "args": { + "External id": 34120,"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": 4183437, "tid": 31318, + "ts": 658972018601.962, "dur": 4.946, + "args": { + "External id": 34121,"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": 4183437, "tid": 31318, + "ts": 658972018602.836, "dur": 3.534, + "args": { + "External id": 34122,"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": 4183437, "tid": 31318, + "ts": 658972018605.907, "dur": 0.338, + "args": { + "External id": 34123,"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": 4183437, "tid": 31318, + "ts": 658972018607.456, "dur": 37.491, + "args": { + "External id": 34124,"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": 4183437, "tid": 31318, + "ts": 658972018701.130, "dur": 9.892, + "args": { + "External id": 34125,"Record function id": 0, "Sequence number": 460009, "Fwd thread id": 1, "Ev Idx": 844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018702.773, "dur": 6.261, + "args": { + "External id": 34126,"Sequence number": 460009, "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": 4183437, "tid": 31318, "ts": 658972018702.773, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972018704.986, "dur": 3.893, + "args": { + "External id": 34127,"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": 4183437, "tid": 31318, + "ts": 658972018706.276, "dur": 2.426, + "args": { + "External id": 34128,"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": 4183437, "tid": 31318, + "ts": 658972018714.267, "dur": 9.630, + "args": { + "External id": 34129,"Record function id": 0, "Sequence number": 460008, "Fwd thread id": 1, "Ev Idx": 848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018715.449, "dur": 6.590, + "args": { + "External id": 34130,"Sequence number": 460008, "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": 4183437, "tid": 31318, "ts": 658972018715.449, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972018716.148, "dur": 5.724, + "args": { + "External id": 34131,"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": 4183437, "tid": 31318, + "ts": 658972018717.052, "dur": 4.335, + "args": { + "External id": 34132,"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": 4183437, "tid": 31318, + "ts": 658972018720.647, "dur": 0.629, + "args": { + "External id": 34133,"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": 4183437, "tid": 31318, + "ts": 658972018729.466, "dur": 9.516, + "args": { + "External id": 34134,"Record function id": 0, "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972018731.210, "dur": 7.018, + "args": { + "External id": 34135,"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": 4183437, "tid": 31318, + "ts": 658972018733.765, "dur": 4.087, + "args": { + "External id": 34136,"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": 4183437, "tid": 31318, + "ts": 658972018735.208, "dur": 2.554, + "args": { + "External id": 34137,"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": 4183437, "tid": 31318, + "ts": 658972018742.210, "dur": 6.422, + "args": { + "External id": 34138,"Record function id": 0, "Sequence number": 460007, "Fwd thread id": 1, "Ev Idx": 857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018743.500, "dur": 3.327, + "args": { + "External id": 34139,"Sequence number": 460007, "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": 4183437, "tid": 31318, "ts": 658972018743.500, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972018744.719, "dur": 1.968, + "args": { + "External id": 34140,"Record 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": 4183437, "tid": 31318, + "ts": 658972018745.791, "dur": 0.745, + "args": { + "External id": 34141,"Record 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": 4183437, "tid": 31318, + "ts": 658972018751.767, "dur": 100.834, + "args": { + "External id": 34142,"Record function id": 0, "Sequence number": 460006, "Fwd thread id": 1, "Ev Idx": 861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018752.376, "dur": 94.314, + "args": { + "External id": 34143,"Sequence number": 460006, "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": 4183437, "tid": 31318, "ts": 658972018752.376, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972018756.217, "dur": 3.809, + "args": { + "External id": 34144,"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": 4183437, "tid": 31318, + "ts": 658972018756.974, "dur": 2.565, + "args": { + "External id": 34145,"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": 4183437, "tid": 31318, + "ts": 658972018758.798, "dur": 0.597, + "args": { + "External id": 34146,"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": 4183437, "tid": 31318, + "ts": 658972018760.702, "dur": 40.623, + "args": { + "External id": 34147,"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": 4183437, "tid": 31318, + "ts": 658972018802.445, "dur": 4.270, + "args": { + "External id": 34148,"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": 4183437, "tid": 31318, + "ts": 658972018803.138, "dur": 3.016, + "args": { + "External id": 34149,"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": 4183437, "tid": 31318, + "ts": 658972018804.972, "dur": 1.062, + "args": { + "External id": 34150,"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": 4183437, "tid": 31318, + "ts": 658972018809.474, "dur": 4.940, + "args": { + "External id": 34151,"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": 4183437, "tid": 31318, + "ts": 658972018810.230, "dur": 3.738, + "args": { + "External id": 34152,"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": 4183437, "tid": 31318, + "ts": 658972018812.201, "dur": 1.679, + "args": { + "External id": 34153,"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": 4183437, "tid": 31318, + "ts": 658972018814.820, "dur": 31.147, + "args": { + "External id": 34154,"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": 4183437, "tid": 31318, + "ts": 658972018856.885, "dur": 31.668, + "args": { + "External id": 34155,"Record function id": 0, "Sequence number": 460005, "Fwd thread id": 1, "Ev Idx": 874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018857.796, "dur": 4.160, + "args": { + "External id": 34156,"Sequence number": 460005, "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": 4183437, "tid": 31318, "ts": 658972018857.796, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972018859.484, "dur": 2.321, + "args": { + "External id": 34157,"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": 4183437, "tid": 31318, + "ts": 658972018860.593, "dur": 1.079, + "args": { + "External id": 34158,"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": 4183437, "tid": 31318, + "ts": 658972018864.683, "dur": 20.024, + "args": { + "External id": 34159,"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": 4183437, "tid": 31318, + "ts": 658972018892.245, "dur": 7.775, + "args": { + "External id": 34160,"Record function id": 0, "Sequence number": 460004, "Fwd thread id": 1, "Ev Idx": 879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018893.044, "dur": 5.210, + "args": { + "External id": 34161,"Sequence number": 460004, "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": 4183437, "tid": 31318, "ts": 658972018893.044, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972018893.870, "dur": 4.213, + "args": { + "External id": 34162,"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": 4183437, "tid": 31318, + "ts": 658972018894.902, "dur": 2.649, + "args": { + "External id": 34163,"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": 4183437, "tid": 31318, + "ts": 658972018896.635, "dur": 0.785, + "args": { + "External id": 34164,"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": 4183437, "tid": 31318, + "ts": 658972018904.192, "dur": 7.662, + "args": { + "External id": 34165,"Record function id": 0, "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972018905.726, "dur": 5.525, + "args": { + "External id": 34166,"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": 4183437, "tid": 31318, + "ts": 658972018906.856, "dur": 4.027, + "args": { + "External id": 34167,"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": 4183437, "tid": 31318, + "ts": 658972018909.407, "dur": 1.356, + "args": { + "External id": 34168,"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": 4183437, "tid": 31318, + "ts": 658972018915.205, "dur": 6.505, + "args": { + "External id": 34169,"Record function id": 0, "Sequence number": 460003, "Fwd thread id": 1, "Ev Idx": 888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018916.670, "dur": 3.046, + "args": { + "External id": 34170,"Sequence number": 460003, "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": 4183437, "tid": 31318, "ts": 658972018916.670, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972018917.914, "dur": 1.673, + "args": { + "External id": 34171,"Record 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": 4183437, "tid": 31318, + "ts": 658972018918.541, "dur": 0.942, + "args": { + "External id": 34172,"Record 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": 4183437, "tid": 31318, + "ts": 658972018926.289, "dur": 97.606, + "args": { + "External id": 34173,"Record function id": 0, "Sequence number": 460002, "Fwd thread id": 1, "Ev Idx": 892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972018927.215, "dur": 89.832, + "args": { + "External id": 34174,"Sequence number": 460002, "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": 4183437, "tid": 31318, "ts": 658972018927.215, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972018929.377, "dur": 5.366, + "args": { + "External id": 34175,"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": 4183437, "tid": 31318, + "ts": 658972018930.392, "dur": 3.877, + "args": { + "External id": 34176,"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": 4183437, "tid": 31318, + "ts": 658972018933.478, "dur": 0.653, + "args": { + "External id": 34177,"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": 4183437, "tid": 31318, + "ts": 658972018935.502, "dur": 36.913, + "args": { + "External id": 34178,"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": 4183437, "tid": 31318, + "ts": 658972018973.555, "dur": 3.850, + "args": { + "External id": 34179,"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": 4183437, "tid": 31318, + "ts": 658972018974.007, "dur": 2.815, + "args": { + "External id": 34180,"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": 4183437, "tid": 31318, + "ts": 658972018975.769, "dur": 0.923, + "args": { + "External id": 34181,"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": 4183437, "tid": 31318, + "ts": 658972018978.518, "dur": 7.131, + "args": { + "External id": 34182,"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": 4183437, "tid": 31318, + "ts": 658972018982.687, "dur": 2.500, + "args": { + "External id": 34183,"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": 4183437, "tid": 31318, + "ts": 658972018984.514, "dur": 0.607, + "args": { + "External id": 34184,"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": 4183437, "tid": 31318, + "ts": 658972018986.213, "dur": 30.134, + "args": { + "External id": 34185,"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": 4183437, "tid": 31318, + "ts": 658972019028.114, "dur": 24.026, + "args": { + "External id": 34186,"Record function id": 0, "Sequence number": 460001, "Fwd thread id": 1, "Ev Idx": 905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972019029.216, "dur": 4.095, + "args": { + "External id": 34187,"Sequence number": 460001, "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": 4183437, "tid": 31318, "ts": 658972019029.216, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972019030.741, "dur": 2.423, + "args": { + "External id": 34188,"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": 4183437, "tid": 31318, + "ts": 658972019031.914, "dur": 1.140, + "args": { + "External id": 34189,"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": 4183437, "tid": 31318, + "ts": 658972019035.596, "dur": 14.664, + "args": { + "External id": 34190,"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": 4183437, "tid": 31318, + "ts": 658972019055.517, "dur": 9.111, + "args": { + "External id": 34191,"Record function id": 0, "Sequence number": 460000, "Fwd thread id": 1, "Ev Idx": 910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972019057.767, "dur": 5.136, + "args": { + "External id": 34192,"Sequence number": 460000, "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": 4183437, "tid": 31318, "ts": 658972019057.767, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972019058.681, "dur": 4.039, + "args": { + "External id": 34193,"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": 4183437, "tid": 31318, + "ts": 658972019059.495, "dur": 2.636, + "args": { + "External id": 34194,"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": 4183437, "tid": 31318, + "ts": 658972019061.505, "dur": 0.531, + "args": { + "External id": 34195,"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": 4183437, "tid": 31318, + "ts": 658972019068.564, "dur": 4.770, + "args": { + "External id": 34196,"Record function id": 0, "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972019069.983, "dur": 2.822, + "args": { + "External id": 34197,"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": 4183437, "tid": 31318, + "ts": 658972019070.735, "dur": 1.785, + "args": { + "External id": 34198,"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": 4183437, "tid": 31318, + "ts": 658972019071.207, "dur": 1.207, + "args": { + "External id": 34199,"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": 4183437, "tid": 31318, + "ts": 658972019077.707, "dur": 373.889, + "args": { + "External id": 34200,"Record function id": 0, "Sequence number": 459999, "Fwd thread id": 1, "Ev Idx": 919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972019079.266, "dur": 342.378, + "args": { + "External id": 34201,"Sequence number": 459999, "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": 4183437, "tid": 31318, "ts": 658972019079.266, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972019111.920, "dur": 3.407, + "args": { + "External id": 34202,"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": 4183437, "tid": 31318, + "ts": 658972019114.205, "dur": 0.947, + "args": { + "External id": 34203,"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": 4183437, "tid": 31318, + "ts": 658972019129.818, "dur": 5.109, + "args": { + "External id": 34204,"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": 4183437, "tid": 31318, + "ts": 658972019144.391, "dur": 2.686, + "args": { + "External id": 34205,"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": 4183437, "tid": 31318, + "ts": 658972019315.232, "dur": 2.731, + "args": { + "External id": 34206,"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": 4183437, "tid": 31318, + "ts": 658972019322.349, "dur": 34.628, + "args": { + "External id": 34207,"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": 4183437, "tid": 31318, + "ts": 658972019333.722, "dur": 1.033, + "args": { + "External id": 34208,"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": 4183437, "tid": 31318, + "ts": 658972019366.622, "dur": 32.191, + "args": { + "External id": 34209,"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": 4183437, "tid": 31318, + "ts": 658972019368.469, "dur": 30.136, + "args": { + "External id": 34210,"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": 4183437, "tid": 31318, + "ts": 658972019375.310, "dur": 5.207, + "args": { + "External id": 34211,"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": 4183437, "tid": 31318, + "ts": 658972019382.074, "dur": 16.029, + "args": { + "External id": 34212,"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": 4183437, "tid": 31318, + "ts": 658972019403.467, "dur": 2.592, + "args": { + "External id": 34213,"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": 4183437, "tid": 31318, + "ts": 658972019404.921, "dur": 1.000, + "args": { + "External id": 34214,"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": 4183437, "tid": 31318, + "ts": 658972019412.127, "dur": 2.161, + "args": { + "External id": 34215,"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": 4183437, "tid": 31318, + "ts": 658972019413.135, "dur": 1.011, + "args": { + "External id": 34216,"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": 4183437, "tid": 31318, + "ts": 658972019433.041, "dur": 14.352, + "args": { + "External id": 34217,"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": 4183437, "tid": 31318, + "ts": 658972019463.487, "dur": 8.354, + "args": { + "External id": 34218,"Record function id": 0, "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972019465.743, "dur": 5.323, + "args": { + "External id": 34219,"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": 4183437, "tid": 31318, + "ts": 658972019467.631, "dur": 2.536, + "args": { + "External id": 34220,"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": 4183437, "tid": 31318, + "ts": 658972019468.574, "dur": 1.511, + "args": { + "External id": 34221,"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": 4183437, "tid": 31318, + "ts": 658972019475.461, "dur": 5.456, + "args": { + "External id": 34222,"Record function id": 0, "Sequence number": 459998, "Fwd thread id": 1, "Ev Idx": 941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972019476.353, "dur": 1.244, + "args": { + "External id": 34223,"Sequence number": 459998, "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": 4183437, "tid": 31318, "ts": 658972019476.353, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972019485.030, "dur": 444.661, + "args": { + "External id": 34224,"Record function id": 0, "Sequence number": 459997, "Fwd thread id": 1, "Ev Idx": 943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972019486.453, "dur": 432.020, + "args": { + "External id": 34225,"Sequence number": 459997, "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": 4183437, "tid": 31318, "ts": 658972019486.453, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972019517.191, "dur": 8.378, + "args": { + "External id": 34226,"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": 4183437, "tid": 31318, + "ts": 658972019522.253, "dur": 3.037, + "args": { + "External id": 34227,"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": 4183437, "tid": 31318, + "ts": 658972019528.786, "dur": 5.044, + "args": { + "External id": 34228,"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": 4183437, "tid": 31318, + "ts": 658972019530.087, "dur": 3.139, + "args": { + "External id": 34229,"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": 4183437, "tid": 31318, + "ts": 658972019532.483, "dur": 0.615, + "args": { + "External id": 34230,"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": 4183437, "tid": 31318, + "ts": 658972019537.207, "dur": 81.187, + "args": { + "External id": 34231,"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": 4183437, "tid": 31318, + "ts": 658972019538.185, "dur": 6.441, + "args": { + "External id": 34232,"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": 4183437, "tid": 31318, + "ts": 658972019540.279, "dur": 3.820, + "args": { + "External id": 34233,"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": 4183437, "tid": 31318, + "ts": 658972019541.839, "dur": 2.138, + "args": { + "External id": 34234,"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": 4183437, "tid": 31318, + "ts": 658972019545.847, "dur": 71.971, + "args": { + "External id": 34235,"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": 4183437, "tid": 31318, + "ts": 658972019546.960, "dur": 70.251, + "args": { + "External id": 34236,"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": 4183437, "tid": 31318, + "ts": 658972019622.218, "dur": 3.340, + "args": { + "External id": 34237,"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": 4183437, "tid": 31318, + "ts": 658972019623.802, "dur": 1.633, + "args": { + "External id": 34238,"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": 4183437, "tid": 31318, + "ts": 658972019706.021, "dur": 6.730, + "args": { + "External id": 34239,"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": 4183437, "tid": 31318, + "ts": 658972019714.027, "dur": 2.116, + "args": { + "External id": 34240,"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": 4183437, "tid": 31318, + "ts": 658972019717.042, "dur": 1.616, + "args": { + "External id": 34241,"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": 4183437, "tid": 31318, + "ts": 658972019754.609, "dur": 2.740, + "args": { + "External id": 34242,"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": 4183437, "tid": 31318, + "ts": 658972019755.569, "dur": 1.618, + "args": { + "External id": 34243,"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": 4183437, "tid": 31318, + "ts": 658972019780.542, "dur": 118.680, + "args": { + "External id": 34244,"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": 4183437, "tid": 31318, + "ts": 658972019785.908, "dur": 6.280, + "args": { + "External id": 34245,"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": 4183437, "tid": 31318, + "ts": 658972019790.222, "dur": 0.986, + "args": { + "External id": 34246,"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": 4183437, "tid": 31318, + "ts": 658972019793.901, "dur": 7.884, + "args": { + "External id": 34247,"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": 4183437, "tid": 31318, + "ts": 658972019798.616, "dur": 2.475, + "args": { + "External id": 34248,"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": 4183437, "tid": 31318, + "ts": 658972019803.136, "dur": 3.098, + "args": { + "External id": 34249,"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": 4183437, "tid": 31318, + "ts": 658972019805.355, "dur": 0.499, + "args": { + "External id": 34250,"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": 4183437, "tid": 31318, + "ts": 658972019807.201, "dur": 2.487, + "args": { + "External id": 34251,"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": 4183437, "tid": 31318, + "ts": 658972019808.796, "dur": 0.404, + "args": { + "External id": 34252,"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": 4183437, "tid": 31318, + "ts": 658972019813.471, "dur": 3.190, + "args": { + "External id": 34253,"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": 4183437, "tid": 31318, + "ts": 658972019815.648, "dur": 0.703, + "args": { + "External id": 34254,"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": 4183437, "tid": 31318, + "ts": 658972019817.834, "dur": 6.168, + "args": { + "External id": 34255,"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": 4183437, "tid": 31318, + "ts": 658972019821.688, "dur": 2.117, + "args": { + "External id": 34256,"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": 4183437, "tid": 31318, + "ts": 658972019825.094, "dur": 2.924, + "args": { + "External id": 34257,"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": 4183437, "tid": 31318, + "ts": 658972019827.322, "dur": 0.284, + "args": { + "External id": 34258,"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": 4183437, "tid": 31318, + "ts": 658972019830.227, "dur": 4.323, + "args": { + "External id": 34259,"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": 4183437, "tid": 31318, + "ts": 658972019831.546, "dur": 2.895, + "args": { + "External id": 34260,"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": 4183437, "tid": 31318, + "ts": 658972019836.160, "dur": 49.353, + "args": { + "External id": 34261,"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": 4183437, "tid": 31318, + "ts": 658972019887.536, "dur": 3.036, + "args": { + "External id": 34262,"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": 4183437, "tid": 31318, + "ts": 658972019891.541, "dur": 3.206, + "args": { + "External id": 34263,"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": 4183437, "tid": 31318, + "ts": 658972019893.619, "dur": 0.520, + "args": { + "External id": 34264,"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": 4183437, "tid": 31318, + "ts": 658972019897.454, "dur": 0.804, + "args": { + "External id": 34265,"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": 4183437, "tid": 31318, + "ts": 658972019941.051, "dur": 8.858, + "args": { + "External id": 34266,"Record function id": 0, "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972019943.538, "dur": 5.654, + "args": { + "External id": 34267,"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": 4183437, "tid": 31318, + "ts": 658972019945.373, "dur": 2.853, + "args": { + "External id": 34268,"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": 4183437, "tid": 31318, + "ts": 658972019946.272, "dur": 1.873, + "args": { + "External id": 34269,"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": 4183437, "tid": 31318, + "ts": 658972019953.873, "dur": 6.775, + "args": { + "External id": 34270,"Record function id": 0, "Sequence number": 459996, "Fwd thread id": 1, "Ev Idx": 989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972019955.221, "dur": 3.589, + "args": { + "External id": 34271,"Sequence number": 459996, "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": 4183437, "tid": 31318, "ts": 658972019955.221, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972019956.674, "dur": 1.946, + "args": { + "External id": 34272,"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": 4183437, "tid": 31318, + "ts": 658972019957.544, "dur": 0.924, + "args": { + "External id": 34273,"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": 4183437, "tid": 31318, + "ts": 658972019964.318, "dur": 100.154, + "args": { + "External id": 34274,"Record function id": 0, "Sequence number": 459995, "Fwd thread id": 1, "Ev Idx": 993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972019965.052, "dur": 93.535, + "args": { + "External id": 34275,"Sequence number": 459995, "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": 4183437, "tid": 31318, "ts": 658972019965.052, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972019967.835, "dur": 5.084, + "args": { + "External id": 34276,"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": 4183437, "tid": 31318, + "ts": 658972019968.853, "dur": 3.571, + "args": { + "External id": 34277,"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": 4183437, "tid": 31318, + "ts": 658972019971.714, "dur": 0.549, + "args": { + "External id": 34278,"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": 4183437, "tid": 31318, + "ts": 658972019973.738, "dur": 33.442, + "args": { + "External id": 34279,"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": 4183437, "tid": 31318, + "ts": 658972020008.265, "dur": 4.145, + "args": { + "External id": 34280,"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": 4183437, "tid": 31318, + "ts": 658972020009.055, "dur": 2.732, + "args": { + "External id": 34281,"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": 4183437, "tid": 31318, + "ts": 658972020010.771, "dur": 0.883, + "args": { + "External id": 34282,"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": 4183437, "tid": 31318, + "ts": 658972020013.781, "dur": 4.585, + "args": { + "External id": 34283,"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": 4183437, "tid": 31318, + "ts": 658972020016.220, "dur": 1.735, + "args": { + "External id": 34284,"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": 4183437, "tid": 31318, + "ts": 658972020017.470, "dur": 0.397, + "args": { + "External id": 34285,"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": 4183437, "tid": 31318, + "ts": 658972020019.004, "dur": 38.793, + "args": { + "External id": 34286,"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": 4183437, "tid": 31318, + "ts": 658972020068.800, "dur": 6.697, + "args": { + "External id": 34287,"Record function id": 0, "Sequence number": 459994, "Fwd thread id": 1, "Ev Idx": 1006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020069.611, "dur": 4.505, + "args": { + "External id": 34288,"Sequence number": 459994, "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": 4183437, "tid": 31318, "ts": 658972020069.611, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972020071.457, "dur": 2.506, + "args": { + "External id": 34289,"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": 4183437, "tid": 31318, + "ts": 658972020072.498, "dur": 1.315, + "args": { + "External id": 34290,"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": 4183437, "tid": 31318, + "ts": 658972020078.993, "dur": 9.054, + "args": { + "External id": 34291,"Record function id": 0, "Sequence number": 459993, "Fwd thread id": 1, "Ev Idx": 1010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020079.823, "dur": 6.053, + "args": { + "External id": 34292,"Sequence number": 459993, "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": 4183437, "tid": 31318, "ts": 658972020079.823, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972020080.386, "dur": 5.270, + "args": { + "External id": 34293,"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": 4183437, "tid": 31318, + "ts": 658972020082.651, "dur": 2.537, + "args": { + "External id": 34294,"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": 4183437, "tid": 31318, + "ts": 658972020084.509, "dur": 0.548, + "args": { + "External id": 34295,"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": 4183437, "tid": 31318, + "ts": 658972020092.277, "dur": 5.006, + "args": { + "External id": 34296,"Record function id": 0, "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972020093.673, "dur": 3.094, + "args": { + "External id": 34297,"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": 4183437, "tid": 31318, + "ts": 658972020094.668, "dur": 1.864, + "args": { + "External id": 34298,"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": 4183437, "tid": 31318, + "ts": 658972020095.219, "dur": 1.220, + "args": { + "External id": 34299,"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": 4183437, "tid": 31318, + "ts": 658972020102.521, "dur": 6.451, + "args": { + "External id": 34300,"Record function id": 0, "Sequence number": 459992, "Fwd thread id": 1, "Ev Idx": 1019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020103.520, "dur": 3.400, + "args": { + "External id": 34301,"Sequence number": 459992, "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": 4183437, "tid": 31318, "ts": 658972020103.520, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972020104.784, "dur": 1.966, + "args": { + "External id": 34302,"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": 4183437, "tid": 31318, + "ts": 658972020105.985, "dur": 0.624, + "args": { + "External id": 34303,"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": 4183437, "tid": 31318, + "ts": 658972020113.490, "dur": 103.540, + "args": { + "External id": 34304,"Record function id": 0, "Sequence number": 459991, "Fwd thread id": 1, "Ev Idx": 1023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020132.013, "dur": 77.927, + "args": { + "External id": 34305,"Sequence number": 459991, "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": 4183437, "tid": 31318, "ts": 658972020132.013, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972020134.124, "dur": 2.718, + "args": { + "External id": 34306,"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": 4183437, "tid": 31318, + "ts": 658972020134.545, "dur": 1.846, + "args": { + "External id": 34307,"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": 4183437, "tid": 31318, + "ts": 658972020135.928, "dur": 0.360, + "args": { + "External id": 34308,"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": 4183437, "tid": 31318, + "ts": 658972020137.350, "dur": 26.070, + "args": { + "External id": 34309,"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": 4183437, "tid": 31318, + "ts": 658972020165.995, "dur": 4.335, + "args": { + "External id": 34310,"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": 4183437, "tid": 31318, + "ts": 658972020166.484, "dur": 3.204, + "args": { + "External id": 34311,"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": 4183437, "tid": 31318, + "ts": 658972020167.955, "dur": 1.598, + "args": { + "External id": 34312,"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": 4183437, "tid": 31318, + "ts": 658972020171.277, "dur": 5.103, + "args": { + "External id": 34313,"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": 4183437, "tid": 31318, + "ts": 658972020172.451, "dur": 3.317, + "args": { + "External id": 34314,"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": 4183437, "tid": 31318, + "ts": 658972020173.921, "dur": 1.774, + "args": { + "External id": 34315,"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": 4183437, "tid": 31318, + "ts": 658972020178.343, "dur": 30.671, + "args": { + "External id": 34316,"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": 4183437, "tid": 31318, + "ts": 658972020221.277, "dur": 38.087, + "args": { + "External id": 34317,"Record function id": 0, "Sequence number": 459990, "Fwd thread id": 1, "Ev Idx": 1036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020222.072, "dur": 3.976, + "args": { + "External id": 34318,"Sequence number": 459990, "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": 4183437, "tid": 31318, "ts": 658972020222.072, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972020223.842, "dur": 2.060, + "args": { + "External id": 34319,"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": 4183437, "tid": 31318, + "ts": 658972020224.815, "dur": 0.985, + "args": { + "External id": 34320,"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": 4183437, "tid": 31318, + "ts": 658972020228.554, "dur": 28.049, + "args": { + "External id": 34321,"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": 4183437, "tid": 31318, + "ts": 658972020281.646, "dur": 11.840, + "args": { + "External id": 34322,"Record function id": 0, "Sequence number": 459989, "Fwd thread id": 1, "Ev Idx": 1041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020283.454, "dur": 7.407, + "args": { + "External id": 34323,"Sequence number": 459989, "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": 4183437, "tid": 31318, "ts": 658972020283.454, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972020284.377, "dur": 6.267, + "args": { + "External id": 34324,"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": 4183437, "tid": 31318, + "ts": 658972020285.266, "dur": 4.365, + "args": { + "External id": 34325,"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": 4183437, "tid": 31318, + "ts": 658972020288.800, "dur": 0.568, + "args": { + "External id": 34326,"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": 4183437, "tid": 31318, + "ts": 658972020298.548, "dur": 5.710, + "args": { + "External id": 34327,"Record function id": 0, "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972020300.375, "dur": 3.356, + "args": { + "External id": 34328,"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": 4183437, "tid": 31318, + "ts": 658972020301.520, "dur": 1.935, + "args": { + "External id": 34329,"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": 4183437, "tid": 31318, + "ts": 658972020301.997, "dur": 1.349, + "args": { + "External id": 34330,"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": 4183437, "tid": 31318, + "ts": 658972020308.277, "dur": 441.444, + "args": { + "External id": 34331,"Record function id": 0, "Sequence number": 459988, "Fwd thread id": 1, "Ev Idx": 1050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972020309.713, "dur": 400.255, + "args": { + "External id": 34332,"Sequence number": 459988, "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": 4183437, "tid": 31318, "ts": 658972020309.713, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183437, "tid": 31318, + "ts": 658972020334.863, "dur": 34.905, + "args": { + "External id": 34333,"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": 4183437, "tid": 31318, + "ts": 658972020336.142, "dur": 33.427, + "args": { + "External id": 34334,"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": 4183437, "tid": 31318, + "ts": 658972020338.924, "dur": 6.500, + "args": { + "External id": 34335,"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": 4183437, "tid": 31318, + "ts": 658972020341.506, "dur": 3.328, + "args": { + "External id": 34336,"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": 4183437, "tid": 31318, + "ts": 658972020346.517, "dur": 22.561, + "args": { + "External id": 34337,"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": 4183437, "tid": 31318, + "ts": 658972020379.996, "dur": 2.608, + "args": { + "External id": 34338,"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": 4183437, "tid": 31318, + "ts": 658972020381.127, "dur": 1.324, + "args": { + "External id": 34339,"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": 4183437, "tid": 31318, + "ts": 658972020387.712, "dur": 3.293, + "args": { + "External id": 34340,"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": 4183437, "tid": 31318, + "ts": 658972020388.457, "dur": 2.443, + "args": { + "External id": 34341,"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": 4183437, "tid": 31318, + "ts": 658972020403.372, "dur": 1.951, + "args": { + "External id": 34342,"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": 4183437, "tid": 31318, + "ts": 658972020415.339, "dur": 2.980, + "args": { + "External id": 34343,"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": 4183437, "tid": 31318, + "ts": 658972020566.766, "dur": 2.029, + "args": { + "External id": 34344,"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": 4183437, "tid": 31318, + "ts": 658972020572.899, "dur": 29.275, + "args": { + "External id": 34345,"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": 4183437, "tid": 31318, + "ts": 658972020581.319, "dur": 0.950, + "args": { + "External id": 34346,"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": 4183437, "tid": 31318, + "ts": 658972020607.261, "dur": 25.587, + "args": { + "External id": 34347,"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": 4183437, "tid": 31318, + "ts": 658972020608.815, "dur": 23.829, + "args": { + "External id": 34348,"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": 4183437, "tid": 31318, + "ts": 658972020612.788, "dur": 4.144, + "args": { + "External id": 34349,"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": 4183437, "tid": 31318, + "ts": 658972020618.006, "dur": 14.061, + "args": { + "External id": 34350,"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": 4183437, "tid": 31318, + "ts": 658972020637.263, "dur": 2.088, + "args": { + "External id": 34351,"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": 4183437, "tid": 31318, + "ts": 658972020638.222, "dur": 0.997, + "args": { + "External id": 34352,"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": 4183437, "tid": 31318, + "ts": 658972020646.714, "dur": 2.248, + "args": { + "External id": 34353,"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": 4183437, "tid": 31318, + "ts": 658972020647.749, "dur": 1.103, + "args": { + "External id": 34354,"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": 4183437, "tid": 31318, + "ts": 658972020651.306, "dur": 47.297, + "args": { + "External id": 34355,"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": 4183437, "tid": 31318, + "ts": 658972020652.169, "dur": 45.827, + "args": { + "External id": 34356,"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": 4183437, "tid": 31318, + "ts": 658972020725.873, "dur": 22.265, + "args": { + "External id": 34357,"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": 4183437, "tid": 31318, + "ts": 658972020762.684, "dur": 9.894, + "args": { + "External id": 34358,"Record function id": 0, "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972020764.790, "dur": 7.168, + "args": { + "External id": 34359,"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": 4183437, "tid": 31318, + "ts": 658972020766.527, "dur": 4.464, + "args": { + "External id": 34360,"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": 4183437, "tid": 31318, + "ts": 658972020769.161, "dur": 1.709, + "args": { + "External id": 34361,"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": 4183437, "tid": 31318, + "ts": 658972020776.718, "dur": 8.266, + "args": { + "External id": 34362,"Record function id": 0, "Sequence number": 459987, "Fwd thread id": 1, "Ev Idx": 1081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020777.931, "dur": 4.867, + "args": { + "External id": 34363,"Sequence number": 459987, "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": 4183437, "tid": 31318, "ts": 658972020777.931, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972020779.945, "dur": 2.686, + "args": { + "External id": 34364,"Record 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": 4183437, "tid": 31318, + "ts": 658972020781.024, "dur": 1.451, + "args": { + "External id": 34365,"Record 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": 4183437, "tid": 31318, + "ts": 658972020788.318, "dur": 132.996, + "args": { + "External id": 34366,"Record function id": 0, "Sequence number": 459986, "Fwd thread id": 1, "Ev Idx": 1085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020789.020, "dur": 126.633, + "args": { + "External id": 34367,"Sequence number": 459986, "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": 4183437, "tid": 31318, "ts": 658972020789.020, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972020792.063, "dur": 6.040, + "args": { + "External id": 34368,"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": 4183437, "tid": 31318, + "ts": 658972020793.385, "dur": 4.163, + "args": { + "External id": 34369,"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": 4183437, "tid": 31318, + "ts": 658972020796.176, "dur": 1.205, + "args": { + "External id": 34370,"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": 4183437, "tid": 31318, + "ts": 658972020799.180, "dur": 66.622, + "args": { + "External id": 34371,"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": 4183437, "tid": 31318, + "ts": 658972020866.803, "dur": 4.887, + "args": { + "External id": 34372,"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": 4183437, "tid": 31318, + "ts": 658972020867.551, "dur": 3.551, + "args": { + "External id": 34373,"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": 4183437, "tid": 31318, + "ts": 658972020869.334, "dur": 1.617, + "args": { + "External id": 34374,"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": 4183437, "tid": 31318, + "ts": 658972020873.271, "dur": 4.649, + "args": { + "External id": 34375,"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": 4183437, "tid": 31318, + "ts": 658972020875.600, "dur": 1.921, + "args": { + "External id": 34376,"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": 4183437, "tid": 31318, + "ts": 658972020877.079, "dur": 0.379, + "args": { + "External id": 34377,"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": 4183437, "tid": 31318, + "ts": 658972020878.635, "dur": 36.377, + "args": { + "External id": 34378,"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": 4183437, "tid": 31318, + "ts": 658972020926.091, "dur": 8.156, + "args": { + "External id": 34379,"Record function id": 0, "Sequence number": 459985, "Fwd thread id": 1, "Ev Idx": 1098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020927.162, "dur": 5.340, + "args": { + "External id": 34380,"Sequence number": 459985, "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": 4183437, "tid": 31318, "ts": 658972020927.162, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972020928.679, "dur": 3.670, + "args": { + "External id": 34381,"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": 4183437, "tid": 31318, + "ts": 658972020929.824, "dur": 2.358, + "args": { + "External id": 34382,"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": 4183437, "tid": 31318, + "ts": 658972020937.514, "dur": 7.858, + "args": { + "External id": 34383,"Record function id": 0, "Sequence number": 459984, "Fwd thread id": 1, "Ev Idx": 1102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020938.142, "dur": 5.230, + "args": { + "External id": 34384,"Sequence number": 459984, "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": 4183437, "tid": 31318, "ts": 658972020938.142, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972020938.848, "dur": 4.327, + "args": { + "External id": 34385,"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": 4183437, "tid": 31318, + "ts": 658972020940.449, "dur": 2.239, + "args": { + "External id": 34386,"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": 4183437, "tid": 31318, + "ts": 658972020942.162, "dur": 0.381, + "args": { + "External id": 34387,"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": 4183437, "tid": 31318, + "ts": 658972020949.438, "dur": 4.488, + "args": { + "External id": 34388,"Record function id": 0, "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972020950.945, "dur": 2.470, + "args": { + "External id": 34389,"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": 4183437, "tid": 31318, + "ts": 658972020951.788, "dur": 1.380, + "args": { + "External id": 34390,"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": 4183437, "tid": 31318, + "ts": 658972020952.203, "dur": 0.854, + "args": { + "External id": 34391,"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": 4183437, "tid": 31318, + "ts": 658972020959.159, "dur": 5.387, + "args": { + "External id": 34392,"Record function id": 0, "Sequence number": 459983, "Fwd thread id": 1, "Ev Idx": 1111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972020959.748, "dur": 3.194, + "args": { + "External id": 34393,"Sequence number": 459983, "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": 4183437, "tid": 31318, "ts": 658972020959.748, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972020960.862, "dur": 1.944, + "args": { + "External id": 34394,"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": 4183437, "tid": 31318, + "ts": 658972020961.527, "dur": 1.143, + "args": { + "External id": 34395,"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": 4183437, "tid": 31318, + "ts": 658972020968.414, "dur": 343.494, + "args": { + "External id": 34396,"Record function id": 0, "Sequence number": 459982, "Fwd thread id": 1, "Ev Idx": 1115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183437, "tid": 31318, + "ts": 658972020969.875, "dur": 324.774, + "args": { + "External id": 34397,"Sequence number": 459982, "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": 4183437, "tid": 31318, "ts": 658972020969.875, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 31318, + "ts": 658972020982.976, "dur": 6.852, + "args": { + "External id": 34398,"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": 4183437, "tid": 31318, + "ts": 658972020985.580, "dur": 3.739, + "args": { + "External id": 34399,"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": 4183437, "tid": 31318, + "ts": 658972020991.691, "dur": 5.280, + "args": { + "External id": 34400,"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": 4183437, "tid": 31318, + "ts": 658972020993.572, "dur": 3.183, + "args": { + "External id": 34401,"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": 4183437, "tid": 31318, + "ts": 658972021005.384, "dur": 4.774, + "args": { + "External id": 34402,"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": 4183437, "tid": 31318, + "ts": 658972021008.454, "dur": 1.502, + "args": { + "External id": 34403,"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": 4183437, "tid": 31318, + "ts": 658972021036.852, "dur": 210.725, + "args": { + "External id": 34404,"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": 4183437, "tid": 31318, + "ts": 658972021111.990, "dur": 4.512, + "args": { + "External id": 34405,"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": 4183437, "tid": 31318, + "ts": 658972021118.358, "dur": 3.787, + "args": { + "External id": 34406,"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": 4183437, "tid": 31318, + "ts": 658972021259.460, "dur": 23.475, + "args": { + "External id": 34407,"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": 4183437, "tid": 31318, + "ts": 658972021288.380, "dur": 0.958, + "args": { + "External id": 34408,"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": 4183437, "tid": 31318, + "ts": 658972021291.435, "dur": 0.560, + "args": { + "External id": 34409,"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": 4183437, "tid": 31318, + "ts": 658972021321.777, "dur": 222.464, + "args": { + "External id": 34410,"Record function id": 0, "Sequence number": 459981, "Fwd thread id": 1, "Ev Idx": 1129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972021323.704, "dur": 214.165, + "args": { + "External id": 34411,"Sequence number": 459981, "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": 4183437, "tid": 31318, "ts": 658972021323.704, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183437, "tid": 31318, + "ts": 658972021343.643, "dur": 48.643, + "args": { + "External id": 34412,"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": 4183437, "tid": 31318, + "ts": 658972021346.991, "dur": 3.768, + "args": { + "External id": 34413,"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": 4183437, "tid": 31318, + "ts": 658972021352.127, "dur": 39.588, + "args": { + "External id": 34414,"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": 4183437, "tid": 31318, + "ts": 658972021402.209, "dur": 5.708, + "args": { + "External id": 34415,"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": 4183437, "tid": 31318, + "ts": 658972021404.001, "dur": 3.636, + "args": { + "External id": 34416,"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": 4183437, "tid": 31318, + "ts": 658972021551.249, "dur": 198.480, + "args": { + "External id": 34417,"Record function id": 0, "Sequence number": 459980, "Fwd thread id": 1, "Ev Idx": 1136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972021553.194, "dur": 188.614, + "args": { + "External id": 34418,"Sequence number": 459980, "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": 4183437, "tid": 31318, "ts": 658972021553.194, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183437, "tid": 31318, + "ts": 658972021564.257, "dur": 34.078, + "args": { + "External id": 34419,"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": 4183437, "tid": 31318, + "ts": 658972021566.577, "dur": 3.023, + "args": { + "External id": 34420,"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": 4183437, "tid": 31318, + "ts": 658972021574.005, "dur": 23.818, + "args": { + "External id": 34421,"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": 4183437, "tid": 31318, + "ts": 658972021605.721, "dur": 4.846, + "args": { + "External id": 34422,"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": 4183437, "tid": 31318, + "ts": 658972021608.121, "dur": 2.143, + "args": { + "External id": 34423,"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": 4183437, "tid": 31318, + "ts": 658972021758.869, "dur": 16.725, + "args": { + "External id": 34424,"Record function id": 0, "Sequence number": 459979, "Fwd thread id": 1, "Ev Idx": 1143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972021760.489, "dur": 12.414, + "args": { + "External id": 34425,"Sequence number": 459979, "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": 4183437, "tid": 31318, "ts": 658972021760.489, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972021763.413, "dur": 9.186, + "args": { + "External id": 34426,"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": 4183437, "tid": 31318, + "ts": 658972021765.262, "dur": 7.127, + "args": { + "External id": 34427,"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": 4183437, "tid": 31318, + "ts": 658972021779.263, "dur": 6.553, + "args": { + "External id": 34428,"Record function id": 0, "Sequence number": 459978, "Fwd thread id": 1, "Ev Idx": 1147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972021780.255, "dur": 3.706, + "args": { + "External id": 34429,"Sequence number": 459978, "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": 4183437, "tid": 31318, "ts": 658972021780.255, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972021781.680, "dur": 2.123, + "args": { + "External id": 34430,"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": 4183437, "tid": 31318, + "ts": 658972021782.713, "dur": 0.972, + "args": { + "External id": 34431,"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": 4183437, "tid": 31318, + "ts": 658972021788.956, "dur": 7.085, + "args": { + "External id": 34432,"Record function id": 0, "Sequence number": 459977, "Fwd thread id": 1, "Ev Idx": 1151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972021789.863, "dur": 4.170, + "args": { + "External id": 34433,"Sequence number": 459977, "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": 4183437, "tid": 31318, "ts": 658972021789.863, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972021791.442, "dur": 2.439, + "args": { + "External id": 34434,"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": 4183437, "tid": 31318, + "ts": 658972021792.789, "dur": 0.994, + "args": { + "External id": 34435,"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": 4183437, "tid": 31318, + "ts": 658972021799.736, "dur": 7.724, + "args": { + "External id": 34436,"Record function id": 0, "Sequence number": 459976, "Fwd thread id": 1, "Ev Idx": 1155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972021801.114, "dur": 4.317, + "args": { + "External id": 34437,"Sequence number": 459976, "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": 4183437, "tid": 31318, "ts": 658972021801.114, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972021802.664, "dur": 2.603, + "args": { + "External id": 34438,"Record 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": 4183437, "tid": 31318, + "ts": 658972021804.232, "dur": 0.922, + "args": { + "External id": 34439,"Record 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": 4183437, "tid": 31318, + "ts": 658972021811.094, "dur": 151.937, + "args": { + "External id": 34440,"Record function id": 0, "Sequence number": 459975, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972021811.996, "dur": 144.222, + "args": { + "External id": 34441,"Sequence number": 459975, "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": 4183437, "tid": 31318, "ts": 658972021811.996, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972021816.187, "dur": 6.789, + "args": { + "External id": 34442,"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": 4183437, "tid": 31318, + "ts": 658972021818.086, "dur": 4.310, + "args": { + "External id": 34443,"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": 4183437, "tid": 31318, + "ts": 658972021820.652, "dur": 1.442, + "args": { + "External id": 34444,"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": 4183437, "tid": 31318, + "ts": 658972021824.533, "dur": 78.352, + "args": { + "External id": 34445,"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": 4183437, "tid": 31318, + "ts": 658972021904.312, "dur": 5.390, + "args": { + "External id": 34446,"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": 4183437, "tid": 31318, + "ts": 658972021905.443, "dur": 3.442, + "args": { + "External id": 34447,"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": 4183437, "tid": 31318, + "ts": 658972021907.652, "dur": 1.072, + "args": { + "External id": 34448,"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": 4183437, "tid": 31318, + "ts": 658972021911.413, "dur": 3.860, + "args": { + "External id": 34449,"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": 4183437, "tid": 31318, + "ts": 658972021912.616, "dur": 2.163, + "args": { + "External id": 34450,"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": 4183437, "tid": 31318, + "ts": 658972021914.093, "dur": 0.620, + "args": { + "External id": 34451,"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": 4183437, "tid": 31318, + "ts": 658972021916.097, "dur": 39.333, + "args": { + "External id": 34452,"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": 4183437, "tid": 31318, + "ts": 658972021969.760, "dur": 7.549, + "args": { + "External id": 34453,"Record function id": 0, "Sequence number": 459974, "Fwd thread id": 1, "Ev Idx": 1172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972021970.647, "dur": 4.755, + "args": { + "External id": 34454,"Sequence number": 459974, "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": 4183437, "tid": 31318, "ts": 658972021970.647, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972021973.028, "dur": 2.239, + "args": { + "External id": 34455,"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": 4183437, "tid": 31318, + "ts": 658972021974.053, "dur": 1.116, + "args": { + "External id": 34456,"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": 4183437, "tid": 31318, + "ts": 658972021980.794, "dur": 9.643, + "args": { + "External id": 34457,"Record function id": 0, "Sequence number": 459973, "Fwd thread id": 1, "Ev Idx": 1176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972021982.036, "dur": 6.465, + "args": { + "External id": 34458,"Sequence number": 459973, "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": 4183437, "tid": 31318, "ts": 658972021982.036, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972021983.191, "dur": 5.069, + "args": { + "External id": 34459,"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": 4183437, "tid": 31318, + "ts": 658972021984.330, "dur": 3.408, + "args": { + "External id": 34460,"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": 4183437, "tid": 31318, + "ts": 658972021986.724, "dur": 0.859, + "args": { + "External id": 34461,"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": 4183437, "tid": 31318, + "ts": 658972021996.030, "dur": 9.526, + "args": { + "External id": 34462,"Record function id": 0, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972021997.894, "dur": 6.980, + "args": { + "External id": 34463,"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": 4183437, "tid": 31318, + "ts": 658972022000.530, "dur": 4.014, + "args": { + "External id": 34464,"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": 4183437, "tid": 31318, + "ts": 658972022001.950, "dur": 2.474, + "args": { + "External id": 34465,"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": 4183437, "tid": 31318, + "ts": 658972022009.085, "dur": 7.565, + "args": { + "External id": 34466,"Record function id": 0, "Sequence number": 459972, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972022010.250, "dur": 4.661, + "args": { + "External id": 34467,"Sequence number": 459972, "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": 4183437, "tid": 31318, "ts": 658972022010.250, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972022012.215, "dur": 2.546, + "args": { + "External id": 34468,"Record 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": 4183437, "tid": 31318, + "ts": 658972022013.692, "dur": 0.917, + "args": { + "External id": 34469,"Record 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": 4183437, "tid": 31318, + "ts": 658972022020.116, "dur": 92.296, + "args": { + "External id": 34470,"Record function id": 0, "Sequence number": 459971, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972022021.216, "dur": 85.875, + "args": { + "External id": 34471,"Sequence number": 459971, "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": 4183437, "tid": 31318, "ts": 658972022021.216, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972022022.976, "dur": 3.688, + "args": { + "External id": 34472,"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": 4183437, "tid": 31318, + "ts": 658972022023.712, "dur": 2.506, + "args": { + "External id": 34473,"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": 4183437, "tid": 31318, + "ts": 658972022025.565, "dur": 0.509, + "args": { + "External id": 34474,"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": 4183437, "tid": 31318, + "ts": 658972022027.673, "dur": 33.383, + "args": { + "External id": 34475,"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": 4183437, "tid": 31318, + "ts": 658972022062.187, "dur": 4.362, + "args": { + "External id": 34476,"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": 4183437, "tid": 31318, + "ts": 658972022062.971, "dur": 2.965, + "args": { + "External id": 34477,"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": 4183437, "tid": 31318, + "ts": 658972022065.072, "dur": 0.746, + "args": { + "External id": 34478,"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": 4183437, "tid": 31318, + "ts": 658972022067.654, "dur": 6.028, + "args": { + "External id": 34479,"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": 4183437, "tid": 31318, + "ts": 658972022068.896, "dur": 4.337, + "args": { + "External id": 34480,"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": 4183437, "tid": 31318, + "ts": 658972022070.965, "dur": 2.142, + "args": { + "External id": 34481,"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": 4183437, "tid": 31318, + "ts": 658972022074.474, "dur": 31.864, + "args": { + "External id": 34482,"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": 4183437, "tid": 31318, + "ts": 658972022116.762, "dur": 32.487, + "args": { + "External id": 34483,"Record function id": 0, "Sequence number": 459970, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972022118.011, "dur": 4.687, + "args": { + "External id": 34484,"Sequence number": 459970, "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": 4183437, "tid": 31318, "ts": 658972022118.011, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972022119.756, "dur": 2.786, + "args": { + "External id": 34485,"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": 4183437, "tid": 31318, + "ts": 658972022121.147, "dur": 1.254, + "args": { + "External id": 34486,"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": 4183437, "tid": 31318, + "ts": 658972022125.395, "dur": 21.654, + "args": { + "External id": 34487,"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": 4183437, "tid": 31318, + "ts": 658972022153.101, "dur": 9.385, + "args": { + "External id": 34488,"Record function id": 0, "Sequence number": 459969, "Fwd thread id": 1, "Ev Idx": 1207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972022154.377, "dur": 6.004, + "args": { + "External id": 34489,"Sequence number": 459969, "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": 4183437, "tid": 31318, "ts": 658972022154.377, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972022155.622, "dur": 4.560, + "args": { + "External id": 34490,"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": 4183437, "tid": 31318, + "ts": 658972022156.596, "dur": 3.028, + "args": { + "External id": 34491,"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": 4183437, "tid": 31318, + "ts": 658972022158.643, "dur": 0.859, + "args": { + "External id": 34492,"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": 4183437, "tid": 31318, + "ts": 658972022166.527, "dur": 5.691, + "args": { + "External id": 34493,"Record function id": 0, "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972022168.113, "dur": 3.572, + "args": { + "External id": 34494,"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": 4183437, "tid": 31318, + "ts": 658972022169.213, "dur": 2.181, + "args": { + "External id": 34495,"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": 4183437, "tid": 31318, + "ts": 658972022170.064, "dur": 1.237, + "args": { + "External id": 34496,"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": 4183437, "tid": 31318, + "ts": 658972022175.615, "dur": 9.096, + "args": { + "External id": 34497,"Record function id": 0, "Sequence number": 459968, "Fwd thread id": 1, "Ev Idx": 1216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972022176.953, "dur": 6.341, + "args": { + "External id": 34498,"Sequence number": 459968, "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": 4183437, "tid": 31318, "ts": 658972022176.953, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972022179.281, "dur": 3.870, + "args": { + "External id": 34499,"Record 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": 4183437, "tid": 31318, + "ts": 658972022182.245, "dur": 0.759, + "args": { + "External id": 34500,"Record 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": 4183437, "tid": 31318, + "ts": 658972022188.062, "dur": 114.021, + "args": { + "External id": 34501,"Record function id": 0, "Sequence number": 459967, "Fwd thread id": 1, "Ev Idx": 1220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972022189.052, "dur": 105.583, + "args": { + "External id": 34502,"Sequence number": 459967, "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": 4183437, "tid": 31318, "ts": 658972022189.052, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972022191.602, "dur": 3.856, + "args": { + "External id": 34503,"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": 4183437, "tid": 31318, + "ts": 658972022192.247, "dur": 2.720, + "args": { + "External id": 34504,"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": 4183437, "tid": 31318, + "ts": 658972022194.413, "dur": 0.447, + "args": { + "External id": 34505,"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": 4183437, "tid": 31318, + "ts": 658972022196.361, "dur": 35.014, + "args": { + "External id": 34506,"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": 4183437, "tid": 31318, + "ts": 658972022232.668, "dur": 5.218, + "args": { + "External id": 34507,"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": 4183437, "tid": 31318, + "ts": 658972022233.415, "dur": 3.805, + "args": { + "External id": 34508,"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": 4183437, "tid": 31318, + "ts": 658972022235.702, "dur": 1.391, + "args": { + "External id": 34509,"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": 4183437, "tid": 31318, + "ts": 658972022239.040, "dur": 4.702, + "args": { + "External id": 34510,"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": 4183437, "tid": 31318, + "ts": 658972022240.803, "dur": 2.506, + "args": { + "External id": 34511,"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": 4183437, "tid": 31318, + "ts": 658972022242.511, "dur": 0.722, + "args": { + "External id": 34512,"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": 4183437, "tid": 31318, + "ts": 658972022244.412, "dur": 48.818, + "args": { + "External id": 34513,"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": 4183437, "tid": 31318, + "ts": 658972022308.468, "dur": 28.764, + "args": { + "External id": 34514,"Record function id": 0, "Sequence number": 459966, "Fwd thread id": 1, "Ev Idx": 1233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972022309.844, "dur": 5.521, + "args": { + "External id": 34515,"Sequence number": 459966, "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": 4183437, "tid": 31318, "ts": 658972022309.844, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972022312.015, "dur": 3.223, + "args": { + "External id": 34516,"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": 4183437, "tid": 31318, + "ts": 658972022313.426, "dur": 1.714, + "args": { + "External id": 34517,"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": 4183437, "tid": 31318, + "ts": 658972022317.862, "dur": 17.176, + "args": { + "External id": 34518,"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": 4183437, "tid": 31318, + "ts": 658972022340.826, "dur": 8.345, + "args": { + "External id": 34519,"Record function id": 0, "Sequence number": 459965, "Fwd thread id": 1, "Ev Idx": 1238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972022341.776, "dur": 5.547, + "args": { + "External id": 34520,"Sequence number": 459965, "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": 4183437, "tid": 31318, "ts": 658972022341.776, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972022342.778, "dur": 4.348, + "args": { + "External id": 34521,"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": 4183437, "tid": 31318, + "ts": 658972022343.843, "dur": 2.723, + "args": { + "External id": 34522,"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": 4183437, "tid": 31318, + "ts": 658972022345.931, "dur": 0.480, + "args": { + "External id": 34523,"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": 4183437, "tid": 31318, + "ts": 658972022353.667, "dur": 6.218, + "args": { + "External id": 34524,"Record function id": 0, "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972022355.439, "dur": 3.942, + "args": { + "External id": 34525,"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": 4183437, "tid": 31318, + "ts": 658972022356.706, "dur": 2.155, + "args": { + "External id": 34526,"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": 4183437, "tid": 31318, + "ts": 658972022357.630, "dur": 1.137, + "args": { + "External id": 34527,"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": 4183437, "tid": 31318, + "ts": 658972022365.875, "dur": 400.544, + "args": { + "External id": 34528,"Record function id": 0, "Sequence number": 459964, "Fwd thread id": 1, "Ev Idx": 1247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972022367.616, "dur": 363.943, + "args": { + "External id": 34529,"Sequence number": 459964, "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": 4183437, "tid": 31318, "ts": 658972022367.616, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972022397.673, "dur": 2.522, + "args": { + "External id": 34530,"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": 4183437, "tid": 31318, + "ts": 658972022398.677, "dur": 1.367, + "args": { + "External id": 34531,"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": 4183437, "tid": 31318, + "ts": 658972022414.253, "dur": 5.844, + "args": { + "External id": 34532,"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": 4183437, "tid": 31318, + "ts": 658972022430.159, "dur": 2.965, + "args": { + "External id": 34533,"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": 4183437, "tid": 31318, + "ts": 658972022578.708, "dur": 1.595, + "args": { + "External id": 34534,"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": 4183437, "tid": 31318, + "ts": 658972022584.389, "dur": 31.540, + "args": { + "External id": 34535,"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": 4183437, "tid": 31318, + "ts": 658972022593.834, "dur": 0.782, + "args": { + "External id": 34536,"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": 4183437, "tid": 31318, + "ts": 658972022621.518, "dur": 29.701, + "args": { + "External id": 34537,"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": 4183437, "tid": 31318, + "ts": 658972022623.546, "dur": 27.482, + "args": { + "External id": 34538,"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": 4183437, "tid": 31318, + "ts": 658972022628.033, "dur": 4.104, + "args": { + "External id": 34539,"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": 4183437, "tid": 31318, + "ts": 658972022633.909, "dur": 16.502, + "args": { + "External id": 34540,"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": 4183437, "tid": 31318, + "ts": 658972022708.338, "dur": 5.014, + "args": { + "External id": 34541,"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": 4183437, "tid": 31318, + "ts": 658972022710.705, "dur": 2.405, + "args": { + "External id": 34542,"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": 4183437, "tid": 31318, + "ts": 658972022721.830, "dur": 2.277, + "args": { + "External id": 34543,"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": 4183437, "tid": 31318, + "ts": 658972022723.091, "dur": 0.931, + "args": { + "External id": 34544,"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": 4183437, "tid": 31318, + "ts": 658972022742.571, "dur": 19.471, + "args": { + "External id": 34545,"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": 4183437, "tid": 31318, + "ts": 658972022778.970, "dur": 9.855, + "args": { + "External id": 34546,"Record function id": 0, "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972022781.672, "dur": 6.446, + "args": { + "External id": 34547,"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": 4183437, "tid": 31318, + "ts": 658972022783.881, "dur": 3.144, + "args": { + "External id": 34548,"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": 4183437, "tid": 31318, + "ts": 658972022785.297, "dur": 1.618, + "args": { + "External id": 34549,"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": 4183437, "tid": 31318, + "ts": 658972022792.757, "dur": 5.701, + "args": { + "External id": 34550,"Record function id": 0, "Sequence number": 459963, "Fwd thread id": 1, "Ev Idx": 1269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972022794.238, "dur": 1.148, + "args": { + "External id": 34551,"Sequence number": 459963, "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": 4183437, "tid": 31318, "ts": 658972022794.238, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972022802.340, "dur": 379.172, + "args": { + "External id": 34552,"Record function id": 0, "Sequence number": 459962, "Fwd thread id": 1, "Ev Idx": 1271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972022804.114, "dur": 367.896, + "args": { + "External id": 34553,"Sequence number": 459962, "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": 4183437, "tid": 31318, "ts": 658972022804.114, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972022835.615, "dur": 8.333, + "args": { + "External id": 34554,"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": 4183437, "tid": 31318, + "ts": 658972022840.615, "dur": 3.082, + "args": { + "External id": 34555,"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": 4183437, "tid": 31318, + "ts": 658972022847.336, "dur": 6.646, + "args": { + "External id": 34556,"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": 4183437, "tid": 31318, + "ts": 658972022849.174, "dur": 4.147, + "args": { + "External id": 34557,"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": 4183437, "tid": 31318, + "ts": 658972022852.243, "dur": 0.914, + "args": { + "External id": 34558,"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": 4183437, "tid": 31318, + "ts": 658972022857.632, "dur": 84.279, + "args": { + "External id": 34559,"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": 4183437, "tid": 31318, + "ts": 658972022858.662, "dur": 6.009, + "args": { + "External id": 34560,"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": 4183437, "tid": 31318, + "ts": 658972022859.509, "dur": 4.698, + "args": { + "External id": 34561,"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": 4183437, "tid": 31318, + "ts": 658972022861.653, "dur": 2.450, + "args": { + "External id": 34562,"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": 4183437, "tid": 31318, + "ts": 658972022865.929, "dur": 75.510, + "args": { + "External id": 34563,"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": 4183437, "tid": 31318, + "ts": 658972022867.734, "dur": 72.942, + "args": { + "External id": 34564,"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": 4183437, "tid": 31318, + "ts": 658972022946.318, "dur": 3.140, + "args": { + "External id": 34565,"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": 4183437, "tid": 31318, + "ts": 658972022947.991, "dur": 1.316, + "args": { + "External id": 34566,"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": 4183437, "tid": 31318, + "ts": 658972022982.416, "dur": 5.488, + "args": { + "External id": 34567,"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": 4183437, "tid": 31318, + "ts": 658972022989.426, "dur": 1.890, + "args": { + "External id": 34568,"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": 4183437, "tid": 31318, + "ts": 658972022992.540, "dur": 1.558, + "args": { + "External id": 34569,"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": 4183437, "tid": 31318, + "ts": 658972023024.710, "dur": 2.570, + "args": { + "External id": 34570,"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": 4183437, "tid": 31318, + "ts": 658972023025.874, "dur": 1.273, + "args": { + "External id": 34571,"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": 4183437, "tid": 31318, + "ts": 658972023048.382, "dur": 108.175, + "args": { + "External id": 34572,"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": 4183437, "tid": 31318, + "ts": 658972023053.523, "dur": 6.400, + "args": { + "External id": 34573,"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": 4183437, "tid": 31318, + "ts": 658972023057.353, "dur": 1.873, + "args": { + "External id": 34574,"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": 4183437, "tid": 31318, + "ts": 658972023061.369, "dur": 6.643, + "args": { + "External id": 34575,"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": 4183437, "tid": 31318, + "ts": 658972023064.686, "dur": 2.614, + "args": { + "External id": 34576,"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": 4183437, "tid": 31318, + "ts": 658972023069.503, "dur": 2.561, + "args": { + "External id": 34577,"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": 4183437, "tid": 31318, + "ts": 658972023071.035, "dur": 0.662, + "args": { + "External id": 34578,"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": 4183437, "tid": 31318, + "ts": 658972023073.185, "dur": 3.315, + "args": { + "External id": 34579,"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": 4183437, "tid": 31318, + "ts": 658972023075.242, "dur": 0.725, + "args": { + "External id": 34580,"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": 4183437, "tid": 31318, + "ts": 658972023080.605, "dur": 3.423, + "args": { + "External id": 34581,"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": 4183437, "tid": 31318, + "ts": 658972023083.047, "dur": 0.641, + "args": { + "External id": 34582,"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": 4183437, "tid": 31318, + "ts": 658972023085.687, "dur": 5.929, + "args": { + "External id": 34583,"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": 4183437, "tid": 31318, + "ts": 658972023089.571, "dur": 1.871, + "args": { + "External id": 34584,"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": 4183437, "tid": 31318, + "ts": 658972023092.798, "dur": 2.691, + "args": { + "External id": 34585,"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": 4183437, "tid": 31318, + "ts": 658972023094.551, "dur": 0.629, + "args": { + "External id": 34586,"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": 4183437, "tid": 31318, + "ts": 658972023096.592, "dur": 4.214, + "args": { + "External id": 34587,"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": 4183437, "tid": 31318, + "ts": 658972023097.921, "dur": 2.782, + "args": { + "External id": 34588,"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": 4183437, "tid": 31318, + "ts": 658972023102.185, "dur": 40.759, + "args": { + "External id": 34589,"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": 4183437, "tid": 31318, + "ts": 658972023145.066, "dur": 3.245, + "args": { + "External id": 34590,"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": 4183437, "tid": 31318, + "ts": 658972023149.429, "dur": 2.715, + "args": { + "External id": 34591,"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": 4183437, "tid": 31318, + "ts": 658972023151.071, "dur": 0.602, + "args": { + "External id": 34592,"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": 4183437, "tid": 31318, + "ts": 658972023154.700, "dur": 0.791, + "args": { + "External id": 34593,"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": 4183437, "tid": 31318, + "ts": 658972023189.381, "dur": 8.529, + "args": { + "External id": 34594,"Record function id": 0, "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972023191.474, "dur": 5.658, + "args": { + "External id": 34595,"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": 4183437, "tid": 31318, + "ts": 658972023193.040, "dur": 3.215, + "args": { + "External id": 34596,"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": 4183437, "tid": 31318, + "ts": 658972023194.470, "dur": 1.701, + "args": { + "External id": 34597,"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": 4183437, "tid": 31318, + "ts": 658972023201.436, "dur": 7.374, + "args": { + "External id": 34598,"Record function id": 0, "Sequence number": 459961, "Fwd thread id": 1, "Ev Idx": 1317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972023202.843, "dur": 4.263, + "args": { + "External id": 34599,"Sequence number": 459961, "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": 4183437, "tid": 31318, "ts": 658972023202.843, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972023204.445, "dur": 2.473, + "args": { + "External id": 34600,"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": 4183437, "tid": 31318, + "ts": 658972023205.893, "dur": 0.884, + "args": { + "External id": 34601,"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": 4183437, "tid": 31318, + "ts": 658972023212.305, "dur": 124.341, + "args": { + "External id": 34602,"Record function id": 0, "Sequence number": 459960, "Fwd thread id": 1, "Ev Idx": 1321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972023213.376, "dur": 116.701, + "args": { + "External id": 34603,"Sequence number": 459960, "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": 4183437, "tid": 31318, "ts": 658972023213.376, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972023217.091, "dur": 4.618, + "args": { + "External id": 34604,"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": 4183437, "tid": 31318, + "ts": 658972023218.440, "dur": 2.746, + "args": { + "External id": 34605,"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": 4183437, "tid": 31318, + "ts": 658972023220.346, "dur": 0.686, + "args": { + "External id": 34606,"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": 4183437, "tid": 31318, + "ts": 658972023222.946, "dur": 32.237, + "args": { + "External id": 34607,"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": 4183437, "tid": 31318, + "ts": 658972023256.479, "dur": 4.684, + "args": { + "External id": 34608,"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": 4183437, "tid": 31318, + "ts": 658972023257.493, "dur": 2.644, + "args": { + "External id": 34609,"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": 4183437, "tid": 31318, + "ts": 658972023259.307, "dur": 0.694, + "args": { + "External id": 34610,"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": 4183437, "tid": 31318, + "ts": 658972023278.380, "dur": 5.792, + "args": { + "External id": 34611,"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": 4183437, "tid": 31318, + "ts": 658972023280.215, "dur": 3.312, + "args": { + "External id": 34612,"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": 4183437, "tid": 31318, + "ts": 658972023282.713, "dur": 0.545, + "args": { + "External id": 34613,"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": 4183437, "tid": 31318, + "ts": 658972023285.175, "dur": 43.900, + "args": { + "External id": 34614,"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": 4183437, "tid": 31318, + "ts": 658972023342.449, "dur": 7.366, + "args": { + "External id": 34615,"Record function id": 0, "Sequence number": 459959, "Fwd thread id": 1, "Ev Idx": 1334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972023343.594, "dur": 5.125, + "args": { + "External id": 34616,"Sequence number": 459959, "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": 4183437, "tid": 31318, "ts": 658972023343.594, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972023345.829, "dur": 2.741, + "args": { + "External id": 34617,"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": 4183437, "tid": 31318, + "ts": 658972023347.141, "dur": 1.329, + "args": { + "External id": 34618,"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": 4183437, "tid": 31318, + "ts": 658972023353.368, "dur": 9.080, + "args": { + "External id": 34619,"Record function id": 0, "Sequence number": 459958, "Fwd thread id": 1, "Ev Idx": 1338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972023354.560, "dur": 5.681, + "args": { + "External id": 34620,"Sequence number": 459958, "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": 4183437, "tid": 31318, "ts": 658972023354.560, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972023355.836, "dur": 4.181, + "args": { + "External id": 34621,"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": 4183437, "tid": 31318, + "ts": 658972023356.645, "dur": 2.907, + "args": { + "External id": 34622,"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": 4183437, "tid": 31318, + "ts": 658972023358.986, "dur": 0.420, + "args": { + "External id": 34623,"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": 4183437, "tid": 31318, + "ts": 658972023366.275, "dur": 6.820, + "args": { + "External id": 34624,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972023368.106, "dur": 4.421, + "args": { + "External id": 34625,"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": 4183437, "tid": 31318, + "ts": 658972023369.341, "dur": 2.863, + "args": { + "External id": 34626,"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": 4183437, "tid": 31318, + "ts": 658972023370.470, "dur": 1.647, + "args": { + "External id": 34627,"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": 4183437, "tid": 31318, + "ts": 658972023376.300, "dur": 6.730, + "args": { + "External id": 34628,"Record function id": 0, "Sequence number": 459957, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972023377.614, "dur": 3.484, + "args": { + "External id": 34629,"Sequence number": 459957, "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": 4183437, "tid": 31318, "ts": 658972023377.614, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972023379.020, "dur": 1.930, + "args": { + "External id": 34630,"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": 4183437, "tid": 31318, + "ts": 658972023380.120, "dur": 0.694, + "args": { + "External id": 34631,"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": 4183437, "tid": 31318, + "ts": 658972023386.319, "dur": 85.826, + "args": { + "External id": 34632,"Record function id": 0, "Sequence number": 459956, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972023387.111, "dur": 78.963, + "args": { + "External id": 34633,"Sequence number": 459956, "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": 4183437, "tid": 31318, "ts": 658972023387.111, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972023389.497, "dur": 3.943, + "args": { + "External id": 34634,"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": 4183437, "tid": 31318, + "ts": 658972023390.443, "dur": 2.545, + "args": { + "External id": 34635,"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": 4183437, "tid": 31318, + "ts": 658972023392.351, "dur": 0.543, + "args": { + "External id": 34636,"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": 4183437, "tid": 31318, + "ts": 658972023394.261, "dur": 26.372, + "args": { + "External id": 34637,"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": 4183437, "tid": 31318, + "ts": 658972023421.683, "dur": 4.018, + "args": { + "External id": 34638,"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": 4183437, "tid": 31318, + "ts": 658972023422.684, "dur": 2.458, + "args": { + "External id": 34639,"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": 4183437, "tid": 31318, + "ts": 658972023424.326, "dur": 0.678, + "args": { + "External id": 34640,"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": 4183437, "tid": 31318, + "ts": 658972023426.959, "dur": 6.351, + "args": { + "External id": 34641,"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": 4183437, "tid": 31318, + "ts": 658972023428.529, "dur": 4.379, + "args": { + "External id": 34642,"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": 4183437, "tid": 31318, + "ts": 658972023430.346, "dur": 2.479, + "args": { + "External id": 34643,"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": 4183437, "tid": 31318, + "ts": 658972023434.046, "dur": 31.358, + "args": { + "External id": 34644,"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": 4183437, "tid": 31318, + "ts": 658972023477.962, "dur": 30.437, + "args": { + "External id": 34645,"Record function id": 0, "Sequence number": 459955, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972023479.213, "dur": 4.479, + "args": { + "External id": 34646,"Sequence number": 459955, "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": 4183437, "tid": 31318, "ts": 658972023479.213, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972023481.095, "dur": 2.460, + "args": { + "External id": 34647,"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": 4183437, "tid": 31318, + "ts": 658972023482.476, "dur": 0.981, + "args": { + "External id": 34648,"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": 4183437, "tid": 31318, + "ts": 658972023486.188, "dur": 19.331, + "args": { + "External id": 34649,"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": 4183437, "tid": 31318, + "ts": 658972023512.143, "dur": 8.618, + "args": { + "External id": 34650,"Record function id": 0, "Sequence number": 459954, "Fwd thread id": 1, "Ev Idx": 1369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972023513.407, "dur": 5.664, + "args": { + "External id": 34651,"Sequence number": 459954, "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": 4183437, "tid": 31318, "ts": 658972023513.407, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972023514.530, "dur": 4.345, + "args": { + "External id": 34652,"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": 4183437, "tid": 31318, + "ts": 658972023515.334, "dur": 3.035, + "args": { + "External id": 34653,"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": 4183437, "tid": 31318, + "ts": 658972023517.799, "dur": 0.452, + "args": { + "External id": 34654,"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": 4183437, "tid": 31318, + "ts": 658972023524.808, "dur": 5.660, + "args": { + "External id": 34655,"Record function id": 0, "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972023526.446, "dur": 3.512, + "args": { + "External id": 34656,"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": 4183437, "tid": 31318, + "ts": 658972023527.301, "dur": 2.384, + "args": { + "External id": 34657,"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": 4183437, "tid": 31318, + "ts": 658972023528.339, "dur": 1.259, + "args": { + "External id": 34658,"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": 4183437, "tid": 31318, + "ts": 658972023534.459, "dur": 450.287, + "args": { + "External id": 34659,"Record function id": 0, "Sequence number": 459953, "Fwd thread id": 1, "Ev Idx": 1378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972023539.247, "dur": 413.280, + "args": { + "External id": 34660,"Sequence number": 459953, "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": 4183437, "tid": 31318, "ts": 658972023539.247, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183437, "tid": 31318, + "ts": 658972023562.062, "dur": 32.178, + "args": { + "External id": 34661,"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": 4183437, "tid": 31318, + "ts": 658972023563.433, "dur": 30.604, + "args": { + "External id": 34662,"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": 4183437, "tid": 31318, + "ts": 658972023566.554, "dur": 6.285, + "args": { + "External id": 34663,"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": 4183437, "tid": 31318, + "ts": 658972023569.193, "dur": 3.144, + "args": { + "External id": 34664,"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": 4183437, "tid": 31318, + "ts": 658972023574.302, "dur": 19.270, + "args": { + "External id": 34665,"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": 4183437, "tid": 31318, + "ts": 658972023605.133, "dur": 2.870, + "args": { + "External id": 34666,"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": 4183437, "tid": 31318, + "ts": 658972023606.628, "dur": 1.268, + "args": { + "External id": 34667,"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": 4183437, "tid": 31318, + "ts": 658972023612.005, "dur": 3.498, + "args": { + "External id": 34668,"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": 4183437, "tid": 31318, + "ts": 658972023613.170, "dur": 2.239, + "args": { + "External id": 34669,"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": 4183437, "tid": 31318, + "ts": 658972023627.799, "dur": 2.766, + "args": { + "External id": 34670,"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": 4183437, "tid": 31318, + "ts": 658972023640.996, "dur": 4.400, + "args": { + "External id": 34671,"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": 4183437, "tid": 31318, + "ts": 658972023844.184, "dur": 3.708, + "args": { + "External id": 34672,"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": 4183437, "tid": 31318, + "ts": 658972023852.186, "dur": 32.799, + "args": { + "External id": 34673,"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": 4183437, "tid": 31318, + "ts": 658972023862.187, "dur": 0.958, + "args": { + "External id": 34674,"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": 4183437, "tid": 31318, + "ts": 658972023890.926, "dur": 28.500, + "args": { + "External id": 34675,"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": 4183437, "tid": 31318, + "ts": 658972023893.090, "dur": 26.088, + "args": { + "External id": 34676,"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": 4183437, "tid": 31318, + "ts": 658972023898.328, "dur": 3.975, + "args": { + "External id": 34677,"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": 4183437, "tid": 31318, + "ts": 658972023903.923, "dur": 14.739, + "args": { + "External id": 34678,"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": 4183437, "tid": 31318, + "ts": 658972023924.071, "dur": 2.454, + "args": { + "External id": 34679,"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": 4183437, "tid": 31318, + "ts": 658972023925.400, "dur": 1.032, + "args": { + "External id": 34680,"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": 4183437, "tid": 31318, + "ts": 658972023933.544, "dur": 2.903, + "args": { + "External id": 34681,"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": 4183437, "tid": 31318, + "ts": 658972023934.829, "dur": 1.475, + "args": { + "External id": 34682,"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": 4183437, "tid": 31318, + "ts": 658972023938.837, "dur": 4.570, + "args": { + "External id": 34683,"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": 4183437, "tid": 31318, + "ts": 658972023940.666, "dur": 2.641, + "args": { + "External id": 34684,"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": 4183437, "tid": 31318, + "ts": 658972023966.994, "dur": 16.183, + "args": { + "External id": 34685,"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": 4183437, "tid": 31318, + "ts": 658972023997.269, "dur": 8.750, + "args": { + "External id": 34686,"Record function id": 0, "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972023999.470, "dur": 5.764, + "args": { + "External id": 34687,"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": 4183437, "tid": 31318, + "ts": 658972024001.428, "dur": 2.852, + "args": { + "External id": 34688,"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": 4183437, "tid": 31318, + "ts": 658972024002.637, "dur": 1.552, + "args": { + "External id": 34689,"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": 4183437, "tid": 31318, + "ts": 658972024009.755, "dur": 9.309, + "args": { + "External id": 34690,"Record function id": 0, "Sequence number": 459952, "Fwd thread id": 1, "Ev Idx": 1409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972024011.174, "dur": 5.541, + "args": { + "External id": 34691,"Sequence number": 459952, "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": 4183437, "tid": 31318, "ts": 658972024011.174, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972024013.235, "dur": 3.241, + "args": { + "External id": 34692,"Record 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": 4183437, "tid": 31318, + "ts": 658972024014.909, "dur": 1.396, + "args": { + "External id": 34693,"Record 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": 4183437, "tid": 31318, + "ts": 658972024022.403, "dur": 128.487, + "args": { + "External id": 34694,"Record function id": 0, "Sequence number": 459951, "Fwd thread id": 1, "Ev Idx": 1413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972024023.336, "dur": 121.733, + "args": { + "External id": 34695,"Sequence number": 459951, "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": 4183437, "tid": 31318, "ts": 658972024023.336, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972024026.332, "dur": 5.444, + "args": { + "External id": 34696,"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": 4183437, "tid": 31318, + "ts": 658972024027.923, "dur": 3.233, + "args": { + "External id": 34697,"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": 4183437, "tid": 31318, + "ts": 658972024030.165, "dur": 0.777, + "args": { + "External id": 34698,"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": 4183437, "tid": 31318, + "ts": 658972024033.189, "dur": 62.771, + "args": { + "External id": 34699,"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": 4183437, "tid": 31318, + "ts": 658972024097.446, "dur": 5.681, + "args": { + "External id": 34700,"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": 4183437, "tid": 31318, + "ts": 658972024098.227, "dur": 4.293, + "args": { + "External id": 34701,"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": 4183437, "tid": 31318, + "ts": 658972024100.331, "dur": 1.943, + "args": { + "External id": 34702,"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": 4183437, "tid": 31318, + "ts": 658972024104.468, "dur": 4.457, + "args": { + "External id": 34703,"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": 4183437, "tid": 31318, + "ts": 658972024105.679, "dur": 2.600, + "args": { + "External id": 34704,"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": 4183437, "tid": 31318, + "ts": 658972024107.808, "dur": 0.359, + "args": { + "External id": 34705,"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": 4183437, "tid": 31318, + "ts": 658972024109.964, "dur": 34.347, + "args": { + "External id": 34706,"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": 4183437, "tid": 31318, + "ts": 658972024155.534, "dur": 9.590, + "args": { + "External id": 34707,"Record function id": 0, "Sequence number": 459950, "Fwd thread id": 1, "Ev Idx": 1426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972024156.400, "dur": 7.035, + "args": { + "External id": 34708,"Sequence number": 459950, "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": 4183437, "tid": 31318, "ts": 658972024156.400, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972024158.438, "dur": 4.835, + "args": { + "External id": 34709,"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": 4183437, "tid": 31318, + "ts": 658972024160.192, "dur": 2.912, + "args": { + "External id": 34710,"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": 4183437, "tid": 31318, + "ts": 658972024168.438, "dur": 8.586, + "args": { + "External id": 34711,"Record function id": 0, "Sequence number": 459949, "Fwd thread id": 1, "Ev Idx": 1430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972024169.495, "dur": 5.661, + "args": { + "External id": 34712,"Sequence number": 459949, "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": 4183437, "tid": 31318, "ts": 658972024169.495, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972024170.481, "dur": 4.455, + "args": { + "External id": 34713,"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": 4183437, "tid": 31318, + "ts": 658972024171.490, "dur": 2.936, + "args": { + "External id": 34714,"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": 4183437, "tid": 31318, + "ts": 658972024173.554, "dur": 0.697, + "args": { + "External id": 34715,"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": 4183437, "tid": 31318, + "ts": 658972024180.786, "dur": 5.733, + "args": { + "External id": 34716,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972024182.590, "dur": 3.390, + "args": { + "External id": 34717,"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": 4183437, "tid": 31318, + "ts": 658972024183.433, "dur": 2.278, + "args": { + "External id": 34718,"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": 4183437, "tid": 31318, + "ts": 658972024184.568, "dur": 1.060, + "args": { + "External id": 34719,"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": 4183437, "tid": 31318, + "ts": 658972024189.415, "dur": 6.719, + "args": { + "External id": 34720,"Record function id": 0, "Sequence number": 459948, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972024190.340, "dur": 3.797, + "args": { + "External id": 34721,"Sequence number": 459948, "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": 4183437, "tid": 31318, "ts": 658972024190.340, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972024191.755, "dur": 2.231, + "args": { + "External id": 34722,"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": 4183437, "tid": 31318, + "ts": 658972024192.611, "dur": 1.247, + "args": { + "External id": 34723,"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": 4183437, "tid": 31318, + "ts": 658972024200.247, "dur": 298.220, + "args": { + "External id": 34724,"Record function id": 0, "Sequence number": 459947, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183437, "tid": 31318, + "ts": 658972024201.869, "dur": 279.878, + "args": { + "External id": 34725,"Sequence number": 459947, "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": 4183437, "tid": 31318, "ts": 658972024201.869, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 31318, + "ts": 658972024214.995, "dur": 6.758, + "args": { + "External id": 34726,"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": 4183437, "tid": 31318, + "ts": 658972024217.726, "dur": 3.593, + "args": { + "External id": 34727,"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": 4183437, "tid": 31318, + "ts": 658972024223.751, "dur": 3.631, + "args": { + "External id": 34728,"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": 4183437, "tid": 31318, + "ts": 658972024225.605, "dur": 1.589, + "args": { + "External id": 34729,"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": 4183437, "tid": 31318, + "ts": 658972024229.204, "dur": 3.504, + "args": { + "External id": 34730,"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": 4183437, "tid": 31318, + "ts": 658972024231.059, "dur": 1.448, + "args": { + "External id": 34731,"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": 4183437, "tid": 31318, + "ts": 658972024255.747, "dur": 201.114, + "args": { + "External id": 34732,"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": 4183437, "tid": 31318, + "ts": 658972024358.812, "dur": 6.405, + "args": { + "External id": 34733,"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": 4183437, "tid": 31318, + "ts": 658972024367.249, "dur": 3.594, + "args": { + "External id": 34734,"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": 4183437, "tid": 31318, + "ts": 658972024468.953, "dur": 3.668, + "args": { + "External id": 34735,"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": 4183437, "tid": 31318, + "ts": 658972024475.915, "dur": 0.738, + "args": { + "External id": 34736,"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": 4183437, "tid": 31318, + "ts": 658972024478.532, "dur": 0.592, + "args": { + "External id": 34737,"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": 4183437, "tid": 31318, + "ts": 658972024507.428, "dur": 276.986, + "args": { + "External id": 34738,"Record function id": 0, "Sequence number": 459946, "Fwd thread id": 1, "Ev Idx": 1457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972024509.401, "dur": 266.857, + "args": { + "External id": 34739,"Sequence number": 459946, "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": 4183437, "tid": 31318, "ts": 658972024509.401, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183437, "tid": 31318, + "ts": 658972024528.617, "dur": 51.427, + "args": { + "External id": 34740,"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": 4183437, "tid": 31318, + "ts": 658972024532.014, "dur": 3.178, + "args": { + "External id": 34741,"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": 4183437, "tid": 31318, + "ts": 658972024536.747, "dur": 42.673, + "args": { + "External id": 34742,"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": 4183437, "tid": 31318, + "ts": 658972024589.805, "dur": 4.784, + "args": { + "External id": 34743,"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": 4183437, "tid": 31318, + "ts": 658972024591.733, "dur": 2.475, + "args": { + "External id": 34744,"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": 4183437, "tid": 31318, + "ts": 658972024794.536, "dur": 152.626, + "args": { + "External id": 34745,"Record function id": 0, "Sequence number": 459945, "Fwd thread id": 1, "Ev Idx": 1464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972024796.598, "dur": 144.075, + "args": { + "External id": 34746,"Sequence number": 459945, "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": 4183437, "tid": 31318, "ts": 658972024796.598, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183437, "tid": 31318, + "ts": 658972024809.530, "dur": 36.133, + "args": { + "External id": 34747,"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": 4183437, "tid": 31318, + "ts": 658972024812.982, "dur": 3.653, + "args": { + "External id": 34748,"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": 4183437, "tid": 31318, + "ts": 658972024817.757, "dur": 27.399, + "args": { + "External id": 34749,"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": 4183437, "tid": 31318, + "ts": 658972024852.806, "dur": 4.342, + "args": { + "External id": 34750,"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": 4183437, "tid": 31318, + "ts": 658972024855.001, "dur": 1.840, + "args": { + "External id": 34751,"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": 4183437, "tid": 31318, + "ts": 658972024953.103, "dur": 15.554, + "args": { + "External id": 34752,"Record function id": 0, "Sequence number": 459944, "Fwd thread id": 1, "Ev Idx": 1471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972024954.658, "dur": 11.758, + "args": { + "External id": 34753,"Sequence number": 459944, "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": 4183437, "tid": 31318, "ts": 658972024954.658, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972024957.576, "dur": 8.541, + "args": { + "External id": 34754,"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": 4183437, "tid": 31318, + "ts": 658972024959.393, "dur": 6.541, + "args": { + "External id": 34755,"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": 4183437, "tid": 31318, + "ts": 658972024972.207, "dur": 7.286, + "args": { + "External id": 34756,"Record function id": 0, "Sequence number": 459943, "Fwd thread id": 1, "Ev Idx": 1475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972024973.686, "dur": 3.882, + "args": { + "External id": 34757,"Sequence number": 459943, "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": 4183437, "tid": 31318, "ts": 658972024973.686, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972024975.172, "dur": 2.266, + "args": { + "External id": 34758,"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": 4183437, "tid": 31318, + "ts": 658972024976.477, "dur": 0.868, + "args": { + "External id": 34759,"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": 4183437, "tid": 31318, + "ts": 658972024982.384, "dur": 7.107, + "args": { + "External id": 34760,"Record function id": 0, "Sequence number": 459942, "Fwd thread id": 1, "Ev Idx": 1479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972024983.466, "dur": 4.547, + "args": { + "External id": 34761,"Sequence number": 459942, "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": 4183437, "tid": 31318, "ts": 658972024983.466, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972024984.973, "dur": 2.906, + "args": { + "External id": 34762,"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": 4183437, "tid": 31318, + "ts": 658972024986.601, "dur": 1.135, + "args": { + "External id": 34763,"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": 4183437, "tid": 31318, + "ts": 658972024992.888, "dur": 6.571, + "args": { + "External id": 34764,"Record function id": 0, "Sequence number": 459941, "Fwd thread id": 1, "Ev Idx": 1483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972024994.084, "dur": 3.509, + "args": { + "External id": 34765,"Sequence number": 459941, "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": 4183437, "tid": 31318, "ts": 658972024994.084, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972024995.376, "dur": 2.094, + "args": { + "External id": 34766,"Record 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": 4183437, "tid": 31318, + "ts": 658972024996.473, "dur": 0.887, + "args": { + "External id": 34767,"Record 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": 4183437, "tid": 31318, + "ts": 658972025003.065, "dur": 159.078, + "args": { + "External id": 34768,"Record function id": 0, "Sequence number": 459940, "Fwd thread id": 1, "Ev Idx": 1487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025004.004, "dur": 151.509, + "args": { + "External id": 34769,"Sequence number": 459940, "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": 4183437, "tid": 31318, "ts": 658972025004.004, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972025007.887, "dur": 7.335, + "args": { + "External id": 34770,"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": 4183437, "tid": 31318, + "ts": 658972025009.802, "dur": 4.777, + "args": { + "External id": 34771,"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": 4183437, "tid": 31318, + "ts": 658972025012.591, "dur": 1.718, + "args": { + "External id": 34772,"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": 4183437, "tid": 31318, + "ts": 658972025017.086, "dur": 82.287, + "args": { + "External id": 34773,"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": 4183437, "tid": 31318, + "ts": 658972025101.046, "dur": 5.907, + "args": { + "External id": 34774,"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": 4183437, "tid": 31318, + "ts": 658972025102.139, "dur": 3.865, + "args": { + "External id": 34775,"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": 4183437, "tid": 31318, + "ts": 658972025104.839, "dur": 0.943, + "args": { + "External id": 34776,"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": 4183437, "tid": 31318, + "ts": 658972025108.506, "dur": 5.039, + "args": { + "External id": 34777,"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": 4183437, "tid": 31318, + "ts": 658972025110.209, "dur": 2.815, + "args": { + "External id": 34778,"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": 4183437, "tid": 31318, + "ts": 658972025112.337, "dur": 0.565, + "args": { + "External id": 34779,"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": 4183437, "tid": 31318, + "ts": 658972025114.408, "dur": 40.292, + "args": { + "External id": 34780,"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": 4183437, "tid": 31318, + "ts": 658972025166.724, "dur": 8.171, + "args": { + "External id": 34781,"Record function id": 0, "Sequence number": 459939, "Fwd thread id": 1, "Ev Idx": 1500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025167.513, "dur": 5.923, + "args": { + "External id": 34782,"Sequence number": 459939, "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": 4183437, "tid": 31318, "ts": 658972025167.513, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972025170.220, "dur": 3.073, + "args": { + "External id": 34783,"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": 4183437, "tid": 31318, + "ts": 658972025171.508, "dur": 1.599, + "args": { + "External id": 34784,"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": 4183437, "tid": 31318, + "ts": 658972025178.063, "dur": 9.138, + "args": { + "External id": 34785,"Record function id": 0, "Sequence number": 459938, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025179.236, "dur": 5.958, + "args": { + "External id": 34786,"Sequence number": 459938, "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": 4183437, "tid": 31318, "ts": 658972025179.236, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972025180.449, "dur": 4.546, + "args": { + "External id": 34787,"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": 4183437, "tid": 31318, + "ts": 658972025181.789, "dur": 2.715, + "args": { + "External id": 34788,"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": 4183437, "tid": 31318, + "ts": 658972025183.760, "dur": 0.616, + "args": { + "External id": 34789,"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": 4183437, "tid": 31318, + "ts": 658972025192.836, "dur": 9.950, + "args": { + "External id": 34790,"Record function id": 0, "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972025194.820, "dur": 7.247, + "args": { + "External id": 34791,"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": 4183437, "tid": 31318, + "ts": 658972025197.238, "dur": 4.422, + "args": { + "External id": 34792,"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": 4183437, "tid": 31318, + "ts": 658972025198.863, "dur": 2.693, + "args": { + "External id": 34793,"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": 4183437, "tid": 31318, + "ts": 658972025206.624, "dur": 8.028, + "args": { + "External id": 34794,"Record function id": 0, "Sequence number": 459937, "Fwd thread id": 1, "Ev Idx": 1513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025207.836, "dur": 4.484, + "args": { + "External id": 34795,"Sequence number": 459937, "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": 4183437, "tid": 31318, "ts": 658972025207.836, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972025209.770, "dur": 2.386, + "args": { + "External id": 34796,"Record 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": 4183437, "tid": 31318, + "ts": 658972025211.086, "dur": 0.941, + "args": { + "External id": 34797,"Record 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": 4183437, "tid": 31318, + "ts": 658972025218.215, "dur": 123.122, + "args": { + "External id": 34798,"Record function id": 0, "Sequence number": 459936, "Fwd thread id": 1, "Ev Idx": 1517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025219.393, "dur": 115.482, + "args": { + "External id": 34799,"Sequence number": 459936, "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": 4183437, "tid": 31318, "ts": 658972025219.393, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972025221.095, "dur": 4.620, + "args": { + "External id": 34800,"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": 4183437, "tid": 31318, + "ts": 658972025221.980, "dur": 3.310, + "args": { + "External id": 34801,"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": 4183437, "tid": 31318, + "ts": 658972025224.322, "dur": 0.810, + "args": { + "External id": 34802,"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": 4183437, "tid": 31318, + "ts": 658972025226.453, "dur": 35.115, + "args": { + "External id": 34803,"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": 4183437, "tid": 31318, + "ts": 658972025281.268, "dur": 6.292, + "args": { + "External id": 34804,"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": 4183437, "tid": 31318, + "ts": 658972025282.726, "dur": 4.119, + "args": { + "External id": 34805,"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": 4183437, "tid": 31318, + "ts": 658972025285.454, "dur": 1.100, + "args": { + "External id": 34806,"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": 4183437, "tid": 31318, + "ts": 658972025289.046, "dur": 6.113, + "args": { + "External id": 34807,"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": 4183437, "tid": 31318, + "ts": 658972025290.594, "dur": 4.055, + "args": { + "External id": 34808,"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": 4183437, "tid": 31318, + "ts": 658972025292.464, "dur": 2.093, + "args": { + "External id": 34809,"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": 4183437, "tid": 31318, + "ts": 658972025296.144, "dur": 37.947, + "args": { + "External id": 34810,"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": 4183437, "tid": 31318, + "ts": 658972025349.790, "dur": 37.676, + "args": { + "External id": 34811,"Record function id": 0, "Sequence number": 459935, "Fwd thread id": 1, "Ev Idx": 1530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025351.222, "dur": 6.645, + "args": { + "External id": 34812,"Sequence number": 459935, "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": 4183437, "tid": 31318, "ts": 658972025351.222, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972025353.151, "dur": 4.571, + "args": { + "External id": 34813,"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": 4183437, "tid": 31318, + "ts": 658972025356.311, "dur": 1.262, + "args": { + "External id": 34814,"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": 4183437, "tid": 31318, + "ts": 658972025360.929, "dur": 23.849, + "args": { + "External id": 34815,"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": 4183437, "tid": 31318, + "ts": 658972025391.392, "dur": 23.338, + "args": { + "External id": 34816,"Record function id": 0, "Sequence number": 459934, "Fwd thread id": 1, "Ev Idx": 1535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025407.674, "dur": 5.367, + "args": { + "External id": 34817,"Sequence number": 459934, "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": 4183437, "tid": 31318, "ts": 658972025407.674, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972025408.664, "dur": 4.173, + "args": { + "External id": 34818,"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": 4183437, "tid": 31318, + "ts": 658972025409.736, "dur": 2.624, + "args": { + "External id": 34819,"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": 4183437, "tid": 31318, + "ts": 658972025411.858, "dur": 0.354, + "args": { + "External id": 34820,"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": 4183437, "tid": 31318, + "ts": 658972025418.785, "dur": 6.540, + "args": { + "External id": 34821,"Record function id": 0, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972025420.536, "dur": 4.235, + "args": { + "External id": 34822,"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": 4183437, "tid": 31318, + "ts": 658972025421.796, "dur": 2.640, + "args": { + "External id": 34823,"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": 4183437, "tid": 31318, + "ts": 658972025422.832, "dur": 1.499, + "args": { + "External id": 34824,"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": 4183437, "tid": 31318, + "ts": 658972025428.481, "dur": 6.328, + "args": { + "External id": 34825,"Record function id": 0, "Sequence number": 459933, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025429.734, "dur": 3.547, + "args": { + "External id": 34826,"Sequence number": 459933, "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": 4183437, "tid": 31318, "ts": 658972025429.734, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972025430.885, "dur": 2.250, + "args": { + "External id": 34827,"Record 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": 4183437, "tid": 31318, + "ts": 658972025432.035, "dur": 0.964, + "args": { + "External id": 34828,"Record 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": 4183437, "tid": 31318, + "ts": 658972025437.911, "dur": 93.193, + "args": { + "External id": 34829,"Record function id": 0, "Sequence number": 459932, "Fwd thread id": 1, "Ev Idx": 1548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025438.739, "dur": 85.773, + "args": { + "External id": 34830,"Sequence number": 459932, "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": 4183437, "tid": 31318, "ts": 658972025438.739, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972025440.954, "dur": 3.459, + "args": { + "External id": 34831,"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": 4183437, "tid": 31318, + "ts": 658972025441.588, "dur": 2.368, + "args": { + "External id": 34832,"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": 4183437, "tid": 31318, + "ts": 658972025443.417, "dur": 0.435, + "args": { + "External id": 34833,"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": 4183437, "tid": 31318, + "ts": 658972025445.169, "dur": 36.610, + "args": { + "External id": 34834,"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": 4183437, "tid": 31318, + "ts": 658972025482.939, "dur": 3.978, + "args": { + "External id": 34835,"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": 4183437, "tid": 31318, + "ts": 658972025483.633, "dur": 2.774, + "args": { + "External id": 34836,"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": 4183437, "tid": 31318, + "ts": 658972025485.421, "dur": 0.876, + "args": { + "External id": 34837,"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": 4183437, "tid": 31318, + "ts": 658972025488.077, "dur": 3.612, + "args": { + "External id": 34838,"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": 4183437, "tid": 31318, + "ts": 658972025489.217, "dur": 2.028, + "args": { + "External id": 34839,"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": 4183437, "tid": 31318, + "ts": 658972025490.784, "dur": 0.366, + "args": { + "External id": 34840,"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": 4183437, "tid": 31318, + "ts": 658972025492.409, "dur": 31.492, + "args": { + "External id": 34841,"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": 4183437, "tid": 31318, + "ts": 658972025535.241, "dur": 25.194, + "args": { + "External id": 34842,"Record function id": 0, "Sequence number": 459931, "Fwd thread id": 1, "Ev Idx": 1561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025536.050, "dur": 4.147, + "args": { + "External id": 34843,"Sequence number": 459931, "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": 4183437, "tid": 31318, "ts": 658972025536.050, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972025537.737, "dur": 2.300, + "args": { + "External id": 34844,"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": 4183437, "tid": 31318, + "ts": 658972025538.985, "dur": 0.925, + "args": { + "External id": 34845,"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": 4183437, "tid": 31318, + "ts": 658972025542.367, "dur": 15.716, + "args": { + "External id": 34846,"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": 4183437, "tid": 31318, + "ts": 658972025563.867, "dur": 7.812, + "args": { + "External id": 34847,"Record function id": 0, "Sequence number": 459930, "Fwd thread id": 1, "Ev Idx": 1566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183437, "tid": 31318, + "ts": 658972025564.905, "dur": 4.819, + "args": { + "External id": 34848,"Sequence number": 459930, "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": 4183437, "tid": 31318, "ts": 658972025564.905, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183437, "tid": 31318, + "ts": 658972025565.816, "dur": 3.698, + "args": { + "External id": 34849,"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": 4183437, "tid": 31318, + "ts": 658972025566.716, "dur": 2.326, + "args": { + "External id": 34850,"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": 4183437, "tid": 31318, + "ts": 658972025568.575, "dur": 0.295, + "args": { + "External id": 34851,"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": 4183437, "tid": 31318, + "ts": 658972025575.356, "dur": 5.183, + "args": { + "External id": 34852,"Record function id": 0, "Ev Idx": 1571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972025577.015, "dur": 3.070, + "args": { + "External id": 34853,"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": 4183437, "tid": 31318, + "ts": 658972025577.741, "dur": 2.054, + "args": { + "External id": 34854,"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": 4183437, "tid": 31318, + "ts": 658972025578.516, "dur": 1.192, + "args": { + "External id": 34855,"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": 4183437, "tid": 31318, + "ts": 658972025584.619, "dur": 409.641, + "args": { + "External id": 34856,"Record function id": 0, "Sequence number": 459929, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972025585.803, "dur": 370.356, + "args": { + "External id": 34857,"Sequence number": 459929, "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": 4183437, "tid": 31318, "ts": 658972025585.803, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 31318, + "ts": 658972025615.343, "dur": 2.545, + "args": { + "External id": 34858,"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": 4183437, "tid": 31318, + "ts": 658972025616.523, "dur": 1.144, + "args": { + "External id": 34859,"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": 4183437, "tid": 31318, + "ts": 658972025632.157, "dur": 5.388, + "args": { + "External id": 34860,"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": 4183437, "tid": 31318, + "ts": 658972025647.408, "dur": 2.983, + "args": { + "External id": 34861,"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": 4183437, "tid": 31318, + "ts": 658972025847.483, "dur": 3.195, + "args": { + "External id": 34862,"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": 4183437, "tid": 31318, + "ts": 658972025854.727, "dur": 37.313, + "args": { + "External id": 34863,"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": 4183437, "tid": 31318, + "ts": 658972025865.687, "dur": 0.993, + "args": { + "External id": 34864,"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": 4183437, "tid": 31318, + "ts": 658972025897.502, "dur": 34.455, + "args": { + "External id": 34865,"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": 4183437, "tid": 31318, + "ts": 658972025899.683, "dur": 32.068, + "args": { + "External id": 34866,"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": 4183437, "tid": 31318, + "ts": 658972025904.606, "dur": 3.677, + "args": { + "External id": 34867,"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": 4183437, "tid": 31318, + "ts": 658972025909.930, "dur": 21.282, + "args": { + "External id": 34868,"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": 4183437, "tid": 31318, + "ts": 658972025937.050, "dur": 2.724, + "args": { + "External id": 34869,"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": 4183437, "tid": 31318, + "ts": 658972025938.438, "dur": 1.212, + "args": { + "External id": 34870,"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": 4183437, "tid": 31318, + "ts": 658972025946.416, "dur": 2.604, + "args": { + "External id": 34871,"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": 4183437, "tid": 31318, + "ts": 658972025947.796, "dur": 1.131, + "args": { + "External id": 34872,"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": 4183437, "tid": 31318, + "ts": 658972025969.325, "dur": 20.271, + "args": { + "External id": 34873,"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": 4183437, "tid": 31318, + "ts": 658972026005.852, "dur": 8.997, + "args": { + "External id": 34874,"Record function id": 0, "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972026008.442, "dur": 5.732, + "args": { + "External id": 34875,"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": 4183437, "tid": 31318, + "ts": 658972026010.185, "dur": 3.084, + "args": { + "External id": 34876,"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": 4183437, "tid": 31318, + "ts": 658972026011.622, "dur": 1.548, + "args": { + "External id": 34877,"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": 4183437, "tid": 31318, + "ts": 658972026019.353, "dur": 2633.059, + "args": { + "External id": 34878,"Record function id": 0, "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 4183437, "tid": 31318, + "ts": 658972026049.280, "dur": 915.752, + "args": { + "External id": 34879,"Record function id": 0, "Ev Idx": 1598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.18", "pid": 4183437, "tid": 31318, + "ts": 658972026073.775, "dur": 882.108, + "args": { + "External id": 34880,"Record function id": 0, "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 4183437, "tid": 31318, + "ts": 658972026086.562, "dur": 854.025, + "args": { + "External id": 34881,"Record function id": 0, "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972026158.554, "dur": 7.404, + "args": { + "External id": 34882,"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": 4183437, "tid": 31318, + "ts": 658972026180.978, "dur": 29.623, + "args": { + "External id": 34883,"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": 4183437, "tid": 31318, + "ts": 658972026185.084, "dur": 1.545, + "args": { + "External id": 34884,"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": 4183437, "tid": 31318, + "ts": 658972026188.621, "dur": 2.428, + "args": { + "External id": 34885,"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": 4183437, "tid": 31318, + "ts": 658972026193.049, "dur": 0.367, + "args": { + "External id": 34886,"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": 4183437, "tid": 31318, + "ts": 658972026194.888, "dur": 0.451, + "args": { + "External id": 34887,"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": 4183437, "tid": 31318, + "ts": 658972026196.951, "dur": 0.542, + "args": { + "External id": 34888,"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": 4183437, "tid": 31318, + "ts": 658972026199.457, "dur": 0.622, + "args": { + "External id": 34889,"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": 4183437, "tid": 31318, + "ts": 658972026201.237, "dur": 0.458, + "args": { + "External id": 34890,"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": 4183437, "tid": 31318, + "ts": 658972026202.915, "dur": 0.847, + "args": { + "External id": 34891,"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": 4183437, "tid": 31318, + "ts": 658972026205.005, "dur": 0.283, + "args": { + "External id": 34892,"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": 4183437, "tid": 31318, + "ts": 658972026224.914, "dur": 32.239, + "args": { + "External id": 34893,"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": 4183437, "tid": 31318, + "ts": 658972026313.331, "dur": 111.904, + "args": { + "External id": 34894,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972026324.633, "dur": 7.842, + "args": { + "External id": 34895,"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": 4183437, "tid": 31318, + "ts": 658972026338.056, "dur": 10.242, + "args": { + "External id": 34896,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972026342.170, "dur": 5.716, + "args": { + "External id": 34897,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972026345.563, "dur": 0.769, + "args": { + "External id": 34898,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972026355.445, "dur": 24.530, + "args": { + "External id": 34899,"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": 4183437, "tid": 31318, + "ts": 658972026357.798, "dur": 0.308, + "args": { + "External id": 34900,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972026359.819, "dur": 1.080, + "args": { + "External id": 34901,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972026362.490, "dur": 0.351, + "args": { + "External id": 34902,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972026364.183, "dur": 0.396, + "args": { + "External id": 34903,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972026366.787, "dur": 0.366, + "args": { + "External id": 34904,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972026367.999, "dur": 0.450, + "args": { + "External id": 34905,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972026369.216, "dur": 1.527, + "args": { + "External id": 34906,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972026372.243, "dur": 0.399, + "args": { + "External id": 34907,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972026373.759, "dur": 0.407, + "args": { + "External id": 34908,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972026390.258, "dur": 25.998, + "args": { + "External id": 34909,"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": 4183437, "tid": 31318, + "ts": 658972026483.557, "dur": 355.213, + "args": { + "External id": 34910,"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": 4183437, "tid": 31318, + "ts": 658972026513.998, "dur": 318.980, + "args": { + "External id": 34911,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972026523.921, "dur": 302.488, + "args": { + "External id": 34912,"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": 4183437, "tid": 31318, + "ts": 658972026861.707, "dur": 2.122, + "args": { + "External id": 34913,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972026972.866, "dur": 1659.142, + "args": { + "External id": 34914,"Sequence number": 459928, "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": 4183437, "tid": 31318, "ts": 658972026972.866, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972027098.577, "dur": 105.158, + "args": { + "External id": 34915,"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": 4183437, "tid": 31318, + "ts": 658972027245.311, "dur": 64.979, + "args": { + "External id": 34916,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972027332.624, "dur": 45.183, + "args": { + "External id": 34917,"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": 4183437, "tid": 31318, + "ts": 658972027387.657, "dur": 25.445, + "args": { + "External id": 34918,"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": 4183437, "tid": 31318, + "ts": 658972027418.651, "dur": 32.849, + "args": { + "External id": 34919,"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": 4183437, "tid": 31318, + "ts": 658972027460.517, "dur": 21.278, + "args": { + "External id": 34920,"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": 4183437, "tid": 31318, + "ts": 658972027491.959, "dur": 29.230, + "args": { + "External id": 34921,"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": 4183437, "tid": 31318, + "ts": 658972027552.865, "dur": 24.679, + "args": { + "External id": 34922,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972027595.708, "dur": 36.312, + "args": { + "External id": 34923,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972027652.332, "dur": 78.641, + "args": { + "External id": 34924,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972027751.536, "dur": 18.112, + "args": { + "External id": 34925,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972027781.965, "dur": 45.442, + "args": { + "External id": 34926,"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": 4183437, "tid": 31318, + "ts": 658972027830.965, "dur": 30.256, + "args": { + "External id": 34927,"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": 4183437, "tid": 31318, + "ts": 658972027888.108, "dur": 174.841, + "args": { + "External id": 34928,"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": 4183437, "tid": 31318, + "ts": 658972027971.524, "dur": 5.765, + "args": { + "External id": 34929,"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": 4183437, "tid": 31318, + "ts": 658972027979.345, "dur": 3.760, + "args": { + "External id": 34930,"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": 4183437, "tid": 31318, + "ts": 658972028094.288, "dur": 28.380, + "args": { + "External id": 34931,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972028134.047, "dur": 15.621, + "args": { + "External id": 34932,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972028158.369, "dur": 42.560, + "args": { + "External id": 34933,"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": 4183437, "tid": 31318, + "ts": 658972028206.384, "dur": 34.755, + "args": { + "External id": 34934,"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": 4183437, "tid": 31318, + "ts": 658972028247.926, "dur": 48.628, + "args": { + "External id": 34935,"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": 4183437, "tid": 31318, + "ts": 658972028305.710, "dur": 31.399, + "args": { + "External id": 34936,"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": 4183437, "tid": 31318, + "ts": 658972028346.688, "dur": 26.641, + "args": { + "External id": 34937,"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": 4183437, "tid": 31318, + "ts": 658972028379.464, "dur": 29.917, + "args": { + "External id": 34938,"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": 4183437, "tid": 31318, + "ts": 658972028429.030, "dur": 24.884, + "args": { + "External id": 34939,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972028474.308, "dur": 27.575, + "args": { + "External id": 34940,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972028520.983, "dur": 17.521, + "args": { + "External id": 34941,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972028553.117, "dur": 15.532, + "args": { + "External id": 34942,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972028584.373, "dur": 18.011, + "args": { + "External id": 34943,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972028710.594, "dur": 16.229, + "args": { + "External id": 34944,"Record function id": 0, "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972028714.207, "dur": 11.567, + "args": { + "External id": 34945,"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": 4183437, "tid": 31318, + "ts": 658972028718.641, "dur": 5.683, + "args": { + "External id": 34946,"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": 4183437, "tid": 31318, + "ts": 658972028720.120, "dur": 3.992, + "args": { + "External id": 34947,"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": 4183437, "tid": 31318, + "ts": 658972028730.613, "dur": 5.056, + "args": { + "External id": 34948,"Record function id": 0, "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972028732.309, "dur": 2.930, + "args": { + "External id": 34949,"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": 4183437, "tid": 31318, + "ts": 658972028733.144, "dur": 1.509, + "args": { + "External id": 34950,"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": 4183437, "tid": 31318, + "ts": 658972028733.761, "dur": 0.827, + "args": { + "External id": 34951,"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": 4183437, "tid": 31318, + "ts": 658972028738.901, "dur": 4.472, + "args": { + "External id": 34952,"Record function id": 0, "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972028740.341, "dur": 2.595, + "args": { + "External id": 34953,"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": 4183437, "tid": 31318, + "ts": 658972028740.977, "dur": 1.497, + "args": { + "External id": 34954,"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": 4183437, "tid": 31318, + "ts": 658972028741.750, "dur": 0.606, + "args": { + "External id": 34955,"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": 4183437, "tid": 31318, + "ts": 658972028746.589, "dur": 5.720, + "args": { + "External id": 34956,"Record function id": 0, "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972028747.854, "dur": 4.037, + "args": { + "External id": 34957,"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": 4183437, "tid": 31318, + "ts": 658972028748.556, "dur": 2.879, + "args": { + "External id": 34958,"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": 4183437, "tid": 31318, + "ts": 658972028748.910, "dur": 2.437, + "args": { + "External id": 34959,"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": 4183437, "tid": 31318, + "ts": 658972028755.314, "dur": 4.494, + "args": { + "External id": 34960,"Record function id": 0, "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972028756.657, "dur": 2.705, + "args": { + "External id": 34961,"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": 4183437, "tid": 31318, + "ts": 658972028757.339, "dur": 1.457, + "args": { + "External id": 34962,"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": 4183437, "tid": 31318, + "ts": 658972028758.027, "dur": 0.705, + "args": { + "External id": 34963,"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": 4183437, "tid": 31318, + "ts": 658972028762.766, "dur": 4.307, + "args": { + "External id": 34964,"Record function id": 0, "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972028763.915, "dur": 2.754, + "args": { + "External id": 34965,"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": 4183437, "tid": 31318, + "ts": 658972028764.528, "dur": 1.642, + "args": { + "External id": 34966,"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": 4183437, "tid": 31318, + "ts": 658972028765.437, "dur": 0.671, + "args": { + "External id": 34967,"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": 4183437, "tid": 31318, + "ts": 658972028770.221, "dur": 4.305, + "args": { + "External id": 34968,"Record function id": 0, "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972028771.568, "dur": 2.501, + "args": { + "External id": 34969,"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": 4183437, "tid": 31318, + "ts": 658972028772.094, "dur": 1.501, + "args": { + "External id": 34970,"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": 4183437, "tid": 31318, + "ts": 658972028772.792, "dur": 0.737, + "args": { + "External id": 34971,"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": 4183437, "tid": 31318, + "ts": 658972028777.521, "dur": 3.924, + "args": { + "External id": 34972,"Record function id": 0, "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972028778.564, "dur": 2.457, + "args": { + "External id": 34973,"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": 4183437, "tid": 31318, + "ts": 658972028779.034, "dur": 1.507, + "args": { + "External id": 34974,"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": 4183437, "tid": 31318, + "ts": 658972028779.805, "dur": 0.671, + "args": { + "External id": 34975,"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": 4183437, "tid": 31318, + "ts": 658972028786.384, "dur": 4.152, + "args": { + "External id": 34976,"Record function id": 0, "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972028787.549, "dur": 2.522, + "args": { + "External id": 34977,"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": 4183437, "tid": 31318, + "ts": 658972028788.083, "dur": 1.537, + "args": { + "External id": 34978,"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": 4183437, "tid": 31318, + "ts": 658972028788.926, "dur": 0.626, + "args": { + "External id": 34979,"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": 4183437, "tid": 31318, + "ts": 658972028794.242, "dur": 57993.140, + "args": { + "External id": 34980,"Record function id": 0, "Sequence number": 459927, "Fwd thread id": 1, "Ev Idx": 1699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972028795.601, "dur": 57983.122, + "args": { + "External id": 34981,"Sequence number": 459927, "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": 4183437, "tid": 31318, "ts": 658972028795.601, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 4183437, "tid": 31318, + "ts": 658972028826.865, "dur": 38.161, + "args": { + "External id": 34982,"Record function id": 0, "Ev Idx": 1701 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 4183437, "tid": 31318, + "ts": 658972028872.629, "dur": 70.796, + "args": { + "External id": 34983,"Record function id": 0, "Ev Idx": 1702 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 4183437, "tid": 31318, + "ts": 658972028949.947, "dur": 57820.585, + "args": { + "External id": 34984,"Record function id": 0, "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972029007.734, "dur": 7.802, + "args": { + "External id": 34985,"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": 4183437, "tid": 31318, + "ts": 658972029024.987, "dur": 4.791, + "args": { + "External id": 34986,"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": 4183437, "tid": 31318, + "ts": 658972029046.865, "dur": 56890.617, + "args": { + "External id": 34987,"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": 4183437, "tid": 31318, + "ts": 658972029062.776, "dur": 56865.960, + "args": { + "External id": 34988,"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": 4183437, "tid": 31318, + "ts": 658972029097.148, "dur": 5.132, + "args": { + "External id": 34989,"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": 4183437, "tid": 31318, + "ts": 658972029108.132, "dur": 56780.219, + "args": { + "External id": 34990,"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": 4183437, "tid": 31318, + "ts": 658972029110.645, "dur": 56776.802, + "args": { + "External id": 34991,"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": 4183437, "tid": 31318, + "ts": 658972029114.243, "dur": 6.624, + "args": { + "External id": 34992,"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": 4183437, "tid": 31318, + "ts": 658972029122.711, "dur": 56761.094, + "args": { + "External id": 34993,"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": 4183437, "tid": 31318, + "ts": 658972086035.359, "dur": 10.508, + "args": { + "External id": 34994,"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": 4183437, "tid": 31318, + "ts": 658972086038.391, "dur": 7.132, + "args": { + "External id": 34995,"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": 4183437, "tid": 31318, + "ts": 658972086093.119, "dur": 323.741, + "args": { + "External id": 34996,"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": 4183437, "tid": 31318, + "ts": 658972086120.667, "dur": 290.921, + "args": { + "External id": 34997,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972086133.816, "dur": 272.201, + "args": { + "External id": 34998,"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": 4183437, "tid": 31318, + "ts": 658972086435.890, "dur": 2.107, + "args": { + "External id": 34999,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972086497.355, "dur": 6.220, + "args": { + "External id": 35000,"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": 4183437, "tid": 31318, + "ts": 658972086561.752, "dur": 1.516, + "args": { + "External id": 35001,"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": 4183437, "tid": 31318, + "ts": 658972086579.719, "dur": 1.344, + "args": { + "External id": 35002,"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": 4183437, "tid": 31318, + "ts": 658972086594.070, "dur": 0.885, + "args": { + "External id": 35003,"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": 4183437, "tid": 31318, + "ts": 658972086607.044, "dur": 0.922, + "args": { + "External id": 35004,"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": 4183437, "tid": 31318, + "ts": 658972086621.335, "dur": 0.701, + "args": { + "External id": 35005,"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": 4183437, "tid": 31318, + "ts": 658972086633.043, "dur": 1.065, + "args": { + "External id": 35006,"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": 4183437, "tid": 31318, + "ts": 658972086647.921, "dur": 2.567, + "args": { + "External id": 35007,"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": 4183437, "tid": 31318, + "ts": 658972086700.980, "dur": 1.421, + "args": { + "External id": 35008,"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": 4183437, "tid": 31318, + "ts": 658972086801.902, "dur": 2642.397, + "args": { + "External id": 35009,"Record function id": 0, "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 4183437, "tid": 31318, + "ts": 658972086821.417, "dur": 1009.687, + "args": { + "External id": 35010,"Record function id": 0, "Ev Idx": 1729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 4183437, "tid": 31318, + "ts": 658972086842.555, "dur": 298.456, + "args": { + "External id": 35011,"Record function id": 0, "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972086919.116, "dur": 4.011, + "args": { + "External id": 35012,"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": 4183437, "tid": 31318, + "ts": 658972086926.341, "dur": 1.059, + "args": { + "External id": 35013,"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": 4183437, "tid": 31318, + "ts": 658972086929.320, "dur": 0.951, + "args": { + "External id": 35014,"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": 4183437, "tid": 31318, + "ts": 658972086932.383, "dur": 2.089, + "args": { + "External id": 35015,"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": 4183437, "tid": 31318, + "ts": 658972086936.389, "dur": 0.825, + "args": { + "External id": 35016,"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": 4183437, "tid": 31318, + "ts": 658972086938.865, "dur": 0.990, + "args": { + "External id": 35017,"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": 4183437, "tid": 31318, + "ts": 658972086941.575, "dur": 2.283, + "args": { + "External id": 35018,"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": 4183437, "tid": 31318, + "ts": 658972086945.635, "dur": 0.694, + "args": { + "External id": 35019,"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": 4183437, "tid": 31318, + "ts": 658972086948.124, "dur": 0.662, + "args": { + "External id": 35020,"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": 4183437, "tid": 31318, + "ts": 658972086950.614, "dur": 0.841, + "args": { + "External id": 35021,"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": 4183437, "tid": 31318, + "ts": 658972086969.288, "dur": 143.890, + "args": { + "External id": 35022,"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": 4183437, "tid": 31318, + "ts": 658972086985.518, "dur": 123.465, + "args": { + "External id": 35023,"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": 4183437, "tid": 31318, + "ts": 658972086999.538, "dur": 12.397, + "args": { + "External id": 35024,"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": 4183437, "tid": 31318, + "ts": 658972087014.771, "dur": 62.943, + "args": { + "External id": 35025,"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": 4183437, "tid": 31318, + "ts": 658972087017.251, "dur": 60.093, + "args": { + "External id": 35026,"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": 4183437, "tid": 31318, + "ts": 658972087021.112, "dur": 6.795, + "args": { + "External id": 35027,"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": 4183437, "tid": 31318, + "ts": 658972087029.568, "dur": 47.262, + "args": { + "External id": 35028,"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": 4183437, "tid": 31318, + "ts": 658972087216.028, "dur": 606.554, + "args": { + "External id": 35029,"Record function id": 0, "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 4183437, "tid": 31318, + "ts": 658972087232.376, "dur": 577.295, + "args": { + "External id": 35030,"Record function id": 0, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972087301.321, "dur": 6.310, + "args": { + "External id": 35031,"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": 4183437, "tid": 31318, + "ts": 658972087322.687, "dur": 32.158, + "args": { + "External id": 35032,"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": 4183437, "tid": 31318, + "ts": 658972087327.759, "dur": 2.269, + "args": { + "External id": 35033,"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": 4183437, "tid": 31318, + "ts": 658972087332.126, "dur": 0.402, + "args": { + "External id": 35034,"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": 4183437, "tid": 31318, + "ts": 658972087334.164, "dur": 0.209, + "args": { + "External id": 35035,"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": 4183437, "tid": 31318, + "ts": 658972087337.118, "dur": 0.348, + "args": { + "External id": 35036,"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": 4183437, "tid": 31318, + "ts": 658972087338.648, "dur": 0.391, + "args": { + "External id": 35037,"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": 4183437, "tid": 31318, + "ts": 658972087340.398, "dur": 0.524, + "args": { + "External id": 35038,"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": 4183437, "tid": 31318, + "ts": 658972087343.179, "dur": 1.629, + "args": { + "External id": 35039,"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": 4183437, "tid": 31318, + "ts": 658972087345.962, "dur": 0.335, + "args": { + "External id": 35040,"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": 4183437, "tid": 31318, + "ts": 658972087347.807, "dur": 1.366, + "args": { + "External id": 35041,"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": 4183437, "tid": 31318, + "ts": 658972087367.189, "dur": 33.245, + "args": { + "External id": 35042,"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": 4183437, "tid": 31318, + "ts": 658972087430.901, "dur": 100.971, + "args": { + "External id": 35043,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972087440.887, "dur": 4.307, + "args": { + "External id": 35044,"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": 4183437, "tid": 31318, + "ts": 658972087450.235, "dur": 10.005, + "args": { + "External id": 35045,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972087454.471, "dur": 5.347, + "args": { + "External id": 35046,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972087457.964, "dur": 0.574, + "args": { + "External id": 35047,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972087466.766, "dur": 24.830, + "args": { + "External id": 35048,"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": 4183437, "tid": 31318, + "ts": 658972087469.091, "dur": 0.593, + "args": { + "External id": 35049,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972087471.006, "dur": 1.892, + "args": { + "External id": 35050,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972087474.313, "dur": 0.300, + "args": { + "External id": 35051,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972087475.499, "dur": 1.429, + "args": { + "External id": 35052,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972087478.881, "dur": 0.303, + "args": { + "External id": 35053,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972087480.444, "dur": 0.423, + "args": { + "External id": 35054,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972087481.878, "dur": 0.354, + "args": { + "External id": 35055,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972087484.208, "dur": 0.257, + "args": { + "External id": 35056,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972087486.019, "dur": 0.272, + "args": { + "External id": 35057,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972087503.203, "dur": 20.191, + "args": { + "External id": 35058,"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": 4183437, "tid": 31318, + "ts": 658972087576.138, "dur": 161.957, + "args": { + "External id": 35059,"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": 4183437, "tid": 31318, + "ts": 658972087598.600, "dur": 132.217, + "args": { + "External id": 35060,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972087609.783, "dur": 116.408, + "args": { + "External id": 35061,"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": 4183437, "tid": 31318, + "ts": 658972087754.856, "dur": 1.835, + "args": { + "External id": 35062,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972087839.476, "dur": 1584.890, + "args": { + "External id": 35063,"Sequence number": 459926, "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": 4183437, "tid": 31318, "ts": 658972087839.476, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972087953.006, "dur": 99.880, + "args": { + "External id": 35064,"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": 4183437, "tid": 31318, + "ts": 658972088098.531, "dur": 41.310, + "args": { + "External id": 35065,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972088159.001, "dur": 39.653, + "args": { + "External id": 35066,"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": 4183437, "tid": 31318, + "ts": 658972088211.144, "dur": 25.947, + "args": { + "External id": 35067,"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": 4183437, "tid": 31318, + "ts": 658972088244.314, "dur": 54.706, + "args": { + "External id": 35068,"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": 4183437, "tid": 31318, + "ts": 658972088308.698, "dur": 27.750, + "args": { + "External id": 35069,"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": 4183437, "tid": 31318, + "ts": 658972088343.101, "dur": 28.737, + "args": { + "External id": 35070,"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": 4183437, "tid": 31318, + "ts": 658972088399.074, "dur": 23.076, + "args": { + "External id": 35071,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972088441.776, "dur": 27.793, + "args": { + "External id": 35072,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972088489.809, "dur": 20.339, + "args": { + "External id": 35073,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972088522.161, "dur": 14.855, + "args": { + "External id": 35074,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972088543.837, "dur": 36.085, + "args": { + "External id": 35075,"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": 4183437, "tid": 31318, + "ts": 658972088583.139, "dur": 30.157, + "args": { + "External id": 35076,"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": 4183437, "tid": 31318, + "ts": 658972088640.759, "dur": 214.263, + "args": { + "External id": 35077,"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": 4183437, "tid": 31318, + "ts": 658972088761.504, "dur": 7.580, + "args": { + "External id": 35078,"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": 4183437, "tid": 31318, + "ts": 658972088770.987, "dur": 1.781, + "args": { + "External id": 35079,"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": 4183437, "tid": 31318, + "ts": 658972088890.196, "dur": 28.864, + "args": { + "External id": 35080,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972088930.121, "dur": 14.757, + "args": { + "External id": 35081,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972088952.980, "dur": 53.558, + "args": { + "External id": 35082,"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": 4183437, "tid": 31318, + "ts": 658972089012.586, "dur": 31.087, + "args": { + "External id": 35083,"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": 4183437, "tid": 31318, + "ts": 658972089052.600, "dur": 28.297, + "args": { + "External id": 35084,"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": 4183437, "tid": 31318, + "ts": 658972089085.420, "dur": 27.380, + "args": { + "External id": 35085,"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": 4183437, "tid": 31318, + "ts": 658972089118.780, "dur": 26.385, + "args": { + "External id": 35086,"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": 4183437, "tid": 31318, + "ts": 658972089150.936, "dur": 27.453, + "args": { + "External id": 35087,"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": 4183437, "tid": 31318, + "ts": 658972089208.297, "dur": 28.386, + "args": { + "External id": 35088,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972089255.084, "dur": 43.168, + "args": { + "External id": 35089,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972089318.046, "dur": 17.273, + "args": { + "External id": 35090,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972089352.714, "dur": 16.647, + "args": { + "External id": 35091,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972089380.419, "dur": 14.309, + "args": { + "External id": 35092,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972089465.499, "dur": 14.459, + "args": { + "External id": 35093,"Record function id": 0, "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972089468.815, "dur": 10.190, + "args": { + "External id": 35094,"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": 4183437, "tid": 31318, + "ts": 658972089472.822, "dur": 5.288, + "args": { + "External id": 35095,"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": 4183437, "tid": 31318, + "ts": 658972089474.203, "dur": 3.828, + "args": { + "External id": 35096,"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": 4183437, "tid": 31318, + "ts": 658972089483.696, "dur": 4.464, + "args": { + "External id": 35097,"Record function id": 0, "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972089484.945, "dur": 2.773, + "args": { + "External id": 35098,"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": 4183437, "tid": 31318, + "ts": 658972089485.771, "dur": 1.416, + "args": { + "External id": 35099,"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": 4183437, "tid": 31318, + "ts": 658972089486.315, "dur": 0.763, + "args": { + "External id": 35100,"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": 4183437, "tid": 31318, + "ts": 658972089491.360, "dur": 6.029, + "args": { + "External id": 35101,"Record function id": 0, "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972089492.351, "dur": 4.610, + "args": { + "External id": 35102,"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": 4183437, "tid": 31318, + "ts": 658972089492.978, "dur": 3.539, + "args": { + "External id": 35103,"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": 4183437, "tid": 31318, + "ts": 658972089493.748, "dur": 2.686, + "args": { + "External id": 35104,"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": 4183437, "tid": 31318, + "ts": 658972089500.514, "dur": 4.390, + "args": { + "External id": 35105,"Record function id": 0, "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972089501.415, "dur": 3.059, + "args": { + "External id": 35106,"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": 4183437, "tid": 31318, + "ts": 658972089502.130, "dur": 1.905, + "args": { + "External id": 35107,"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": 4183437, "tid": 31318, + "ts": 658972089502.978, "dur": 0.990, + "args": { + "External id": 35108,"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": 4183437, "tid": 31318, + "ts": 658972089508.281, "dur": 3.684, + "args": { + "External id": 35109,"Record function id": 0, "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972089509.394, "dur": 2.173, + "args": { + "External id": 35110,"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": 4183437, "tid": 31318, + "ts": 658972089509.864, "dur": 1.272, + "args": { + "External id": 35111,"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": 4183437, "tid": 31318, + "ts": 658972089510.391, "dur": 0.679, + "args": { + "External id": 35112,"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": 4183437, "tid": 31318, + "ts": 658972089515.067, "dur": 4.441, + "args": { + "External id": 35113,"Record function id": 0, "Ev Idx": 1832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972089516.686, "dur": 2.419, + "args": { + "External id": 35114,"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": 4183437, "tid": 31318, + "ts": 658972089517.191, "dur": 1.462, + "args": { + "External id": 35115,"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": 4183437, "tid": 31318, + "ts": 658972089517.885, "dur": 0.703, + "args": { + "External id": 35116,"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": 4183437, "tid": 31318, + "ts": 658972089522.828, "dur": 4.009, + "args": { + "External id": 35117,"Record function id": 0, "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972089524.058, "dur": 2.385, + "args": { + "External id": 35118,"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": 4183437, "tid": 31318, + "ts": 658972089524.720, "dur": 1.296, + "args": { + "External id": 35119,"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": 4183437, "tid": 31318, + "ts": 658972089525.281, "dur": 0.668, + "args": { + "External id": 35120,"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": 4183437, "tid": 31318, + "ts": 658972089529.901, "dur": 3.645, + "args": { + "External id": 35121,"Record function id": 0, "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972089530.939, "dur": 2.186, + "args": { + "External id": 35122,"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": 4183437, "tid": 31318, + "ts": 658972089531.415, "dur": 1.279, + "args": { + "External id": 35123,"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": 4183437, "tid": 31318, + "ts": 658972089531.974, "dur": 0.655, + "args": { + "External id": 35124,"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": 4183437, "tid": 31318, + "ts": 658972089536.605, "dur": 3.666, + "args": { + "External id": 35125,"Record function id": 0, "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972089537.803, "dur": 2.029, + "args": { + "External id": 35126,"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": 4183437, "tid": 31318, + "ts": 658972089538.259, "dur": 1.149, + "args": { + "External id": 35127,"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": 4183437, "tid": 31318, + "ts": 658972089538.819, "dur": 0.523, + "args": { + "External id": 35128,"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": 4183437, "tid": 31318, + "ts": 658972089544.061, "dur": 14759.194, + "args": { + "External id": 35129,"Record function id": 0, "Sequence number": 459925, "Fwd thread id": 1, "Ev Idx": 1848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972089545.148, "dur": 14749.707, + "args": { + "External id": 35130,"Sequence number": 459925, "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": 4183437, "tid": 31318, "ts": 658972089545.148, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 4183437, "tid": 31318, + "ts": 658972089574.523, "dur": 35.684, + "args": { + "External id": 35131,"Record function id": 0, "Ev Idx": 1850 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 4183437, "tid": 31318, + "ts": 658972089617.530, "dur": 106.002, + "args": { + "External id": 35132,"Record function id": 0, "Ev Idx": 1851 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 4183437, "tid": 31318, + "ts": 658972089731.849, "dur": 14554.117, + "args": { + "External id": 35133,"Record function id": 0, "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972089825.133, "dur": 7.754, + "args": { + "External id": 35134,"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": 4183437, "tid": 31318, + "ts": 658972089843.065, "dur": 5.860, + "args": { + "External id": 35135,"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": 4183437, "tid": 31318, + "ts": 658972089868.147, "dur": 13708.476, + "args": { + "External id": 35136,"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": 4183437, "tid": 31318, + "ts": 658972089881.850, "dur": 13683.039, + "args": { + "External id": 35137,"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": 4183437, "tid": 31318, + "ts": 658972089909.125, "dur": 16.267, + "args": { + "External id": 35138,"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": 4183437, "tid": 31318, + "ts": 658972089931.024, "dur": 13598.881, + "args": { + "External id": 35139,"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": 4183437, "tid": 31318, + "ts": 658972089933.347, "dur": 13595.906, + "args": { + "External id": 35140,"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": 4183437, "tid": 31318, + "ts": 658972089938.218, "dur": 4.248, + "args": { + "External id": 35141,"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": 4183437, "tid": 31318, + "ts": 658972089944.091, "dur": 13581.352, + "args": { + "External id": 35142,"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": 4183437, "tid": 31318, + "ts": 658972103689.496, "dur": 10.525, + "args": { + "External id": 35143,"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": 4183437, "tid": 31318, + "ts": 658972103692.458, "dur": 7.063, + "args": { + "External id": 35144,"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": 4183437, "tid": 31318, + "ts": 658972103729.458, "dur": 261.019, + "args": { + "External id": 35145,"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": 4183437, "tid": 31318, + "ts": 658972103754.888, "dur": 231.144, + "args": { + "External id": 35146,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972103767.558, "dur": 214.059, + "args": { + "External id": 35147,"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": 4183437, "tid": 31318, + "ts": 658972104005.829, "dur": 1.847, + "args": { + "External id": 35148,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972104063.207, "dur": 5.976, + "args": { + "External id": 35149,"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": 4183437, "tid": 31318, + "ts": 658972104116.692, "dur": 1.088, + "args": { + "External id": 35150,"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": 4183437, "tid": 31318, + "ts": 658972104133.188, "dur": 2.757, + "args": { + "External id": 35151,"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": 4183437, "tid": 31318, + "ts": 658972104150.346, "dur": 0.800, + "args": { + "External id": 35152,"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": 4183437, "tid": 31318, + "ts": 658972104162.290, "dur": 0.905, + "args": { + "External id": 35153,"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": 4183437, "tid": 31318, + "ts": 658972104173.409, "dur": 1.077, + "args": { + "External id": 35154,"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": 4183437, "tid": 31318, + "ts": 658972104184.468, "dur": 2.616, + "args": { + "External id": 35155,"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": 4183437, "tid": 31318, + "ts": 658972104198.033, "dur": 2.588, + "args": { + "External id": 35156,"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": 4183437, "tid": 31318, + "ts": 658972104209.783, "dur": 0.781, + "args": { + "External id": 35157,"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": 4183437, "tid": 31318, + "ts": 658972104318.758, "dur": 2692.173, + "args": { + "External id": 35158,"Record function id": 0, "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 4183437, "tid": 31318, + "ts": 658972104338.519, "dur": 1003.400, + "args": { + "External id": 35159,"Record function id": 0, "Ev Idx": 1878 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 4183437, "tid": 31318, + "ts": 658972104353.591, "dur": 339.631, + "args": { + "External id": 35160,"Record function id": 0, "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972104436.095, "dur": 4.672, + "args": { + "External id": 35161,"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": 4183437, "tid": 31318, + "ts": 658972104443.790, "dur": 1.051, + "args": { + "External id": 35162,"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": 4183437, "tid": 31318, + "ts": 658972104446.816, "dur": 6.085, + "args": { + "External id": 35163,"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": 4183437, "tid": 31318, + "ts": 658972104454.658, "dur": 0.919, + "args": { + "External id": 35164,"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": 4183437, "tid": 31318, + "ts": 658972104457.048, "dur": 0.873, + "args": { + "External id": 35165,"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": 4183437, "tid": 31318, + "ts": 658972104459.541, "dur": 0.982, + "args": { + "External id": 35166,"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": 4183437, "tid": 31318, + "ts": 658972104461.927, "dur": 2.532, + "args": { + "External id": 35167,"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": 4183437, "tid": 31318, + "ts": 658972104465.783, "dur": 0.900, + "args": { + "External id": 35168,"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": 4183437, "tid": 31318, + "ts": 658972104467.956, "dur": 0.966, + "args": { + "External id": 35169,"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": 4183437, "tid": 31318, + "ts": 658972104470.455, "dur": 0.781, + "args": { + "External id": 35170,"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": 4183437, "tid": 31318, + "ts": 658972104488.099, "dur": 135.875, + "args": { + "External id": 35171,"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": 4183437, "tid": 31318, + "ts": 658972104503.482, "dur": 116.143, + "args": { + "External id": 35172,"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": 4183437, "tid": 31318, + "ts": 658972104515.360, "dur": 15.121, + "args": { + "External id": 35173,"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": 4183437, "tid": 31318, + "ts": 658972104533.076, "dur": 60.943, + "args": { + "External id": 35174,"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": 4183437, "tid": 31318, + "ts": 658972104535.523, "dur": 58.197, + "args": { + "External id": 35175,"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": 4183437, "tid": 31318, + "ts": 658972104540.001, "dur": 4.941, + "args": { + "External id": 35176,"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": 4183437, "tid": 31318, + "ts": 658972104546.344, "dur": 46.777, + "args": { + "External id": 35177,"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": 4183437, "tid": 31318, + "ts": 658972104774.604, "dur": 559.074, + "args": { + "External id": 35178,"Record function id": 0, "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 4183437, "tid": 31318, + "ts": 658972104793.785, "dur": 527.470, + "args": { + "External id": 35179,"Record function id": 0, "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972104852.816, "dur": 5.890, + "args": { + "External id": 35180,"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": 4183437, "tid": 31318, + "ts": 658972104872.974, "dur": 29.445, + "args": { + "External id": 35181,"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": 4183437, "tid": 31318, + "ts": 658972104877.264, "dur": 1.547, + "args": { + "External id": 35182,"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": 4183437, "tid": 31318, + "ts": 658972104881.036, "dur": 1.466, + "args": { + "External id": 35183,"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": 4183437, "tid": 31318, + "ts": 658972104884.007, "dur": 0.413, + "args": { + "External id": 35184,"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": 4183437, "tid": 31318, + "ts": 658972104885.639, "dur": 0.508, + "args": { + "External id": 35185,"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": 4183437, "tid": 31318, + "ts": 658972104887.791, "dur": 0.419, + "args": { + "External id": 35186,"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": 4183437, "tid": 31318, + "ts": 658972104889.422, "dur": 2.107, + "args": { + "External id": 35187,"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": 4183437, "tid": 31318, + "ts": 658972104892.506, "dur": 0.661, + "args": { + "External id": 35188,"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": 4183437, "tid": 31318, + "ts": 658972104895.363, "dur": 0.388, + "args": { + "External id": 35189,"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": 4183437, "tid": 31318, + "ts": 658972104896.687, "dur": 0.373, + "args": { + "External id": 35190,"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": 4183437, "tid": 31318, + "ts": 658972104915.200, "dur": 32.548, + "args": { + "External id": 35191,"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": 4183437, "tid": 31318, + "ts": 658972104977.570, "dur": 98.496, + "args": { + "External id": 35192,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972104987.267, "dur": 3.306, + "args": { + "External id": 35193,"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": 4183437, "tid": 31318, + "ts": 658972104995.211, "dur": 9.006, + "args": { + "External id": 35194,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972104999.194, "dur": 4.597, + "args": { + "External id": 35195,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972105002.048, "dur": 0.560, + "args": { + "External id": 35196,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972105010.194, "dur": 29.702, + "args": { + "External id": 35197,"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": 4183437, "tid": 31318, + "ts": 658972105012.284, "dur": 0.381, + "args": { + "External id": 35198,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972105015.087, "dur": 0.274, + "args": { + "External id": 35199,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972105021.620, "dur": 1.822, + "args": { + "External id": 35200,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972105024.378, "dur": 2.087, + "args": { + "External id": 35201,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972105027.560, "dur": 0.169, + "args": { + "External id": 35202,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972105028.897, "dur": 0.365, + "args": { + "External id": 35203,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972105031.276, "dur": 0.330, + "args": { + "External id": 35204,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972105032.599, "dur": 0.529, + "args": { + "External id": 35205,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972105033.915, "dur": 0.230, + "args": { + "External id": 35206,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972105048.518, "dur": 20.025, + "args": { + "External id": 35207,"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": 4183437, "tid": 31318, + "ts": 658972105120.679, "dur": 113.601, + "args": { + "External id": 35208,"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": 4183437, "tid": 31318, + "ts": 658972105141.825, "dur": 89.059, + "args": { + "External id": 35209,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972105150.712, "dur": 75.815, + "args": { + "External id": 35210,"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": 4183437, "tid": 31318, + "ts": 658972105249.133, "dur": 1.819, + "args": { + "External id": 35211,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972105349.413, "dur": 1642.254, + "args": { + "External id": 35212,"Sequence number": 459924, "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": 4183437, "tid": 31318, "ts": 658972105349.413, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972105461.287, "dur": 99.952, + "args": { + "External id": 35213,"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": 4183437, "tid": 31318, + "ts": 658972105602.330, "dur": 35.919, + "args": { + "External id": 35214,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972105695.282, "dur": 50.400, + "args": { + "External id": 35215,"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": 4183437, "tid": 31318, + "ts": 658972105759.531, "dur": 29.438, + "args": { + "External id": 35216,"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": 4183437, "tid": 31318, + "ts": 658972105795.590, "dur": 33.969, + "args": { + "External id": 35217,"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": 4183437, "tid": 31318, + "ts": 658972105835.889, "dur": 20.190, + "args": { + "External id": 35218,"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": 4183437, "tid": 31318, + "ts": 658972105867.825, "dur": 30.666, + "args": { + "External id": 35219,"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": 4183437, "tid": 31318, + "ts": 658972105925.976, "dur": 29.321, + "args": { + "External id": 35220,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972105972.907, "dur": 26.196, + "args": { + "External id": 35221,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972106021.951, "dur": 23.024, + "args": { + "External id": 35222,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972106057.977, "dur": 14.458, + "args": { + "External id": 35223,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972106081.928, "dur": 39.472, + "args": { + "External id": 35224,"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": 4183437, "tid": 31318, + "ts": 658972106124.484, "dur": 30.760, + "args": { + "External id": 35225,"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": 4183437, "tid": 31318, + "ts": 658972106183.904, "dur": 193.061, + "args": { + "External id": 35226,"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": 4183437, "tid": 31318, + "ts": 658972106279.515, "dur": 7.957, + "args": { + "External id": 35227,"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": 4183437, "tid": 31318, + "ts": 658972106290.381, "dur": 2.720, + "args": { + "External id": 35228,"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": 4183437, "tid": 31318, + "ts": 658972106408.510, "dur": 25.260, + "args": { + "External id": 35229,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972106445.839, "dur": 17.603, + "args": { + "External id": 35230,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972106471.731, "dur": 50.961, + "args": { + "External id": 35231,"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": 4183437, "tid": 31318, + "ts": 658972106528.370, "dur": 30.845, + "args": { + "External id": 35232,"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": 4183437, "tid": 31318, + "ts": 658972106567.533, "dur": 31.843, + "args": { + "External id": 35233,"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": 4183437, "tid": 31318, + "ts": 658972106603.794, "dur": 31.319, + "args": { + "External id": 35234,"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": 4183437, "tid": 31318, + "ts": 658972106640.960, "dur": 64.360, + "args": { + "External id": 35235,"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": 4183437, "tid": 31318, + "ts": 658972106715.825, "dur": 47.708, + "args": { + "External id": 35236,"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": 4183437, "tid": 31318, + "ts": 658972106791.270, "dur": 31.474, + "args": { + "External id": 35237,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972106841.335, "dur": 23.916, + "args": { + "External id": 35238,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972106882.673, "dur": 18.765, + "args": { + "External id": 35239,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972106915.635, "dur": 15.104, + "args": { + "External id": 35240,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972106946.706, "dur": 17.046, + "args": { + "External id": 35241,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972107032.648, "dur": 14.230, + "args": { + "External id": 35242,"Record function id": 0, "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972107035.385, "dur": 10.559, + "args": { + "External id": 35243,"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": 4183437, "tid": 31318, + "ts": 658972107039.570, "dur": 5.416, + "args": { + "External id": 35244,"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": 4183437, "tid": 31318, + "ts": 658972107040.924, "dur": 3.960, + "args": { + "External id": 35245,"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": 4183437, "tid": 31318, + "ts": 658972107050.739, "dur": 6.007, + "args": { + "External id": 35246,"Record function id": 0, "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972107052.171, "dur": 4.108, + "args": { + "External id": 35247,"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": 4183437, "tid": 31318, + "ts": 658972107053.026, "dur": 2.747, + "args": { + "External id": 35248,"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": 4183437, "tid": 31318, + "ts": 658972107053.478, "dur": 2.208, + "args": { + "External id": 35249,"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": 4183437, "tid": 31318, + "ts": 658972107059.949, "dur": 4.167, + "args": { + "External id": 35250,"Record function id": 0, "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972107061.145, "dur": 2.541, + "args": { + "External id": 35251,"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": 4183437, "tid": 31318, + "ts": 658972107061.831, "dur": 1.402, + "args": { + "External id": 35252,"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": 4183437, "tid": 31318, + "ts": 658972107062.440, "dur": 0.714, + "args": { + "External id": 35253,"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": 4183437, "tid": 31318, + "ts": 658972107067.329, "dur": 3.513, + "args": { + "External id": 35254,"Record function id": 0, "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972107068.552, "dur": 1.850, + "args": { + "External id": 35255,"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": 4183437, "tid": 31318, + "ts": 658972107069.074, "dur": 0.937, + "args": { + "External id": 35256,"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": 4183437, "tid": 31318, + "ts": 658972107069.360, "dur": 0.585, + "args": { + "External id": 35257,"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": 4183437, "tid": 31318, + "ts": 658972107073.938, "dur": 3.707, + "args": { + "External id": 35258,"Record function id": 0, "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972107075.013, "dur": 2.236, + "args": { + "External id": 35259,"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": 4183437, "tid": 31318, + "ts": 658972107075.475, "dur": 1.333, + "args": { + "External id": 35260,"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": 4183437, "tid": 31318, + "ts": 658972107076.185, "dur": 0.558, + "args": { + "External id": 35261,"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": 4183437, "tid": 31318, + "ts": 658972107080.776, "dur": 3.663, + "args": { + "External id": 35262,"Record function id": 0, "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972107081.679, "dur": 2.344, + "args": { + "External id": 35263,"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": 4183437, "tid": 31318, + "ts": 658972107082.340, "dur": 1.271, + "args": { + "External id": 35264,"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": 4183437, "tid": 31318, + "ts": 658972107082.893, "dur": 0.652, + "args": { + "External id": 35265,"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": 4183437, "tid": 31318, + "ts": 658972107087.592, "dur": 3.545, + "args": { + "External id": 35266,"Record function id": 0, "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972107088.654, "dur": 2.061, + "args": { + "External id": 35267,"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": 4183437, "tid": 31318, + "ts": 658972107089.150, "dur": 1.172, + "args": { + "External id": 35268,"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": 4183437, "tid": 31318, + "ts": 658972107089.702, "dur": 0.556, + "args": { + "External id": 35269,"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": 4183437, "tid": 31318, + "ts": 658972107094.228, "dur": 3.274, + "args": { + "External id": 35270,"Record function id": 0, "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972107095.099, "dur": 1.992, + "args": { + "External id": 35271,"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": 4183437, "tid": 31318, + "ts": 658972107095.564, "dur": 1.107, + "args": { + "External id": 35272,"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": 4183437, "tid": 31318, + "ts": 658972107095.966, "dur": 0.639, + "args": { + "External id": 35273,"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": 4183437, "tid": 31318, + "ts": 658972107100.512, "dur": 5.057, + "args": { + "External id": 35274,"Record function id": 0, "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972107101.505, "dur": 3.618, + "args": { + "External id": 35275,"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": 4183437, "tid": 31318, + "ts": 658972107101.984, "dur": 2.742, + "args": { + "External id": 35276,"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": 4183437, "tid": 31318, + "ts": 658972107102.399, "dur": 2.265, + "args": { + "External id": 35277,"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": 4183437, "tid": 31318, + "ts": 658972107109.291, "dur": 14856.832, + "args": { + "External id": 35278,"Record function id": 0, "Sequence number": 459923, "Fwd thread id": 1, "Ev Idx": 1997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972107110.433, "dur": 14847.692, + "args": { + "External id": 35279,"Sequence number": 459923, "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": 4183437, "tid": 31318, "ts": 658972107110.433, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 4183437, "tid": 31318, + "ts": 658972107139.321, "dur": 37.902, + "args": { + "External id": 35280,"Record function id": 0, "Ev Idx": 1999 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 4183437, "tid": 31318, + "ts": 658972107184.297, "dur": 61.591, + "args": { + "External id": 35281,"Record function id": 0, "Ev Idx": 2000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 4183437, "tid": 31318, + "ts": 658972107251.583, "dur": 14698.929, + "args": { + "External id": 35282,"Record function id": 0, "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972107359.888, "dur": 7.890, + "args": { + "External id": 35283,"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": 4183437, "tid": 31318, + "ts": 658972107377.873, "dur": 4.656, + "args": { + "External id": 35284,"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": 4183437, "tid": 31318, + "ts": 658972107396.380, "dur": 13832.810, + "args": { + "External id": 35285,"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": 4183437, "tid": 31318, + "ts": 658972107409.126, "dur": 13811.531, + "args": { + "External id": 35286,"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": 4183437, "tid": 31318, + "ts": 658972107437.174, "dur": 13.500, + "args": { + "External id": 35287,"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": 4183437, "tid": 31318, + "ts": 658972107455.614, "dur": 13728.738, + "args": { + "External id": 35288,"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": 4183437, "tid": 31318, + "ts": 658972107457.858, "dur": 13725.779, + "args": { + "External id": 35289,"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": 4183437, "tid": 31318, + "ts": 658972107461.268, "dur": 5.144, + "args": { + "External id": 35290,"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": 4183437, "tid": 31318, + "ts": 658972107468.040, "dur": 13711.932, + "args": { + "External id": 35291,"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": 4183437, "tid": 31318, + "ts": 658972121332.269, "dur": 10.303, + "args": { + "External id": 35292,"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": 4183437, "tid": 31318, + "ts": 658972121335.435, "dur": 6.566, + "args": { + "External id": 35293,"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": 4183437, "tid": 31318, + "ts": 658972121368.827, "dur": 258.443, + "args": { + "External id": 35294,"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": 4183437, "tid": 31318, + "ts": 658972121394.046, "dur": 228.934, + "args": { + "External id": 35295,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972121406.398, "dur": 211.850, + "args": { + "External id": 35296,"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": 4183437, "tid": 31318, + "ts": 658972121643.499, "dur": 2.041, + "args": { + "External id": 35297,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972121749.168, "dur": 6.270, + "args": { + "External id": 35298,"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": 4183437, "tid": 31318, + "ts": 658972121799.612, "dur": 2.881, + "args": { + "External id": 35299,"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": 4183437, "tid": 31318, + "ts": 658972121817.310, "dur": 1.279, + "args": { + "External id": 35300,"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": 4183437, "tid": 31318, + "ts": 658972121829.683, "dur": 1.122, + "args": { + "External id": 35301,"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": 4183437, "tid": 31318, + "ts": 658972121840.826, "dur": 0.967, + "args": { + "External id": 35302,"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": 4183437, "tid": 31318, + "ts": 658972121852.437, "dur": 2.440, + "args": { + "External id": 35303,"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": 4183437, "tid": 31318, + "ts": 658972121864.786, "dur": 0.896, + "args": { + "External id": 35304,"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": 4183437, "tid": 31318, + "ts": 658972121877.254, "dur": 2.847, + "args": { + "External id": 35305,"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": 4183437, "tid": 31318, + "ts": 658972121890.857, "dur": 0.876, + "args": { + "External id": 35306,"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": 4183437, "tid": 31318, + "ts": 658972121984.704, "dur": 2730.133, + "args": { + "External id": 35307,"Record function id": 0, "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 4183437, "tid": 31318, + "ts": 658972122003.174, "dur": 1046.131, + "args": { + "External id": 35308,"Record function id": 0, "Ev Idx": 2027 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 4183437, "tid": 31318, + "ts": 658972122018.559, "dur": 325.868, + "args": { + "External id": 35309,"Record function id": 0, "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972122096.076, "dur": 6.324, + "args": { + "External id": 35310,"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": 4183437, "tid": 31318, + "ts": 658972122105.164, "dur": 0.933, + "args": { + "External id": 35311,"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": 4183437, "tid": 31318, + "ts": 658972122107.868, "dur": 1.140, + "args": { + "External id": 35312,"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": 4183437, "tid": 31318, + "ts": 658972122110.873, "dur": 0.921, + "args": { + "External id": 35313,"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": 4183437, "tid": 31318, + "ts": 658972122113.397, "dur": 0.582, + "args": { + "External id": 35314,"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": 4183437, "tid": 31318, + "ts": 658972122115.891, "dur": 0.926, + "args": { + "External id": 35315,"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": 4183437, "tid": 31318, + "ts": 658972122119.063, "dur": 2.218, + "args": { + "External id": 35316,"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": 4183437, "tid": 31318, + "ts": 658972122122.768, "dur": 1.197, + "args": { + "External id": 35317,"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": 4183437, "tid": 31318, + "ts": 658972122125.487, "dur": 2.820, + "args": { + "External id": 35318,"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": 4183437, "tid": 31318, + "ts": 658972122129.967, "dur": 0.777, + "args": { + "External id": 35319,"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": 4183437, "tid": 31318, + "ts": 658972122147.494, "dur": 162.240, + "args": { + "External id": 35320,"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": 4183437, "tid": 31318, + "ts": 658972122163.159, "dur": 141.446, + "args": { + "External id": 35321,"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": 4183437, "tid": 31318, + "ts": 658972122177.154, "dur": 14.423, + "args": { + "External id": 35322,"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": 4183437, "tid": 31318, + "ts": 658972122194.206, "dur": 63.574, + "args": { + "External id": 35323,"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": 4183437, "tid": 31318, + "ts": 658972122198.004, "dur": 59.444, + "args": { + "External id": 35324,"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": 4183437, "tid": 31318, + "ts": 658972122201.457, "dur": 5.150, + "args": { + "External id": 35325,"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": 4183437, "tid": 31318, + "ts": 658972122208.189, "dur": 48.528, + "args": { + "External id": 35326,"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": 4183437, "tid": 31318, + "ts": 658972122423.712, "dur": 617.114, + "args": { + "External id": 35327,"Record function id": 0, "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 4183437, "tid": 31318, + "ts": 658972122440.429, "dur": 587.837, + "args": { + "External id": 35328,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972122511.268, "dur": 6.490, + "args": { + "External id": 35329,"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": 4183437, "tid": 31318, + "ts": 658972122532.773, "dur": 28.648, + "args": { + "External id": 35330,"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": 4183437, "tid": 31318, + "ts": 658972122536.994, "dur": 1.482, + "args": { + "External id": 35331,"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": 4183437, "tid": 31318, + "ts": 658972122541.606, "dur": 0.349, + "args": { + "External id": 35332,"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": 4183437, "tid": 31318, + "ts": 658972122542.804, "dur": 0.405, + "args": { + "External id": 35333,"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": 4183437, "tid": 31318, + "ts": 658972122544.006, "dur": 2.987, + "args": { + "External id": 35334,"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": 4183437, "tid": 31318, + "ts": 658972122547.620, "dur": 0.190, + "args": { + "External id": 35335,"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": 4183437, "tid": 31318, + "ts": 658972122548.436, "dur": 0.322, + "args": { + "External id": 35336,"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": 4183437, "tid": 31318, + "ts": 658972122550.794, "dur": 0.361, + "args": { + "External id": 35337,"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": 4183437, "tid": 31318, + "ts": 658972122552.056, "dur": 0.236, + "args": { + "External id": 35338,"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": 4183437, "tid": 31318, + "ts": 658972122553.155, "dur": 0.152, + "args": { + "External id": 35339,"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": 4183437, "tid": 31318, + "ts": 658972122571.129, "dur": 31.004, + "args": { + "External id": 35340,"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": 4183437, "tid": 31318, + "ts": 658972122635.569, "dur": 163.627, + "args": { + "External id": 35341,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972122645.027, "dur": 3.318, + "args": { + "External id": 35342,"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": 4183437, "tid": 31318, + "ts": 658972122705.007, "dur": 12.499, + "args": { + "External id": 35343,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972122709.492, "dur": 7.553, + "args": { + "External id": 35344,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972122713.707, "dur": 1.564, + "args": { + "External id": 35345,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972122726.749, "dur": 26.297, + "args": { + "External id": 35346,"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": 4183437, "tid": 31318, + "ts": 658972122728.648, "dur": 1.859, + "args": { + "External id": 35347,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972122732.077, "dur": 0.373, + "args": { + "External id": 35348,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972122733.463, "dur": 0.395, + "args": { + "External id": 35349,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972122736.414, "dur": 0.247, + "args": { + "External id": 35350,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972122737.760, "dur": 0.224, + "args": { + "External id": 35351,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972122739.427, "dur": 1.497, + "args": { + "External id": 35352,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972122741.997, "dur": 0.297, + "args": { + "External id": 35353,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972122743.543, "dur": 0.291, + "args": { + "External id": 35354,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972122746.233, "dur": 1.742, + "args": { + "External id": 35355,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972122765.811, "dur": 24.892, + "args": { + "External id": 35356,"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": 4183437, "tid": 31318, + "ts": 658972122846.947, "dur": 115.651, + "args": { + "External id": 35357,"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": 4183437, "tid": 31318, + "ts": 658972122871.622, "dur": 87.646, + "args": { + "External id": 35358,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972122881.467, "dur": 73.952, + "args": { + "External id": 35359,"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": 4183437, "tid": 31318, + "ts": 658972122976.188, "dur": 1.664, + "args": { + "External id": 35360,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972123056.458, "dur": 1636.558, + "args": { + "External id": 35361,"Sequence number": 459922, "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": 4183437, "tid": 31318, "ts": 658972123056.458, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972123166.447, "dur": 117.143, + "args": { + "External id": 35362,"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": 4183437, "tid": 31318, + "ts": 658972123330.756, "dur": 45.267, + "args": { + "External id": 35363,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972123394.513, "dur": 43.754, + "args": { + "External id": 35364,"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": 4183437, "tid": 31318, + "ts": 658972123447.834, "dur": 25.978, + "args": { + "External id": 35365,"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": 4183437, "tid": 31318, + "ts": 658972123479.703, "dur": 33.169, + "args": { + "External id": 35366,"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": 4183437, "tid": 31318, + "ts": 658972123520.444, "dur": 20.379, + "args": { + "External id": 35367,"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": 4183437, "tid": 31318, + "ts": 658972123550.016, "dur": 29.685, + "args": { + "External id": 35368,"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": 4183437, "tid": 31318, + "ts": 658972123603.609, "dur": 24.460, + "args": { + "External id": 35369,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972123645.509, "dur": 72.287, + "args": { + "External id": 35370,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972123740.798, "dur": 19.556, + "args": { + "External id": 35371,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972123774.160, "dur": 14.088, + "args": { + "External id": 35372,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972123797.371, "dur": 39.622, + "args": { + "External id": 35373,"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": 4183437, "tid": 31318, + "ts": 658972123840.272, "dur": 30.888, + "args": { + "External id": 35374,"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": 4183437, "tid": 31318, + "ts": 658972123901.429, "dur": 173.212, + "args": { + "External id": 35375,"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": 4183437, "tid": 31318, + "ts": 658972123985.146, "dur": 5.596, + "args": { + "External id": 35376,"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": 4183437, "tid": 31318, + "ts": 658972123992.393, "dur": 2.970, + "args": { + "External id": 35377,"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": 4183437, "tid": 31318, + "ts": 658972124107.812, "dur": 23.428, + "args": { + "External id": 35378,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972124143.060, "dur": 16.321, + "args": { + "External id": 35379,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972124167.958, "dur": 46.066, + "args": { + "External id": 35380,"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": 4183437, "tid": 31318, + "ts": 658972124221.337, "dur": 31.843, + "args": { + "External id": 35381,"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": 4183437, "tid": 31318, + "ts": 658972124260.063, "dur": 50.479, + "args": { + "External id": 35382,"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": 4183437, "tid": 31318, + "ts": 658972124318.125, "dur": 29.503, + "args": { + "External id": 35383,"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": 4183437, "tid": 31318, + "ts": 658972124353.890, "dur": 26.875, + "args": { + "External id": 35384,"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": 4183437, "tid": 31318, + "ts": 658972124389.913, "dur": 48.799, + "args": { + "External id": 35385,"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": 4183437, "tid": 31318, + "ts": 658972124464.106, "dur": 28.355, + "args": { + "External id": 35386,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972124511.738, "dur": 27.980, + "args": { + "External id": 35387,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972124551.846, "dur": 17.297, + "args": { + "External id": 35388,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972124583.433, "dur": 18.598, + "args": { + "External id": 35389,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972124612.876, "dur": 16.209, + "args": { + "External id": 35390,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972124737.449, "dur": 16.004, + "args": { + "External id": 35391,"Record function id": 0, "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972124740.667, "dur": 11.811, + "args": { + "External id": 35392,"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": 4183437, "tid": 31318, + "ts": 658972124745.014, "dur": 6.584, + "args": { + "External id": 35393,"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": 4183437, "tid": 31318, + "ts": 658972124746.417, "dur": 5.093, + "args": { + "External id": 35394,"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": 4183437, "tid": 31318, + "ts": 658972124757.264, "dur": 3.943, + "args": { + "External id": 35395,"Record function id": 0, "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972124758.559, "dur": 2.231, + "args": { + "External id": 35396,"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": 4183437, "tid": 31318, + "ts": 658972124759.180, "dur": 1.170, + "args": { + "External id": 35397,"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": 4183437, "tid": 31318, + "ts": 658972124759.503, "dur": 0.768, + "args": { + "External id": 35398,"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": 4183437, "tid": 31318, + "ts": 658972124764.423, "dur": 4.388, + "args": { + "External id": 35399,"Record function id": 0, "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972124765.764, "dur": 2.650, + "args": { + "External id": 35400,"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": 4183437, "tid": 31318, + "ts": 658972124766.516, "dur": 1.462, + "args": { + "External id": 35401,"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": 4183437, "tid": 31318, + "ts": 658972124767.058, "dur": 0.832, + "args": { + "External id": 35402,"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": 4183437, "tid": 31318, + "ts": 658972124772.058, "dur": 3.502, + "args": { + "External id": 35403,"Record function id": 0, "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972124773.047, "dur": 2.122, + "args": { + "External id": 35404,"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": 4183437, "tid": 31318, + "ts": 658972124773.724, "dur": 1.039, + "args": { + "External id": 35405,"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": 4183437, "tid": 31318, + "ts": 658972124774.071, "dur": 0.627, + "args": { + "External id": 35406,"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": 4183437, "tid": 31318, + "ts": 658972124778.683, "dur": 3.706, + "args": { + "External id": 35407,"Record function id": 0, "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972124779.895, "dur": 2.098, + "args": { + "External id": 35408,"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": 4183437, "tid": 31318, + "ts": 658972124780.553, "dur": 1.014, + "args": { + "External id": 35409,"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": 4183437, "tid": 31318, + "ts": 658972124780.927, "dur": 0.574, + "args": { + "External id": 35410,"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": 4183437, "tid": 31318, + "ts": 658972124785.871, "dur": 3.556, + "args": { + "External id": 35411,"Record function id": 0, "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972124786.778, "dur": 2.229, + "args": { + "External id": 35412,"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": 4183437, "tid": 31318, + "ts": 658972124787.270, "dur": 1.322, + "args": { + "External id": 35413,"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": 4183437, "tid": 31318, + "ts": 658972124787.894, "dur": 0.630, + "args": { + "External id": 35414,"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": 4183437, "tid": 31318, + "ts": 658972124792.855, "dur": 3.209, + "args": { + "External id": 35415,"Record function id": 0, "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972124793.716, "dur": 1.943, + "args": { + "External id": 35416,"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": 4183437, "tid": 31318, + "ts": 658972124794.207, "dur": 1.029, + "args": { + "External id": 35417,"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": 4183437, "tid": 31318, + "ts": 658972124794.577, "dur": 0.596, + "args": { + "External id": 35418,"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": 4183437, "tid": 31318, + "ts": 658972124799.515, "dur": 5.328, + "args": { + "External id": 35419,"Record function id": 0, "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972124800.418, "dur": 4.011, + "args": { + "External id": 35420,"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": 4183437, "tid": 31318, + "ts": 658972124800.924, "dur": 3.107, + "args": { + "External id": 35421,"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": 4183437, "tid": 31318, + "ts": 658972124802.085, "dur": 1.886, + "args": { + "External id": 35422,"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": 4183437, "tid": 31318, + "ts": 658972124808.083, "dur": 4.187, + "args": { + "External id": 35423,"Record function id": 0, "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972124809.200, "dur": 2.680, + "args": { + "External id": 35424,"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": 4183437, "tid": 31318, + "ts": 658972124809.675, "dur": 1.799, + "args": { + "External id": 35425,"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": 4183437, "tid": 31318, + "ts": 658972124810.421, "dur": 0.986, + "args": { + "External id": 35426,"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": 4183437, "tid": 31318, + "ts": 658972124815.866, "dur": 18378.200, + "args": { + "External id": 35427,"Record function id": 0, "Sequence number": 459921, "Fwd thread id": 1, "Ev Idx": 2146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972124817.061, "dur": 18369.114, + "args": { + "External id": 35428,"Sequence number": 459921, "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": 4183437, "tid": 31318, "ts": 658972124817.061, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 4183437, "tid": 31318, + "ts": 658972124845.748, "dur": 38.298, + "args": { + "External id": 35429,"Record function id": 0, "Ev Idx": 2148 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 4183437, "tid": 31318, + "ts": 658972124891.472, "dur": 65.578, + "args": { + "External id": 35430,"Record function id": 0, "Ev Idx": 2149 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 4183437, "tid": 31318, + "ts": 658972124962.508, "dur": 18215.979, + "args": { + "External id": 35431,"Record function id": 0, "Ev Idx": 2150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972125051.838, "dur": 7.531, + "args": { + "External id": 35432,"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": 4183437, "tid": 31318, + "ts": 658972125068.541, "dur": 4.463, + "args": { + "External id": 35433,"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": 4183437, "tid": 31318, + "ts": 658972125085.771, "dur": 17332.145, + "args": { + "External id": 35434,"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": 4183437, "tid": 31318, + "ts": 658972125099.018, "dur": 17310.377, + "args": { + "External id": 35435,"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": 4183437, "tid": 31318, + "ts": 658972125129.333, "dur": 13.633, + "args": { + "External id": 35436,"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": 4183437, "tid": 31318, + "ts": 658972125148.479, "dur": 17224.161, + "args": { + "External id": 35437,"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": 4183437, "tid": 31318, + "ts": 658972125152.013, "dur": 17219.975, + "args": { + "External id": 35438,"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": 4183437, "tid": 31318, + "ts": 658972125155.545, "dur": 4.344, + "args": { + "External id": 35439,"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": 4183437, "tid": 31318, + "ts": 658972125161.389, "dur": 17206.776, + "args": { + "External id": 35440,"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": 4183437, "tid": 31318, + "ts": 658972142505.752, "dur": 9.685, + "args": { + "External id": 35441,"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": 4183437, "tid": 31318, + "ts": 658972142508.601, "dur": 6.399, + "args": { + "External id": 35442,"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": 4183437, "tid": 31318, + "ts": 658972142542.374, "dur": 360.535, + "args": { + "External id": 35443,"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": 4183437, "tid": 31318, + "ts": 658972142565.462, "dur": 332.326, + "args": { + "External id": 35444,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972142576.632, "dur": 313.924, + "args": { + "External id": 35445,"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": 4183437, "tid": 31318, + "ts": 658972142921.351, "dur": 2.324, + "args": { + "External id": 35446,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972142982.878, "dur": 6.280, + "args": { + "External id": 35447,"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": 4183437, "tid": 31318, + "ts": 658972143034.442, "dur": 1.573, + "args": { + "External id": 35448,"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": 4183437, "tid": 31318, + "ts": 658972143050.824, "dur": 1.496, + "args": { + "External id": 35449,"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": 4183437, "tid": 31318, + "ts": 658972143063.223, "dur": 1.121, + "args": { + "External id": 35450,"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": 4183437, "tid": 31318, + "ts": 658972143073.573, "dur": 0.746, + "args": { + "External id": 35451,"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": 4183437, "tid": 31318, + "ts": 658972143084.183, "dur": 0.880, + "args": { + "External id": 35452,"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": 4183437, "tid": 31318, + "ts": 658972143094.819, "dur": 1.142, + "args": { + "External id": 35453,"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": 4183437, "tid": 31318, + "ts": 658972143106.237, "dur": 2.520, + "args": { + "External id": 35454,"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": 4183437, "tid": 31318, + "ts": 658972143118.450, "dur": 0.736, + "args": { + "External id": 35455,"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": 4183437, "tid": 31318, + "ts": 658972143207.749, "dur": 2670.520, + "args": { + "External id": 35456,"Record function id": 0, "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 4183437, "tid": 31318, + "ts": 658972143229.373, "dur": 986.702, + "args": { + "External id": 35457,"Record function id": 0, "Ev Idx": 2176 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 4183437, "tid": 31318, + "ts": 658972143244.468, "dur": 320.104, + "args": { + "External id": 35458,"Record function id": 0, "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972143347.550, "dur": 4.234, + "args": { + "External id": 35459,"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": 4183437, "tid": 31318, + "ts": 658972143354.966, "dur": 1.057, + "args": { + "External id": 35460,"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": 4183437, "tid": 31318, + "ts": 658972143357.739, "dur": 0.928, + "args": { + "External id": 35461,"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": 4183437, "tid": 31318, + "ts": 658972143360.050, "dur": 0.729, + "args": { + "External id": 35462,"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": 4183437, "tid": 31318, + "ts": 658972143362.415, "dur": 0.935, + "args": { + "External id": 35463,"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": 4183437, "tid": 31318, + "ts": 658972143364.861, "dur": 0.615, + "args": { + "External id": 35464,"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": 4183437, "tid": 31318, + "ts": 658972143366.943, "dur": 2.157, + "args": { + "External id": 35465,"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": 4183437, "tid": 31318, + "ts": 658972143370.620, "dur": 1.543, + "args": { + "External id": 35466,"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": 4183437, "tid": 31318, + "ts": 658972143373.797, "dur": 0.801, + "args": { + "External id": 35467,"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": 4183437, "tid": 31318, + "ts": 658972143375.947, "dur": 0.750, + "args": { + "External id": 35468,"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": 4183437, "tid": 31318, + "ts": 658972143394.765, "dur": 140.017, + "args": { + "External id": 35469,"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": 4183437, "tid": 31318, + "ts": 658972143410.677, "dur": 119.765, + "args": { + "External id": 35470,"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": 4183437, "tid": 31318, + "ts": 658972143422.324, "dur": 12.464, + "args": { + "External id": 35471,"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": 4183437, "tid": 31318, + "ts": 658972143437.623, "dur": 64.605, + "args": { + "External id": 35472,"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": 4183437, "tid": 31318, + "ts": 658972143440.233, "dur": 61.609, + "args": { + "External id": 35473,"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": 4183437, "tid": 31318, + "ts": 658972143444.588, "dur": 6.011, + "args": { + "External id": 35474,"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": 4183437, "tid": 31318, + "ts": 658972143452.252, "dur": 48.993, + "args": { + "External id": 35475,"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": 4183437, "tid": 31318, + "ts": 658972143644.304, "dur": 564.388, + "args": { + "External id": 35476,"Record function id": 0, "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 4183437, "tid": 31318, + "ts": 658972143702.619, "dur": 494.581, + "args": { + "External id": 35477,"Record function id": 0, "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972143761.141, "dur": 5.917, + "args": { + "External id": 35478,"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": 4183437, "tid": 31318, + "ts": 658972143782.334, "dur": 26.750, + "args": { + "External id": 35479,"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": 4183437, "tid": 31318, + "ts": 658972143786.860, "dur": 1.726, + "args": { + "External id": 35480,"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": 4183437, "tid": 31318, + "ts": 658972143790.220, "dur": 0.359, + "args": { + "External id": 35481,"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": 4183437, "tid": 31318, + "ts": 658972143792.069, "dur": 1.811, + "args": { + "External id": 35482,"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": 4183437, "tid": 31318, + "ts": 658972143794.804, "dur": 0.204, + "args": { + "External id": 35483,"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": 4183437, "tid": 31318, + "ts": 658972143796.013, "dur": 0.967, + "args": { + "External id": 35484,"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": 4183437, "tid": 31318, + "ts": 658972143797.876, "dur": 0.357, + "args": { + "External id": 35485,"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": 4183437, "tid": 31318, + "ts": 658972143799.178, "dur": 0.526, + "args": { + "External id": 35486,"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": 4183437, "tid": 31318, + "ts": 658972143801.471, "dur": 0.592, + "args": { + "External id": 35487,"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": 4183437, "tid": 31318, + "ts": 658972143802.895, "dur": 0.423, + "args": { + "External id": 35488,"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": 4183437, "tid": 31318, + "ts": 658972143818.703, "dur": 34.033, + "args": { + "External id": 35489,"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": 4183437, "tid": 31318, + "ts": 658972143885.496, "dur": 96.645, + "args": { + "External id": 35490,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972143895.063, "dur": 3.385, + "args": { + "External id": 35491,"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": 4183437, "tid": 31318, + "ts": 658972143903.523, "dur": 13.565, + "args": { + "External id": 35492,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972143907.632, "dur": 9.011, + "args": { + "External id": 35493,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972143910.576, "dur": 1.787, + "args": { + "External id": 35494,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972143922.969, "dur": 21.396, + "args": { + "External id": 35495,"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": 4183437, "tid": 31318, + "ts": 658972143924.377, "dur": 0.562, + "args": { + "External id": 35496,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972143927.266, "dur": 0.507, + "args": { + "External id": 35497,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972143928.590, "dur": 0.607, + "args": { + "External id": 35498,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972143929.950, "dur": 0.189, + "args": { + "External id": 35499,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972143932.175, "dur": 0.180, + "args": { + "External id": 35500,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972143933.367, "dur": 0.329, + "args": { + "External id": 35501,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972143934.771, "dur": 1.076, + "args": { + "External id": 35502,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972143936.753, "dur": 1.252, + "args": { + "External id": 35503,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972143938.809, "dur": 0.622, + "args": { + "External id": 35504,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972143953.818, "dur": 20.486, + "args": { + "External id": 35505,"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": 4183437, "tid": 31318, + "ts": 658972144026.127, "dur": 109.369, + "args": { + "External id": 35506,"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": 4183437, "tid": 31318, + "ts": 658972144048.213, "dur": 83.791, + "args": { + "External id": 35507,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972144057.466, "dur": 70.642, + "args": { + "External id": 35508,"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": 4183437, "tid": 31318, + "ts": 658972144148.503, "dur": 1.688, + "args": { + "External id": 35509,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972144223.580, "dur": 1635.365, + "args": { + "External id": 35510,"Sequence number": 459920, "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": 4183437, "tid": 31318, "ts": 658972144223.580, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972144351.952, "dur": 101.867, + "args": { + "External id": 35511,"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": 4183437, "tid": 31318, + "ts": 658972144492.312, "dur": 37.411, + "args": { + "External id": 35512,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972144547.083, "dur": 42.695, + "args": { + "External id": 35513,"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": 4183437, "tid": 31318, + "ts": 658972144598.028, "dur": 27.053, + "args": { + "External id": 35514,"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": 4183437, "tid": 31318, + "ts": 658972144630.830, "dur": 76.991, + "args": { + "External id": 35515,"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": 4183437, "tid": 31318, + "ts": 658972144719.780, "dur": 26.111, + "args": { + "External id": 35516,"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": 4183437, "tid": 31318, + "ts": 658972144754.098, "dur": 29.268, + "args": { + "External id": 35517,"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": 4183437, "tid": 31318, + "ts": 658972144807.976, "dur": 25.557, + "args": { + "External id": 35518,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972144853.111, "dur": 27.183, + "args": { + "External id": 35519,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972144901.125, "dur": 19.494, + "args": { + "External id": 35520,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972144932.146, "dur": 14.964, + "args": { + "External id": 35521,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972144955.818, "dur": 38.580, + "args": { + "External id": 35522,"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": 4183437, "tid": 31318, + "ts": 658972144997.784, "dur": 30.113, + "args": { + "External id": 35523,"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": 4183437, "tid": 31318, + "ts": 658972145054.070, "dur": 174.769, + "args": { + "External id": 35524,"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": 4183437, "tid": 31318, + "ts": 658972145138.997, "dur": 6.004, + "args": { + "External id": 35525,"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": 4183437, "tid": 31318, + "ts": 658972145146.828, "dur": 2.593, + "args": { + "External id": 35526,"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": 4183437, "tid": 31318, + "ts": 658972145259.912, "dur": 43.605, + "args": { + "External id": 35527,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972145319.288, "dur": 16.450, + "args": { + "External id": 35528,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972145345.290, "dur": 47.808, + "args": { + "External id": 35529,"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": 4183437, "tid": 31318, + "ts": 658972145399.618, "dur": 32.084, + "args": { + "External id": 35530,"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": 4183437, "tid": 31318, + "ts": 658972145441.199, "dur": 27.829, + "args": { + "External id": 35531,"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": 4183437, "tid": 31318, + "ts": 658972145473.768, "dur": 30.183, + "args": { + "External id": 35532,"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": 4183437, "tid": 31318, + "ts": 658972145509.388, "dur": 26.827, + "args": { + "External id": 35533,"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": 4183437, "tid": 31318, + "ts": 658972145544.598, "dur": 30.446, + "args": { + "External id": 35534,"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": 4183437, "tid": 31318, + "ts": 658972145590.478, "dur": 23.680, + "args": { + "External id": 35535,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972145632.503, "dur": 62.684, + "args": { + "External id": 35536,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972145732.816, "dur": 25.782, + "args": { + "External id": 35537,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972145779.467, "dur": 16.690, + "args": { + "External id": 35538,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972145808.295, "dur": 17.342, + "args": { + "External id": 35539,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972145902.295, "dur": 15.114, + "args": { + "External id": 35540,"Record function id": 0, "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972145905.535, "dur": 10.963, + "args": { + "External id": 35541,"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": 4183437, "tid": 31318, + "ts": 658972145909.927, "dur": 5.687, + "args": { + "External id": 35542,"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": 4183437, "tid": 31318, + "ts": 658972145911.409, "dur": 4.111, + "args": { + "External id": 35543,"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": 4183437, "tid": 31318, + "ts": 658972145921.408, "dur": 5.195, + "args": { + "External id": 35544,"Record function id": 0, "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972145922.839, "dur": 3.319, + "args": { + "External id": 35545,"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": 4183437, "tid": 31318, + "ts": 658972145923.385, "dur": 2.229, + "args": { + "External id": 35546,"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": 4183437, "tid": 31318, + "ts": 658972145923.888, "dur": 1.638, + "args": { + "External id": 35547,"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": 4183437, "tid": 31318, + "ts": 658972145930.015, "dur": 3.744, + "args": { + "External id": 35548,"Record function id": 0, "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972145931.108, "dur": 2.227, + "args": { + "External id": 35549,"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": 4183437, "tid": 31318, + "ts": 658972145931.800, "dur": 1.111, + "args": { + "External id": 35550,"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": 4183437, "tid": 31318, + "ts": 658972145932.305, "dur": 0.526, + "args": { + "External id": 35551,"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": 4183437, "tid": 31318, + "ts": 658972145936.835, "dur": 3.433, + "args": { + "External id": 35552,"Record function id": 0, "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972145937.774, "dur": 2.074, + "args": { + "External id": 35553,"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": 4183437, "tid": 31318, + "ts": 658972145938.474, "dur": 0.971, + "args": { + "External id": 35554,"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": 4183437, "tid": 31318, + "ts": 658972145938.785, "dur": 0.596, + "args": { + "External id": 35555,"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": 4183437, "tid": 31318, + "ts": 658972145943.336, "dur": 4.612, + "args": { + "External id": 35556,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972145944.819, "dur": 2.652, + "args": { + "External id": 35557,"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": 4183437, "tid": 31318, + "ts": 658972145945.329, "dur": 1.572, + "args": { + "External id": 35558,"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": 4183437, "tid": 31318, + "ts": 658972145945.902, "dur": 0.938, + "args": { + "External id": 35559,"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": 4183437, "tid": 31318, + "ts": 658972145951.004, "dur": 3.881, + "args": { + "External id": 35560,"Record function id": 0, "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972145952.334, "dur": 2.136, + "args": { + "External id": 35561,"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": 4183437, "tid": 31318, + "ts": 658972145952.842, "dur": 1.224, + "args": { + "External id": 35562,"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": 4183437, "tid": 31318, + "ts": 658972145953.451, "dur": 0.546, + "args": { + "External id": 35563,"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": 4183437, "tid": 31318, + "ts": 658972145958.019, "dur": 3.441, + "args": { + "External id": 35564,"Record function id": 0, "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972145959.227, "dur": 1.820, + "args": { + "External id": 35565,"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": 4183437, "tid": 31318, + "ts": 658972145959.677, "dur": 0.959, + "args": { + "External id": 35566,"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": 4183437, "tid": 31318, + "ts": 658972145959.999, "dur": 0.571, + "args": { + "External id": 35567,"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": 4183437, "tid": 31318, + "ts": 658972145964.425, "dur": 3.726, + "args": { + "External id": 35568,"Record function id": 0, "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972145965.555, "dur": 2.199, + "args": { + "External id": 35569,"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": 4183437, "tid": 31318, + "ts": 658972145966.075, "dur": 1.276, + "args": { + "External id": 35570,"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": 4183437, "tid": 31318, + "ts": 658972145966.730, "dur": 0.557, + "args": { + "External id": 35571,"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": 4183437, "tid": 31318, + "ts": 658972145971.384, "dur": 4.564, + "args": { + "External id": 35572,"Record function id": 0, "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972145972.288, "dur": 3.256, + "args": { + "External id": 35573,"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": 4183437, "tid": 31318, + "ts": 658972145972.811, "dur": 2.308, + "args": { + "External id": 35574,"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": 4183437, "tid": 31318, + "ts": 658972145973.383, "dur": 1.676, + "args": { + "External id": 35575,"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": 4183437, "tid": 31318, + "ts": 658972145979.907, "dur": 14733.020, + "args": { + "External id": 35576,"Record function id": 0, "Sequence number": 459919, "Fwd thread id": 1, "Ev Idx": 2295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972145981.204, "dur": 14722.097, + "args": { + "External id": 35577,"Sequence number": 459919, "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": 4183437, "tid": 31318, "ts": 658972145981.204, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 4183437, "tid": 31318, + "ts": 658972146008.511, "dur": 36.566, + "args": { + "External id": 35578,"Record function id": 0, "Ev Idx": 2297 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 4183437, "tid": 31318, + "ts": 658972146052.278, "dur": 61.144, + "args": { + "External id": 35579,"Record function id": 0, "Ev Idx": 2298 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 4183437, "tid": 31318, + "ts": 658972146119.026, "dur": 14530.831, + "args": { + "External id": 35580,"Record function id": 0, "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972146203.690, "dur": 6.850, + "args": { + "External id": 35581,"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": 4183437, "tid": 31318, + "ts": 658972146222.501, "dur": 4.771, + "args": { + "External id": 35582,"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": 4183437, "tid": 31318, + "ts": 658972146241.016, "dur": 13751.927, + "args": { + "External id": 35583,"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": 4183437, "tid": 31318, + "ts": 658972146254.156, "dur": 13730.048, + "args": { + "External id": 35584,"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": 4183437, "tid": 31318, + "ts": 658972146301.282, "dur": 13.640, + "args": { + "External id": 35585,"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": 4183437, "tid": 31318, + "ts": 658972146320.160, "dur": 13625.182, + "args": { + "External id": 35586,"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": 4183437, "tid": 31318, + "ts": 658972146323.657, "dur": 13621.003, + "args": { + "External id": 35587,"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": 4183437, "tid": 31318, + "ts": 658972146327.348, "dur": 5.360, + "args": { + "External id": 35588,"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": 4183437, "tid": 31318, + "ts": 658972146334.360, "dur": 13606.996, + "args": { + "External id": 35589,"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": 4183437, "tid": 31318, + "ts": 658972160079.243, "dur": 9.266, + "args": { + "External id": 35590,"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": 4183437, "tid": 31318, + "ts": 658972160081.872, "dur": 6.296, + "args": { + "External id": 35591,"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": 4183437, "tid": 31318, + "ts": 658972160115.443, "dur": 271.258, + "args": { + "External id": 35592,"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": 4183437, "tid": 31318, + "ts": 658972160139.810, "dur": 241.998, + "args": { + "External id": 35593,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972160151.036, "dur": 225.694, + "args": { + "External id": 35594,"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": 4183437, "tid": 31318, + "ts": 658972160403.608, "dur": 1.968, + "args": { + "External id": 35595,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972160458.374, "dur": 6.139, + "args": { + "External id": 35596,"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": 4183437, "tid": 31318, + "ts": 658972160507.484, "dur": 1.395, + "args": { + "External id": 35597,"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": 4183437, "tid": 31318, + "ts": 658972160524.020, "dur": 1.258, + "args": { + "External id": 35598,"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": 4183437, "tid": 31318, + "ts": 658972160535.920, "dur": 1.053, + "args": { + "External id": 35599,"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": 4183437, "tid": 31318, + "ts": 658972160547.087, "dur": 1.132, + "args": { + "External id": 35600,"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": 4183437, "tid": 31318, + "ts": 658972160557.745, "dur": 0.891, + "args": { + "External id": 35601,"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": 4183437, "tid": 31318, + "ts": 658972160569.979, "dur": 1.060, + "args": { + "External id": 35602,"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": 4183437, "tid": 31318, + "ts": 658972160581.663, "dur": 1.568, + "args": { + "External id": 35603,"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": 4183437, "tid": 31318, + "ts": 658972160592.791, "dur": 0.855, + "args": { + "External id": 35604,"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": 4183437, "tid": 31318, + "ts": 658972160728.737, "dur": 2592.034, + "args": { + "External id": 35605,"Record function id": 0, "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 4183437, "tid": 31318, + "ts": 658972160749.868, "dur": 975.068, + "args": { + "External id": 35606,"Record function id": 0, "Ev Idx": 2325 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 4183437, "tid": 31318, + "ts": 658972160763.987, "dur": 298.340, + "args": { + "External id": 35607,"Record function id": 0, "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972160842.076, "dur": 4.566, + "args": { + "External id": 35608,"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": 4183437, "tid": 31318, + "ts": 658972160849.793, "dur": 2.119, + "args": { + "External id": 35609,"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": 4183437, "tid": 31318, + "ts": 658972160853.895, "dur": 1.029, + "args": { + "External id": 35610,"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": 4183437, "tid": 31318, + "ts": 658972160856.982, "dur": 0.618, + "args": { + "External id": 35611,"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": 4183437, "tid": 31318, + "ts": 658972160859.493, "dur": 0.949, + "args": { + "External id": 35612,"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": 4183437, "tid": 31318, + "ts": 658972160862.182, "dur": 0.595, + "args": { + "External id": 35613,"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": 4183437, "tid": 31318, + "ts": 658972160864.755, "dur": 2.027, + "args": { + "External id": 35614,"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": 4183437, "tid": 31318, + "ts": 658972160868.247, "dur": 0.583, + "args": { + "External id": 35615,"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": 4183437, "tid": 31318, + "ts": 658972160870.460, "dur": 0.913, + "args": { + "External id": 35616,"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": 4183437, "tid": 31318, + "ts": 658972160872.626, "dur": 1.532, + "args": { + "External id": 35617,"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": 4183437, "tid": 31318, + "ts": 658972160891.713, "dur": 143.572, + "args": { + "External id": 35618,"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": 4183437, "tid": 31318, + "ts": 658972160907.457, "dur": 123.163, + "args": { + "External id": 35619,"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": 4183437, "tid": 31318, + "ts": 658972160920.918, "dur": 12.461, + "args": { + "External id": 35620,"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": 4183437, "tid": 31318, + "ts": 658972160936.315, "dur": 64.196, + "args": { + "External id": 35621,"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": 4183437, "tid": 31318, + "ts": 658972160938.758, "dur": 61.440, + "args": { + "External id": 35622,"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": 4183437, "tid": 31318, + "ts": 658972160942.471, "dur": 4.947, + "args": { + "External id": 35623,"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": 4183437, "tid": 31318, + "ts": 658972160949.002, "dur": 50.537, + "args": { + "External id": 35624,"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": 4183437, "tid": 31318, + "ts": 658972161134.995, "dur": 582.102, + "args": { + "External id": 35625,"Record function id": 0, "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 4183437, "tid": 31318, + "ts": 658972161149.722, "dur": 554.505, + "args": { + "External id": 35626,"Record function id": 0, "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972161201.099, "dur": 4.772, + "args": { + "External id": 35627,"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": 4183437, "tid": 31318, + "ts": 658972161224.330, "dur": 28.201, + "args": { + "External id": 35628,"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": 4183437, "tid": 31318, + "ts": 658972161228.367, "dur": 2.814, + "args": { + "External id": 35629,"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": 4183437, "tid": 31318, + "ts": 658972161232.693, "dur": 0.415, + "args": { + "External id": 35630,"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": 4183437, "tid": 31318, + "ts": 658972161234.403, "dur": 0.164, + "args": { + "External id": 35631,"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": 4183437, "tid": 31318, + "ts": 658972161237.251, "dur": 0.562, + "args": { + "External id": 35632,"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": 4183437, "tid": 31318, + "ts": 658972161238.800, "dur": 1.901, + "args": { + "External id": 35633,"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": 4183437, "tid": 31318, + "ts": 658972161241.661, "dur": 0.262, + "args": { + "External id": 35634,"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": 4183437, "tid": 31318, + "ts": 658972161243.699, "dur": 0.360, + "args": { + "External id": 35635,"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": 4183437, "tid": 31318, + "ts": 658972161244.880, "dur": 0.472, + "args": { + "External id": 35636,"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": 4183437, "tid": 31318, + "ts": 658972161246.108, "dur": 1.278, + "args": { + "External id": 35637,"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": 4183437, "tid": 31318, + "ts": 658972161283.180, "dur": 33.110, + "args": { + "External id": 35638,"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": 4183437, "tid": 31318, + "ts": 658972161350.518, "dur": 95.219, + "args": { + "External id": 35639,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972161360.897, "dur": 4.800, + "args": { + "External id": 35640,"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": 4183437, "tid": 31318, + "ts": 658972161371.071, "dur": 9.761, + "args": { + "External id": 35641,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972161375.001, "dur": 5.412, + "args": { + "External id": 35642,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972161378.402, "dur": 0.477, + "args": { + "External id": 35643,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972161387.443, "dur": 20.647, + "args": { + "External id": 35644,"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": 4183437, "tid": 31318, + "ts": 658972161389.290, "dur": 0.333, + "args": { + "External id": 35645,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972161390.738, "dur": 2.365, + "args": { + "External id": 35646,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972161393.912, "dur": 0.203, + "args": { + "External id": 35647,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972161394.923, "dur": 0.475, + "args": { + "External id": 35648,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972161397.343, "dur": 0.300, + "args": { + "External id": 35649,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972161398.435, "dur": 0.484, + "args": { + "External id": 35650,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972161399.572, "dur": 0.317, + "args": { + "External id": 35651,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972161401.301, "dur": 0.349, + "args": { + "External id": 35652,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972161402.614, "dur": 0.478, + "args": { + "External id": 35653,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972161418.217, "dur": 18.573, + "args": { + "External id": 35654,"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": 4183437, "tid": 31318, + "ts": 658972161491.340, "dur": 110.141, + "args": { + "External id": 35655,"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": 4183437, "tid": 31318, + "ts": 658972161513.810, "dur": 84.480, + "args": { + "External id": 35656,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972161524.129, "dur": 70.042, + "args": { + "External id": 35657,"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": 4183437, "tid": 31318, + "ts": 658972161614.367, "dur": 1.893, + "args": { + "External id": 35658,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972161732.589, "dur": 1569.572, + "args": { + "External id": 35659,"Sequence number": 459918, "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": 4183437, "tid": 31318, "ts": 658972161732.589, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972161845.412, "dur": 106.633, + "args": { + "External id": 35660,"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": 4183437, "tid": 31318, + "ts": 658972161989.637, "dur": 36.774, + "args": { + "External id": 35661,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972162044.022, "dur": 41.911, + "args": { + "External id": 35662,"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": 4183437, "tid": 31318, + "ts": 658972162095.239, "dur": 26.758, + "args": { + "External id": 35663,"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": 4183437, "tid": 31318, + "ts": 658972162127.714, "dur": 33.123, + "args": { + "External id": 35664,"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": 4183437, "tid": 31318, + "ts": 658972162167.027, "dur": 21.430, + "args": { + "External id": 35665,"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": 4183437, "tid": 31318, + "ts": 658972162199.127, "dur": 29.275, + "args": { + "External id": 35666,"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": 4183437, "tid": 31318, + "ts": 658972162249.781, "dur": 44.873, + "args": { + "External id": 35667,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972162317.833, "dur": 28.209, + "args": { + "External id": 35668,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972162365.246, "dur": 19.847, + "args": { + "External id": 35669,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972162397.312, "dur": 15.160, + "args": { + "External id": 35670,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972162420.346, "dur": 40.318, + "args": { + "External id": 35671,"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": 4183437, "tid": 31318, + "ts": 658972162464.022, "dur": 30.656, + "args": { + "External id": 35672,"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": 4183437, "tid": 31318, + "ts": 658972162521.578, "dur": 215.486, + "args": { + "External id": 35673,"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": 4183437, "tid": 31318, + "ts": 658972162601.082, "dur": 6.302, + "args": { + "External id": 35674,"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": 4183437, "tid": 31318, + "ts": 658972162608.983, "dur": 2.764, + "args": { + "External id": 35675,"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": 4183437, "tid": 31318, + "ts": 658972162774.879, "dur": 27.577, + "args": { + "External id": 35676,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972162813.156, "dur": 14.770, + "args": { + "External id": 35677,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972162837.861, "dur": 53.292, + "args": { + "External id": 35678,"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": 4183437, "tid": 31318, + "ts": 658972162897.182, "dur": 34.667, + "args": { + "External id": 35679,"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": 4183437, "tid": 31318, + "ts": 658972162938.482, "dur": 29.870, + "args": { + "External id": 35680,"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": 4183437, "tid": 31318, + "ts": 658972162973.269, "dur": 28.091, + "args": { + "External id": 35681,"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": 4183437, "tid": 31318, + "ts": 658972163007.732, "dur": 27.601, + "args": { + "External id": 35682,"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": 4183437, "tid": 31318, + "ts": 658972163041.935, "dur": 27.832, + "args": { + "External id": 35683,"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": 4183437, "tid": 31318, + "ts": 658972163085.435, "dur": 32.754, + "args": { + "External id": 35684,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972163140.928, "dur": 24.921, + "args": { + "External id": 35685,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972163180.057, "dur": 15.390, + "args": { + "External id": 35686,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972163208.757, "dur": 16.827, + "args": { + "External id": 35687,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972163240.108, "dur": 14.345, + "args": { + "External id": 35688,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972163345.906, "dur": 15.018, + "args": { + "External id": 35689,"Record function id": 0, "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972163348.944, "dur": 11.046, + "args": { + "External id": 35690,"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": 4183437, "tid": 31318, + "ts": 658972163353.264, "dur": 5.772, + "args": { + "External id": 35691,"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": 4183437, "tid": 31318, + "ts": 658972163354.518, "dur": 4.415, + "args": { + "External id": 35692,"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": 4183437, "tid": 31318, + "ts": 658972163364.769, "dur": 4.648, + "args": { + "External id": 35693,"Record function id": 0, "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972163365.949, "dur": 3.021, + "args": { + "External id": 35694,"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": 4183437, "tid": 31318, + "ts": 658972163366.902, "dur": 1.603, + "args": { + "External id": 35695,"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": 4183437, "tid": 31318, + "ts": 658972163367.514, "dur": 0.910, + "args": { + "External id": 35696,"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": 4183437, "tid": 31318, + "ts": 658972163372.648, "dur": 4.190, + "args": { + "External id": 35697,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972163373.744, "dur": 2.660, + "args": { + "External id": 35698,"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": 4183437, "tid": 31318, + "ts": 658972163374.659, "dur": 1.339, + "args": { + "External id": 35699,"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": 4183437, "tid": 31318, + "ts": 658972163375.211, "dur": 0.701, + "args": { + "External id": 35700,"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": 4183437, "tid": 31318, + "ts": 658972163379.994, "dur": 3.852, + "args": { + "External id": 35701,"Record function id": 0, "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972163380.877, "dur": 2.538, + "args": { + "External id": 35702,"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": 4183437, "tid": 31318, + "ts": 658972163381.678, "dur": 1.346, + "args": { + "External id": 35703,"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": 4183437, "tid": 31318, + "ts": 658972163382.199, "dur": 0.762, + "args": { + "External id": 35704,"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": 4183437, "tid": 31318, + "ts": 658972163386.873, "dur": 6.744, + "args": { + "External id": 35705,"Record function id": 0, "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972163391.191, "dur": 1.977, + "args": { + "External id": 35706,"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": 4183437, "tid": 31318, + "ts": 658972163391.654, "dur": 1.123, + "args": { + "External id": 35707,"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": 4183437, "tid": 31318, + "ts": 658972163392.161, "dur": 0.557, + "args": { + "External id": 35708,"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": 4183437, "tid": 31318, + "ts": 658972163396.699, "dur": 3.891, + "args": { + "External id": 35709,"Record function id": 0, "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972163397.696, "dur": 2.504, + "args": { + "External id": 35710,"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": 4183437, "tid": 31318, + "ts": 658972163398.199, "dur": 1.548, + "args": { + "External id": 35711,"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": 4183437, "tid": 31318, + "ts": 658972163398.578, "dur": 1.107, + "args": { + "External id": 35712,"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": 4183437, "tid": 31318, + "ts": 658972163403.682, "dur": 3.759, + "args": { + "External id": 35713,"Record function id": 0, "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972163404.717, "dur": 2.311, + "args": { + "External id": 35714,"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": 4183437, "tid": 31318, + "ts": 658972163405.204, "dur": 1.399, + "args": { + "External id": 35715,"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": 4183437, "tid": 31318, + "ts": 658972163405.537, "dur": 1.005, + "args": { + "External id": 35716,"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": 4183437, "tid": 31318, + "ts": 658972163410.447, "dur": 3.607, + "args": { + "External id": 35717,"Record function id": 0, "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972163411.475, "dur": 2.130, + "args": { + "External id": 35718,"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": 4183437, "tid": 31318, + "ts": 658972163411.990, "dur": 1.227, + "args": { + "External id": 35719,"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": 4183437, "tid": 31318, + "ts": 658972163412.424, "dur": 0.726, + "args": { + "External id": 35720,"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": 4183437, "tid": 31318, + "ts": 658972163417.115, "dur": 3.597, + "args": { + "External id": 35721,"Record function id": 0, "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972163418.156, "dur": 2.154, + "args": { + "External id": 35722,"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": 4183437, "tid": 31318, + "ts": 658972163418.650, "dur": 1.251, + "args": { + "External id": 35723,"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": 4183437, "tid": 31318, + "ts": 658972163419.068, "dur": 0.768, + "args": { + "External id": 35724,"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": 4183437, "tid": 31318, + "ts": 658972163424.783, "dur": 14788.491, + "args": { + "External id": 35725,"Record function id": 0, "Sequence number": 459917, "Fwd thread id": 1, "Ev Idx": 2444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972163425.970, "dur": 14779.459, + "args": { + "External id": 35726,"Sequence number": 459917, "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": 4183437, "tid": 31318, "ts": 658972163425.970, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 4183437, "tid": 31318, + "ts": 658972163454.100, "dur": 40.579, + "args": { + "External id": 35727,"Record function id": 0, "Ev Idx": 2446 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 4183437, "tid": 31318, + "ts": 658972163502.454, "dur": 64.555, + "args": { + "External id": 35728,"Record function id": 0, "Ev Idx": 2447 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 4183437, "tid": 31318, + "ts": 658972163572.576, "dur": 14625.135, + "args": { + "External id": 35729,"Record function id": 0, "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972163695.352, "dur": 8.593, + "args": { + "External id": 35730,"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": 4183437, "tid": 31318, + "ts": 658972163714.607, "dur": 5.061, + "args": { + "External id": 35731,"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": 4183437, "tid": 31318, + "ts": 658972163735.345, "dur": 13754.031, + "args": { + "External id": 35732,"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": 4183437, "tid": 31318, + "ts": 658972163748.842, "dur": 13732.062, + "args": { + "External id": 35733,"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": 4183437, "tid": 31318, + "ts": 658972163771.313, "dur": 13.368, + "args": { + "External id": 35734,"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": 4183437, "tid": 31318, + "ts": 658972163789.811, "dur": 13656.070, + "args": { + "External id": 35735,"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": 4183437, "tid": 31318, + "ts": 658972163792.235, "dur": 13652.875, + "args": { + "External id": 35736,"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": 4183437, "tid": 31318, + "ts": 658972163796.691, "dur": 4.579, + "args": { + "External id": 35737,"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": 4183437, "tid": 31318, + "ts": 658972163803.004, "dur": 13638.115, + "args": { + "External id": 35738,"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": 4183437, "tid": 31318, + "ts": 658972177577.607, "dur": 9.377, + "args": { + "External id": 35739,"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": 4183437, "tid": 31318, + "ts": 658972177580.372, "dur": 6.302, + "args": { + "External id": 35740,"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": 4183437, "tid": 31318, + "ts": 658972177613.978, "dur": 308.968, + "args": { + "External id": 35741,"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": 4183437, "tid": 31318, + "ts": 658972177639.862, "dur": 277.979, + "args": { + "External id": 35742,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972177689.786, "dur": 223.375, + "args": { + "External id": 35743,"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": 4183437, "tid": 31318, + "ts": 658972177941.362, "dur": 2.079, + "args": { + "External id": 35744,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972177998.990, "dur": 6.303, + "args": { + "External id": 35745,"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": 4183437, "tid": 31318, + "ts": 658972178048.467, "dur": 1.386, + "args": { + "External id": 35746,"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": 4183437, "tid": 31318, + "ts": 658972178065.600, "dur": 1.152, + "args": { + "External id": 35747,"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": 4183437, "tid": 31318, + "ts": 658972178078.073, "dur": 1.066, + "args": { + "External id": 35748,"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": 4183437, "tid": 31318, + "ts": 658972178090.907, "dur": 0.816, + "args": { + "External id": 35749,"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": 4183437, "tid": 31318, + "ts": 658972178102.171, "dur": 1.328, + "args": { + "External id": 35750,"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": 4183437, "tid": 31318, + "ts": 658972178114.466, "dur": 1.160, + "args": { + "External id": 35751,"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": 4183437, "tid": 31318, + "ts": 658972178125.775, "dur": 2.153, + "args": { + "External id": 35752,"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": 4183437, "tid": 31318, + "ts": 658972178137.194, "dur": 1.127, + "args": { + "External id": 35753,"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": 4183437, "tid": 31318, + "ts": 658972178226.250, "dur": 2698.196, + "args": { + "External id": 35754,"Record function id": 0, "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 4183437, "tid": 31318, + "ts": 658972178244.514, "dur": 1002.348, + "args": { + "External id": 35755,"Record function id": 0, "Ev Idx": 2474 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 4183437, "tid": 31318, + "ts": 658972178260.738, "dur": 325.159, + "args": { + "External id": 35756,"Record function id": 0, "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972178361.028, "dur": 4.700, + "args": { + "External id": 35757,"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": 4183437, "tid": 31318, + "ts": 658972178368.950, "dur": 1.219, + "args": { + "External id": 35758,"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": 4183437, "tid": 31318, + "ts": 658972178371.840, "dur": 1.170, + "args": { + "External id": 35759,"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": 4183437, "tid": 31318, + "ts": 658972178374.649, "dur": 1.216, + "args": { + "External id": 35760,"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": 4183437, "tid": 31318, + "ts": 658972178378.153, "dur": 1.151, + "args": { + "External id": 35761,"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": 4183437, "tid": 31318, + "ts": 658972178381.119, "dur": 1.337, + "args": { + "External id": 35762,"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": 4183437, "tid": 31318, + "ts": 658972178384.215, "dur": 2.732, + "args": { + "External id": 35763,"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": 4183437, "tid": 31318, + "ts": 658972178388.487, "dur": 1.236, + "args": { + "External id": 35764,"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": 4183437, "tid": 31318, + "ts": 658972178391.634, "dur": 1.347, + "args": { + "External id": 35765,"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": 4183437, "tid": 31318, + "ts": 658972178394.659, "dur": 0.926, + "args": { + "External id": 35766,"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": 4183437, "tid": 31318, + "ts": 658972178413.878, "dur": 142.189, + "args": { + "External id": 35767,"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": 4183437, "tid": 31318, + "ts": 658972178434.140, "dur": 117.841, + "args": { + "External id": 35768,"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": 4183437, "tid": 31318, + "ts": 658972178446.633, "dur": 13.064, + "args": { + "External id": 35769,"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": 4183437, "tid": 31318, + "ts": 658972178462.471, "dur": 63.085, + "args": { + "External id": 35770,"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": 4183437, "tid": 31318, + "ts": 658972178465.454, "dur": 59.752, + "args": { + "External id": 35771,"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": 4183437, "tid": 31318, + "ts": 658972178469.155, "dur": 5.625, + "args": { + "External id": 35772,"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": 4183437, "tid": 31318, + "ts": 658972178476.338, "dur": 48.368, + "args": { + "External id": 35773,"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": 4183437, "tid": 31318, + "ts": 658972178712.482, "dur": 527.115, + "args": { + "External id": 35774,"Record function id": 0, "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 4183437, "tid": 31318, + "ts": 658972178729.457, "dur": 498.703, + "args": { + "External id": 35775,"Record function id": 0, "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972178786.963, "dur": 6.321, + "args": { + "External id": 35776,"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": 4183437, "tid": 31318, + "ts": 658972178808.111, "dur": 30.362, + "args": { + "External id": 35777,"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": 4183437, "tid": 31318, + "ts": 658972178813.082, "dur": 1.442, + "args": { + "External id": 35778,"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": 4183437, "tid": 31318, + "ts": 658972178817.147, "dur": 0.407, + "args": { + "External id": 35779,"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": 4183437, "tid": 31318, + "ts": 658972178818.575, "dur": 0.518, + "args": { + "External id": 35780,"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": 4183437, "tid": 31318, + "ts": 658972178820.962, "dur": 0.341, + "args": { + "External id": 35781,"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": 4183437, "tid": 31318, + "ts": 658972178822.813, "dur": 0.649, + "args": { + "External id": 35782,"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": 4183437, "tid": 31318, + "ts": 658972178824.768, "dur": 1.323, + "args": { + "External id": 35783,"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": 4183437, "tid": 31318, + "ts": 658972178827.233, "dur": 1.005, + "args": { + "External id": 35784,"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": 4183437, "tid": 31318, + "ts": 658972178829.493, "dur": 0.811, + "args": { + "External id": 35785,"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": 4183437, "tid": 31318, + "ts": 658972178832.143, "dur": 0.540, + "args": { + "External id": 35786,"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": 4183437, "tid": 31318, + "ts": 658972178848.325, "dur": 33.639, + "args": { + "External id": 35787,"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": 4183437, "tid": 31318, + "ts": 658972178911.795, "dur": 97.887, + "args": { + "External id": 35788,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972178921.942, "dur": 3.422, + "args": { + "External id": 35789,"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": 4183437, "tid": 31318, + "ts": 658972178930.077, "dur": 9.935, + "args": { + "External id": 35790,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972178934.231, "dur": 5.380, + "args": { + "External id": 35791,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972178937.366, "dur": 0.934, + "args": { + "External id": 35792,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972178946.611, "dur": 25.208, + "args": { + "External id": 35793,"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": 4183437, "tid": 31318, + "ts": 658972178948.666, "dur": 0.900, + "args": { + "External id": 35794,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972178950.784, "dur": 0.958, + "args": { + "External id": 35795,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972178953.404, "dur": 0.690, + "args": { + "External id": 35796,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972178955.223, "dur": 0.604, + "args": { + "External id": 35797,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972178957.144, "dur": 0.820, + "args": { + "External id": 35798,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972178959.677, "dur": 0.978, + "args": { + "External id": 35799,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972178962.078, "dur": 0.982, + "args": { + "External id": 35800,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972178964.184, "dur": 1.107, + "args": { + "External id": 35801,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972178966.251, "dur": 0.528, + "args": { + "External id": 35802,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972178981.406, "dur": 20.372, + "args": { + "External id": 35803,"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": 4183437, "tid": 31318, + "ts": 658972179057.063, "dur": 108.688, + "args": { + "External id": 35804,"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": 4183437, "tid": 31318, + "ts": 658972179077.145, "dur": 85.370, + "args": { + "External id": 35805,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972179089.349, "dur": 69.310, + "args": { + "External id": 35806,"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": 4183437, "tid": 31318, + "ts": 658972179178.826, "dur": 1.637, + "args": { + "External id": 35807,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972179254.114, "dur": 1647.275, + "args": { + "External id": 35808,"Sequence number": 459916, "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": 4183437, "tid": 31318, "ts": 658972179254.114, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972179384.844, "dur": 101.761, + "args": { + "External id": 35809,"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": 4183437, "tid": 31318, + "ts": 658972179528.888, "dur": 36.825, + "args": { + "External id": 35810,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972179582.807, "dur": 39.035, + "args": { + "External id": 35811,"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": 4183437, "tid": 31318, + "ts": 658972179630.595, "dur": 67.483, + "args": { + "External id": 35812,"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": 4183437, "tid": 31318, + "ts": 658972179708.468, "dur": 38.156, + "args": { + "External id": 35813,"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": 4183437, "tid": 31318, + "ts": 658972179754.117, "dur": 20.674, + "args": { + "External id": 35814,"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": 4183437, "tid": 31318, + "ts": 658972179782.137, "dur": 29.180, + "args": { + "External id": 35815,"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": 4183437, "tid": 31318, + "ts": 658972179834.929, "dur": 29.147, + "args": { + "External id": 35816,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972179882.316, "dur": 30.368, + "args": { + "External id": 35817,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972179931.108, "dur": 20.393, + "args": { + "External id": 35818,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972179963.527, "dur": 15.474, + "args": { + "External id": 35819,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972179987.923, "dur": 37.245, + "args": { + "External id": 35820,"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": 4183437, "tid": 31318, + "ts": 658972180028.387, "dur": 30.780, + "args": { + "External id": 35821,"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": 4183437, "tid": 31318, + "ts": 658972180086.431, "dur": 195.496, + "args": { + "External id": 35822,"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": 4183437, "tid": 31318, + "ts": 658972180165.989, "dur": 6.766, + "args": { + "External id": 35823,"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": 4183437, "tid": 31318, + "ts": 658972180174.624, "dur": 4.001, + "args": { + "External id": 35824,"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": 4183437, "tid": 31318, + "ts": 658972180317.970, "dur": 31.653, + "args": { + "External id": 35825,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972180362.087, "dur": 15.153, + "args": { + "External id": 35826,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972180390.410, "dur": 51.033, + "args": { + "External id": 35827,"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": 4183437, "tid": 31318, + "ts": 658972180447.305, "dur": 32.213, + "args": { + "External id": 35828,"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": 4183437, "tid": 31318, + "ts": 658972180487.538, "dur": 28.133, + "args": { + "External id": 35829,"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": 4183437, "tid": 31318, + "ts": 658972180520.494, "dur": 28.358, + "args": { + "External id": 35830,"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": 4183437, "tid": 31318, + "ts": 658972180554.745, "dur": 26.913, + "args": { + "External id": 35831,"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": 4183437, "tid": 31318, + "ts": 658972180587.988, "dur": 27.651, + "args": { + "External id": 35832,"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": 4183437, "tid": 31318, + "ts": 658972180635.917, "dur": 77.485, + "args": { + "External id": 35833,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972180746.618, "dur": 27.589, + "args": { + "External id": 35834,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972180788.442, "dur": 20.451, + "args": { + "External id": 35835,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972180825.975, "dur": 13.593, + "args": { + "External id": 35836,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972180852.561, "dur": 18.753, + "args": { + "External id": 35837,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972180946.050, "dur": 35.233, + "args": { + "External id": 35838,"Record function id": 0, "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972180948.998, "dur": 31.379, + "args": { + "External id": 35839,"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": 4183437, "tid": 31318, + "ts": 658972180953.558, "dur": 25.808, + "args": { + "External id": 35840,"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": 4183437, "tid": 31318, + "ts": 658972180971.655, "dur": 7.615, + "args": { + "External id": 35841,"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": 4183437, "tid": 31318, + "ts": 658972180985.196, "dur": 3.980, + "args": { + "External id": 35842,"Record function id": 0, "Ev Idx": 2561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972180986.337, "dur": 2.405, + "args": { + "External id": 35843,"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": 4183437, "tid": 31318, + "ts": 658972180986.919, "dur": 1.398, + "args": { + "External id": 35844,"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": 4183437, "tid": 31318, + "ts": 658972180987.293, "dur": 0.942, + "args": { + "External id": 35845,"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": 4183437, "tid": 31318, + "ts": 658972180992.431, "dur": 3.952, + "args": { + "External id": 35846,"Record function id": 0, "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972180993.706, "dur": 2.266, + "args": { + "External id": 35847,"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": 4183437, "tid": 31318, + "ts": 658972180994.263, "dur": 1.313, + "args": { + "External id": 35848,"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": 4183437, "tid": 31318, + "ts": 658972180994.691, "dur": 0.807, + "args": { + "External id": 35849,"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": 4183437, "tid": 31318, + "ts": 658972180999.499, "dur": 3.419, + "args": { + "External id": 35850,"Record function id": 0, "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972181000.459, "dur": 2.056, + "args": { + "External id": 35851,"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": 4183437, "tid": 31318, + "ts": 658972181000.969, "dur": 1.156, + "args": { + "External id": 35852,"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": 4183437, "tid": 31318, + "ts": 658972181001.424, "dur": 0.635, + "args": { + "External id": 35853,"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": 4183437, "tid": 31318, + "ts": 658972181006.035, "dur": 3.518, + "args": { + "External id": 35854,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972181007.031, "dur": 2.138, + "args": { + "External id": 35855,"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": 4183437, "tid": 31318, + "ts": 658972181007.554, "dur": 1.186, + "args": { + "External id": 35856,"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": 4183437, "tid": 31318, + "ts": 658972181007.856, "dur": 0.820, + "args": { + "External id": 35857,"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": 4183437, "tid": 31318, + "ts": 658972181012.616, "dur": 3.584, + "args": { + "External id": 35858,"Record function id": 0, "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972181013.562, "dur": 2.213, + "args": { + "External id": 35859,"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": 4183437, "tid": 31318, + "ts": 658972181014.026, "dur": 1.343, + "args": { + "External id": 35860,"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": 4183437, "tid": 31318, + "ts": 658972181014.314, "dur": 0.981, + "args": { + "External id": 35861,"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": 4183437, "tid": 31318, + "ts": 658972181019.364, "dur": 3.715, + "args": { + "External id": 35862,"Record function id": 0, "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972181020.455, "dur": 2.216, + "args": { + "External id": 35863,"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": 4183437, "tid": 31318, + "ts": 658972181020.961, "dur": 1.309, + "args": { + "External id": 35864,"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": 4183437, "tid": 31318, + "ts": 658972181021.379, "dur": 0.827, + "args": { + "External id": 35865,"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": 4183437, "tid": 31318, + "ts": 658972181026.068, "dur": 3.356, + "args": { + "External id": 35866,"Record function id": 0, "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972181026.931, "dur": 2.101, + "args": { + "External id": 35867,"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": 4183437, "tid": 31318, + "ts": 658972181027.409, "dur": 1.236, + "args": { + "External id": 35868,"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": 4183437, "tid": 31318, + "ts": 658972181027.750, "dur": 0.832, + "args": { + "External id": 35869,"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": 4183437, "tid": 31318, + "ts": 658972181035.436, "dur": 3.327, + "args": { + "External id": 35870,"Record function id": 0, "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972181036.329, "dur": 2.053, + "args": { + "External id": 35871,"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": 4183437, "tid": 31318, + "ts": 658972181036.773, "dur": 1.225, + "args": { + "External id": 35872,"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": 4183437, "tid": 31318, + "ts": 658972181037.170, "dur": 0.760, + "args": { + "External id": 35873,"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": 4183437, "tid": 31318, + "ts": 658972181042.655, "dur": 14781.017, + "args": { + "External id": 35874,"Record function id": 0, "Sequence number": 459915, "Fwd thread id": 1, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972181043.662, "dur": 14771.201, + "args": { + "External id": 35875,"Sequence number": 459915, "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": 4183437, "tid": 31318, "ts": 658972181043.662, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 4183437, "tid": 31318, + "ts": 658972181071.661, "dur": 40.449, + "args": { + "External id": 35876,"Record function id": 0, "Ev Idx": 2595 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 4183437, "tid": 31318, + "ts": 658972181119.666, "dur": 64.295, + "args": { + "External id": 35877,"Record function id": 0, "Ev Idx": 2596 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 4183437, "tid": 31318, + "ts": 658972181189.834, "dur": 14617.102, + "args": { + "External id": 35878,"Record function id": 0, "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972181294.228, "dur": 8.504, + "args": { + "External id": 35879,"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": 4183437, "tid": 31318, + "ts": 658972181312.941, "dur": 5.366, + "args": { + "External id": 35880,"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": 4183437, "tid": 31318, + "ts": 658972181334.506, "dur": 13712.180, + "args": { + "External id": 35881,"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": 4183437, "tid": 31318, + "ts": 658972181348.385, "dur": 13690.444, + "args": { + "External id": 35882,"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": 4183437, "tid": 31318, + "ts": 658972181375.632, "dur": 13.718, + "args": { + "External id": 35883,"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": 4183437, "tid": 31318, + "ts": 658972181394.297, "dur": 13609.650, + "args": { + "External id": 35884,"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": 4183437, "tid": 31318, + "ts": 658972181396.700, "dur": 13606.504, + "args": { + "External id": 35885,"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": 4183437, "tid": 31318, + "ts": 658972181400.097, "dur": 5.059, + "args": { + "External id": 35886,"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": 4183437, "tid": 31318, + "ts": 658972181406.705, "dur": 13593.446, + "args": { + "External id": 35887,"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": 4183437, "tid": 31318, + "ts": 658972195131.959, "dur": 9.305, + "args": { + "External id": 35888,"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": 4183437, "tid": 31318, + "ts": 658972195135.003, "dur": 5.912, + "args": { + "External id": 35889,"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": 4183437, "tid": 31318, + "ts": 658972195168.471, "dur": 320.227, + "args": { + "External id": 35890,"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": 4183437, "tid": 31318, + "ts": 658972195194.245, "dur": 289.424, + "args": { + "External id": 35891,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972195206.230, "dur": 272.255, + "args": { + "External id": 35892,"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": 4183437, "tid": 31318, + "ts": 658972195506.269, "dur": 2.183, + "args": { + "External id": 35893,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972195564.557, "dur": 6.252, + "args": { + "External id": 35894,"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": 4183437, "tid": 31318, + "ts": 658972195614.159, "dur": 1.497, + "args": { + "External id": 35895,"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": 4183437, "tid": 31318, + "ts": 658972195631.463, "dur": 1.675, + "args": { + "External id": 35896,"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": 4183437, "tid": 31318, + "ts": 658972195644.728, "dur": 1.110, + "args": { + "External id": 35897,"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": 4183437, "tid": 31318, + "ts": 658972195694.695, "dur": 1.525, + "args": { + "External id": 35898,"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": 4183437, "tid": 31318, + "ts": 658972195708.518, "dur": 1.194, + "args": { + "External id": 35899,"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": 4183437, "tid": 31318, + "ts": 658972195720.982, "dur": 0.903, + "args": { + "External id": 35900,"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": 4183437, "tid": 31318, + "ts": 658972195732.037, "dur": 2.305, + "args": { + "External id": 35901,"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": 4183437, "tid": 31318, + "ts": 658972195743.409, "dur": 1.118, + "args": { + "External id": 35902,"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": 4183437, "tid": 31318, + "ts": 658972195838.403, "dur": 2591.727, + "args": { + "External id": 35903,"Record function id": 0, "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 4183437, "tid": 31318, + "ts": 658972195857.343, "dur": 980.190, + "args": { + "External id": 35904,"Record function id": 0, "Ev Idx": 2623 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 4183437, "tid": 31318, + "ts": 658972195871.669, "dur": 289.682, + "args": { + "External id": 35905,"Record function id": 0, "Ev Idx": 2624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972195945.366, "dur": 4.240, + "args": { + "External id": 35906,"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": 4183437, "tid": 31318, + "ts": 658972195952.581, "dur": 1.533, + "args": { + "External id": 35907,"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": 4183437, "tid": 31318, + "ts": 658972195956.017, "dur": 1.321, + "args": { + "External id": 35908,"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": 4183437, "tid": 31318, + "ts": 658972195959.372, "dur": 0.773, + "args": { + "External id": 35909,"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": 4183437, "tid": 31318, + "ts": 658972195961.889, "dur": 1.489, + "args": { + "External id": 35910,"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": 4183437, "tid": 31318, + "ts": 658972195965.037, "dur": 0.904, + "args": { + "External id": 35911,"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": 4183437, "tid": 31318, + "ts": 658972195967.586, "dur": 2.451, + "args": { + "External id": 35912,"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": 4183437, "tid": 31318, + "ts": 658972195971.346, "dur": 0.987, + "args": { + "External id": 35913,"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": 4183437, "tid": 31318, + "ts": 658972195974.061, "dur": 1.320, + "args": { + "External id": 35914,"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": 4183437, "tid": 31318, + "ts": 658972195976.806, "dur": 1.459, + "args": { + "External id": 35915,"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": 4183437, "tid": 31318, + "ts": 658972195996.264, "dur": 137.781, + "args": { + "External id": 35916,"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": 4183437, "tid": 31318, + "ts": 658972196012.612, "dur": 117.083, + "args": { + "External id": 35917,"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": 4183437, "tid": 31318, + "ts": 658972196024.713, "dur": 14.080, + "args": { + "External id": 35918,"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": 4183437, "tid": 31318, + "ts": 658972196041.524, "dur": 62.171, + "args": { + "External id": 35919,"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": 4183437, "tid": 31318, + "ts": 658972196044.379, "dur": 59.003, + "args": { + "External id": 35920,"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": 4183437, "tid": 31318, + "ts": 658972196047.891, "dur": 5.698, + "args": { + "External id": 35921,"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": 4183437, "tid": 31318, + "ts": 658972196055.277, "dur": 47.503, + "args": { + "External id": 35922,"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": 4183437, "tid": 31318, + "ts": 658972196235.769, "dur": 593.633, + "args": { + "External id": 35923,"Record function id": 0, "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 4183437, "tid": 31318, + "ts": 658972196250.649, "dur": 566.377, + "args": { + "External id": 35924,"Record function id": 0, "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972196325.368, "dur": 6.453, + "args": { + "External id": 35925,"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": 4183437, "tid": 31318, + "ts": 658972196350.539, "dur": 26.071, + "args": { + "External id": 35926,"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": 4183437, "tid": 31318, + "ts": 658972196354.719, "dur": 1.826, + "args": { + "External id": 35927,"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": 4183437, "tid": 31318, + "ts": 658972196358.867, "dur": 0.748, + "args": { + "External id": 35928,"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": 4183437, "tid": 31318, + "ts": 658972196360.510, "dur": 0.550, + "args": { + "External id": 35929,"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": 4183437, "tid": 31318, + "ts": 658972196362.223, "dur": 0.871, + "args": { + "External id": 35930,"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": 4183437, "tid": 31318, + "ts": 658972196363.940, "dur": 0.603, + "args": { + "External id": 35931,"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": 4183437, "tid": 31318, + "ts": 658972196365.803, "dur": 0.820, + "args": { + "External id": 35932,"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": 4183437, "tid": 31318, + "ts": 658972196367.741, "dur": 0.426, + "args": { + "External id": 35933,"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": 4183437, "tid": 31318, + "ts": 658972196369.214, "dur": 0.590, + "args": { + "External id": 35934,"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": 4183437, "tid": 31318, + "ts": 658972196370.548, "dur": 0.766, + "args": { + "External id": 35935,"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": 4183437, "tid": 31318, + "ts": 658972196387.812, "dur": 34.513, + "args": { + "External id": 35936,"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": 4183437, "tid": 31318, + "ts": 658972196453.114, "dur": 92.886, + "args": { + "External id": 35937,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972196462.732, "dur": 3.726, + "args": { + "External id": 35938,"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": 4183437, "tid": 31318, + "ts": 658972196471.683, "dur": 9.555, + "args": { + "External id": 35939,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972196475.896, "dur": 4.898, + "args": { + "External id": 35940,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972196478.879, "dur": 0.704, + "args": { + "External id": 35941,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972196487.420, "dur": 22.918, + "args": { + "External id": 35942,"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": 4183437, "tid": 31318, + "ts": 658972196489.153, "dur": 1.314, + "args": { + "External id": 35943,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972196491.832, "dur": 0.718, + "args": { + "External id": 35944,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972196493.785, "dur": 0.667, + "args": { + "External id": 35945,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972196495.837, "dur": 0.644, + "args": { + "External id": 35946,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972196497.672, "dur": 0.662, + "args": { + "External id": 35947,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972196499.661, "dur": 0.604, + "args": { + "External id": 35948,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972196501.370, "dur": 0.317, + "args": { + "External id": 35949,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972196502.810, "dur": 0.865, + "args": { + "External id": 35950,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972196505.047, "dur": 0.410, + "args": { + "External id": 35951,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972196520.967, "dur": 17.037, + "args": { + "External id": 35952,"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": 4183437, "tid": 31318, + "ts": 658972196591.980, "dur": 152.488, + "args": { + "External id": 35953,"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": 4183437, "tid": 31318, + "ts": 658972196613.523, "dur": 126.974, + "args": { + "External id": 35954,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972196622.882, "dur": 112.732, + "args": { + "External id": 35955,"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": 4183437, "tid": 31318, + "ts": 658972196759.554, "dur": 2.000, + "args": { + "External id": 35956,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972196844.042, "dur": 1565.403, + "args": { + "External id": 35957,"Sequence number": 459914, "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": 4183437, "tid": 31318, "ts": 658972196844.042, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972196962.669, "dur": 104.696, + "args": { + "External id": 35958,"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": 4183437, "tid": 31318, + "ts": 658972197104.659, "dur": 37.360, + "args": { + "External id": 35959,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972197159.054, "dur": 38.129, + "args": { + "External id": 35960,"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": 4183437, "tid": 31318, + "ts": 658972197206.546, "dur": 24.840, + "args": { + "External id": 35961,"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": 4183437, "tid": 31318, + "ts": 658972197238.144, "dur": 49.648, + "args": { + "External id": 35962,"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": 4183437, "tid": 31318, + "ts": 658972197298.134, "dur": 23.994, + "args": { + "External id": 35963,"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": 4183437, "tid": 31318, + "ts": 658972197329.874, "dur": 29.863, + "args": { + "External id": 35964,"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": 4183437, "tid": 31318, + "ts": 658972197383.428, "dur": 22.101, + "args": { + "External id": 35965,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972197421.936, "dur": 25.809, + "args": { + "External id": 35966,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972197464.487, "dur": 19.014, + "args": { + "External id": 35967,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972197494.738, "dur": 13.563, + "args": { + "External id": 35968,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972197516.500, "dur": 35.232, + "args": { + "External id": 35969,"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": 4183437, "tid": 31318, + "ts": 658972197554.931, "dur": 40.272, + "args": { + "External id": 35970,"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": 4183437, "tid": 31318, + "ts": 658972197624.543, "dur": 210.986, + "args": { + "External id": 35971,"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": 4183437, "tid": 31318, + "ts": 658972197742.337, "dur": 6.453, + "args": { + "External id": 35972,"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": 4183437, "tid": 31318, + "ts": 658972197750.958, "dur": 2.606, + "args": { + "External id": 35973,"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": 4183437, "tid": 31318, + "ts": 658972197865.655, "dur": 28.356, + "args": { + "External id": 35974,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972197905.228, "dur": 14.501, + "args": { + "External id": 35975,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972197930.444, "dur": 48.839, + "args": { + "External id": 35976,"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": 4183437, "tid": 31318, + "ts": 658972197988.562, "dur": 31.789, + "args": { + "External id": 35977,"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": 4183437, "tid": 31318, + "ts": 658972198026.797, "dur": 31.161, + "args": { + "External id": 35978,"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": 4183437, "tid": 31318, + "ts": 658972198062.478, "dur": 28.192, + "args": { + "External id": 35979,"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": 4183437, "tid": 31318, + "ts": 658972198096.417, "dur": 26.898, + "args": { + "External id": 35980,"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": 4183437, "tid": 31318, + "ts": 658972198129.975, "dur": 27.302, + "args": { + "External id": 35981,"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": 4183437, "tid": 31318, + "ts": 658972198172.697, "dur": 22.488, + "args": { + "External id": 35982,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972198210.610, "dur": 37.294, + "args": { + "External id": 35983,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972198286.709, "dur": 24.484, + "args": { + "External id": 35984,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972198329.055, "dur": 19.105, + "args": { + "External id": 35985,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972198359.716, "dur": 17.550, + "args": { + "External id": 35986,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972198455.467, "dur": 14.651, + "args": { + "External id": 35987,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972198458.445, "dur": 10.648, + "args": { + "External id": 35988,"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": 4183437, "tid": 31318, + "ts": 658972198462.540, "dur": 5.665, + "args": { + "External id": 35989,"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": 4183437, "tid": 31318, + "ts": 658972198464.108, "dur": 3.990, + "args": { + "External id": 35990,"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": 4183437, "tid": 31318, + "ts": 658972198473.807, "dur": 4.329, + "args": { + "External id": 35991,"Record function id": 0, "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972198474.988, "dur": 2.705, + "args": { + "External id": 35992,"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": 4183437, "tid": 31318, + "ts": 658972198475.770, "dur": 1.455, + "args": { + "External id": 35993,"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": 4183437, "tid": 31318, + "ts": 658972198476.256, "dur": 0.909, + "args": { + "External id": 35994,"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": 4183437, "tid": 31318, + "ts": 658972198481.471, "dur": 3.994, + "args": { + "External id": 35995,"Record function id": 0, "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972198482.461, "dur": 2.524, + "args": { + "External id": 35996,"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": 4183437, "tid": 31318, + "ts": 658972198483.166, "dur": 1.345, + "args": { + "External id": 35997,"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": 4183437, "tid": 31318, + "ts": 658972198483.633, "dur": 0.798, + "args": { + "External id": 35998,"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": 4183437, "tid": 31318, + "ts": 658972198488.551, "dur": 3.700, + "args": { + "External id": 35999,"Record function id": 0, "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972198489.512, "dur": 2.333, + "args": { + "External id": 36000,"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": 4183437, "tid": 31318, + "ts": 658972198490.336, "dur": 1.108, + "args": { + "External id": 36001,"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": 4183437, "tid": 31318, + "ts": 658972198490.786, "dur": 0.579, + "args": { + "External id": 36002,"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": 4183437, "tid": 31318, + "ts": 658972198495.232, "dur": 3.929, + "args": { + "External id": 36003,"Record function id": 0, "Ev Idx": 2722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972198496.451, "dur": 2.251, + "args": { + "External id": 36004,"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": 4183437, "tid": 31318, + "ts": 658972198497.004, "dur": 1.287, + "args": { + "External id": 36005,"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": 4183437, "tid": 31318, + "ts": 658972198497.558, "dur": 0.669, + "args": { + "External id": 36006,"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": 4183437, "tid": 31318, + "ts": 658972198502.135, "dur": 3.617, + "args": { + "External id": 36007,"Record function id": 0, "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972198503.056, "dur": 2.288, + "args": { + "External id": 36008,"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": 4183437, "tid": 31318, + "ts": 658972198503.540, "dur": 1.344, + "args": { + "External id": 36009,"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": 4183437, "tid": 31318, + "ts": 658972198503.943, "dur": 0.877, + "args": { + "External id": 36010,"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": 4183437, "tid": 31318, + "ts": 658972198508.857, "dur": 7.276, + "args": { + "External id": 36011,"Record function id": 0, "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972198509.978, "dur": 5.729, + "args": { + "External id": 36012,"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": 4183437, "tid": 31318, + "ts": 658972198514.218, "dur": 1.086, + "args": { + "External id": 36013,"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": 4183437, "tid": 31318, + "ts": 658972198514.698, "dur": 0.540, + "args": { + "External id": 36014,"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": 4183437, "tid": 31318, + "ts": 658972198519.117, "dur": 3.227, + "args": { + "External id": 36015,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972198519.980, "dur": 1.961, + "args": { + "External id": 36016,"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": 4183437, "tid": 31318, + "ts": 658972198520.486, "dur": 1.022, + "args": { + "External id": 36017,"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": 4183437, "tid": 31318, + "ts": 658972198520.824, "dur": 0.618, + "args": { + "External id": 36018,"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": 4183437, "tid": 31318, + "ts": 658972198525.411, "dur": 3.183, + "args": { + "External id": 36019,"Record function id": 0, "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972198526.247, "dur": 1.929, + "args": { + "External id": 36020,"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": 4183437, "tid": 31318, + "ts": 658972198526.751, "dur": 1.019, + "args": { + "External id": 36021,"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": 4183437, "tid": 31318, + "ts": 658972198527.137, "dur": 0.533, + "args": { + "External id": 36022,"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": 4183437, "tid": 31318, + "ts": 658972198532.511, "dur": 14821.910, + "args": { + "External id": 36023,"Record function id": 0, "Sequence number": 459913, "Fwd thread id": 1, "Ev Idx": 2742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972198533.905, "dur": 14812.397, + "args": { + "External id": 36024,"Sequence number": 459913, "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": 4183437, "tid": 31318, "ts": 658972198533.905, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 4183437, "tid": 31318, + "ts": 658972198560.520, "dur": 36.391, + "args": { + "External id": 36025,"Record function id": 0, "Ev Idx": 2744 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 4183437, "tid": 31318, + "ts": 658972198603.990, "dur": 110.850, + "args": { + "External id": 36026,"Record function id": 0, "Ev Idx": 2745 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 4183437, "tid": 31318, + "ts": 658972198723.296, "dur": 14615.259, + "args": { + "External id": 36027,"Record function id": 0, "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972198815.222, "dur": 7.650, + "args": { + "External id": 36028,"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": 4183437, "tid": 31318, + "ts": 658972198832.902, "dur": 5.204, + "args": { + "External id": 36029,"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": 4183437, "tid": 31318, + "ts": 658972198851.451, "dur": 13824.891, + "args": { + "External id": 36030,"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": 4183437, "tid": 31318, + "ts": 658972198865.366, "dur": 13780.463, + "args": { + "External id": 36031,"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": 4183437, "tid": 31318, + "ts": 658972198889.984, "dur": 13.355, + "args": { + "External id": 36032,"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": 4183437, "tid": 31318, + "ts": 658972198908.818, "dur": 13699.285, + "args": { + "External id": 36033,"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": 4183437, "tid": 31318, + "ts": 658972198911.537, "dur": 13695.951, + "args": { + "External id": 36034,"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": 4183437, "tid": 31318, + "ts": 658972198915.425, "dur": 4.651, + "args": { + "External id": 36035,"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": 4183437, "tid": 31318, + "ts": 658972198921.765, "dur": 13682.009, + "args": { + "External id": 36036,"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": 4183437, "tid": 31318, + "ts": 658972212762.841, "dur": 9.554, + "args": { + "External id": 36037,"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": 4183437, "tid": 31318, + "ts": 658972212765.954, "dur": 6.097, + "args": { + "External id": 36038,"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": 4183437, "tid": 31318, + "ts": 658972212801.896, "dur": 254.646, + "args": { + "External id": 36039,"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": 4183437, "tid": 31318, + "ts": 658972212824.732, "dur": 227.465, + "args": { + "External id": 36040,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972212835.795, "dur": 210.328, + "args": { + "External id": 36041,"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": 4183437, "tid": 31318, + "ts": 658972213070.743, "dur": 2.010, + "args": { + "External id": 36042,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972213121.739, "dur": 5.934, + "args": { + "External id": 36043,"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": 4183437, "tid": 31318, + "ts": 658972213172.314, "dur": 1.365, + "args": { + "External id": 36044,"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": 4183437, "tid": 31318, + "ts": 658972213190.113, "dur": 1.320, + "args": { + "External id": 36045,"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": 4183437, "tid": 31318, + "ts": 658972213202.608, "dur": 0.813, + "args": { + "External id": 36046,"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": 4183437, "tid": 31318, + "ts": 658972213214.993, "dur": 1.120, + "args": { + "External id": 36047,"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": 4183437, "tid": 31318, + "ts": 658972213226.283, "dur": 1.316, + "args": { + "External id": 36048,"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": 4183437, "tid": 31318, + "ts": 658972213237.082, "dur": 1.047, + "args": { + "External id": 36049,"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": 4183437, "tid": 31318, + "ts": 658972213248.797, "dur": 2.759, + "args": { + "External id": 36050,"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": 4183437, "tid": 31318, + "ts": 658972213260.644, "dur": 0.902, + "args": { + "External id": 36051,"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": 4183437, "tid": 31318, + "ts": 658972213368.890, "dur": 2533.692, + "args": { + "External id": 36052,"Record function id": 0, "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 4183437, "tid": 31318, + "ts": 658972213386.903, "dur": 944.212, + "args": { + "External id": 36053,"Record function id": 0, "Ev Idx": 2772 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 4183437, "tid": 31318, + "ts": 658972213401.774, "dur": 330.587, + "args": { + "External id": 36054,"Record function id": 0, "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972213477.584, "dur": 4.308, + "args": { + "External id": 36055,"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": 4183437, "tid": 31318, + "ts": 658972213485.241, "dur": 1.006, + "args": { + "External id": 36056,"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": 4183437, "tid": 31318, + "ts": 658972213488.064, "dur": 1.111, + "args": { + "External id": 36057,"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": 4183437, "tid": 31318, + "ts": 658972213490.921, "dur": 1.208, + "args": { + "External id": 36058,"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": 4183437, "tid": 31318, + "ts": 658972213493.687, "dur": 0.993, + "args": { + "External id": 36059,"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": 4183437, "tid": 31318, + "ts": 658972213497.555, "dur": 1.187, + "args": { + "External id": 36060,"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": 4183437, "tid": 31318, + "ts": 658972213500.315, "dur": 2.094, + "args": { + "External id": 36061,"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": 4183437, "tid": 31318, + "ts": 658972213503.874, "dur": 1.169, + "args": { + "External id": 36062,"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": 4183437, "tid": 31318, + "ts": 658972213506.449, "dur": 0.806, + "args": { + "External id": 36063,"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": 4183437, "tid": 31318, + "ts": 658972213508.641, "dur": 0.812, + "args": { + "External id": 36064,"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": 4183437, "tid": 31318, + "ts": 658972213526.549, "dur": 174.972, + "args": { + "External id": 36065,"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": 4183437, "tid": 31318, + "ts": 658972213542.034, "dur": 154.210, + "args": { + "External id": 36066,"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": 4183437, "tid": 31318, + "ts": 658972213553.294, "dur": 13.718, + "args": { + "External id": 36067,"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": 4183437, "tid": 31318, + "ts": 658972213569.843, "dur": 60.235, + "args": { + "External id": 36068,"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": 4183437, "tid": 31318, + "ts": 658972213572.906, "dur": 56.863, + "args": { + "External id": 36069,"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": 4183437, "tid": 31318, + "ts": 658972213576.936, "dur": 5.249, + "args": { + "External id": 36070,"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": 4183437, "tid": 31318, + "ts": 658972213583.836, "dur": 45.406, + "args": { + "External id": 36071,"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": 4183437, "tid": 31318, + "ts": 658972213808.278, "dur": 514.833, + "args": { + "External id": 36072,"Record function id": 0, "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 4183437, "tid": 31318, + "ts": 658972213824.415, "dur": 485.758, + "args": { + "External id": 36073,"Record function id": 0, "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972213878.393, "dur": 5.603, + "args": { + "External id": 36074,"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": 4183437, "tid": 31318, + "ts": 658972213897.546, "dur": 26.799, + "args": { + "External id": 36075,"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": 4183437, "tid": 31318, + "ts": 658972213902.111, "dur": 1.684, + "args": { + "External id": 36076,"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": 4183437, "tid": 31318, + "ts": 658972213905.820, "dur": 0.609, + "args": { + "External id": 36077,"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": 4183437, "tid": 31318, + "ts": 658972213907.898, "dur": 0.337, + "args": { + "External id": 36078,"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": 4183437, "tid": 31318, + "ts": 658972213909.679, "dur": 0.767, + "args": { + "External id": 36079,"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": 4183437, "tid": 31318, + "ts": 658972213911.528, "dur": 0.587, + "args": { + "External id": 36080,"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": 4183437, "tid": 31318, + "ts": 658972213913.168, "dur": 0.612, + "args": { + "External id": 36081,"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": 4183437, "tid": 31318, + "ts": 658972213914.944, "dur": 0.513, + "args": { + "External id": 36082,"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": 4183437, "tid": 31318, + "ts": 658972213916.446, "dur": 0.631, + "args": { + "External id": 36083,"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": 4183437, "tid": 31318, + "ts": 658972213918.237, "dur": 0.578, + "args": { + "External id": 36084,"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": 4183437, "tid": 31318, + "ts": 658972213934.139, "dur": 28.816, + "args": { + "External id": 36085,"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": 4183437, "tid": 31318, + "ts": 658972213996.597, "dur": 87.468, + "args": { + "External id": 36086,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972214006.161, "dur": 3.056, + "args": { + "External id": 36087,"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": 4183437, "tid": 31318, + "ts": 658972214013.946, "dur": 9.602, + "args": { + "External id": 36088,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972214017.883, "dur": 5.249, + "args": { + "External id": 36089,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972214021.182, "dur": 0.673, + "args": { + "External id": 36090,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972214033.311, "dur": 15.848, + "args": { + "External id": 36091,"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": 4183437, "tid": 31318, + "ts": 658972214034.719, "dur": 0.802, + "args": { + "External id": 36092,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972214036.859, "dur": 0.319, + "args": { + "External id": 36093,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972214038.312, "dur": 0.352, + "args": { + "External id": 36094,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972214039.424, "dur": 0.247, + "args": { + "External id": 36095,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972214040.660, "dur": 0.232, + "args": { + "External id": 36096,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972214041.704, "dur": 0.274, + "args": { + "External id": 36097,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972214042.720, "dur": 0.217, + "args": { + "External id": 36098,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972214043.679, "dur": 0.320, + "args": { + "External id": 36099,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972214044.729, "dur": 0.410, + "args": { + "External id": 36100,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972214058.005, "dur": 18.267, + "args": { + "External id": 36101,"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": 4183437, "tid": 31318, + "ts": 658972214126.011, "dur": 104.828, + "args": { + "External id": 36102,"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": 4183437, "tid": 31318, + "ts": 658972214145.744, "dur": 81.691, + "args": { + "External id": 36103,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972214154.961, "dur": 68.276, + "args": { + "External id": 36104,"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": 4183437, "tid": 31318, + "ts": 658972214242.495, "dur": 1.861, + "args": { + "External id": 36105,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972214339.114, "dur": 1540.477, + "args": { + "External id": 36106,"Sequence number": 459912, "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": 4183437, "tid": 31318, "ts": 658972214339.114, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972214448.527, "dur": 101.984, + "args": { + "External id": 36107,"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": 4183437, "tid": 31318, + "ts": 658972214590.794, "dur": 37.642, + "args": { + "External id": 36108,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972214647.749, "dur": 85.281, + "args": { + "External id": 36109,"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": 4183437, "tid": 31318, + "ts": 658972214746.966, "dur": 31.490, + "args": { + "External id": 36110,"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": 4183437, "tid": 31318, + "ts": 658972214785.151, "dur": 36.276, + "args": { + "External id": 36111,"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": 4183437, "tid": 31318, + "ts": 658972214827.506, "dur": 22.919, + "args": { + "External id": 36112,"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": 4183437, "tid": 31318, + "ts": 658972214857.073, "dur": 29.266, + "args": { + "External id": 36113,"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": 4183437, "tid": 31318, + "ts": 658972214908.132, "dur": 23.218, + "args": { + "External id": 36114,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972214945.895, "dur": 25.861, + "args": { + "External id": 36115,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972214988.809, "dur": 17.128, + "args": { + "External id": 36116,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972215017.536, "dur": 13.230, + "args": { + "External id": 36117,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972215038.930, "dur": 35.678, + "args": { + "External id": 36118,"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": 4183437, "tid": 31318, + "ts": 658972215077.676, "dur": 31.141, + "args": { + "External id": 36119,"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": 4183437, "tid": 31318, + "ts": 658972215135.187, "dur": 184.390, + "args": { + "External id": 36120,"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": 4183437, "tid": 31318, + "ts": 658972215208.226, "dur": 5.532, + "args": { + "External id": 36121,"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": 4183437, "tid": 31318, + "ts": 658972215215.552, "dur": 2.317, + "args": { + "External id": 36122,"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": 4183437, "tid": 31318, + "ts": 658972215350.036, "dur": 24.082, + "args": { + "External id": 36123,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972215383.629, "dur": 13.813, + "args": { + "External id": 36124,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972215407.028, "dur": 43.681, + "args": { + "External id": 36125,"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": 4183437, "tid": 31318, + "ts": 658972215455.887, "dur": 31.198, + "args": { + "External id": 36126,"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": 4183437, "tid": 31318, + "ts": 658972215492.977, "dur": 27.850, + "args": { + "External id": 36127,"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": 4183437, "tid": 31318, + "ts": 658972215525.314, "dur": 27.834, + "args": { + "External id": 36128,"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": 4183437, "tid": 31318, + "ts": 658972215558.366, "dur": 29.618, + "args": { + "External id": 36129,"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": 4183437, "tid": 31318, + "ts": 658972215593.687, "dur": 27.255, + "args": { + "External id": 36130,"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": 4183437, "tid": 31318, + "ts": 658972215635.027, "dur": 58.749, + "args": { + "External id": 36131,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972215716.191, "dur": 23.812, + "args": { + "External id": 36132,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972215752.364, "dur": 18.934, + "args": { + "External id": 36133,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972215798.551, "dur": 21.817, + "args": { + "External id": 36134,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972215834.286, "dur": 15.475, + "args": { + "External id": 36135,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972215924.475, "dur": 15.767, + "args": { + "External id": 36136,"Record function id": 0, "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972215927.950, "dur": 11.362, + "args": { + "External id": 36137,"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": 4183437, "tid": 31318, + "ts": 658972215932.111, "dur": 6.109, + "args": { + "External id": 36138,"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": 4183437, "tid": 31318, + "ts": 658972215933.490, "dur": 4.649, + "args": { + "External id": 36139,"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": 4183437, "tid": 31318, + "ts": 658972215944.099, "dur": 4.719, + "args": { + "External id": 36140,"Record function id": 0, "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972215945.453, "dur": 2.863, + "args": { + "External id": 36141,"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": 4183437, "tid": 31318, + "ts": 658972215946.163, "dur": 1.692, + "args": { + "External id": 36142,"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": 4183437, "tid": 31318, + "ts": 658972215946.686, "dur": 1.060, + "args": { + "External id": 36143,"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": 4183437, "tid": 31318, + "ts": 658972215952.116, "dur": 8.036, + "args": { + "External id": 36144,"Record function id": 0, "Ev Idx": 2863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972215957.285, "dur": 2.405, + "args": { + "External id": 36145,"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": 4183437, "tid": 31318, + "ts": 658972215957.926, "dur": 1.322, + "args": { + "External id": 36146,"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": 4183437, "tid": 31318, + "ts": 658972215958.396, "dur": 0.757, + "args": { + "External id": 36147,"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": 4183437, "tid": 31318, + "ts": 658972215963.255, "dur": 3.778, + "args": { + "External id": 36148,"Record function id": 0, "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972215964.534, "dur": 2.095, + "args": { + "External id": 36149,"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": 4183437, "tid": 31318, + "ts": 658972215965.146, "dur": 1.020, + "args": { + "External id": 36150,"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": 4183437, "tid": 31318, + "ts": 658972215965.575, "dur": 0.518, + "args": { + "External id": 36151,"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": 4183437, "tid": 31318, + "ts": 658972215970.073, "dur": 4.006, + "args": { + "External id": 36152,"Record function id": 0, "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972215971.034, "dur": 2.609, + "args": { + "External id": 36153,"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": 4183437, "tid": 31318, + "ts": 658972215971.677, "dur": 1.540, + "args": { + "External id": 36154,"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": 4183437, "tid": 31318, + "ts": 658972215972.352, "dur": 0.801, + "args": { + "External id": 36155,"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": 4183437, "tid": 31318, + "ts": 658972215977.097, "dur": 3.732, + "args": { + "External id": 36156,"Record function id": 0, "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972215978.284, "dur": 2.108, + "args": { + "External id": 36157,"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": 4183437, "tid": 31318, + "ts": 658972215978.781, "dur": 1.128, + "args": { + "External id": 36158,"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": 4183437, "tid": 31318, + "ts": 658972215979.124, "dur": 0.688, + "args": { + "External id": 36159,"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": 4183437, "tid": 31318, + "ts": 658972215983.909, "dur": 3.590, + "args": { + "External id": 36160,"Record function id": 0, "Ev Idx": 2879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972215985.079, "dur": 2.010, + "args": { + "External id": 36161,"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": 4183437, "tid": 31318, + "ts": 658972215985.593, "dur": 1.071, + "args": { + "External id": 36162,"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": 4183437, "tid": 31318, + "ts": 658972215986.059, "dur": 0.539, + "args": { + "External id": 36163,"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": 4183437, "tid": 31318, + "ts": 658972215990.859, "dur": 4.092, + "args": { + "External id": 36164,"Record function id": 0, "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972215991.702, "dur": 2.808, + "args": { + "External id": 36165,"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": 4183437, "tid": 31318, + "ts": 658972215992.212, "dur": 1.806, + "args": { + "External id": 36166,"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": 4183437, "tid": 31318, + "ts": 658972215992.866, "dur": 1.086, + "args": { + "External id": 36167,"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": 4183437, "tid": 31318, + "ts": 658972215998.079, "dur": 3.469, + "args": { + "External id": 36168,"Record function id": 0, "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972215999.108, "dur": 2.043, + "args": { + "External id": 36169,"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": 4183437, "tid": 31318, + "ts": 658972215999.605, "dur": 1.110, + "args": { + "External id": 36170,"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": 4183437, "tid": 31318, + "ts": 658972216000.030, "dur": 0.620, + "args": { + "External id": 36171,"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": 4183437, "tid": 31318, + "ts": 658972216005.160, "dur": 16594.920, + "args": { + "External id": 36172,"Record function id": 0, "Sequence number": 459911, "Fwd thread id": 1, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972216006.244, "dur": 16585.838, + "args": { + "External id": 36173,"Sequence number": 459911, "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": 4183437, "tid": 31318, "ts": 658972216006.244, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 4183437, "tid": 31318, + "ts": 658972216033.182, "dur": 36.375, + "args": { + "External id": 36174,"Record function id": 0, "Ev Idx": 2893 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 4183437, "tid": 31318, + "ts": 658972216076.778, "dur": 66.938, + "args": { + "External id": 36175,"Record function id": 0, "Ev Idx": 2894 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 4183437, "tid": 31318, + "ts": 658972216149.884, "dur": 16434.393, + "args": { + "External id": 36176,"Record function id": 0, "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972216241.028, "dur": 6.695, + "args": { + "External id": 36177,"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": 4183437, "tid": 31318, + "ts": 658972216256.392, "dur": 4.739, + "args": { + "External id": 36178,"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": 4183437, "tid": 31318, + "ts": 658972216301.022, "dur": 15570.970, + "args": { + "External id": 36179,"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": 4183437, "tid": 31318, + "ts": 658972216315.050, "dur": 15548.627, + "args": { + "External id": 36180,"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": 4183437, "tid": 31318, + "ts": 658972216338.042, "dur": 14.122, + "args": { + "External id": 36181,"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": 4183437, "tid": 31318, + "ts": 658972216357.328, "dur": 15472.207, + "args": { + "External id": 36182,"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": 4183437, "tid": 31318, + "ts": 658972216359.986, "dur": 15468.918, + "args": { + "External id": 36183,"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": 4183437, "tid": 31318, + "ts": 658972216364.034, "dur": 5.058, + "args": { + "External id": 36184,"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": 4183437, "tid": 31318, + "ts": 658972216370.808, "dur": 15454.800, + "args": { + "External id": 36185,"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": 4183437, "tid": 31318, + "ts": 658972231960.657, "dur": 9.541, + "args": { + "External id": 36186,"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": 4183437, "tid": 31318, + "ts": 658972231963.511, "dur": 6.289, + "args": { + "External id": 36187,"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": 4183437, "tid": 31318, + "ts": 658972231995.150, "dur": 323.537, + "args": { + "External id": 36188,"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": 4183437, "tid": 31318, + "ts": 658972232018.235, "dur": 295.599, + "args": { + "External id": 36189,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972232029.328, "dur": 279.043, + "args": { + "External id": 36190,"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": 4183437, "tid": 31318, + "ts": 658972232336.289, "dur": 1.960, + "args": { + "External id": 36191,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972232393.659, "dur": 6.461, + "args": { + "External id": 36192,"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": 4183437, "tid": 31318, + "ts": 658972232443.816, "dur": 1.415, + "args": { + "External id": 36193,"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": 4183437, "tid": 31318, + "ts": 658972232458.593, "dur": 1.200, + "args": { + "External id": 36194,"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": 4183437, "tid": 31318, + "ts": 658972232470.224, "dur": 1.197, + "args": { + "External id": 36195,"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": 4183437, "tid": 31318, + "ts": 658972232481.703, "dur": 0.961, + "args": { + "External id": 36196,"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": 4183437, "tid": 31318, + "ts": 658972232491.540, "dur": 0.798, + "args": { + "External id": 36197,"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": 4183437, "tid": 31318, + "ts": 658972232501.844, "dur": 0.800, + "args": { + "External id": 36198,"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": 4183437, "tid": 31318, + "ts": 658972232511.867, "dur": 1.985, + "args": { + "External id": 36199,"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": 4183437, "tid": 31318, + "ts": 658972232523.232, "dur": 1.006, + "args": { + "External id": 36200,"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": 4183437, "tid": 31318, + "ts": 658972232613.524, "dur": 2597.866, + "args": { + "External id": 36201,"Record function id": 0, "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 4183437, "tid": 31318, + "ts": 658972232631.672, "dur": 967.558, + "args": { + "External id": 36202,"Record function id": 0, "Ev Idx": 2921 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 4183437, "tid": 31318, + "ts": 658972232645.374, "dur": 343.776, + "args": { + "External id": 36203,"Record function id": 0, "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972232772.690, "dur": 5.219, + "args": { + "External id": 36204,"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": 4183437, "tid": 31318, + "ts": 658972232781.067, "dur": 1.117, + "args": { + "External id": 36205,"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": 4183437, "tid": 31318, + "ts": 658972232784.059, "dur": 0.805, + "args": { + "External id": 36206,"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": 4183437, "tid": 31318, + "ts": 658972232786.424, "dur": 1.048, + "args": { + "External id": 36207,"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": 4183437, "tid": 31318, + "ts": 658972232788.952, "dur": 1.083, + "args": { + "External id": 36208,"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": 4183437, "tid": 31318, + "ts": 658972232791.480, "dur": 1.015, + "args": { + "External id": 36209,"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": 4183437, "tid": 31318, + "ts": 658972232793.963, "dur": 1.999, + "args": { + "External id": 36210,"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": 4183437, "tid": 31318, + "ts": 658972232797.311, "dur": 0.680, + "args": { + "External id": 36211,"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": 4183437, "tid": 31318, + "ts": 658972232799.124, "dur": 0.736, + "args": { + "External id": 36212,"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": 4183437, "tid": 31318, + "ts": 658972232801.366, "dur": 0.866, + "args": { + "External id": 36213,"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": 4183437, "tid": 31318, + "ts": 658972232819.165, "dur": 139.994, + "args": { + "External id": 36214,"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": 4183437, "tid": 31318, + "ts": 658972232835.344, "dur": 119.666, + "args": { + "External id": 36215,"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": 4183437, "tid": 31318, + "ts": 658972232847.491, "dur": 14.242, + "args": { + "External id": 36216,"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": 4183437, "tid": 31318, + "ts": 658972232864.599, "dur": 63.720, + "args": { + "External id": 36217,"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": 4183437, "tid": 31318, + "ts": 658972232867.207, "dur": 60.689, + "args": { + "External id": 36218,"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": 4183437, "tid": 31318, + "ts": 658972232871.086, "dur": 5.858, + "args": { + "External id": 36219,"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": 4183437, "tid": 31318, + "ts": 658972232878.659, "dur": 48.630, + "args": { + "External id": 36220,"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": 4183437, "tid": 31318, + "ts": 658972233064.213, "dur": 526.799, + "args": { + "External id": 36221,"Record function id": 0, "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 4183437, "tid": 31318, + "ts": 658972233080.947, "dur": 498.659, + "args": { + "External id": 36222,"Record function id": 0, "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972233133.876, "dur": 4.457, + "args": { + "External id": 36223,"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": 4183437, "tid": 31318, + "ts": 658972233152.994, "dur": 22.192, + "args": { + "External id": 36224,"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": 4183437, "tid": 31318, + "ts": 658972233157.405, "dur": 1.750, + "args": { + "External id": 36225,"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": 4183437, "tid": 31318, + "ts": 658972233160.739, "dur": 0.627, + "args": { + "External id": 36226,"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": 4183437, "tid": 31318, + "ts": 658972233162.374, "dur": 0.309, + "args": { + "External id": 36227,"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": 4183437, "tid": 31318, + "ts": 658972233163.571, "dur": 0.408, + "args": { + "External id": 36228,"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": 4183437, "tid": 31318, + "ts": 658972233164.781, "dur": 0.458, + "args": { + "External id": 36229,"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": 4183437, "tid": 31318, + "ts": 658972233166.180, "dur": 0.273, + "args": { + "External id": 36230,"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": 4183437, "tid": 31318, + "ts": 658972233169.148, "dur": 0.297, + "args": { + "External id": 36231,"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": 4183437, "tid": 31318, + "ts": 658972233170.386, "dur": 0.446, + "args": { + "External id": 36232,"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": 4183437, "tid": 31318, + "ts": 658972233171.729, "dur": 0.250, + "args": { + "External id": 36233,"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": 4183437, "tid": 31318, + "ts": 658972233184.148, "dur": 27.382, + "args": { + "External id": 36234,"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": 4183437, "tid": 31318, + "ts": 658972233241.485, "dur": 120.169, + "args": { + "External id": 36235,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972233250.841, "dur": 2.847, + "args": { + "External id": 36236,"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": 4183437, "tid": 31318, + "ts": 658972233258.192, "dur": 26.869, + "args": { + "External id": 36237,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972233262.182, "dur": 22.390, + "args": { + "External id": 36238,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972233281.701, "dur": 0.977, + "args": { + "External id": 36239,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972233293.347, "dur": 23.901, + "args": { + "External id": 36240,"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": 4183437, "tid": 31318, + "ts": 658972233295.891, "dur": 0.459, + "args": { + "External id": 36241,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972233298.222, "dur": 0.689, + "args": { + "External id": 36242,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972233300.364, "dur": 0.786, + "args": { + "External id": 36243,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972233302.759, "dur": 0.784, + "args": { + "External id": 36244,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972233304.711, "dur": 0.305, + "args": { + "External id": 36245,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972233306.323, "dur": 0.516, + "args": { + "External id": 36246,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972233307.945, "dur": 0.458, + "args": { + "External id": 36247,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972233309.969, "dur": 0.683, + "args": { + "External id": 36248,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972233311.790, "dur": 0.544, + "args": { + "External id": 36249,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972233330.176, "dur": 19.809, + "args": { + "External id": 36250,"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": 4183437, "tid": 31318, + "ts": 658972233405.942, "dur": 111.431, + "args": { + "External id": 36251,"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": 4183437, "tid": 31318, + "ts": 658972233431.981, "dur": 81.948, + "args": { + "External id": 36252,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972233440.996, "dur": 68.935, + "args": { + "External id": 36253,"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": 4183437, "tid": 31318, + "ts": 658972233531.043, "dur": 1.743, + "args": { + "External id": 36254,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972233606.105, "dur": 1586.159, + "args": { + "External id": 36255,"Sequence number": 459910, "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": 4183437, "tid": 31318, "ts": 658972233606.105, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972233756.605, "dur": 107.393, + "args": { + "External id": 36256,"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": 4183437, "tid": 31318, + "ts": 658972233900.581, "dur": 38.902, + "args": { + "External id": 36257,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972233955.792, "dur": 37.846, + "args": { + "External id": 36258,"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": 4183437, "tid": 31318, + "ts": 658972234002.925, "dur": 24.479, + "args": { + "External id": 36259,"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": 4183437, "tid": 31318, + "ts": 658972234034.058, "dur": 32.999, + "args": { + "External id": 36260,"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": 4183437, "tid": 31318, + "ts": 658972234073.755, "dur": 24.328, + "args": { + "External id": 36261,"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": 4183437, "tid": 31318, + "ts": 658972234104.796, "dur": 28.480, + "args": { + "External id": 36262,"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": 4183437, "tid": 31318, + "ts": 658972234157.557, "dur": 20.619, + "args": { + "External id": 36263,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972234196.117, "dur": 28.511, + "args": { + "External id": 36264,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972234242.267, "dur": 17.885, + "args": { + "External id": 36265,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972234296.977, "dur": 16.857, + "args": { + "External id": 36266,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972234323.318, "dur": 40.066, + "args": { + "External id": 36267,"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": 4183437, "tid": 31318, + "ts": 658972234366.513, "dur": 30.227, + "args": { + "External id": 36268,"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": 4183437, "tid": 31318, + "ts": 658972234422.040, "dur": 166.227, + "args": { + "External id": 36269,"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": 4183437, "tid": 31318, + "ts": 658972234496.736, "dur": 6.257, + "args": { + "External id": 36270,"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": 4183437, "tid": 31318, + "ts": 658972234504.979, "dur": 3.024, + "args": { + "External id": 36271,"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": 4183437, "tid": 31318, + "ts": 658972234616.591, "dur": 26.307, + "args": { + "External id": 36272,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972234691.140, "dur": 18.411, + "args": { + "External id": 36273,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972234719.816, "dur": 49.730, + "args": { + "External id": 36274,"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": 4183437, "tid": 31318, + "ts": 658972234778.939, "dur": 31.837, + "args": { + "External id": 36275,"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": 4183437, "tid": 31318, + "ts": 658972234817.458, "dur": 31.160, + "args": { + "External id": 36276,"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": 4183437, "tid": 31318, + "ts": 658972234853.264, "dur": 28.306, + "args": { + "External id": 36277,"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": 4183437, "tid": 31318, + "ts": 658972234887.915, "dur": 30.778, + "args": { + "External id": 36278,"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": 4183437, "tid": 31318, + "ts": 658972234925.229, "dur": 29.986, + "args": { + "External id": 36279,"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": 4183437, "tid": 31318, + "ts": 658972234971.253, "dur": 24.834, + "args": { + "External id": 36280,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972235016.487, "dur": 40.085, + "args": { + "External id": 36281,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972235080.066, "dur": 18.578, + "args": { + "External id": 36282,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972235113.460, "dur": 18.299, + "args": { + "External id": 36283,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972235143.707, "dur": 16.297, + "args": { + "External id": 36284,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972235233.564, "dur": 18.008, + "args": { + "External id": 36285,"Record function id": 0, "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972235236.705, "dur": 14.044, + "args": { + "External id": 36286,"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": 4183437, "tid": 31318, + "ts": 658972235244.057, "dur": 5.769, + "args": { + "External id": 36287,"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": 4183437, "tid": 31318, + "ts": 658972235245.382, "dur": 4.362, + "args": { + "External id": 36288,"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": 4183437, "tid": 31318, + "ts": 658972235255.283, "dur": 4.650, + "args": { + "External id": 36289,"Record function id": 0, "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972235256.685, "dur": 2.789, + "args": { + "External id": 36290,"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": 4183437, "tid": 31318, + "ts": 658972235257.337, "dur": 1.658, + "args": { + "External id": 36291,"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": 4183437, "tid": 31318, + "ts": 658972235257.852, "dur": 1.038, + "args": { + "External id": 36292,"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": 4183437, "tid": 31318, + "ts": 658972235262.994, "dur": 23.720, + "args": { + "External id": 36293,"Record function id": 0, "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972235281.043, "dur": 4.671, + "args": { + "External id": 36294,"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": 4183437, "tid": 31318, + "ts": 658972235282.299, "dur": 2.585, + "args": { + "External id": 36295,"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": 4183437, "tid": 31318, + "ts": 658972235283.112, "dur": 1.505, + "args": { + "External id": 36296,"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": 4183437, "tid": 31318, + "ts": 658972235291.503, "dur": 4.366, + "args": { + "External id": 36297,"Record function id": 0, "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972235293.069, "dur": 2.373, + "args": { + "External id": 36298,"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": 4183437, "tid": 31318, + "ts": 658972235293.672, "dur": 1.335, + "args": { + "External id": 36299,"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": 4183437, "tid": 31318, + "ts": 658972235294.129, "dur": 0.800, + "args": { + "External id": 36300,"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": 4183437, "tid": 31318, + "ts": 658972235302.418, "dur": 3.963, + "args": { + "External id": 36301,"Record function id": 0, "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972235303.487, "dur": 2.431, + "args": { + "External id": 36302,"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": 4183437, "tid": 31318, + "ts": 658972235304.071, "dur": 1.390, + "args": { + "External id": 36303,"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": 4183437, "tid": 31318, + "ts": 658972235304.396, "dur": 0.992, + "args": { + "External id": 36304,"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": 4183437, "tid": 31318, + "ts": 658972235309.348, "dur": 3.661, + "args": { + "External id": 36305,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972235310.349, "dur": 2.170, + "args": { + "External id": 36306,"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": 4183437, "tid": 31318, + "ts": 658972235310.838, "dur": 1.263, + "args": { + "External id": 36307,"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": 4183437, "tid": 31318, + "ts": 658972235311.229, "dur": 0.778, + "args": { + "External id": 36308,"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": 4183437, "tid": 31318, + "ts": 658972235316.102, "dur": 3.743, + "args": { + "External id": 36309,"Record function id": 0, "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972235317.001, "dur": 2.394, + "args": { + "External id": 36310,"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": 4183437, "tid": 31318, + "ts": 658972235317.487, "dur": 1.502, + "args": { + "External id": 36311,"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": 4183437, "tid": 31318, + "ts": 658972235317.743, "dur": 1.181, + "args": { + "External id": 36312,"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": 4183437, "tid": 31318, + "ts": 658972235323.071, "dur": 3.334, + "args": { + "External id": 36313,"Record function id": 0, "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972235324.052, "dur": 1.937, + "args": { + "External id": 36314,"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": 4183437, "tid": 31318, + "ts": 658972235324.503, "dur": 1.061, + "args": { + "External id": 36315,"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": 4183437, "tid": 31318, + "ts": 658972235324.805, "dur": 0.696, + "args": { + "External id": 36316,"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": 4183437, "tid": 31318, + "ts": 658972235329.468, "dur": 3.406, + "args": { + "External id": 36317,"Record function id": 0, "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972235330.409, "dur": 2.028, + "args": { + "External id": 36318,"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": 4183437, "tid": 31318, + "ts": 658972235330.874, "dur": 1.135, + "args": { + "External id": 36319,"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": 4183437, "tid": 31318, + "ts": 658972235331.274, "dur": 0.671, + "args": { + "External id": 36320,"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": 4183437, "tid": 31318, + "ts": 658972235336.253, "dur": 14841.155, + "args": { + "External id": 36321,"Record function id": 0, "Sequence number": 459909, "Fwd thread id": 1, "Ev Idx": 3040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972235337.470, "dur": 14831.440, + "args": { + "External id": 36322,"Sequence number": 459909, "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": 4183437, "tid": 31318, "ts": 658972235337.470, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 4183437, "tid": 31318, + "ts": 658972235367.189, "dur": 36.096, + "args": { + "External id": 36323,"Record function id": 0, "Ev Idx": 3042 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 4183437, "tid": 31318, + "ts": 658972235410.539, "dur": 64.086, + "args": { + "External id": 36324,"Record function id": 0, "Ev Idx": 3043 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 4183437, "tid": 31318, + "ts": 658972235483.833, "dur": 14677.759, + "args": { + "External id": 36325,"Record function id": 0, "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972235569.328, "dur": 7.415, + "args": { + "External id": 36326,"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": 4183437, "tid": 31318, + "ts": 658972235585.855, "dur": 4.823, + "args": { + "External id": 36327,"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": 4183437, "tid": 31318, + "ts": 658972235604.089, "dur": 13872.416, + "args": { + "External id": 36328,"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": 4183437, "tid": 31318, + "ts": 658972235622.157, "dur": 13845.885, + "args": { + "External id": 36329,"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": 4183437, "tid": 31318, + "ts": 658972235644.572, "dur": 53.085, + "args": { + "External id": 36330,"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": 4183437, "tid": 31318, + "ts": 658972235704.257, "dur": 13725.960, + "args": { + "External id": 36331,"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": 4183437, "tid": 31318, + "ts": 658972235707.036, "dur": 13722.576, + "args": { + "External id": 36332,"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": 4183437, "tid": 31318, + "ts": 658972235711.182, "dur": 5.502, + "args": { + "External id": 36333,"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": 4183437, "tid": 31318, + "ts": 658972235718.403, "dur": 13707.393, + "args": { + "External id": 36334,"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": 4183437, "tid": 31318, + "ts": 658972249565.330, "dur": 12.389, + "args": { + "External id": 36335,"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": 4183437, "tid": 31318, + "ts": 658972249568.158, "dur": 9.164, + "args": { + "External id": 36336,"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": 4183437, "tid": 31318, + "ts": 658972249605.216, "dur": 285.472, + "args": { + "External id": 36337,"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": 4183437, "tid": 31318, + "ts": 658972249628.555, "dur": 257.542, + "args": { + "External id": 36338,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972249639.232, "dur": 241.984, + "args": { + "External id": 36339,"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": 4183437, "tid": 31318, + "ts": 658972249909.049, "dur": 2.039, + "args": { + "External id": 36340,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972249965.368, "dur": 6.047, + "args": { + "External id": 36341,"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": 4183437, "tid": 31318, + "ts": 658972250015.365, "dur": 1.487, + "args": { + "External id": 36342,"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": 4183437, "tid": 31318, + "ts": 658972250031.667, "dur": 1.515, + "args": { + "External id": 36343,"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": 4183437, "tid": 31318, + "ts": 658972250044.933, "dur": 1.165, + "args": { + "External id": 36344,"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": 4183437, "tid": 31318, + "ts": 658972250055.819, "dur": 1.326, + "args": { + "External id": 36345,"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": 4183437, "tid": 31318, + "ts": 658972250067.752, "dur": 1.118, + "args": { + "External id": 36346,"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": 4183437, "tid": 31318, + "ts": 658972250078.423, "dur": 1.292, + "args": { + "External id": 36347,"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": 4183437, "tid": 31318, + "ts": 658972250090.224, "dur": 1.919, + "args": { + "External id": 36348,"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": 4183437, "tid": 31318, + "ts": 658972250101.086, "dur": 1.319, + "args": { + "External id": 36349,"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": 4183437, "tid": 31318, + "ts": 658972250190.883, "dur": 2625.165, + "args": { + "External id": 36350,"Record function id": 0, "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 4183437, "tid": 31318, + "ts": 658972250208.635, "dur": 985.924, + "args": { + "External id": 36351,"Record function id": 0, "Ev Idx": 3070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 4183437, "tid": 31318, + "ts": 658972250222.555, "dur": 328.330, + "args": { + "External id": 36352,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972250332.858, "dur": 4.963, + "args": { + "External id": 36353,"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": 4183437, "tid": 31318, + "ts": 658972250341.343, "dur": 0.995, + "args": { + "External id": 36354,"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": 4183437, "tid": 31318, + "ts": 658972250343.940, "dur": 1.643, + "args": { + "External id": 36355,"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": 4183437, "tid": 31318, + "ts": 658972250347.011, "dur": 1.808, + "args": { + "External id": 36356,"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": 4183437, "tid": 31318, + "ts": 658972250349.976, "dur": 1.283, + "args": { + "External id": 36357,"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": 4183437, "tid": 31318, + "ts": 658972250352.443, "dur": 1.043, + "args": { + "External id": 36358,"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": 4183437, "tid": 31318, + "ts": 658972250354.770, "dur": 1.003, + "args": { + "External id": 36359,"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": 4183437, "tid": 31318, + "ts": 658972250357.107, "dur": 1.004, + "args": { + "External id": 36360,"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": 4183437, "tid": 31318, + "ts": 658972250359.656, "dur": 1.678, + "args": { + "External id": 36361,"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": 4183437, "tid": 31318, + "ts": 658972250362.758, "dur": 1.170, + "args": { + "External id": 36362,"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": 4183437, "tid": 31318, + "ts": 658972250382.707, "dur": 137.353, + "args": { + "External id": 36363,"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": 4183437, "tid": 31318, + "ts": 658972250398.500, "dur": 116.920, + "args": { + "External id": 36364,"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": 4183437, "tid": 31318, + "ts": 658972250410.440, "dur": 13.131, + "args": { + "External id": 36365,"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": 4183437, "tid": 31318, + "ts": 658972250426.640, "dur": 61.180, + "args": { + "External id": 36366,"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": 4183437, "tid": 31318, + "ts": 658972250428.969, "dur": 58.575, + "args": { + "External id": 36367,"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": 4183437, "tid": 31318, + "ts": 658972250432.782, "dur": 5.023, + "args": { + "External id": 36368,"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": 4183437, "tid": 31318, + "ts": 658972250439.283, "dur": 47.708, + "args": { + "External id": 36369,"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": 4183437, "tid": 31318, + "ts": 658972250628.112, "dur": 558.119, + "args": { + "External id": 36370,"Record function id": 0, "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 4183437, "tid": 31318, + "ts": 658972250646.141, "dur": 528.669, + "args": { + "External id": 36371,"Record function id": 0, "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972250745.204, "dur": 6.666, + "args": { + "External id": 36372,"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": 4183437, "tid": 31318, + "ts": 658972250766.719, "dur": 23.793, + "args": { + "External id": 36373,"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": 4183437, "tid": 31318, + "ts": 658972250771.199, "dur": 1.619, + "args": { + "External id": 36374,"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": 4183437, "tid": 31318, + "ts": 658972250774.179, "dur": 0.789, + "args": { + "External id": 36375,"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": 4183437, "tid": 31318, + "ts": 658972250775.855, "dur": 1.035, + "args": { + "External id": 36376,"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": 4183437, "tid": 31318, + "ts": 658972250777.626, "dur": 0.783, + "args": { + "External id": 36377,"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": 4183437, "tid": 31318, + "ts": 658972250779.204, "dur": 0.512, + "args": { + "External id": 36378,"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": 4183437, "tid": 31318, + "ts": 658972250780.565, "dur": 0.499, + "args": { + "External id": 36379,"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": 4183437, "tid": 31318, + "ts": 658972250782.114, "dur": 0.500, + "args": { + "External id": 36380,"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": 4183437, "tid": 31318, + "ts": 658972250783.938, "dur": 0.637, + "args": { + "External id": 36381,"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": 4183437, "tid": 31318, + "ts": 658972250785.653, "dur": 0.698, + "args": { + "External id": 36382,"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": 4183437, "tid": 31318, + "ts": 658972250800.150, "dur": 30.172, + "args": { + "External id": 36383,"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": 4183437, "tid": 31318, + "ts": 658972250860.546, "dur": 96.233, + "args": { + "External id": 36384,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972250870.106, "dur": 3.517, + "args": { + "External id": 36385,"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": 4183437, "tid": 31318, + "ts": 658972250878.443, "dur": 10.340, + "args": { + "External id": 36386,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972250882.753, "dur": 5.606, + "args": { + "External id": 36387,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972250885.660, "dur": 0.849, + "args": { + "External id": 36388,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972250895.014, "dur": 25.322, + "args": { + "External id": 36389,"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": 4183437, "tid": 31318, + "ts": 658972250896.610, "dur": 0.601, + "args": { + "External id": 36390,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972250898.441, "dur": 1.090, + "args": { + "External id": 36391,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972250900.608, "dur": 0.921, + "args": { + "External id": 36392,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972250903.057, "dur": 0.379, + "args": { + "External id": 36393,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972250904.951, "dur": 0.425, + "args": { + "External id": 36394,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972250907.003, "dur": 0.863, + "args": { + "External id": 36395,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972250908.797, "dur": 0.778, + "args": { + "External id": 36396,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972250910.693, "dur": 0.456, + "args": { + "External id": 36397,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972250912.736, "dur": 0.366, + "args": { + "External id": 36398,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972250930.887, "dur": 17.551, + "args": { + "External id": 36399,"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": 4183437, "tid": 31318, + "ts": 658972251003.113, "dur": 109.250, + "args": { + "External id": 36400,"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": 4183437, "tid": 31318, + "ts": 658972251024.635, "dur": 84.611, + "args": { + "External id": 36401,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972251037.762, "dur": 66.897, + "args": { + "External id": 36402,"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": 4183437, "tid": 31318, + "ts": 658972251124.837, "dur": 2.061, + "args": { + "External id": 36403,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972251201.365, "dur": 1595.339, + "args": { + "External id": 36404,"Sequence number": 459908, "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": 4183437, "tid": 31318, "ts": 658972251201.365, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972251333.265, "dur": 105.765, + "args": { + "External id": 36405,"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": 4183437, "tid": 31318, + "ts": 658972251475.209, "dur": 39.027, + "args": { + "External id": 36406,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972251529.887, "dur": 40.096, + "args": { + "External id": 36407,"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": 4183437, "tid": 31318, + "ts": 658972251579.577, "dur": 25.403, + "args": { + "External id": 36408,"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": 4183437, "tid": 31318, + "ts": 658972251611.028, "dur": 32.016, + "args": { + "External id": 36409,"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": 4183437, "tid": 31318, + "ts": 658972251650.532, "dur": 63.631, + "args": { + "External id": 36410,"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": 4183437, "tid": 31318, + "ts": 658972251724.842, "dur": 30.165, + "args": { + "External id": 36411,"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": 4183437, "tid": 31318, + "ts": 658972251782.965, "dur": 22.195, + "args": { + "External id": 36412,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972251824.570, "dur": 26.603, + "args": { + "External id": 36413,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972251869.404, "dur": 22.142, + "args": { + "External id": 36414,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972251902.993, "dur": 13.644, + "args": { + "External id": 36415,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972251924.671, "dur": 37.509, + "args": { + "External id": 36416,"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": 4183437, "tid": 31318, + "ts": 658972251965.170, "dur": 30.414, + "args": { + "External id": 36417,"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": 4183437, "tid": 31318, + "ts": 658972252022.525, "dur": 162.926, + "args": { + "External id": 36418,"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": 4183437, "tid": 31318, + "ts": 658972252096.875, "dur": 5.930, + "args": { + "External id": 36419,"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": 4183437, "tid": 31318, + "ts": 658972252104.701, "dur": 3.120, + "args": { + "External id": 36420,"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": 4183437, "tid": 31318, + "ts": 658972252214.790, "dur": 22.654, + "args": { + "External id": 36421,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972252250.713, "dur": 12.843, + "args": { + "External id": 36422,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972252289.088, "dur": 46.417, + "args": { + "External id": 36423,"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": 4183437, "tid": 31318, + "ts": 658972252341.499, "dur": 31.581, + "args": { + "External id": 36424,"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": 4183437, "tid": 31318, + "ts": 658972252381.730, "dur": 27.057, + "args": { + "External id": 36425,"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": 4183437, "tid": 31318, + "ts": 658972252413.045, "dur": 30.125, + "args": { + "External id": 36426,"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": 4183437, "tid": 31318, + "ts": 658972252448.558, "dur": 26.670, + "args": { + "External id": 36427,"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": 4183437, "tid": 31318, + "ts": 658972252481.479, "dur": 31.431, + "args": { + "External id": 36428,"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": 4183437, "tid": 31318, + "ts": 658972252529.465, "dur": 26.036, + "args": { + "External id": 36429,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972252571.656, "dur": 23.188, + "args": { + "External id": 36430,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972252607.507, "dur": 21.324, + "args": { + "External id": 36431,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972252642.367, "dur": 67.141, + "args": { + "External id": 36432,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972252739.292, "dur": 22.346, + "args": { + "External id": 36433,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972252838.276, "dur": 18.646, + "args": { + "External id": 36434,"Record function id": 0, "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972252841.446, "dur": 14.510, + "args": { + "External id": 36435,"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": 4183437, "tid": 31318, + "ts": 658972252845.766, "dur": 9.369, + "args": { + "External id": 36436,"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": 4183437, "tid": 31318, + "ts": 658972252846.948, "dur": 8.095, + "args": { + "External id": 36437,"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": 4183437, "tid": 31318, + "ts": 658972252860.822, "dur": 4.035, + "args": { + "External id": 36438,"Record function id": 0, "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972252861.935, "dur": 2.498, + "args": { + "External id": 36439,"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": 4183437, "tid": 31318, + "ts": 658972252862.473, "dur": 1.456, + "args": { + "External id": 36440,"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": 4183437, "tid": 31318, + "ts": 658972252862.996, "dur": 0.868, + "args": { + "External id": 36441,"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": 4183437, "tid": 31318, + "ts": 658972252867.988, "dur": 4.307, + "args": { + "External id": 36442,"Record function id": 0, "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972252869.053, "dur": 2.841, + "args": { + "External id": 36443,"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": 4183437, "tid": 31318, + "ts": 658972252869.743, "dur": 1.687, + "args": { + "External id": 36444,"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": 4183437, "tid": 31318, + "ts": 658972252870.327, "dur": 1.022, + "args": { + "External id": 36445,"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": 4183437, "tid": 31318, + "ts": 658972252875.362, "dur": 3.309, + "args": { + "External id": 36446,"Record function id": 0, "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972252876.261, "dur": 2.028, + "args": { + "External id": 36447,"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": 4183437, "tid": 31318, + "ts": 658972252876.777, "dur": 1.086, + "args": { + "External id": 36448,"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": 4183437, "tid": 31318, + "ts": 658972252877.096, "dur": 0.689, + "args": { + "External id": 36449,"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": 4183437, "tid": 31318, + "ts": 658972252881.633, "dur": 3.920, + "args": { + "External id": 36450,"Record function id": 0, "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972252882.581, "dur": 2.541, + "args": { + "External id": 36451,"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": 4183437, "tid": 31318, + "ts": 658972252883.097, "dur": 1.580, + "args": { + "External id": 36452,"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": 4183437, "tid": 31318, + "ts": 658972252883.580, "dur": 1.032, + "args": { + "External id": 36453,"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": 4183437, "tid": 31318, + "ts": 658972252888.587, "dur": 3.891, + "args": { + "External id": 36454,"Record function id": 0, "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972252889.676, "dur": 2.380, + "args": { + "External id": 36455,"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": 4183437, "tid": 31318, + "ts": 658972252890.151, "dur": 1.484, + "args": { + "External id": 36456,"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": 4183437, "tid": 31318, + "ts": 658972252890.792, "dur": 0.773, + "args": { + "External id": 36457,"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": 4183437, "tid": 31318, + "ts": 658972252895.486, "dur": 3.978, + "args": { + "External id": 36458,"Record function id": 0, "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972252896.411, "dur": 2.659, + "args": { + "External id": 36459,"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": 4183437, "tid": 31318, + "ts": 658972252897.082, "dur": 1.544, + "args": { + "External id": 36460,"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": 4183437, "tid": 31318, + "ts": 658972252897.520, "dur": 1.042, + "args": { + "External id": 36461,"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": 4183437, "tid": 31318, + "ts": 658972252902.578, "dur": 3.783, + "args": { + "External id": 36462,"Record function id": 0, "Ev Idx": 3181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972252903.497, "dur": 2.448, + "args": { + "External id": 36463,"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": 4183437, "tid": 31318, + "ts": 658972252904.049, "dur": 1.474, + "args": { + "External id": 36464,"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": 4183437, "tid": 31318, + "ts": 658972252904.404, "dur": 1.054, + "args": { + "External id": 36465,"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": 4183437, "tid": 31318, + "ts": 658972252912.612, "dur": 4.118, + "args": { + "External id": 36466,"Record function id": 0, "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972252913.750, "dur": 2.584, + "args": { + "External id": 36467,"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": 4183437, "tid": 31318, + "ts": 658972252914.339, "dur": 1.563, + "args": { + "External id": 36468,"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": 4183437, "tid": 31318, + "ts": 658972252914.806, "dur": 1.024, + "args": { + "External id": 36469,"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": 4183437, "tid": 31318, + "ts": 658972252920.654, "dur": 14918.460, + "args": { + "External id": 36470,"Record function id": 0, "Sequence number": 459907, "Fwd thread id": 1, "Ev Idx": 3189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972252922.159, "dur": 14908.665, + "args": { + "External id": 36471,"Sequence number": 459907, "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": 4183437, "tid": 31318, "ts": 658972252922.159, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 4183437, "tid": 31318, + "ts": 658972252949.105, "dur": 38.485, + "args": { + "External id": 36472,"Record function id": 0, "Ev Idx": 3191 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 4183437, "tid": 31318, + "ts": 658972252994.864, "dur": 62.837, + "args": { + "External id": 36473,"Record function id": 0, "Ev Idx": 3192 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 4183437, "tid": 31318, + "ts": 658972253063.573, "dur": 14759.427, + "args": { + "External id": 36474,"Record function id": 0, "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972253145.405, "dur": 7.588, + "args": { + "External id": 36475,"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": 4183437, "tid": 31318, + "ts": 658972253161.576, "dur": 4.533, + "args": { + "External id": 36476,"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": 4183437, "tid": 31318, + "ts": 658972253178.871, "dur": 13945.462, + "args": { + "External id": 36477,"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": 4183437, "tid": 31318, + "ts": 658972253191.772, "dur": 13924.251, + "args": { + "External id": 36478,"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": 4183437, "tid": 31318, + "ts": 658972253219.070, "dur": 13.513, + "args": { + "External id": 36479,"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": 4183437, "tid": 31318, + "ts": 658972253237.643, "dur": 13843.033, + "args": { + "External id": 36480,"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": 4183437, "tid": 31318, + "ts": 658972253240.677, "dur": 13839.302, + "args": { + "External id": 36481,"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": 4183437, "tid": 31318, + "ts": 658972253244.181, "dur": 4.819, + "args": { + "External id": 36482,"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": 4183437, "tid": 31318, + "ts": 658972253250.648, "dur": 13825.976, + "args": { + "External id": 36483,"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": 4183437, "tid": 31318, + "ts": 658972267212.085, "dur": 9.536, + "args": { + "External id": 36484,"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": 4183437, "tid": 31318, + "ts": 658972267214.903, "dur": 6.365, + "args": { + "External id": 36485,"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": 4183437, "tid": 31318, + "ts": 658972267247.765, "dur": 269.921, + "args": { + "External id": 36486,"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": 4183437, "tid": 31318, + "ts": 658972267284.052, "dur": 229.067, + "args": { + "External id": 36487,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972267296.280, "dur": 212.545, + "args": { + "External id": 36488,"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": 4183437, "tid": 31318, + "ts": 658972267534.286, "dur": 2.280, + "args": { + "External id": 36489,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972267588.291, "dur": 6.447, + "args": { + "External id": 36490,"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": 4183437, "tid": 31318, + "ts": 658972267638.768, "dur": 1.508, + "args": { + "External id": 36491,"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": 4183437, "tid": 31318, + "ts": 658972267691.335, "dur": 2.163, + "args": { + "External id": 36492,"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": 4183437, "tid": 31318, + "ts": 658972267708.417, "dur": 0.978, + "args": { + "External id": 36493,"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": 4183437, "tid": 31318, + "ts": 658972267718.538, "dur": 1.039, + "args": { + "External id": 36494,"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": 4183437, "tid": 31318, + "ts": 658972267729.755, "dur": 1.063, + "args": { + "External id": 36495,"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": 4183437, "tid": 31318, + "ts": 658972267740.545, "dur": 1.769, + "args": { + "External id": 36496,"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": 4183437, "tid": 31318, + "ts": 658972267751.595, "dur": 1.611, + "args": { + "External id": 36497,"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": 4183437, "tid": 31318, + "ts": 658972267762.052, "dur": 1.661, + "args": { + "External id": 36498,"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": 4183437, "tid": 31318, + "ts": 658972267854.114, "dur": 2547.998, + "args": { + "External id": 36499,"Record function id": 0, "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 4183437, "tid": 31318, + "ts": 658972267872.351, "dur": 941.778, + "args": { + "External id": 36500,"Record function id": 0, "Ev Idx": 3219 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 4183437, "tid": 31318, + "ts": 658972267886.191, "dur": 281.340, + "args": { + "External id": 36501,"Record function id": 0, "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972267959.112, "dur": 4.917, + "args": { + "External id": 36502,"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": 4183437, "tid": 31318, + "ts": 658972267966.851, "dur": 1.254, + "args": { + "External id": 36503,"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": 4183437, "tid": 31318, + "ts": 658972267969.912, "dur": 1.520, + "args": { + "External id": 36504,"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": 4183437, "tid": 31318, + "ts": 658972267972.951, "dur": 1.132, + "args": { + "External id": 36505,"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": 4183437, "tid": 31318, + "ts": 658972267975.498, "dur": 1.593, + "args": { + "External id": 36506,"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": 4183437, "tid": 31318, + "ts": 658972267978.426, "dur": 1.016, + "args": { + "External id": 36507,"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": 4183437, "tid": 31318, + "ts": 658972267981.368, "dur": 1.793, + "args": { + "External id": 36508,"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": 4183437, "tid": 31318, + "ts": 658972267984.477, "dur": 1.318, + "args": { + "External id": 36509,"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": 4183437, "tid": 31318, + "ts": 658972267987.544, "dur": 1.183, + "args": { + "External id": 36510,"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": 4183437, "tid": 31318, + "ts": 658972267990.211, "dur": 1.145, + "args": { + "External id": 36511,"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": 4183437, "tid": 31318, + "ts": 658972268008.106, "dur": 134.497, + "args": { + "External id": 36512,"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": 4183437, "tid": 31318, + "ts": 658972268023.999, "dur": 114.804, + "args": { + "External id": 36513,"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": 4183437, "tid": 31318, + "ts": 658972268036.486, "dur": 12.312, + "args": { + "External id": 36514,"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": 4183437, "tid": 31318, + "ts": 658972268051.604, "dur": 60.046, + "args": { + "External id": 36515,"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": 4183437, "tid": 31318, + "ts": 658972268054.326, "dur": 56.986, + "args": { + "External id": 36516,"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": 4183437, "tid": 31318, + "ts": 658972268057.991, "dur": 5.699, + "args": { + "External id": 36517,"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": 4183437, "tid": 31318, + "ts": 658972268065.754, "dur": 44.954, + "args": { + "External id": 36518,"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": 4183437, "tid": 31318, + "ts": 658972268239.636, "dur": 565.625, + "args": { + "External id": 36519,"Record function id": 0, "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 4183437, "tid": 31318, + "ts": 658972268254.387, "dur": 538.324, + "args": { + "External id": 36520,"Record function id": 0, "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972268329.092, "dur": 5.962, + "args": { + "External id": 36521,"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": 4183437, "tid": 31318, + "ts": 658972268350.407, "dur": 24.392, + "args": { + "External id": 36522,"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": 4183437, "tid": 31318, + "ts": 658972268354.590, "dur": 1.586, + "args": { + "External id": 36523,"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": 4183437, "tid": 31318, + "ts": 658972268357.586, "dur": 0.585, + "args": { + "External id": 36524,"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": 4183437, "tid": 31318, + "ts": 658972268359.594, "dur": 0.423, + "args": { + "External id": 36525,"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": 4183437, "tid": 31318, + "ts": 658972268360.901, "dur": 0.656, + "args": { + "External id": 36526,"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": 4183437, "tid": 31318, + "ts": 658972268362.745, "dur": 0.585, + "args": { + "External id": 36527,"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": 4183437, "tid": 31318, + "ts": 658972268364.424, "dur": 0.570, + "args": { + "External id": 36528,"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": 4183437, "tid": 31318, + "ts": 658972268366.311, "dur": 0.383, + "args": { + "External id": 36529,"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": 4183437, "tid": 31318, + "ts": 658972268367.862, "dur": 0.373, + "args": { + "External id": 36530,"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": 4183437, "tid": 31318, + "ts": 658972268369.358, "dur": 0.637, + "args": { + "External id": 36531,"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": 4183437, "tid": 31318, + "ts": 658972268384.354, "dur": 29.526, + "args": { + "External id": 36532,"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": 4183437, "tid": 31318, + "ts": 658972268444.423, "dur": 84.819, + "args": { + "External id": 36533,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972268453.710, "dur": 3.280, + "args": { + "External id": 36534,"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": 4183437, "tid": 31318, + "ts": 658972268461.894, "dur": 9.991, + "args": { + "External id": 36535,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972268466.000, "dur": 5.451, + "args": { + "External id": 36536,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972268469.433, "dur": 0.588, + "args": { + "External id": 36537,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972268478.436, "dur": 17.900, + "args": { + "External id": 36538,"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": 4183437, "tid": 31318, + "ts": 658972268480.125, "dur": 0.598, + "args": { + "External id": 36539,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972268482.154, "dur": 0.616, + "args": { + "External id": 36540,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972268484.223, "dur": 0.479, + "args": { + "External id": 36541,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972268485.730, "dur": 0.488, + "args": { + "External id": 36542,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972268486.975, "dur": 0.373, + "args": { + "External id": 36543,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972268488.536, "dur": 0.227, + "args": { + "External id": 36544,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972268489.602, "dur": 0.216, + "args": { + "External id": 36545,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972268490.783, "dur": 0.215, + "args": { + "External id": 36546,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972268491.775, "dur": 0.394, + "args": { + "External id": 36547,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972268504.802, "dur": 17.034, + "args": { + "External id": 36548,"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": 4183437, "tid": 31318, + "ts": 658972268571.365, "dur": 148.380, + "args": { + "External id": 36549,"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": 4183437, "tid": 31318, + "ts": 658972268591.136, "dur": 124.573, + "args": { + "External id": 36550,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972268599.999, "dur": 111.002, + "args": { + "External id": 36551,"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": 4183437, "tid": 31318, + "ts": 658972268735.580, "dur": 2.079, + "args": { + "External id": 36552,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972268821.950, "dur": 1559.804, + "args": { + "External id": 36553,"Sequence number": 459906, "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": 4183437, "tid": 31318, "ts": 658972268821.950, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972268932.880, "dur": 101.031, + "args": { + "External id": 36554,"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": 4183437, "tid": 31318, + "ts": 658972269068.109, "dur": 39.363, + "args": { + "External id": 36555,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972269122.900, "dur": 39.036, + "args": { + "External id": 36556,"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": 4183437, "tid": 31318, + "ts": 658972269171.385, "dur": 29.637, + "args": { + "External id": 36557,"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": 4183437, "tid": 31318, + "ts": 658972269207.361, "dur": 32.074, + "args": { + "External id": 36558,"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": 4183437, "tid": 31318, + "ts": 658972269253.160, "dur": 42.165, + "args": { + "External id": 36559,"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": 4183437, "tid": 31318, + "ts": 658972269305.596, "dur": 35.557, + "args": { + "External id": 36560,"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": 4183437, "tid": 31318, + "ts": 658972269365.590, "dur": 26.813, + "args": { + "External id": 36561,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972269409.634, "dur": 26.998, + "args": { + "External id": 36562,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972269455.073, "dur": 20.576, + "args": { + "External id": 36563,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972269486.504, "dur": 15.207, + "args": { + "External id": 36564,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972269509.492, "dur": 36.197, + "args": { + "External id": 36565,"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": 4183437, "tid": 31318, + "ts": 658972269548.602, "dur": 30.269, + "args": { + "External id": 36566,"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": 4183437, "tid": 31318, + "ts": 658972269604.257, "dur": 212.838, + "args": { + "External id": 36567,"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": 4183437, "tid": 31318, + "ts": 658972269719.513, "dur": 7.293, + "args": { + "External id": 36568,"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": 4183437, "tid": 31318, + "ts": 658972269728.924, "dur": 3.864, + "args": { + "External id": 36569,"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": 4183437, "tid": 31318, + "ts": 658972269847.385, "dur": 27.861, + "args": { + "External id": 36570,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972269886.812, "dur": 15.220, + "args": { + "External id": 36571,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972269909.692, "dur": 50.076, + "args": { + "External id": 36572,"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": 4183437, "tid": 31318, + "ts": 658972269965.317, "dur": 34.178, + "args": { + "External id": 36573,"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": 4183437, "tid": 31318, + "ts": 658972270006.265, "dur": 27.466, + "args": { + "External id": 36574,"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": 4183437, "tid": 31318, + "ts": 658972270041.692, "dur": 30.778, + "args": { + "External id": 36575,"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": 4183437, "tid": 31318, + "ts": 658972270078.216, "dur": 26.446, + "args": { + "External id": 36576,"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": 4183437, "tid": 31318, + "ts": 658972270111.683, "dur": 27.018, + "args": { + "External id": 36577,"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": 4183437, "tid": 31318, + "ts": 658972270153.773, "dur": 24.131, + "args": { + "External id": 36578,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972270192.736, "dur": 41.757, + "args": { + "External id": 36579,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972270253.003, "dur": 33.162, + "args": { + "External id": 36580,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972270307.404, "dur": 15.141, + "args": { + "External id": 36581,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972270334.625, "dur": 15.462, + "args": { + "External id": 36582,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972270426.745, "dur": 15.185, + "args": { + "External id": 36583,"Record function id": 0, "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972270429.898, "dur": 10.972, + "args": { + "External id": 36584,"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": 4183437, "tid": 31318, + "ts": 658972270434.215, "dur": 5.609, + "args": { + "External id": 36585,"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": 4183437, "tid": 31318, + "ts": 658972270435.696, "dur": 4.042, + "args": { + "External id": 36586,"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": 4183437, "tid": 31318, + "ts": 658972270445.680, "dur": 4.920, + "args": { + "External id": 36587,"Record function id": 0, "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972270447.118, "dur": 3.050, + "args": { + "External id": 36588,"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": 4183437, "tid": 31318, + "ts": 658972270448.066, "dur": 1.632, + "args": { + "External id": 36589,"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": 4183437, "tid": 31318, + "ts": 658972270448.481, "dur": 1.121, + "args": { + "External id": 36590,"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": 4183437, "tid": 31318, + "ts": 658972270453.822, "dur": 4.160, + "args": { + "External id": 36591,"Record function id": 0, "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972270454.931, "dur": 2.631, + "args": { + "External id": 36592,"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": 4183437, "tid": 31318, + "ts": 658972270455.655, "dur": 1.474, + "args": { + "External id": 36593,"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": 4183437, "tid": 31318, + "ts": 658972270456.412, "dur": 0.630, + "args": { + "External id": 36594,"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": 4183437, "tid": 31318, + "ts": 658972270461.049, "dur": 4.260, + "args": { + "External id": 36595,"Record function id": 0, "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972270462.215, "dur": 2.674, + "args": { + "External id": 36596,"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": 4183437, "tid": 31318, + "ts": 658972270462.814, "dur": 1.623, + "args": { + "External id": 36597,"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": 4183437, "tid": 31318, + "ts": 658972270463.191, "dur": 1.182, + "args": { + "External id": 36598,"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": 4183437, "tid": 31318, + "ts": 658972270468.283, "dur": 4.491, + "args": { + "External id": 36599,"Record function id": 0, "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972270469.557, "dur": 2.777, + "args": { + "External id": 36600,"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": 4183437, "tid": 31318, + "ts": 658972270470.182, "dur": 1.744, + "args": { + "External id": 36601,"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": 4183437, "tid": 31318, + "ts": 658972270470.956, "dur": 0.906, + "args": { + "External id": 36602,"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": 4183437, "tid": 31318, + "ts": 658972270479.149, "dur": 4.449, + "args": { + "External id": 36603,"Record function id": 0, "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972270480.786, "dur": 2.392, + "args": { + "External id": 36604,"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": 4183437, "tid": 31318, + "ts": 658972270481.394, "dur": 1.366, + "args": { + "External id": 36605,"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": 4183437, "tid": 31318, + "ts": 658972270481.888, "dur": 0.807, + "args": { + "External id": 36606,"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": 4183437, "tid": 31318, + "ts": 658972270486.688, "dur": 4.703, + "args": { + "External id": 36607,"Record function id": 0, "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972270487.869, "dur": 3.117, + "args": { + "External id": 36608,"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": 4183437, "tid": 31318, + "ts": 658972270488.553, "dur": 2.013, + "args": { + "External id": 36609,"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": 4183437, "tid": 31318, + "ts": 658972270489.419, "dur": 1.085, + "args": { + "External id": 36610,"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": 4183437, "tid": 31318, + "ts": 658972270494.555, "dur": 4.080, + "args": { + "External id": 36611,"Record function id": 0, "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972270495.680, "dur": 2.549, + "args": { + "External id": 36612,"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": 4183437, "tid": 31318, + "ts": 658972270496.172, "dur": 1.635, + "args": { + "External id": 36613,"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": 4183437, "tid": 31318, + "ts": 658972270496.655, "dur": 1.083, + "args": { + "External id": 36614,"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": 4183437, "tid": 31318, + "ts": 658972270501.596, "dur": 3.791, + "args": { + "External id": 36615,"Record function id": 0, "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972270502.411, "dur": 2.552, + "args": { + "External id": 36616,"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": 4183437, "tid": 31318, + "ts": 658972270502.910, "dur": 1.620, + "args": { + "External id": 36617,"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": 4183437, "tid": 31318, + "ts": 658972270503.582, "dur": 0.883, + "args": { + "External id": 36618,"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": 4183437, "tid": 31318, + "ts": 658972270508.889, "dur": 18057.567, + "args": { + "External id": 36619,"Record function id": 0, "Sequence number": 459905, "Fwd thread id": 1, "Ev Idx": 3338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972270510.023, "dur": 18047.537, + "args": { + "External id": 36620,"Sequence number": 459905, "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": 4183437, "tid": 31318, "ts": 658972270510.023, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 4183437, "tid": 31318, + "ts": 658972270538.956, "dur": 35.624, + "args": { + "External id": 36621,"Record function id": 0, "Ev Idx": 3340 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 4183437, "tid": 31318, + "ts": 658972270581.415, "dur": 63.961, + "args": { + "External id": 36622,"Record function id": 0, "Ev Idx": 3341 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 4183437, "tid": 31318, + "ts": 658972270686.150, "dur": 17863.231, + "args": { + "External id": 36623,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972270775.119, "dur": 7.620, + "args": { + "External id": 36624,"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": 4183437, "tid": 31318, + "ts": 658972270792.224, "dur": 4.963, + "args": { + "External id": 36625,"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": 4183437, "tid": 31318, + "ts": 658972270810.765, "dur": 17013.179, + "args": { + "External id": 36626,"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": 4183437, "tid": 31318, + "ts": 658972270827.856, "dur": 16988.533, + "args": { + "External id": 36627,"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": 4183437, "tid": 31318, + "ts": 658972270854.464, "dur": 13.445, + "args": { + "External id": 36628,"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": 4183437, "tid": 31318, + "ts": 658972270872.664, "dur": 16910.179, + "args": { + "External id": 36629,"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": 4183437, "tid": 31318, + "ts": 658972270875.050, "dur": 16907.137, + "args": { + "External id": 36630,"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": 4183437, "tid": 31318, + "ts": 658972270882.802, "dur": 5.333, + "args": { + "External id": 36631,"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": 4183437, "tid": 31318, + "ts": 658972270889.746, "dur": 16889.181, + "args": { + "External id": 36632,"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": 4183437, "tid": 31318, + "ts": 658972287913.131, "dur": 9.749, + "args": { + "External id": 36633,"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": 4183437, "tid": 31318, + "ts": 658972287916.160, "dur": 6.412, + "args": { + "External id": 36634,"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": 4183437, "tid": 31318, + "ts": 658972287951.264, "dur": 307.700, + "args": { + "External id": 36635,"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": 4183437, "tid": 31318, + "ts": 658972287974.933, "dur": 279.944, + "args": { + "External id": 36636,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972287984.980, "dur": 265.414, + "args": { + "External id": 36637,"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": 4183437, "tid": 31318, + "ts": 658972288294.281, "dur": 3.033, + "args": { + "External id": 36638,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972288352.827, "dur": 6.104, + "args": { + "External id": 36639,"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": 4183437, "tid": 31318, + "ts": 658972288403.711, "dur": 1.362, + "args": { + "External id": 36640,"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": 4183437, "tid": 31318, + "ts": 658972288420.349, "dur": 1.421, + "args": { + "External id": 36641,"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": 4183437, "tid": 31318, + "ts": 658972288433.656, "dur": 1.092, + "args": { + "External id": 36642,"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": 4183437, "tid": 31318, + "ts": 658972288445.413, "dur": 0.899, + "args": { + "External id": 36643,"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": 4183437, "tid": 31318, + "ts": 658972288455.045, "dur": 1.210, + "args": { + "External id": 36644,"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": 4183437, "tid": 31318, + "ts": 658972288466.080, "dur": 0.894, + "args": { + "External id": 36645,"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": 4183437, "tid": 31318, + "ts": 658972288476.972, "dur": 1.024, + "args": { + "External id": 36646,"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": 4183437, "tid": 31318, + "ts": 658972288487.627, "dur": 1.149, + "args": { + "External id": 36647,"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": 4183437, "tid": 31318, + "ts": 658972288581.338, "dur": 2568.370, + "args": { + "External id": 36648,"Record function id": 0, "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 4183437, "tid": 31318, + "ts": 658972288600.991, "dur": 942.356, + "args": { + "External id": 36649,"Record function id": 0, "Ev Idx": 3368 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 4183437, "tid": 31318, + "ts": 658972288617.292, "dur": 332.176, + "args": { + "External id": 36650,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972288731.191, "dur": 4.759, + "args": { + "External id": 36651,"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": 4183437, "tid": 31318, + "ts": 658972288739.358, "dur": 1.292, + "args": { + "External id": 36652,"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": 4183437, "tid": 31318, + "ts": 658972288742.269, "dur": 1.295, + "args": { + "External id": 36653,"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": 4183437, "tid": 31318, + "ts": 658972288745.135, "dur": 1.663, + "args": { + "External id": 36654,"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": 4183437, "tid": 31318, + "ts": 658972288748.278, "dur": 0.817, + "args": { + "External id": 36655,"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": 4183437, "tid": 31318, + "ts": 658972288750.859, "dur": 1.358, + "args": { + "External id": 36656,"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": 4183437, "tid": 31318, + "ts": 658972288753.736, "dur": 1.183, + "args": { + "External id": 36657,"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": 4183437, "tid": 31318, + "ts": 658972288756.361, "dur": 1.104, + "args": { + "External id": 36658,"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": 4183437, "tid": 31318, + "ts": 658972288759.430, "dur": 1.003, + "args": { + "External id": 36659,"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": 4183437, "tid": 31318, + "ts": 658972288761.799, "dur": 1.238, + "args": { + "External id": 36660,"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": 4183437, "tid": 31318, + "ts": 658972288780.798, "dur": 139.604, + "args": { + "External id": 36661,"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": 4183437, "tid": 31318, + "ts": 658972288797.203, "dur": 118.894, + "args": { + "External id": 36662,"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": 4183437, "tid": 31318, + "ts": 658972288809.258, "dur": 14.263, + "args": { + "External id": 36663,"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": 4183437, "tid": 31318, + "ts": 658972288826.378, "dur": 62.114, + "args": { + "External id": 36664,"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": 4183437, "tid": 31318, + "ts": 658972288828.882, "dur": 59.306, + "args": { + "External id": 36665,"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": 4183437, "tid": 31318, + "ts": 658972288833.050, "dur": 6.021, + "args": { + "External id": 36666,"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": 4183437, "tid": 31318, + "ts": 658972288840.695, "dur": 46.884, + "args": { + "External id": 36667,"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": 4183437, "tid": 31318, + "ts": 658972289024.727, "dur": 510.927, + "args": { + "External id": 36668,"Record function id": 0, "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 4183437, "tid": 31318, + "ts": 658972289041.384, "dur": 482.333, + "args": { + "External id": 36669,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972289094.650, "dur": 5.338, + "args": { + "External id": 36670,"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": 4183437, "tid": 31318, + "ts": 658972289114.430, "dur": 22.266, + "args": { + "External id": 36671,"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": 4183437, "tid": 31318, + "ts": 658972289118.391, "dur": 1.378, + "args": { + "External id": 36672,"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": 4183437, "tid": 31318, + "ts": 658972289121.119, "dur": 0.503, + "args": { + "External id": 36673,"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": 4183437, "tid": 31318, + "ts": 658972289123.158, "dur": 0.371, + "args": { + "External id": 36674,"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": 4183437, "tid": 31318, + "ts": 658972289124.832, "dur": 0.598, + "args": { + "External id": 36675,"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": 4183437, "tid": 31318, + "ts": 658972289126.332, "dur": 0.598, + "args": { + "External id": 36676,"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": 4183437, "tid": 31318, + "ts": 658972289127.803, "dur": 0.915, + "args": { + "External id": 36677,"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": 4183437, "tid": 31318, + "ts": 658972289129.694, "dur": 0.630, + "args": { + "External id": 36678,"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": 4183437, "tid": 31318, + "ts": 658972289131.284, "dur": 0.466, + "args": { + "External id": 36679,"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": 4183437, "tid": 31318, + "ts": 658972289132.758, "dur": 0.624, + "args": { + "External id": 36680,"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": 4183437, "tid": 31318, + "ts": 658972289146.992, "dur": 27.467, + "args": { + "External id": 36681,"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": 4183437, "tid": 31318, + "ts": 658972289203.671, "dur": 111.870, + "args": { + "External id": 36682,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972289212.453, "dur": 3.665, + "args": { + "External id": 36683,"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": 4183437, "tid": 31318, + "ts": 658972289220.750, "dur": 9.631, + "args": { + "External id": 36684,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972289224.762, "dur": 5.220, + "args": { + "External id": 36685,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972289227.819, "dur": 0.673, + "args": { + "External id": 36686,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972289236.382, "dur": 22.490, + "args": { + "External id": 36687,"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": 4183437, "tid": 31318, + "ts": 658972289238.081, "dur": 0.887, + "args": { + "External id": 36688,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972289240.288, "dur": 0.897, + "args": { + "External id": 36689,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972289242.174, "dur": 0.619, + "args": { + "External id": 36690,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972289243.702, "dur": 0.653, + "args": { + "External id": 36691,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972289245.161, "dur": 0.603, + "args": { + "External id": 36692,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972289246.781, "dur": 0.567, + "args": { + "External id": 36693,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972289248.293, "dur": 0.410, + "args": { + "External id": 36694,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972289249.482, "dur": 0.423, + "args": { + "External id": 36695,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972289250.888, "dur": 0.584, + "args": { + "External id": 36696,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972289286.040, "dur": 20.763, + "args": { + "External id": 36697,"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": 4183437, "tid": 31318, + "ts": 658972289358.808, "dur": 105.140, + "args": { + "External id": 36698,"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": 4183437, "tid": 31318, + "ts": 658972289379.195, "dur": 81.508, + "args": { + "External id": 36699,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972289388.358, "dur": 68.167, + "args": { + "External id": 36700,"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": 4183437, "tid": 31318, + "ts": 658972289475.751, "dur": 1.534, + "args": { + "External id": 36701,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972289550.557, "dur": 1580.818, + "args": { + "External id": 36702,"Sequence number": 459904, "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": 4183437, "tid": 31318, "ts": 658972289550.557, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972289695.734, "dur": 103.000, + "args": { + "External id": 36703,"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": 4183437, "tid": 31318, + "ts": 658972289836.544, "dur": 38.049, + "args": { + "External id": 36704,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972289891.342, "dur": 40.428, + "args": { + "External id": 36705,"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": 4183437, "tid": 31318, + "ts": 658972289941.562, "dur": 26.640, + "args": { + "External id": 36706,"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": 4183437, "tid": 31318, + "ts": 658972289973.870, "dur": 31.962, + "args": { + "External id": 36707,"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": 4183437, "tid": 31318, + "ts": 658972290011.975, "dur": 20.007, + "args": { + "External id": 36708,"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": 4183437, "tid": 31318, + "ts": 658972290038.399, "dur": 29.679, + "args": { + "External id": 36709,"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": 4183437, "tid": 31318, + "ts": 658972290089.112, "dur": 22.079, + "args": { + "External id": 36710,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972290130.816, "dur": 26.690, + "args": { + "External id": 36711,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972290174.101, "dur": 22.853, + "args": { + "External id": 36712,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972290208.084, "dur": 14.267, + "args": { + "External id": 36713,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972290230.128, "dur": 54.299, + "args": { + "External id": 36714,"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": 4183437, "tid": 31318, + "ts": 658972290289.910, "dur": 37.973, + "args": { + "External id": 36715,"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": 4183437, "tid": 31318, + "ts": 658972290358.409, "dur": 171.213, + "args": { + "External id": 36716,"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": 4183437, "tid": 31318, + "ts": 658972290433.742, "dur": 6.366, + "args": { + "External id": 36717,"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": 4183437, "tid": 31318, + "ts": 658972290441.930, "dur": 3.042, + "args": { + "External id": 36718,"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": 4183437, "tid": 31318, + "ts": 658972290560.434, "dur": 28.090, + "args": { + "External id": 36719,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972290600.039, "dur": 16.091, + "args": { + "External id": 36720,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972290624.192, "dur": 86.953, + "args": { + "External id": 36721,"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": 4183437, "tid": 31318, + "ts": 658972290720.094, "dur": 36.175, + "args": { + "External id": 36722,"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": 4183437, "tid": 31318, + "ts": 658972290763.691, "dur": 27.485, + "args": { + "External id": 36723,"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": 4183437, "tid": 31318, + "ts": 658972290795.746, "dur": 30.933, + "args": { + "External id": 36724,"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": 4183437, "tid": 31318, + "ts": 658972290832.555, "dur": 30.322, + "args": { + "External id": 36725,"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": 4183437, "tid": 31318, + "ts": 658972290868.909, "dur": 27.495, + "args": { + "External id": 36726,"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": 4183437, "tid": 31318, + "ts": 658972290914.474, "dur": 24.297, + "args": { + "External id": 36727,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972290955.282, "dur": 40.184, + "args": { + "External id": 36728,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972291015.259, "dur": 21.432, + "args": { + "External id": 36729,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972291055.344, "dur": 16.362, + "args": { + "External id": 36730,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972291082.614, "dur": 20.035, + "args": { + "External id": 36731,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972291174.540, "dur": 14.230, + "args": { + "External id": 36732,"Record function id": 0, "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972291177.548, "dur": 10.355, + "args": { + "External id": 36733,"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": 4183437, "tid": 31318, + "ts": 658972291181.634, "dur": 5.389, + "args": { + "External id": 36734,"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": 4183437, "tid": 31318, + "ts": 658972291182.899, "dur": 4.035, + "args": { + "External id": 36735,"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": 4183437, "tid": 31318, + "ts": 658972291192.515, "dur": 4.322, + "args": { + "External id": 36736,"Record function id": 0, "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972291193.617, "dur": 2.712, + "args": { + "External id": 36737,"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": 4183437, "tid": 31318, + "ts": 658972291194.243, "dur": 1.525, + "args": { + "External id": 36738,"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": 4183437, "tid": 31318, + "ts": 658972291194.693, "dur": 1.011, + "args": { + "External id": 36739,"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": 4183437, "tid": 31318, + "ts": 658972291200.088, "dur": 3.777, + "args": { + "External id": 36740,"Record function id": 0, "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972291201.268, "dur": 2.110, + "args": { + "External id": 36741,"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": 4183437, "tid": 31318, + "ts": 658972291201.832, "dur": 1.129, + "args": { + "External id": 36742,"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": 4183437, "tid": 31318, + "ts": 658972291202.294, "dur": 0.582, + "args": { + "External id": 36743,"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": 4183437, "tid": 31318, + "ts": 658972291207.034, "dur": 3.520, + "args": { + "External id": 36744,"Record function id": 0, "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972291207.942, "dur": 2.179, + "args": { + "External id": 36745,"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": 4183437, "tid": 31318, + "ts": 658972291208.549, "dur": 1.129, + "args": { + "External id": 36746,"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": 4183437, "tid": 31318, + "ts": 658972291208.903, "dur": 0.711, + "args": { + "External id": 36747,"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": 4183437, "tid": 31318, + "ts": 658972291213.572, "dur": 6.889, + "args": { + "External id": 36748,"Record function id": 0, "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972291214.535, "dur": 5.468, + "args": { + "External id": 36749,"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": 4183437, "tid": 31318, + "ts": 658972291215.152, "dur": 4.419, + "args": { + "External id": 36750,"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": 4183437, "tid": 31318, + "ts": 658972291215.505, "dur": 3.998, + "args": { + "External id": 36751,"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": 4183437, "tid": 31318, + "ts": 658972291223.539, "dur": 3.820, + "args": { + "External id": 36752,"Record function id": 0, "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972291224.446, "dur": 2.499, + "args": { + "External id": 36753,"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": 4183437, "tid": 31318, + "ts": 658972291225.068, "dur": 1.446, + "args": { + "External id": 36754,"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": 4183437, "tid": 31318, + "ts": 658972291225.561, "dur": 0.885, + "args": { + "External id": 36755,"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": 4183437, "tid": 31318, + "ts": 658972291230.467, "dur": 3.527, + "args": { + "External id": 36756,"Record function id": 0, "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972291231.470, "dur": 2.116, + "args": { + "External id": 36757,"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": 4183437, "tid": 31318, + "ts": 658972291231.967, "dur": 1.173, + "args": { + "External id": 36758,"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": 4183437, "tid": 31318, + "ts": 658972291232.449, "dur": 0.624, + "args": { + "External id": 36759,"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": 4183437, "tid": 31318, + "ts": 658972291236.994, "dur": 3.803, + "args": { + "External id": 36760,"Record function id": 0, "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972291237.977, "dur": 2.399, + "args": { + "External id": 36761,"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": 4183437, "tid": 31318, + "ts": 658972291238.485, "dur": 1.472, + "args": { + "External id": 36762,"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": 4183437, "tid": 31318, + "ts": 658972291239.016, "dur": 0.878, + "args": { + "External id": 36763,"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": 4183437, "tid": 31318, + "ts": 658972291244.079, "dur": 3.793, + "args": { + "External id": 36764,"Record function id": 0, "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972291245.159, "dur": 2.287, + "args": { + "External id": 36765,"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": 4183437, "tid": 31318, + "ts": 658972291245.841, "dur": 1.161, + "args": { + "External id": 36766,"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": 4183437, "tid": 31318, + "ts": 658972291246.162, "dur": 0.774, + "args": { + "External id": 36767,"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": 4183437, "tid": 31318, + "ts": 658972291251.487, "dur": 14911.446, + "args": { + "External id": 36768,"Record function id": 0, "Sequence number": 459903, "Fwd thread id": 1, "Ev Idx": 3487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972291252.691, "dur": 14901.599, + "args": { + "External id": 36769,"Sequence number": 459903, "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": 4183437, "tid": 31318, "ts": 658972291252.691, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 4183437, "tid": 31318, + "ts": 658972291300.590, "dur": 41.923, + "args": { + "External id": 36770,"Record function id": 0, "Ev Idx": 3489 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 4183437, "tid": 31318, + "ts": 658972291349.840, "dur": 64.653, + "args": { + "External id": 36771,"Record function id": 0, "Ev Idx": 3490 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 4183437, "tid": 31318, + "ts": 658972291420.102, "dur": 14726.277, + "args": { + "External id": 36772,"Record function id": 0, "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972291509.087, "dur": 7.392, + "args": { + "External id": 36773,"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": 4183437, "tid": 31318, + "ts": 658972291526.107, "dur": 5.064, + "args": { + "External id": 36774,"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": 4183437, "tid": 31318, + "ts": 658972291545.068, "dur": 13925.350, + "args": { + "External id": 36775,"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": 4183437, "tid": 31318, + "ts": 658972291558.063, "dur": 13904.253, + "args": { + "External id": 36776,"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": 4183437, "tid": 31318, + "ts": 658972291579.749, "dur": 13.675, + "args": { + "External id": 36777,"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": 4183437, "tid": 31318, + "ts": 658972291598.283, "dur": 13827.448, + "args": { + "External id": 36778,"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": 4183437, "tid": 31318, + "ts": 658972291600.996, "dur": 13824.178, + "args": { + "External id": 36779,"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": 4183437, "tid": 31318, + "ts": 658972291604.860, "dur": 4.751, + "args": { + "External id": 36780,"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": 4183437, "tid": 31318, + "ts": 658972291611.175, "dur": 13810.281, + "args": { + "External id": 36781,"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": 4183437, "tid": 31318, + "ts": 658972305556.396, "dur": 9.585, + "args": { + "External id": 36782,"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": 4183437, "tid": 31318, + "ts": 658972305559.363, "dur": 6.248, + "args": { + "External id": 36783,"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": 4183437, "tid": 31318, + "ts": 658972305592.877, "dur": 286.916, + "args": { + "External id": 36784,"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": 4183437, "tid": 31318, + "ts": 658972305616.329, "dur": 258.794, + "args": { + "External id": 36785,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972305627.487, "dur": 242.530, + "args": { + "External id": 36786,"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": 4183437, "tid": 31318, + "ts": 658972305896.723, "dur": 2.209, + "args": { + "External id": 36787,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972305951.159, "dur": 6.431, + "args": { + "External id": 36788,"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": 4183437, "tid": 31318, + "ts": 658972306001.472, "dur": 1.403, + "args": { + "External id": 36789,"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": 4183437, "tid": 31318, + "ts": 658972306018.516, "dur": 1.879, + "args": { + "External id": 36790,"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": 4183437, "tid": 31318, + "ts": 658972306031.219, "dur": 1.321, + "args": { + "External id": 36791,"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": 4183437, "tid": 31318, + "ts": 658972306043.150, "dur": 1.049, + "args": { + "External id": 36792,"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": 4183437, "tid": 31318, + "ts": 658972306053.533, "dur": 1.583, + "args": { + "External id": 36793,"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": 4183437, "tid": 31318, + "ts": 658972306065.396, "dur": 1.333, + "args": { + "External id": 36794,"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": 4183437, "tid": 31318, + "ts": 658972306076.481, "dur": 1.202, + "args": { + "External id": 36795,"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": 4183437, "tid": 31318, + "ts": 658972306086.569, "dur": 1.413, + "args": { + "External id": 36796,"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": 4183437, "tid": 31318, + "ts": 658972306176.684, "dur": 2667.514, + "args": { + "External id": 36797,"Record function id": 0, "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 4183437, "tid": 31318, + "ts": 658972306195.773, "dur": 966.925, + "args": { + "External id": 36798,"Record function id": 0, "Ev Idx": 3517 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 4183437, "tid": 31318, + "ts": 658972306210.805, "dur": 314.421, + "args": { + "External id": 36799,"Record function id": 0, "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972306308.054, "dur": 4.902, + "args": { + "External id": 36800,"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": 4183437, "tid": 31318, + "ts": 658972306316.050, "dur": 1.641, + "args": { + "External id": 36801,"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": 4183437, "tid": 31318, + "ts": 658972306319.533, "dur": 1.037, + "args": { + "External id": 36802,"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": 4183437, "tid": 31318, + "ts": 658972306322.158, "dur": 1.054, + "args": { + "External id": 36803,"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": 4183437, "tid": 31318, + "ts": 658972306324.799, "dur": 1.061, + "args": { + "External id": 36804,"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": 4183437, "tid": 31318, + "ts": 658972306327.357, "dur": 0.919, + "args": { + "External id": 36805,"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": 4183437, "tid": 31318, + "ts": 658972306330.358, "dur": 0.958, + "args": { + "External id": 36806,"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": 4183437, "tid": 31318, + "ts": 658972306332.995, "dur": 1.305, + "args": { + "External id": 36807,"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": 4183437, "tid": 31318, + "ts": 658972306335.663, "dur": 1.460, + "args": { + "External id": 36808,"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": 4183437, "tid": 31318, + "ts": 658972306338.513, "dur": 1.470, + "args": { + "External id": 36809,"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": 4183437, "tid": 31318, + "ts": 658972306358.170, "dur": 137.912, + "args": { + "External id": 36810,"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": 4183437, "tid": 31318, + "ts": 658972306374.965, "dur": 116.864, + "args": { + "External id": 36811,"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": 4183437, "tid": 31318, + "ts": 658972306386.875, "dur": 13.131, + "args": { + "External id": 36812,"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": 4183437, "tid": 31318, + "ts": 658972306402.516, "dur": 61.974, + "args": { + "External id": 36813,"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": 4183437, "tid": 31318, + "ts": 658972306405.324, "dur": 58.874, + "args": { + "External id": 36814,"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": 4183437, "tid": 31318, + "ts": 658972306409.431, "dur": 5.776, + "args": { + "External id": 36815,"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": 4183437, "tid": 31318, + "ts": 658972306416.805, "dur": 46.840, + "args": { + "External id": 36816,"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": 4183437, "tid": 31318, + "ts": 658972306600.169, "dur": 553.394, + "args": { + "External id": 36817,"Record function id": 0, "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 4183437, "tid": 31318, + "ts": 658972306617.517, "dur": 523.241, + "args": { + "External id": 36818,"Record function id": 0, "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972306710.864, "dur": 7.529, + "args": { + "External id": 36819,"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": 4183437, "tid": 31318, + "ts": 658972306734.628, "dur": 24.597, + "args": { + "External id": 36820,"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": 4183437, "tid": 31318, + "ts": 658972306739.073, "dur": 1.819, + "args": { + "External id": 36821,"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": 4183437, "tid": 31318, + "ts": 658972306742.293, "dur": 1.086, + "args": { + "External id": 36822,"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": 4183437, "tid": 31318, + "ts": 658972306744.810, "dur": 0.614, + "args": { + "External id": 36823,"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": 4183437, "tid": 31318, + "ts": 658972306746.741, "dur": 0.408, + "args": { + "External id": 36824,"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": 4183437, "tid": 31318, + "ts": 658972306747.979, "dur": 0.686, + "args": { + "External id": 36825,"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": 4183437, "tid": 31318, + "ts": 658972306749.940, "dur": 0.614, + "args": { + "External id": 36826,"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": 4183437, "tid": 31318, + "ts": 658972306751.579, "dur": 0.988, + "args": { + "External id": 36827,"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": 4183437, "tid": 31318, + "ts": 658972306753.533, "dur": 0.516, + "args": { + "External id": 36828,"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": 4183437, "tid": 31318, + "ts": 658972306754.966, "dur": 0.590, + "args": { + "External id": 36829,"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": 4183437, "tid": 31318, + "ts": 658972306768.590, "dur": 32.406, + "args": { + "External id": 36830,"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": 4183437, "tid": 31318, + "ts": 658972306832.977, "dur": 91.555, + "args": { + "External id": 36831,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972306842.469, "dur": 3.791, + "args": { + "External id": 36832,"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": 4183437, "tid": 31318, + "ts": 658972306851.643, "dur": 9.691, + "args": { + "External id": 36833,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972306855.601, "dur": 5.340, + "args": { + "External id": 36834,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972306858.818, "dur": 0.874, + "args": { + "External id": 36835,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972306869.772, "dur": 21.037, + "args": { + "External id": 36836,"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": 4183437, "tid": 31318, + "ts": 658972306871.374, "dur": 0.905, + "args": { + "External id": 36837,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972306873.883, "dur": 0.300, + "args": { + "External id": 36838,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972306875.130, "dur": 0.757, + "args": { + "External id": 36839,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972306877.182, "dur": 0.504, + "args": { + "External id": 36840,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972306878.641, "dur": 0.653, + "args": { + "External id": 36841,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972306879.881, "dur": 1.036, + "args": { + "External id": 36842,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972306881.918, "dur": 0.608, + "args": { + "External id": 36843,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972306883.294, "dur": 0.434, + "args": { + "External id": 36844,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972306884.331, "dur": 0.651, + "args": { + "External id": 36845,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972306899.542, "dur": 17.041, + "args": { + "External id": 36846,"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": 4183437, "tid": 31318, + "ts": 658972306970.621, "dur": 107.494, + "args": { + "External id": 36847,"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": 4183437, "tid": 31318, + "ts": 658972306992.233, "dur": 82.265, + "args": { + "External id": 36848,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972307001.539, "dur": 68.988, + "args": { + "External id": 36849,"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": 4183437, "tid": 31318, + "ts": 658972307090.145, "dur": 1.826, + "args": { + "External id": 36850,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972307169.882, "dur": 1654.166, + "args": { + "External id": 36851,"Sequence number": 459902, "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": 4183437, "tid": 31318, "ts": 658972307169.882, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972307298.415, "dur": 101.532, + "args": { + "External id": 36852,"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": 4183437, "tid": 31318, + "ts": 658972307435.436, "dur": 40.001, + "args": { + "External id": 36853,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972307492.373, "dur": 40.068, + "args": { + "External id": 36854,"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": 4183437, "tid": 31318, + "ts": 658972307541.767, "dur": 25.486, + "args": { + "External id": 36855,"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": 4183437, "tid": 31318, + "ts": 658972307573.863, "dur": 32.428, + "args": { + "External id": 36856,"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": 4183437, "tid": 31318, + "ts": 658972307612.447, "dur": 21.550, + "args": { + "External id": 36857,"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": 4183437, "tid": 31318, + "ts": 658972307642.051, "dur": 69.922, + "args": { + "External id": 36858,"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": 4183437, "tid": 31318, + "ts": 658972307739.734, "dur": 25.972, + "args": { + "External id": 36859,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972307783.421, "dur": 30.855, + "args": { + "External id": 36860,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972307831.542, "dur": 18.279, + "args": { + "External id": 36861,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972307864.027, "dur": 13.777, + "args": { + "External id": 36862,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972307886.800, "dur": 42.032, + "args": { + "External id": 36863,"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": 4183437, "tid": 31318, + "ts": 658972307932.479, "dur": 30.307, + "args": { + "External id": 36864,"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": 4183437, "tid": 31318, + "ts": 658972308010.916, "dur": 168.454, + "args": { + "External id": 36865,"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": 4183437, "tid": 31318, + "ts": 658972308089.560, "dur": 5.729, + "args": { + "External id": 36866,"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": 4183437, "tid": 31318, + "ts": 658972308097.208, "dur": 2.733, + "args": { + "External id": 36867,"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": 4183437, "tid": 31318, + "ts": 658972308213.278, "dur": 30.059, + "args": { + "External id": 36868,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972308254.274, "dur": 33.564, + "args": { + "External id": 36869,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972308301.424, "dur": 50.013, + "args": { + "External id": 36870,"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": 4183437, "tid": 31318, + "ts": 658972308357.607, "dur": 34.468, + "args": { + "External id": 36871,"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": 4183437, "tid": 31318, + "ts": 658972308398.869, "dur": 28.837, + "args": { + "External id": 36872,"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": 4183437, "tid": 31318, + "ts": 658972308432.468, "dur": 32.252, + "args": { + "External id": 36873,"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": 4183437, "tid": 31318, + "ts": 658972308470.420, "dur": 28.320, + "args": { + "External id": 36874,"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": 4183437, "tid": 31318, + "ts": 658972308505.576, "dur": 30.592, + "args": { + "External id": 36875,"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": 4183437, "tid": 31318, + "ts": 658972308552.602, "dur": 27.301, + "args": { + "External id": 36876,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972308602.090, "dur": 44.155, + "args": { + "External id": 36877,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972308708.323, "dur": 20.767, + "args": { + "External id": 36878,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972308745.771, "dur": 17.583, + "args": { + "External id": 36879,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972308775.036, "dur": 15.354, + "args": { + "External id": 36880,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972308866.964, "dur": 17.629, + "args": { + "External id": 36881,"Record function id": 0, "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972308870.022, "dur": 13.602, + "args": { + "External id": 36882,"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": 4183437, "tid": 31318, + "ts": 658972308873.903, "dur": 8.794, + "args": { + "External id": 36883,"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": 4183437, "tid": 31318, + "ts": 658972308875.113, "dur": 7.494, + "args": { + "External id": 36884,"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": 4183437, "tid": 31318, + "ts": 658972308888.384, "dur": 4.352, + "args": { + "External id": 36885,"Record function id": 0, "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972308889.686, "dur": 2.577, + "args": { + "External id": 36886,"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": 4183437, "tid": 31318, + "ts": 658972308890.369, "dur": 1.384, + "args": { + "External id": 36887,"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": 4183437, "tid": 31318, + "ts": 658972308890.871, "dur": 0.810, + "args": { + "External id": 36888,"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": 4183437, "tid": 31318, + "ts": 658972308895.960, "dur": 4.433, + "args": { + "External id": 36889,"Record function id": 0, "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972308897.163, "dur": 2.767, + "args": { + "External id": 36890,"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": 4183437, "tid": 31318, + "ts": 658972308897.704, "dur": 1.756, + "args": { + "External id": 36891,"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": 4183437, "tid": 31318, + "ts": 658972308898.113, "dur": 1.265, + "args": { + "External id": 36892,"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": 4183437, "tid": 31318, + "ts": 658972308903.568, "dur": 3.886, + "args": { + "External id": 36893,"Record function id": 0, "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972308904.884, "dur": 2.142, + "args": { + "External id": 36894,"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": 4183437, "tid": 31318, + "ts": 658972308905.430, "dur": 1.169, + "args": { + "External id": 36895,"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": 4183437, "tid": 31318, + "ts": 658972308905.738, "dur": 0.788, + "args": { + "External id": 36896,"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": 4183437, "tid": 31318, + "ts": 658972308910.599, "dur": 4.524, + "args": { + "External id": 36897,"Record function id": 0, "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972308911.877, "dur": 2.809, + "args": { + "External id": 36898,"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": 4183437, "tid": 31318, + "ts": 658972308912.420, "dur": 1.831, + "args": { + "External id": 36899,"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": 4183437, "tid": 31318, + "ts": 658972308913.048, "dur": 1.139, + "args": { + "External id": 36900,"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": 4183437, "tid": 31318, + "ts": 658972308918.246, "dur": 3.511, + "args": { + "External id": 36901,"Record function id": 0, "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972308919.119, "dur": 2.202, + "args": { + "External id": 36902,"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": 4183437, "tid": 31318, + "ts": 658972308919.632, "dur": 1.264, + "args": { + "External id": 36903,"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": 4183437, "tid": 31318, + "ts": 658972308920.185, "dur": 0.648, + "args": { + "External id": 36904,"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": 4183437, "tid": 31318, + "ts": 658972308924.907, "dur": 3.692, + "args": { + "External id": 36905,"Record function id": 0, "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972308926.066, "dur": 2.120, + "args": { + "External id": 36906,"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": 4183437, "tid": 31318, + "ts": 658972308926.570, "dur": 1.174, + "args": { + "External id": 36907,"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": 4183437, "tid": 31318, + "ts": 658972308926.919, "dur": 0.760, + "args": { + "External id": 36908,"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": 4183437, "tid": 31318, + "ts": 658972308931.639, "dur": 7.258, + "args": { + "External id": 36909,"Record function id": 0, "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972308932.689, "dur": 2.163, + "args": { + "External id": 36910,"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": 4183437, "tid": 31318, + "ts": 658972308933.176, "dur": 1.221, + "args": { + "External id": 36911,"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": 4183437, "tid": 31318, + "ts": 658972308933.711, "dur": 0.624, + "args": { + "External id": 36912,"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": 4183437, "tid": 31318, + "ts": 658972308941.826, "dur": 4.024, + "args": { + "External id": 36913,"Record function id": 0, "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972308942.664, "dur": 2.788, + "args": { + "External id": 36914,"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": 4183437, "tid": 31318, + "ts": 658972308943.141, "dur": 1.785, + "args": { + "External id": 36915,"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": 4183437, "tid": 31318, + "ts": 658972308943.543, "dur": 1.320, + "args": { + "External id": 36916,"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": 4183437, "tid": 31318, + "ts": 658972308949.605, "dur": 14697.496, + "args": { + "External id": 36917,"Record function id": 0, "Sequence number": 459901, "Fwd thread id": 1, "Ev Idx": 3636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972308950.710, "dur": 14688.965, + "args": { + "External id": 36918,"Sequence number": 459901, "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": 4183437, "tid": 31318, "ts": 658972308950.710, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 4183437, "tid": 31318, + "ts": 658972308979.034, "dur": 36.885, + "args": { + "External id": 36919,"Record function id": 0, "Ev Idx": 3638 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 4183437, "tid": 31318, + "ts": 658972309023.077, "dur": 60.233, + "args": { + "External id": 36920,"Record function id": 0, "Ev Idx": 3639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 4183437, "tid": 31318, + "ts": 658972309088.610, "dur": 14543.659, + "args": { + "External id": 36921,"Record function id": 0, "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972309172.028, "dur": 6.467, + "args": { + "External id": 36922,"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": 4183437, "tid": 31318, + "ts": 658972309187.139, "dur": 4.609, + "args": { + "External id": 36923,"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": 4183437, "tid": 31318, + "ts": 658972309204.661, "dur": 13768.562, + "args": { + "External id": 36924,"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": 4183437, "tid": 31318, + "ts": 658972309218.052, "dur": 13747.143, + "args": { + "External id": 36925,"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": 4183437, "tid": 31318, + "ts": 658972309247.889, "dur": 14.138, + "args": { + "External id": 36926,"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": 4183437, "tid": 31318, + "ts": 658972309284.947, "dur": 13646.301, + "args": { + "External id": 36927,"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": 4183437, "tid": 31318, + "ts": 658972309288.187, "dur": 13642.381, + "args": { + "External id": 36928,"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": 4183437, "tid": 31318, + "ts": 658972309291.683, "dur": 5.984, + "args": { + "External id": 36929,"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": 4183437, "tid": 31318, + "ts": 658972309299.526, "dur": 13627.318, + "args": { + "External id": 36930,"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": 4183437, "tid": 31318, + "ts": 658972323058.570, "dur": 9.227, + "args": { + "External id": 36931,"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": 4183437, "tid": 31318, + "ts": 658972323061.427, "dur": 6.023, + "args": { + "External id": 36932,"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": 4183437, "tid": 31318, + "ts": 658972323094.509, "dur": 281.072, + "args": { + "External id": 36933,"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": 4183437, "tid": 31318, + "ts": 658972323117.648, "dur": 253.065, + "args": { + "External id": 36934,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972323128.572, "dur": 236.662, + "args": { + "External id": 36935,"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": 4183437, "tid": 31318, + "ts": 658972323392.460, "dur": 2.032, + "args": { + "External id": 36936,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972323445.507, "dur": 6.011, + "args": { + "External id": 36937,"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": 4183437, "tid": 31318, + "ts": 658972323494.340, "dur": 1.280, + "args": { + "External id": 36938,"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": 4183437, "tid": 31318, + "ts": 658972323510.882, "dur": 1.218, + "args": { + "External id": 36939,"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": 4183437, "tid": 31318, + "ts": 658972323523.223, "dur": 0.928, + "args": { + "External id": 36940,"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": 4183437, "tid": 31318, + "ts": 658972323534.469, "dur": 1.207, + "args": { + "External id": 36941,"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": 4183437, "tid": 31318, + "ts": 658972323545.429, "dur": 1.069, + "args": { + "External id": 36942,"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": 4183437, "tid": 31318, + "ts": 658972323555.929, "dur": 1.036, + "args": { + "External id": 36943,"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": 4183437, "tid": 31318, + "ts": 658972323566.670, "dur": 1.098, + "args": { + "External id": 36944,"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": 4183437, "tid": 31318, + "ts": 658972323576.688, "dur": 0.768, + "args": { + "External id": 36945,"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": 4183437, "tid": 31318, + "ts": 658972323711.669, "dur": 2514.892, + "args": { + "External id": 36946,"Record function id": 0, "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 4183437, "tid": 31318, + "ts": 658972323734.838, "dur": 901.053, + "args": { + "External id": 36947,"Record function id": 0, "Ev Idx": 3666 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 4183437, "tid": 31318, + "ts": 658972323750.726, "dur": 294.808, + "args": { + "External id": 36948,"Record function id": 0, "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972323831.431, "dur": 5.047, + "args": { + "External id": 36949,"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": 4183437, "tid": 31318, + "ts": 658972323839.945, "dur": 1.351, + "args": { + "External id": 36950,"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": 4183437, "tid": 31318, + "ts": 658972323842.932, "dur": 1.111, + "args": { + "External id": 36951,"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": 4183437, "tid": 31318, + "ts": 658972323845.498, "dur": 1.128, + "args": { + "External id": 36952,"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": 4183437, "tid": 31318, + "ts": 658972323848.192, "dur": 1.746, + "args": { + "External id": 36953,"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": 4183437, "tid": 31318, + "ts": 658972323851.499, "dur": 1.295, + "args": { + "External id": 36954,"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": 4183437, "tid": 31318, + "ts": 658972323854.558, "dur": 1.261, + "args": { + "External id": 36955,"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": 4183437, "tid": 31318, + "ts": 658972323857.284, "dur": 1.826, + "args": { + "External id": 36956,"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": 4183437, "tid": 31318, + "ts": 658972323860.881, "dur": 1.094, + "args": { + "External id": 36957,"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": 4183437, "tid": 31318, + "ts": 658972323863.277, "dur": 0.962, + "args": { + "External id": 36958,"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": 4183437, "tid": 31318, + "ts": 658972323881.495, "dur": 137.504, + "args": { + "External id": 36959,"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": 4183437, "tid": 31318, + "ts": 658972323898.207, "dur": 116.632, + "args": { + "External id": 36960,"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": 4183437, "tid": 31318, + "ts": 658972323910.972, "dur": 13.862, + "args": { + "External id": 36961,"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": 4183437, "tid": 31318, + "ts": 658972323927.546, "dur": 61.169, + "args": { + "External id": 36962,"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": 4183437, "tid": 31318, + "ts": 658972323930.243, "dur": 58.098, + "args": { + "External id": 36963,"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": 4183437, "tid": 31318, + "ts": 658972323933.961, "dur": 5.598, + "args": { + "External id": 36964,"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": 4183437, "tid": 31318, + "ts": 658972323941.147, "dur": 46.636, + "args": { + "External id": 36965,"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": 4183437, "tid": 31318, + "ts": 658972324116.961, "dur": 511.244, + "args": { + "External id": 36966,"Record function id": 0, "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 4183437, "tid": 31318, + "ts": 658972324133.692, "dur": 483.194, + "args": { + "External id": 36967,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972324186.773, "dur": 4.576, + "args": { + "External id": 36968,"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": 4183437, "tid": 31318, + "ts": 658972324205.830, "dur": 22.593, + "args": { + "External id": 36969,"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": 4183437, "tid": 31318, + "ts": 658972324210.325, "dur": 1.593, + "args": { + "External id": 36970,"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": 4183437, "tid": 31318, + "ts": 658972324213.316, "dur": 0.424, + "args": { + "External id": 36971,"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": 4183437, "tid": 31318, + "ts": 658972324214.918, "dur": 0.296, + "args": { + "External id": 36972,"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": 4183437, "tid": 31318, + "ts": 658972324216.903, "dur": 0.320, + "args": { + "External id": 36973,"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": 4183437, "tid": 31318, + "ts": 658972324218.138, "dur": 0.816, + "args": { + "External id": 36974,"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": 4183437, "tid": 31318, + "ts": 658972324220.213, "dur": 0.363, + "args": { + "External id": 36975,"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": 4183437, "tid": 31318, + "ts": 658972324221.736, "dur": 0.620, + "args": { + "External id": 36976,"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": 4183437, "tid": 31318, + "ts": 658972324223.376, "dur": 0.640, + "args": { + "External id": 36977,"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": 4183437, "tid": 31318, + "ts": 658972324225.016, "dur": 0.633, + "args": { + "External id": 36978,"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": 4183437, "tid": 31318, + "ts": 658972324238.463, "dur": 43.546, + "args": { + "External id": 36979,"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": 4183437, "tid": 31318, + "ts": 658972324314.516, "dur": 92.533, + "args": { + "External id": 36980,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972324324.362, "dur": 4.729, + "args": { + "External id": 36981,"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": 4183437, "tid": 31318, + "ts": 658972324334.245, "dur": 10.024, + "args": { + "External id": 36982,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972324338.125, "dur": 5.708, + "args": { + "External id": 36983,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972324341.403, "dur": 0.699, + "args": { + "External id": 36984,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972324350.760, "dur": 20.286, + "args": { + "External id": 36985,"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": 4183437, "tid": 31318, + "ts": 658972324352.545, "dur": 0.975, + "args": { + "External id": 36986,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972324354.515, "dur": 0.207, + "args": { + "External id": 36987,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972324355.567, "dur": 0.696, + "args": { + "External id": 36988,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972324357.182, "dur": 0.192, + "args": { + "External id": 36989,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972324358.596, "dur": 0.357, + "args": { + "External id": 36990,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972324359.687, "dur": 0.668, + "args": { + "External id": 36991,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972324361.495, "dur": 0.322, + "args": { + "External id": 36992,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972324362.865, "dur": 0.351, + "args": { + "External id": 36993,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972324364.145, "dur": 0.637, + "args": { + "External id": 36994,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972324380.350, "dur": 19.395, + "args": { + "External id": 36995,"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": 4183437, "tid": 31318, + "ts": 658972324451.755, "dur": 105.579, + "args": { + "External id": 36996,"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": 4183437, "tid": 31318, + "ts": 658972324471.844, "dur": 82.434, + "args": { + "External id": 36997,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972324480.854, "dur": 69.530, + "args": { + "External id": 36998,"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": 4183437, "tid": 31318, + "ts": 658972324568.677, "dur": 2.077, + "args": { + "External id": 36999,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972324642.787, "dur": 1565.224, + "args": { + "External id": 37000,"Sequence number": 459900, "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": 4183437, "tid": 31318, "ts": 658972324642.787, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972324790.798, "dur": 102.422, + "args": { + "External id": 37001,"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": 4183437, "tid": 31318, + "ts": 658972324930.870, "dur": 37.550, + "args": { + "External id": 37002,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972324985.405, "dur": 40.025, + "args": { + "External id": 37003,"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": 4183437, "tid": 31318, + "ts": 658972325034.948, "dur": 27.062, + "args": { + "External id": 37004,"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": 4183437, "tid": 31318, + "ts": 658972325067.804, "dur": 32.736, + "args": { + "External id": 37005,"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": 4183437, "tid": 31318, + "ts": 658972325106.672, "dur": 21.944, + "args": { + "External id": 37006,"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": 4183437, "tid": 31318, + "ts": 658972325134.823, "dur": 28.716, + "args": { + "External id": 37007,"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": 4183437, "tid": 31318, + "ts": 658972325184.772, "dur": 24.895, + "args": { + "External id": 37008,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972325226.829, "dur": 27.618, + "args": { + "External id": 37009,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972325289.241, "dur": 22.282, + "args": { + "External id": 37010,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972325325.316, "dur": 15.882, + "args": { + "External id": 37011,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972325350.496, "dur": 40.615, + "args": { + "External id": 37012,"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": 4183437, "tid": 31318, + "ts": 658972325394.391, "dur": 30.517, + "args": { + "External id": 37013,"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": 4183437, "tid": 31318, + "ts": 658972325452.984, "dur": 166.863, + "args": { + "External id": 37014,"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": 4183437, "tid": 31318, + "ts": 658972325529.499, "dur": 6.047, + "args": { + "External id": 37015,"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": 4183437, "tid": 31318, + "ts": 658972325537.637, "dur": 2.489, + "args": { + "External id": 37016,"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": 4183437, "tid": 31318, + "ts": 658972325687.773, "dur": 28.750, + "args": { + "External id": 37017,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972325731.602, "dur": 14.794, + "args": { + "External id": 37018,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972325756.037, "dur": 48.460, + "args": { + "External id": 37019,"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": 4183437, "tid": 31318, + "ts": 658972325810.871, "dur": 31.248, + "args": { + "External id": 37020,"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": 4183437, "tid": 31318, + "ts": 658972325848.497, "dur": 27.955, + "args": { + "External id": 37021,"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": 4183437, "tid": 31318, + "ts": 658972325881.256, "dur": 27.895, + "args": { + "External id": 37022,"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": 4183437, "tid": 31318, + "ts": 658972325914.728, "dur": 29.998, + "args": { + "External id": 37023,"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": 4183437, "tid": 31318, + "ts": 658972325951.006, "dur": 31.875, + "args": { + "External id": 37024,"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": 4183437, "tid": 31318, + "ts": 658972325998.734, "dur": 22.685, + "args": { + "External id": 37025,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972326037.468, "dur": 25.892, + "args": { + "External id": 37026,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972326075.708, "dur": 16.651, + "args": { + "External id": 37027,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972326128.974, "dur": 19.788, + "args": { + "External id": 37028,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972326160.529, "dur": 18.556, + "args": { + "External id": 37029,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972326251.076, "dur": 32.074, + "args": { + "External id": 37030,"Record function id": 0, "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972326254.419, "dur": 26.991, + "args": { + "External id": 37031,"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": 4183437, "tid": 31318, + "ts": 658972326258.874, "dur": 20.956, + "args": { + "External id": 37032,"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": 4183437, "tid": 31318, + "ts": 658972326260.236, "dur": 19.094, + "args": { + "External id": 37033,"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": 4183437, "tid": 31318, + "ts": 658972326292.594, "dur": 6.029, + "args": { + "External id": 37034,"Record function id": 0, "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972326294.385, "dur": 3.769, + "args": { + "External id": 37035,"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": 4183437, "tid": 31318, + "ts": 658972326295.642, "dur": 2.010, + "args": { + "External id": 37036,"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": 4183437, "tid": 31318, + "ts": 658972326296.091, "dur": 1.490, + "args": { + "External id": 37037,"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": 4183437, "tid": 31318, + "ts": 658972326301.879, "dur": 3.831, + "args": { + "External id": 37038,"Record function id": 0, "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972326302.849, "dur": 2.393, + "args": { + "External id": 37039,"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": 4183437, "tid": 31318, + "ts": 658972326303.421, "dur": 1.379, + "args": { + "External id": 37040,"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": 4183437, "tid": 31318, + "ts": 658972326304.019, "dur": 0.712, + "args": { + "External id": 37041,"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": 4183437, "tid": 31318, + "ts": 658972326308.961, "dur": 3.424, + "args": { + "External id": 37042,"Record function id": 0, "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972326310.105, "dur": 1.851, + "args": { + "External id": 37043,"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": 4183437, "tid": 31318, + "ts": 658972326310.741, "dur": 0.799, + "args": { + "External id": 37044,"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": 4183437, "tid": 31318, + "ts": 658972326310.996, "dur": 0.482, + "args": { + "External id": 37045,"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": 4183437, "tid": 31318, + "ts": 658972326315.529, "dur": 4.020, + "args": { + "External id": 37046,"Record function id": 0, "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972326316.513, "dur": 2.574, + "args": { + "External id": 37047,"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": 4183437, "tid": 31318, + "ts": 658972326316.988, "dur": 1.677, + "args": { + "External id": 37048,"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": 4183437, "tid": 31318, + "ts": 658972326317.594, "dur": 1.008, + "args": { + "External id": 37049,"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": 4183437, "tid": 31318, + "ts": 658972326322.594, "dur": 3.669, + "args": { + "External id": 37050,"Record function id": 0, "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972326323.601, "dur": 2.233, + "args": { + "External id": 37051,"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": 4183437, "tid": 31318, + "ts": 658972326324.068, "dur": 1.351, + "args": { + "External id": 37052,"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": 4183437, "tid": 31318, + "ts": 658972326324.642, "dur": 0.713, + "args": { + "External id": 37053,"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": 4183437, "tid": 31318, + "ts": 658972326329.407, "dur": 3.520, + "args": { + "External id": 37054,"Record function id": 0, "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972326330.320, "dur": 2.147, + "args": { + "External id": 37055,"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": 4183437, "tid": 31318, + "ts": 658972326330.815, "dur": 1.218, + "args": { + "External id": 37056,"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": 4183437, "tid": 31318, + "ts": 658972326331.116, "dur": 0.851, + "args": { + "External id": 37057,"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": 4183437, "tid": 31318, + "ts": 658972326335.949, "dur": 3.776, + "args": { + "External id": 37058,"Record function id": 0, "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972326336.901, "dur": 2.405, + "args": { + "External id": 37059,"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": 4183437, "tid": 31318, + "ts": 658972326337.629, "dur": 1.253, + "args": { + "External id": 37060,"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": 4183437, "tid": 31318, + "ts": 658972326338.192, "dur": 0.622, + "args": { + "External id": 37061,"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": 4183437, "tid": 31318, + "ts": 658972326342.819, "dur": 7.542, + "args": { + "External id": 37062,"Record function id": 0, "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972326343.967, "dur": 5.975, + "args": { + "External id": 37063,"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": 4183437, "tid": 31318, + "ts": 658972326344.658, "dur": 4.860, + "args": { + "External id": 37064,"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": 4183437, "tid": 31318, + "ts": 658972326348.476, "dur": 0.979, + "args": { + "External id": 37065,"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": 4183437, "tid": 31318, + "ts": 658972326354.077, "dur": 15205.348, + "args": { + "External id": 37066,"Record function id": 0, "Sequence number": 459899, "Fwd thread id": 1, "Ev Idx": 3785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972326355.327, "dur": 15195.814, + "args": { + "External id": 37067,"Sequence number": 459899, "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": 4183437, "tid": 31318, "ts": 658972326355.327, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 4183437, "tid": 31318, + "ts": 658972326384.918, "dur": 40.986, + "args": { + "External id": 37068,"Record function id": 0, "Ev Idx": 3787 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 4183437, "tid": 31318, + "ts": 658972326433.033, "dur": 66.696, + "args": { + "External id": 37069,"Record function id": 0, "Ev Idx": 3788 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 4183437, "tid": 31318, + "ts": 658972326505.507, "dur": 15037.930, + "args": { + "External id": 37070,"Record function id": 0, "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972326599.402, "dur": 7.131, + "args": { + "External id": 37071,"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": 4183437, "tid": 31318, + "ts": 658972326615.477, "dur": 4.556, + "args": { + "External id": 37072,"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": 4183437, "tid": 31318, + "ts": 658972326633.818, "dur": 14199.739, + "args": { + "External id": 37073,"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": 4183437, "tid": 31318, + "ts": 658972326646.734, "dur": 14178.451, + "args": { + "External id": 37074,"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": 4183437, "tid": 31318, + "ts": 658972326707.987, "dur": 14.616, + "args": { + "External id": 37075,"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": 4183437, "tid": 31318, + "ts": 658972326727.782, "dur": 14063.859, + "args": { + "External id": 37076,"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": 4183437, "tid": 31318, + "ts": 658972326730.570, "dur": 14060.428, + "args": { + "External id": 37077,"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": 4183437, "tid": 31318, + "ts": 658972326734.670, "dur": 5.472, + "args": { + "External id": 37078,"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": 4183437, "tid": 31318, + "ts": 658972326741.928, "dur": 14045.694, + "args": { + "External id": 37079,"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": 4183437, "tid": 31318, + "ts": 658972340922.282, "dur": 9.164, + "args": { + "External id": 37080,"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": 4183437, "tid": 31318, + "ts": 658972340925.061, "dur": 6.029, + "args": { + "External id": 37081,"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": 4183437, "tid": 31318, + "ts": 658972340956.207, "dur": 306.495, + "args": { + "External id": 37082,"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": 4183437, "tid": 31318, + "ts": 658972340979.238, "dur": 279.348, + "args": { + "External id": 37083,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972340990.521, "dur": 263.215, + "args": { + "External id": 37084,"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": 4183437, "tid": 31318, + "ts": 658972341294.883, "dur": 2.840, + "args": { + "External id": 37085,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972341351.889, "dur": 6.003, + "args": { + "External id": 37086,"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": 4183437, "tid": 31318, + "ts": 658972341400.667, "dur": 1.211, + "args": { + "External id": 37087,"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": 4183437, "tid": 31318, + "ts": 658972341416.027, "dur": 1.030, + "args": { + "External id": 37088,"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": 4183437, "tid": 31318, + "ts": 658972341428.843, "dur": 1.272, + "args": { + "External id": 37089,"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": 4183437, "tid": 31318, + "ts": 658972341441.618, "dur": 0.818, + "args": { + "External id": 37090,"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": 4183437, "tid": 31318, + "ts": 658972341451.847, "dur": 1.480, + "args": { + "External id": 37091,"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": 4183437, "tid": 31318, + "ts": 658972341463.209, "dur": 0.938, + "args": { + "External id": 37092,"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": 4183437, "tid": 31318, + "ts": 658972341473.296, "dur": 1.301, + "args": { + "External id": 37093,"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": 4183437, "tid": 31318, + "ts": 658972341483.320, "dur": 1.133, + "args": { + "External id": 37094,"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": 4183437, "tid": 31318, + "ts": 658972341574.817, "dur": 2551.670, + "args": { + "External id": 37095,"Record function id": 0, "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 4183437, "tid": 31318, + "ts": 658972341594.300, "dur": 942.250, + "args": { + "External id": 37096,"Record function id": 0, "Ev Idx": 3815 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 4183437, "tid": 31318, + "ts": 658972341608.821, "dur": 331.142, + "args": { + "External id": 37097,"Record function id": 0, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972341722.593, "dur": 5.538, + "args": { + "External id": 37098,"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": 4183437, "tid": 31318, + "ts": 658972341731.803, "dur": 1.234, + "args": { + "External id": 37099,"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": 4183437, "tid": 31318, + "ts": 658972341734.801, "dur": 1.140, + "args": { + "External id": 37100,"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": 4183437, "tid": 31318, + "ts": 658972341737.667, "dur": 0.968, + "args": { + "External id": 37101,"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": 4183437, "tid": 31318, + "ts": 658972341740.203, "dur": 1.415, + "args": { + "External id": 37102,"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": 4183437, "tid": 31318, + "ts": 658972341743.167, "dur": 1.537, + "args": { + "External id": 37103,"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": 4183437, "tid": 31318, + "ts": 658972341746.407, "dur": 1.439, + "args": { + "External id": 37104,"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": 4183437, "tid": 31318, + "ts": 658972341749.178, "dur": 1.003, + "args": { + "External id": 37105,"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": 4183437, "tid": 31318, + "ts": 658972341751.708, "dur": 1.512, + "args": { + "External id": 37106,"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": 4183437, "tid": 31318, + "ts": 658972341754.899, "dur": 1.268, + "args": { + "External id": 37107,"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": 4183437, "tid": 31318, + "ts": 658972341774.824, "dur": 136.634, + "args": { + "External id": 37108,"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": 4183437, "tid": 31318, + "ts": 658972341790.858, "dur": 116.276, + "args": { + "External id": 37109,"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": 4183437, "tid": 31318, + "ts": 658972341803.204, "dur": 13.702, + "args": { + "External id": 37110,"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": 4183437, "tid": 31318, + "ts": 658972341819.736, "dur": 61.405, + "args": { + "External id": 37111,"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": 4183437, "tid": 31318, + "ts": 658972341822.412, "dur": 58.415, + "args": { + "External id": 37112,"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": 4183437, "tid": 31318, + "ts": 658972341825.901, "dur": 4.865, + "args": { + "External id": 37113,"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": 4183437, "tid": 31318, + "ts": 658972341832.435, "dur": 47.862, + "args": { + "External id": 37114,"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": 4183437, "tid": 31318, + "ts": 658972342014.732, "dur": 514.559, + "args": { + "External id": 37115,"Record function id": 0, "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 4183437, "tid": 31318, + "ts": 658972342031.221, "dur": 485.732, + "args": { + "External id": 37116,"Record function id": 0, "Ev Idx": 3835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972342086.227, "dur": 4.385, + "args": { + "External id": 37117,"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": 4183437, "tid": 31318, + "ts": 658972342105.576, "dur": 23.704, + "args": { + "External id": 37118,"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": 4183437, "tid": 31318, + "ts": 658972342109.975, "dur": 1.754, + "args": { + "External id": 37119,"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": 4183437, "tid": 31318, + "ts": 658972342112.910, "dur": 0.480, + "args": { + "External id": 37120,"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": 4183437, "tid": 31318, + "ts": 658972342114.986, "dur": 0.312, + "args": { + "External id": 37121,"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": 4183437, "tid": 31318, + "ts": 658972342116.419, "dur": 0.291, + "args": { + "External id": 37122,"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": 4183437, "tid": 31318, + "ts": 658972342118.426, "dur": 0.586, + "args": { + "External id": 37123,"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": 4183437, "tid": 31318, + "ts": 658972342120.063, "dur": 0.398, + "args": { + "External id": 37124,"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": 4183437, "tid": 31318, + "ts": 658972342121.984, "dur": 0.585, + "args": { + "External id": 37125,"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": 4183437, "tid": 31318, + "ts": 658972342123.672, "dur": 0.460, + "args": { + "External id": 37126,"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": 4183437, "tid": 31318, + "ts": 658972342125.330, "dur": 0.357, + "args": { + "External id": 37127,"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": 4183437, "tid": 31318, + "ts": 658972342138.456, "dur": 28.612, + "args": { + "External id": 37128,"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": 4183437, "tid": 31318, + "ts": 658972342197.443, "dur": 108.030, + "args": { + "External id": 37129,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972342206.152, "dur": 3.414, + "args": { + "External id": 37130,"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": 4183437, "tid": 31318, + "ts": 658972342214.473, "dur": 9.957, + "args": { + "External id": 37131,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972342218.310, "dur": 5.693, + "args": { + "External id": 37132,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972342221.526, "dur": 1.095, + "args": { + "External id": 37133,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972342230.920, "dur": 20.729, + "args": { + "External id": 37134,"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": 4183437, "tid": 31318, + "ts": 658972342233.031, "dur": 0.466, + "args": { + "External id": 37135,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972342234.386, "dur": 0.668, + "args": { + "External id": 37136,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972342236.563, "dur": 0.500, + "args": { + "External id": 37137,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972342237.956, "dur": 0.677, + "args": { + "External id": 37138,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972342239.874, "dur": 0.587, + "args": { + "External id": 37139,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972342241.357, "dur": 0.800, + "args": { + "External id": 37140,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972342243.117, "dur": 0.273, + "args": { + "External id": 37141,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972342244.208, "dur": 0.681, + "args": { + "External id": 37142,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972342245.894, "dur": 0.424, + "args": { + "External id": 37143,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972342259.425, "dur": 36.905, + "args": { + "External id": 37144,"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": 4183437, "tid": 31318, + "ts": 658972342350.630, "dur": 104.009, + "args": { + "External id": 37145,"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": 4183437, "tid": 31318, + "ts": 658972342371.832, "dur": 79.679, + "args": { + "External id": 37146,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972342381.210, "dur": 66.450, + "args": { + "External id": 37147,"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": 4183437, "tid": 31318, + "ts": 658972342466.980, "dur": 1.653, + "args": { + "External id": 37148,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972342544.625, "dur": 1560.019, + "args": { + "External id": 37149,"Sequence number": 459898, "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": 4183437, "tid": 31318, "ts": 658972342544.625, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972342688.230, "dur": 101.767, + "args": { + "External id": 37150,"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": 4183437, "tid": 31318, + "ts": 658972342829.437, "dur": 40.370, + "args": { + "External id": 37151,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972342886.213, "dur": 40.046, + "args": { + "External id": 37152,"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": 4183437, "tid": 31318, + "ts": 658972342935.408, "dur": 25.339, + "args": { + "External id": 37153,"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": 4183437, "tid": 31318, + "ts": 658972342966.824, "dur": 32.718, + "args": { + "External id": 37154,"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": 4183437, "tid": 31318, + "ts": 658972343006.533, "dur": 22.110, + "args": { + "External id": 37155,"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": 4183437, "tid": 31318, + "ts": 658972343036.037, "dur": 28.955, + "args": { + "External id": 37156,"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": 4183437, "tid": 31318, + "ts": 658972343089.089, "dur": 23.460, + "args": { + "External id": 37157,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972343129.861, "dur": 30.095, + "args": { + "External id": 37158,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972343177.041, "dur": 24.793, + "args": { + "External id": 37159,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972343212.987, "dur": 23.177, + "args": { + "External id": 37160,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972343244.400, "dur": 57.781, + "args": { + "External id": 37161,"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": 4183437, "tid": 31318, + "ts": 658972343307.070, "dur": 33.083, + "args": { + "External id": 37162,"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": 4183437, "tid": 31318, + "ts": 658972343366.443, "dur": 165.608, + "args": { + "External id": 37163,"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": 4183437, "tid": 31318, + "ts": 658972343443.324, "dur": 5.611, + "args": { + "External id": 37164,"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": 4183437, "tid": 31318, + "ts": 658972343450.985, "dur": 2.638, + "args": { + "External id": 37165,"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": 4183437, "tid": 31318, + "ts": 658972343560.884, "dur": 28.791, + "args": { + "External id": 37166,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972343599.887, "dur": 15.499, + "args": { + "External id": 37167,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972343622.382, "dur": 82.381, + "args": { + "External id": 37168,"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": 4183437, "tid": 31318, + "ts": 658972343714.005, "dur": 34.687, + "args": { + "External id": 37169,"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": 4183437, "tid": 31318, + "ts": 658972343756.139, "dur": 27.662, + "args": { + "External id": 37170,"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": 4183437, "tid": 31318, + "ts": 658972343788.256, "dur": 27.857, + "args": { + "External id": 37171,"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": 4183437, "tid": 31318, + "ts": 658972343821.906, "dur": 26.286, + "args": { + "External id": 37172,"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": 4183437, "tid": 31318, + "ts": 658972343854.286, "dur": 28.993, + "args": { + "External id": 37173,"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": 4183437, "tid": 31318, + "ts": 658972343900.801, "dur": 22.301, + "args": { + "External id": 37174,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972343939.530, "dur": 26.469, + "args": { + "External id": 37175,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972343977.851, "dur": 14.850, + "args": { + "External id": 37176,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972344024.719, "dur": 19.503, + "args": { + "External id": 37177,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972344056.509, "dur": 18.460, + "args": { + "External id": 37178,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972344147.751, "dur": 15.082, + "args": { + "External id": 37179,"Record function id": 0, "Ev Idx": 3898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972344150.723, "dur": 11.010, + "args": { + "External id": 37180,"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": 4183437, "tid": 31318, + "ts": 658972344155.000, "dur": 5.867, + "args": { + "External id": 37181,"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": 4183437, "tid": 31318, + "ts": 658972344156.367, "dur": 4.405, + "args": { + "External id": 37182,"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": 4183437, "tid": 31318, + "ts": 658972344166.684, "dur": 5.006, + "args": { + "External id": 37183,"Record function id": 0, "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972344167.934, "dur": 3.309, + "args": { + "External id": 37184,"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": 4183437, "tid": 31318, + "ts": 658972344168.945, "dur": 1.821, + "args": { + "External id": 37185,"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": 4183437, "tid": 31318, + "ts": 658972344169.656, "dur": 1.045, + "args": { + "External id": 37186,"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": 4183437, "tid": 31318, + "ts": 658972344175.150, "dur": 6.991, + "args": { + "External id": 37187,"Record function id": 0, "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972344179.546, "dur": 2.136, + "args": { + "External id": 37188,"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": 4183437, "tid": 31318, + "ts": 658972344180.067, "dur": 1.207, + "args": { + "External id": 37189,"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": 4183437, "tid": 31318, + "ts": 658972344180.507, "dur": 0.686, + "args": { + "External id": 37190,"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": 4183437, "tid": 31318, + "ts": 658972344185.341, "dur": 3.885, + "args": { + "External id": 37191,"Record function id": 0, "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972344186.252, "dur": 2.569, + "args": { + "External id": 37192,"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": 4183437, "tid": 31318, + "ts": 658972344186.899, "dur": 1.515, + "args": { + "External id": 37193,"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": 4183437, "tid": 31318, + "ts": 658972344187.201, "dur": 1.103, + "args": { + "External id": 37194,"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": 4183437, "tid": 31318, + "ts": 658972344192.385, "dur": 4.054, + "args": { + "External id": 37195,"Record function id": 0, "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972344193.374, "dur": 2.628, + "args": { + "External id": 37196,"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": 4183437, "tid": 31318, + "ts": 658972344194.057, "dur": 1.520, + "args": { + "External id": 37197,"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": 4183437, "tid": 31318, + "ts": 658972344194.825, "dur": 0.689, + "args": { + "External id": 37198,"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": 4183437, "tid": 31318, + "ts": 658972344199.449, "dur": 3.238, + "args": { + "External id": 37199,"Record function id": 0, "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972344200.350, "dur": 1.929, + "args": { + "External id": 37200,"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": 4183437, "tid": 31318, + "ts": 658972344200.916, "dur": 0.912, + "args": { + "External id": 37201,"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": 4183437, "tid": 31318, + "ts": 658972344201.313, "dur": 0.450, + "args": { + "External id": 37202,"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": 4183437, "tid": 31318, + "ts": 658972344205.754, "dur": 4.089, + "args": { + "External id": 37203,"Record function id": 0, "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972344206.961, "dur": 2.445, + "args": { + "External id": 37204,"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": 4183437, "tid": 31318, + "ts": 658972344207.676, "dur": 1.305, + "args": { + "External id": 37205,"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": 4183437, "tid": 31318, + "ts": 658972344208.138, "dur": 0.780, + "args": { + "External id": 37206,"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": 4183437, "tid": 31318, + "ts": 658972344212.831, "dur": 3.894, + "args": { + "External id": 37207,"Record function id": 0, "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972344214.018, "dur": 2.283, + "args": { + "External id": 37208,"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": 4183437, "tid": 31318, + "ts": 658972344214.503, "dur": 1.370, + "args": { + "External id": 37209,"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": 4183437, "tid": 31318, + "ts": 658972344215.191, "dur": 0.616, + "args": { + "External id": 37210,"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": 4183437, "tid": 31318, + "ts": 658972344219.683, "dur": 5.685, + "args": { + "External id": 37211,"Record function id": 0, "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972344220.851, "dur": 4.045, + "args": { + "External id": 37212,"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": 4183437, "tid": 31318, + "ts": 658972344221.504, "dur": 2.974, + "args": { + "External id": 37213,"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": 4183437, "tid": 31318, + "ts": 658972344223.738, "dur": 0.674, + "args": { + "External id": 37214,"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": 4183437, "tid": 31318, + "ts": 658972344229.267, "dur": 15208.297, + "args": { + "External id": 37215,"Record function id": 0, "Sequence number": 459897, "Fwd thread id": 1, "Ev Idx": 3934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972344230.490, "dur": 15198.692, + "args": { + "External id": 37216,"Sequence number": 459897, "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": 4183437, "tid": 31318, "ts": 658972344230.490, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 4183437, "tid": 31318, + "ts": 658972344260.669, "dur": 58.936, + "args": { + "External id": 37217,"Record function id": 0, "Ev Idx": 3936 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 4183437, "tid": 31318, + "ts": 658972344327.925, "dur": 66.899, + "args": { + "External id": 37218,"Record function id": 0, "Ev Idx": 3937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 4183437, "tid": 31318, + "ts": 658972344400.404, "dur": 15020.625, + "args": { + "External id": 37219,"Record function id": 0, "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972344492.935, "dur": 7.771, + "args": { + "External id": 37220,"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": 4183437, "tid": 31318, + "ts": 658972344510.625, "dur": 5.127, + "args": { + "External id": 37221,"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": 4183437, "tid": 31318, + "ts": 658972344529.325, "dur": 14206.288, + "args": { + "External id": 37222,"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": 4183437, "tid": 31318, + "ts": 658972344542.426, "dur": 14185.252, + "args": { + "External id": 37223,"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": 4183437, "tid": 31318, + "ts": 658972344567.490, "dur": 13.005, + "args": { + "External id": 37224,"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": 4183437, "tid": 31318, + "ts": 658972344585.210, "dur": 14102.519, + "args": { + "External id": 37225,"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": 4183437, "tid": 31318, + "ts": 658972344588.149, "dur": 14098.907, + "args": { + "External id": 37226,"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": 4183437, "tid": 31318, + "ts": 658972344592.050, "dur": 4.796, + "args": { + "External id": 37227,"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": 4183437, "tid": 31318, + "ts": 658972344598.443, "dur": 14084.740, + "args": { + "External id": 37228,"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": 4183437, "tid": 31318, + "ts": 658972358822.099, "dur": 9.798, + "args": { + "External id": 37229,"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": 4183437, "tid": 31318, + "ts": 658972358825.167, "dur": 6.292, + "args": { + "External id": 37230,"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": 4183437, "tid": 31318, + "ts": 658972358861.073, "dur": 272.877, + "args": { + "External id": 37231,"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": 4183437, "tid": 31318, + "ts": 658972358883.349, "dur": 246.128, + "args": { + "External id": 37232,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972358894.569, "dur": 229.238, + "args": { + "External id": 37233,"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": 4183437, "tid": 31318, + "ts": 658972359150.840, "dur": 2.134, + "args": { + "External id": 37234,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972359205.432, "dur": 6.260, + "args": { + "External id": 37235,"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": 4183437, "tid": 31318, + "ts": 658972359258.738, "dur": 1.381, + "args": { + "External id": 37236,"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": 4183437, "tid": 31318, + "ts": 658972359294.009, "dur": 1.647, + "args": { + "External id": 37237,"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": 4183437, "tid": 31318, + "ts": 658972359306.738, "dur": 0.979, + "args": { + "External id": 37238,"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": 4183437, "tid": 31318, + "ts": 658972359319.972, "dur": 0.958, + "args": { + "External id": 37239,"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": 4183437, "tid": 31318, + "ts": 658972359330.683, "dur": 0.902, + "args": { + "External id": 37240,"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": 4183437, "tid": 31318, + "ts": 658972359340.873, "dur": 0.874, + "args": { + "External id": 37241,"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": 4183437, "tid": 31318, + "ts": 658972359352.253, "dur": 1.324, + "args": { + "External id": 37242,"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": 4183437, "tid": 31318, + "ts": 658972359362.514, "dur": 1.017, + "args": { + "External id": 37243,"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": 4183437, "tid": 31318, + "ts": 658972359452.583, "dur": 2557.459, + "args": { + "External id": 37244,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 4183437, "tid": 31318, + "ts": 658972359470.385, "dur": 947.538, + "args": { + "External id": 37245,"Record function id": 0, "Ev Idx": 3964 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 4183437, "tid": 31318, + "ts": 658972359483.177, "dur": 331.380, + "args": { + "External id": 37246,"Record function id": 0, "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972359560.075, "dur": 4.096, + "args": { + "External id": 37247,"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": 4183437, "tid": 31318, + "ts": 658972359567.088, "dur": 1.007, + "args": { + "External id": 37248,"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": 4183437, "tid": 31318, + "ts": 658972359569.800, "dur": 1.474, + "args": { + "External id": 37249,"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": 4183437, "tid": 31318, + "ts": 658972359572.800, "dur": 1.040, + "args": { + "External id": 37250,"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": 4183437, "tid": 31318, + "ts": 658972359575.411, "dur": 1.129, + "args": { + "External id": 37251,"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": 4183437, "tid": 31318, + "ts": 658972359577.988, "dur": 1.575, + "args": { + "External id": 37252,"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": 4183437, "tid": 31318, + "ts": 658972359580.993, "dur": 0.920, + "args": { + "External id": 37253,"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": 4183437, "tid": 31318, + "ts": 658972359583.394, "dur": 1.340, + "args": { + "External id": 37254,"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": 4183437, "tid": 31318, + "ts": 658972359586.219, "dur": 1.185, + "args": { + "External id": 37255,"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": 4183437, "tid": 31318, + "ts": 658972359589.092, "dur": 0.845, + "args": { + "External id": 37256,"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": 4183437, "tid": 31318, + "ts": 658972359607.148, "dur": 176.693, + "args": { + "External id": 37257,"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": 4183437, "tid": 31318, + "ts": 658972359623.419, "dur": 155.382, + "args": { + "External id": 37258,"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": 4183437, "tid": 31318, + "ts": 658972359636.304, "dur": 12.742, + "args": { + "External id": 37259,"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": 4183437, "tid": 31318, + "ts": 658972359688.096, "dur": 63.169, + "args": { + "External id": 37260,"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": 4183437, "tid": 31318, + "ts": 658972359691.037, "dur": 59.944, + "args": { + "External id": 37261,"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": 4183437, "tid": 31318, + "ts": 658972359695.055, "dur": 5.939, + "args": { + "External id": 37262,"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": 4183437, "tid": 31318, + "ts": 658972359702.952, "dur": 47.601, + "args": { + "External id": 37263,"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": 4183437, "tid": 31318, + "ts": 658972359894.171, "dur": 516.263, + "args": { + "External id": 37264,"Record function id": 0, "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 4183437, "tid": 31318, + "ts": 658972359910.204, "dur": 488.141, + "args": { + "External id": 37265,"Record function id": 0, "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972359969.227, "dur": 5.145, + "args": { + "External id": 37266,"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": 4183437, "tid": 31318, + "ts": 658972359988.137, "dur": 21.845, + "args": { + "External id": 37267,"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": 4183437, "tid": 31318, + "ts": 658972359992.444, "dur": 1.282, + "args": { + "External id": 37268,"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": 4183437, "tid": 31318, + "ts": 658972359995.432, "dur": 0.845, + "args": { + "External id": 37269,"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": 4183437, "tid": 31318, + "ts": 658972359997.470, "dur": 0.315, + "args": { + "External id": 37270,"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": 4183437, "tid": 31318, + "ts": 658972359998.664, "dur": 0.396, + "args": { + "External id": 37271,"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": 4183437, "tid": 31318, + "ts": 658972360000.166, "dur": 0.305, + "args": { + "External id": 37272,"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": 4183437, "tid": 31318, + "ts": 658972360001.193, "dur": 0.643, + "args": { + "External id": 37273,"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": 4183437, "tid": 31318, + "ts": 658972360002.986, "dur": 0.292, + "args": { + "External id": 37274,"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": 4183437, "tid": 31318, + "ts": 658972360003.872, "dur": 0.754, + "args": { + "External id": 37275,"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": 4183437, "tid": 31318, + "ts": 658972360005.863, "dur": 0.378, + "args": { + "External id": 37276,"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": 4183437, "tid": 31318, + "ts": 658972360019.656, "dur": 28.945, + "args": { + "External id": 37277,"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": 4183437, "tid": 31318, + "ts": 658972360078.163, "dur": 87.738, + "args": { + "External id": 37278,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972360087.072, "dur": 3.174, + "args": { + "External id": 37279,"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": 4183437, "tid": 31318, + "ts": 658972360095.143, "dur": 9.778, + "args": { + "External id": 37280,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972360099.439, "dur": 5.057, + "args": { + "External id": 37281,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972360102.509, "dur": 0.723, + "args": { + "External id": 37282,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972360110.803, "dur": 20.081, + "args": { + "External id": 37283,"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": 4183437, "tid": 31318, + "ts": 658972360112.291, "dur": 0.367, + "args": { + "External id": 37284,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972360113.799, "dur": 0.754, + "args": { + "External id": 37285,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972360115.761, "dur": 0.632, + "args": { + "External id": 37286,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972360117.164, "dur": 0.859, + "args": { + "External id": 37287,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972360119.287, "dur": 0.772, + "args": { + "External id": 37288,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972360120.900, "dur": 0.774, + "args": { + "External id": 37289,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972360122.472, "dur": 0.193, + "args": { + "External id": 37290,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972360123.212, "dur": 0.587, + "args": { + "External id": 37291,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972360124.633, "dur": 0.411, + "args": { + "External id": 37292,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972360140.125, "dur": 18.682, + "args": { + "External id": 37293,"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": 4183437, "tid": 31318, + "ts": 658972360208.096, "dur": 124.878, + "args": { + "External id": 37294,"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": 4183437, "tid": 31318, + "ts": 658972360228.584, "dur": 100.299, + "args": { + "External id": 37295,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972360237.923, "dur": 86.486, + "args": { + "External id": 37296,"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": 4183437, "tid": 31318, + "ts": 658972360347.403, "dur": 1.907, + "args": { + "External id": 37297,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972360425.965, "dur": 1565.854, + "args": { + "External id": 37298,"Sequence number": 459896, "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": 4183437, "tid": 31318, "ts": 658972360425.965, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972360535.024, "dur": 100.029, + "args": { + "External id": 37299,"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": 4183437, "tid": 31318, + "ts": 658972360711.153, "dur": 42.918, + "args": { + "External id": 37300,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972360772.999, "dur": 49.878, + "args": { + "External id": 37301,"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": 4183437, "tid": 31318, + "ts": 658972360832.726, "dur": 31.001, + "args": { + "External id": 37302,"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": 4183437, "tid": 31318, + "ts": 658972360870.024, "dur": 32.396, + "args": { + "External id": 37303,"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": 4183437, "tid": 31318, + "ts": 658972360908.924, "dur": 24.209, + "args": { + "External id": 37304,"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": 4183437, "tid": 31318, + "ts": 658972360940.334, "dur": 29.610, + "args": { + "External id": 37305,"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": 4183437, "tid": 31318, + "ts": 658972360994.524, "dur": 20.850, + "args": { + "External id": 37306,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972361032.173, "dur": 26.072, + "args": { + "External id": 37307,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972361074.528, "dur": 19.913, + "args": { + "External id": 37308,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972361103.797, "dur": 14.879, + "args": { + "External id": 37309,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972361126.478, "dur": 36.374, + "args": { + "External id": 37310,"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": 4183437, "tid": 31318, + "ts": 658972361166.038, "dur": 32.309, + "args": { + "External id": 37311,"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": 4183437, "tid": 31318, + "ts": 658972361222.833, "dur": 188.851, + "args": { + "External id": 37312,"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": 4183437, "tid": 31318, + "ts": 658972361318.988, "dur": 6.754, + "args": { + "External id": 37313,"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": 4183437, "tid": 31318, + "ts": 658972361327.707, "dur": 3.291, + "args": { + "External id": 37314,"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": 4183437, "tid": 31318, + "ts": 658972361441.700, "dur": 25.677, + "args": { + "External id": 37315,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972361477.592, "dur": 14.896, + "args": { + "External id": 37316,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972361499.615, "dur": 49.562, + "args": { + "External id": 37317,"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": 4183437, "tid": 31318, + "ts": 658972361554.914, "dur": 33.370, + "args": { + "External id": 37318,"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": 4183437, "tid": 31318, + "ts": 658972361594.360, "dur": 27.666, + "args": { + "External id": 37319,"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": 4183437, "tid": 31318, + "ts": 658972361626.407, "dur": 65.151, + "args": { + "External id": 37320,"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": 4183437, "tid": 31318, + "ts": 658972361703.043, "dur": 31.879, + "args": { + "External id": 37321,"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": 4183437, "tid": 31318, + "ts": 658972361741.934, "dur": 29.810, + "args": { + "External id": 37322,"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": 4183437, "tid": 31318, + "ts": 658972361787.533, "dur": 23.697, + "args": { + "External id": 37323,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972361826.656, "dur": 24.155, + "args": { + "External id": 37324,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972361863.225, "dur": 16.203, + "args": { + "External id": 37325,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972361911.084, "dur": 22.124, + "args": { + "External id": 37326,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972361944.097, "dur": 18.979, + "args": { + "External id": 37327,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972362034.779, "dur": 13.994, + "args": { + "External id": 37328,"Record function id": 0, "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972362037.764, "dur": 10.037, + "args": { + "External id": 37329,"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": 4183437, "tid": 31318, + "ts": 658972362041.567, "dur": 5.430, + "args": { + "External id": 37330,"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": 4183437, "tid": 31318, + "ts": 658972362042.810, "dur": 4.096, + "args": { + "External id": 37331,"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": 4183437, "tid": 31318, + "ts": 658972362052.504, "dur": 5.503, + "args": { + "External id": 37332,"Record function id": 0, "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972362054.099, "dur": 3.444, + "args": { + "External id": 37333,"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": 4183437, "tid": 31318, + "ts": 658972362054.858, "dur": 2.254, + "args": { + "External id": 37334,"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": 4183437, "tid": 31318, + "ts": 658972362055.592, "dur": 1.449, + "args": { + "External id": 37335,"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": 4183437, "tid": 31318, + "ts": 658972362061.147, "dur": 4.116, + "args": { + "External id": 37336,"Record function id": 0, "Ev Idx": 4055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972362062.458, "dur": 2.316, + "args": { + "External id": 37337,"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": 4183437, "tid": 31318, + "ts": 658972362063.106, "dur": 1.257, + "args": { + "External id": 37338,"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": 4183437, "tid": 31318, + "ts": 658972362063.546, "dur": 0.735, + "args": { + "External id": 37339,"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": 4183437, "tid": 31318, + "ts": 658972362068.386, "dur": 3.319, + "args": { + "External id": 37340,"Record function id": 0, "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972362069.381, "dur": 1.873, + "args": { + "External id": 37341,"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": 4183437, "tid": 31318, + "ts": 658972362070.017, "dur": 0.824, + "args": { + "External id": 37342,"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": 4183437, "tid": 31318, + "ts": 658972362070.326, "dur": 0.451, + "args": { + "External id": 37343,"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": 4183437, "tid": 31318, + "ts": 658972362077.465, "dur": 3.827, + "args": { + "External id": 37344,"Record function id": 0, "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972362078.665, "dur": 2.191, + "args": { + "External id": 37345,"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": 4183437, "tid": 31318, + "ts": 658972362079.210, "dur": 1.197, + "args": { + "External id": 37346,"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": 4183437, "tid": 31318, + "ts": 658972362079.836, "dur": 0.479, + "args": { + "External id": 37347,"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": 4183437, "tid": 31318, + "ts": 658972362084.378, "dur": 3.601, + "args": { + "External id": 37348,"Record function id": 0, "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972362085.347, "dur": 2.206, + "args": { + "External id": 37349,"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": 4183437, "tid": 31318, + "ts": 658972362085.845, "dur": 1.284, + "args": { + "External id": 37350,"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": 4183437, "tid": 31318, + "ts": 658972362086.266, "dur": 0.797, + "args": { + "External id": 37351,"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": 4183437, "tid": 31318, + "ts": 658972362091.078, "dur": 4.276, + "args": { + "External id": 37352,"Record function id": 0, "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972362092.290, "dur": 2.631, + "args": { + "External id": 37353,"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": 4183437, "tid": 31318, + "ts": 658972362093.006, "dur": 1.484, + "args": { + "External id": 37354,"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": 4183437, "tid": 31318, + "ts": 658972362093.779, "dur": 0.651, + "args": { + "External id": 37355,"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": 4183437, "tid": 31318, + "ts": 658972362098.279, "dur": 4.000, + "args": { + "External id": 37356,"Record function id": 0, "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972362099.536, "dur": 2.305, + "args": { + "External id": 37357,"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": 4183437, "tid": 31318, + "ts": 658972362100.050, "dur": 1.357, + "args": { + "External id": 37358,"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": 4183437, "tid": 31318, + "ts": 658972362100.599, "dur": 0.745, + "args": { + "External id": 37359,"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": 4183437, "tid": 31318, + "ts": 658972362105.463, "dur": 3.630, + "args": { + "External id": 37360,"Record function id": 0, "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972362106.487, "dur": 2.165, + "args": { + "External id": 37361,"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": 4183437, "tid": 31318, + "ts": 658972362107.006, "dur": 1.221, + "args": { + "External id": 37362,"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": 4183437, "tid": 31318, + "ts": 658972362107.535, "dur": 0.629, + "args": { + "External id": 37363,"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": 4183437, "tid": 31318, + "ts": 658972362113.151, "dur": 16430.240, + "args": { + "External id": 37364,"Record function id": 0, "Sequence number": 459895, "Fwd thread id": 1, "Ev Idx": 4083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972362114.525, "dur": 16419.945, + "args": { + "External id": 37365,"Sequence number": 459895, "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": 4183437, "tid": 31318, "ts": 658972362114.525, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 4183437, "tid": 31318, + "ts": 658972362147.093, "dur": 35.796, + "args": { + "External id": 37366,"Record function id": 0, "Ev Idx": 4085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 4183437, "tid": 31318, + "ts": 658972362193.868, "dur": 59.991, + "args": { + "External id": 37367,"Record function id": 0, "Ev Idx": 4086 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 4183437, "tid": 31318, + "ts": 658972362259.440, "dur": 16266.884, + "args": { + "External id": 37368,"Record function id": 0, "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972362365.100, "dur": 7.758, + "args": { + "External id": 37369,"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": 4183437, "tid": 31318, + "ts": 658972362383.015, "dur": 4.866, + "args": { + "External id": 37370,"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": 4183437, "tid": 31318, + "ts": 658972362402.146, "dur": 15389.271, + "args": { + "External id": 37371,"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": 4183437, "tid": 31318, + "ts": 658972362415.149, "dur": 15367.915, + "args": { + "External id": 37372,"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": 4183437, "tid": 31318, + "ts": 658972362439.234, "dur": 13.762, + "args": { + "External id": 37373,"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": 4183437, "tid": 31318, + "ts": 658972362460.857, "dur": 15286.557, + "args": { + "External id": 37374,"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": 4183437, "tid": 31318, + "ts": 658972362463.817, "dur": 15282.664, + "args": { + "External id": 37375,"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": 4183437, "tid": 31318, + "ts": 658972362467.229, "dur": 5.116, + "args": { + "External id": 37376,"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": 4183437, "tid": 31318, + "ts": 658972362490.941, "dur": 15252.338, + "args": { + "External id": 37377,"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": 4183437, "tid": 31318, + "ts": 658972377881.198, "dur": 9.687, + "args": { + "External id": 37378,"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": 4183437, "tid": 31318, + "ts": 658972377884.206, "dur": 6.337, + "args": { + "External id": 37379,"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": 4183437, "tid": 31318, + "ts": 658972377916.355, "dur": 322.109, + "args": { + "External id": 37380,"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": 4183437, "tid": 31318, + "ts": 658972377938.981, "dur": 294.457, + "args": { + "External id": 37381,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972377949.631, "dur": 278.959, + "args": { + "External id": 37382,"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": 4183437, "tid": 31318, + "ts": 658972378257.403, "dur": 2.146, + "args": { + "External id": 37383,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972378331.149, "dur": 6.564, + "args": { + "External id": 37384,"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": 4183437, "tid": 31318, + "ts": 658972378381.822, "dur": 1.082, + "args": { + "External id": 37385,"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": 4183437, "tid": 31318, + "ts": 658972378397.755, "dur": 1.324, + "args": { + "External id": 37386,"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": 4183437, "tid": 31318, + "ts": 658972378410.000, "dur": 0.694, + "args": { + "External id": 37387,"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": 4183437, "tid": 31318, + "ts": 658972378421.497, "dur": 0.864, + "args": { + "External id": 37388,"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": 4183437, "tid": 31318, + "ts": 658972378431.909, "dur": 0.748, + "args": { + "External id": 37389,"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": 4183437, "tid": 31318, + "ts": 658972378443.539, "dur": 1.203, + "args": { + "External id": 37390,"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": 4183437, "tid": 31318, + "ts": 658972378455.465, "dur": 1.018, + "args": { + "External id": 37391,"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": 4183437, "tid": 31318, + "ts": 658972378465.851, "dur": 0.802, + "args": { + "External id": 37392,"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": 4183437, "tid": 31318, + "ts": 658972378558.453, "dur": 2569.025, + "args": { + "External id": 37393,"Record function id": 0, "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 4183437, "tid": 31318, + "ts": 658972378577.443, "dur": 963.675, + "args": { + "External id": 37394,"Record function id": 0, "Ev Idx": 4113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 4183437, "tid": 31318, + "ts": 658972378592.055, "dur": 338.863, + "args": { + "External id": 37395,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972378709.884, "dur": 4.733, + "args": { + "External id": 37396,"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": 4183437, "tid": 31318, + "ts": 658972378718.288, "dur": 0.944, + "args": { + "External id": 37397,"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": 4183437, "tid": 31318, + "ts": 658972378720.886, "dur": 1.175, + "args": { + "External id": 37398,"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": 4183437, "tid": 31318, + "ts": 658972378723.882, "dur": 0.872, + "args": { + "External id": 37399,"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": 4183437, "tid": 31318, + "ts": 658972378726.161, "dur": 1.949, + "args": { + "External id": 37400,"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": 4183437, "tid": 31318, + "ts": 658972378729.526, "dur": 0.967, + "args": { + "External id": 37401,"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": 4183437, "tid": 31318, + "ts": 658972378732.071, "dur": 0.942, + "args": { + "External id": 37402,"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": 4183437, "tid": 31318, + "ts": 658972378734.801, "dur": 1.002, + "args": { + "External id": 37403,"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": 4183437, "tid": 31318, + "ts": 658972378737.334, "dur": 1.595, + "args": { + "External id": 37404,"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": 4183437, "tid": 31318, + "ts": 658972378740.487, "dur": 0.535, + "args": { + "External id": 37405,"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": 4183437, "tid": 31318, + "ts": 658972378759.194, "dur": 143.296, + "args": { + "External id": 37406,"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": 4183437, "tid": 31318, + "ts": 658972378776.541, "dur": 121.784, + "args": { + "External id": 37407,"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": 4183437, "tid": 31318, + "ts": 658972378789.130, "dur": 14.115, + "args": { + "External id": 37408,"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": 4183437, "tid": 31318, + "ts": 658972378806.093, "dur": 63.364, + "args": { + "External id": 37409,"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": 4183437, "tid": 31318, + "ts": 658972378808.737, "dur": 60.382, + "args": { + "External id": 37410,"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": 4183437, "tid": 31318, + "ts": 658972378812.573, "dur": 5.584, + "args": { + "External id": 37411,"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": 4183437, "tid": 31318, + "ts": 658972378819.814, "dur": 48.787, + "args": { + "External id": 37412,"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": 4183437, "tid": 31318, + "ts": 658972379012.300, "dur": 521.300, + "args": { + "External id": 37413,"Record function id": 0, "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 4183437, "tid": 31318, + "ts": 658972379029.297, "dur": 492.680, + "args": { + "External id": 37414,"Record function id": 0, "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972379089.158, "dur": 5.270, + "args": { + "External id": 37415,"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": 4183437, "tid": 31318, + "ts": 658972379109.033, "dur": 24.659, + "args": { + "External id": 37416,"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": 4183437, "tid": 31318, + "ts": 658972379113.548, "dur": 1.489, + "args": { + "External id": 37417,"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": 4183437, "tid": 31318, + "ts": 658972379116.454, "dur": 0.635, + "args": { + "External id": 37418,"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": 4183437, "tid": 31318, + "ts": 658972379118.105, "dur": 0.320, + "args": { + "External id": 37419,"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": 4183437, "tid": 31318, + "ts": 658972379119.803, "dur": 0.431, + "args": { + "External id": 37420,"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": 4183437, "tid": 31318, + "ts": 658972379121.443, "dur": 0.199, + "args": { + "External id": 37421,"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": 4183437, "tid": 31318, + "ts": 658972379122.421, "dur": 0.496, + "args": { + "External id": 37422,"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": 4183437, "tid": 31318, + "ts": 658972379127.168, "dur": 0.324, + "args": { + "External id": 37423,"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": 4183437, "tid": 31318, + "ts": 658972379128.426, "dur": 0.324, + "args": { + "External id": 37424,"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": 4183437, "tid": 31318, + "ts": 658972379129.730, "dur": 0.673, + "args": { + "External id": 37425,"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": 4183437, "tid": 31318, + "ts": 658972379142.470, "dur": 30.653, + "args": { + "External id": 37426,"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": 4183437, "tid": 31318, + "ts": 658972379201.568, "dur": 110.772, + "args": { + "External id": 37427,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972379210.580, "dur": 3.371, + "args": { + "External id": 37428,"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": 4183437, "tid": 31318, + "ts": 658972379218.746, "dur": 9.930, + "args": { + "External id": 37429,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972379222.846, "dur": 5.302, + "args": { + "External id": 37430,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972379226.247, "dur": 0.679, + "args": { + "External id": 37431,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972379235.734, "dur": 18.641, + "args": { + "External id": 37432,"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": 4183437, "tid": 31318, + "ts": 658972379237.487, "dur": 0.303, + "args": { + "External id": 37433,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972379239.023, "dur": 0.386, + "args": { + "External id": 37434,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972379240.936, "dur": 0.657, + "args": { + "External id": 37435,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972379242.685, "dur": 0.262, + "args": { + "External id": 37436,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972379243.521, "dur": 0.833, + "args": { + "External id": 37437,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972379245.576, "dur": 0.369, + "args": { + "External id": 37438,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972379246.737, "dur": 0.574, + "args": { + "External id": 37439,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972379248.719, "dur": 0.380, + "args": { + "External id": 37440,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972379249.911, "dur": 0.365, + "args": { + "External id": 37441,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972379264.032, "dur": 38.995, + "args": { + "External id": 37442,"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": 4183437, "tid": 31318, + "ts": 658972379359.070, "dur": 101.978, + "args": { + "External id": 37443,"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": 4183437, "tid": 31318, + "ts": 658972379379.538, "dur": 78.206, + "args": { + "External id": 37444,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972379388.636, "dur": 64.953, + "args": { + "External id": 37445,"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": 4183437, "tid": 31318, + "ts": 658972379472.719, "dur": 1.980, + "args": { + "External id": 37446,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972379549.453, "dur": 1555.517, + "args": { + "External id": 37447,"Sequence number": 459894, "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": 4183437, "tid": 31318, "ts": 658972379549.453, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972379697.438, "dur": 101.851, + "args": { + "External id": 37448,"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": 4183437, "tid": 31318, + "ts": 658972379840.887, "dur": 41.806, + "args": { + "External id": 37449,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972379899.507, "dur": 40.811, + "args": { + "External id": 37450,"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": 4183437, "tid": 31318, + "ts": 658972379950.468, "dur": 24.903, + "args": { + "External id": 37451,"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": 4183437, "tid": 31318, + "ts": 658972379981.310, "dur": 37.215, + "args": { + "External id": 37452,"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": 4183437, "tid": 31318, + "ts": 658972380025.163, "dur": 19.695, + "args": { + "External id": 37453,"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": 4183437, "tid": 31318, + "ts": 658972380051.768, "dur": 29.415, + "args": { + "External id": 37454,"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": 4183437, "tid": 31318, + "ts": 658972380104.246, "dur": 20.916, + "args": { + "External id": 37455,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972380150.170, "dur": 28.980, + "args": { + "External id": 37456,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972380196.938, "dur": 17.976, + "args": { + "External id": 37457,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972380225.949, "dur": 13.729, + "args": { + "External id": 37458,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972380247.126, "dur": 53.891, + "args": { + "External id": 37459,"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": 4183437, "tid": 31318, + "ts": 658972380306.121, "dur": 34.021, + "args": { + "External id": 37460,"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": 4183437, "tid": 31318, + "ts": 658972380367.138, "dur": 163.861, + "args": { + "External id": 37461,"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": 4183437, "tid": 31318, + "ts": 658972380442.883, "dur": 5.850, + "args": { + "External id": 37462,"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": 4183437, "tid": 31318, + "ts": 658972380450.864, "dur": 2.799, + "args": { + "External id": 37463,"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": 4183437, "tid": 31318, + "ts": 658972380560.240, "dur": 24.223, + "args": { + "External id": 37464,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972380598.289, "dur": 13.366, + "args": { + "External id": 37465,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972380618.539, "dur": 78.569, + "args": { + "External id": 37466,"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": 4183437, "tid": 31318, + "ts": 658972380705.919, "dur": 34.243, + "args": { + "External id": 37467,"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": 4183437, "tid": 31318, + "ts": 658972380747.259, "dur": 28.025, + "args": { + "External id": 37468,"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": 4183437, "tid": 31318, + "ts": 658972380779.420, "dur": 27.546, + "args": { + "External id": 37469,"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": 4183437, "tid": 31318, + "ts": 658972380812.550, "dur": 26.202, + "args": { + "External id": 37470,"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": 4183437, "tid": 31318, + "ts": 658972380845.125, "dur": 28.102, + "args": { + "External id": 37471,"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": 4183437, "tid": 31318, + "ts": 658972380894.020, "dur": 25.047, + "args": { + "External id": 37472,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972380948.145, "dur": 33.111, + "args": { + "External id": 37473,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972380998.561, "dur": 17.168, + "args": { + "External id": 37474,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972381030.301, "dur": 16.606, + "args": { + "External id": 37475,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972381060.516, "dur": 15.718, + "args": { + "External id": 37476,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972381148.682, "dur": 15.911, + "args": { + "External id": 37477,"Record function id": 0, "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972381152.192, "dur": 11.380, + "args": { + "External id": 37478,"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": 4183437, "tid": 31318, + "ts": 658972381156.463, "dur": 6.311, + "args": { + "External id": 37479,"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": 4183437, "tid": 31318, + "ts": 658972381158.107, "dur": 4.583, + "args": { + "External id": 37480,"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": 4183437, "tid": 31318, + "ts": 658972381171.214, "dur": 5.306, + "args": { + "External id": 37481,"Record function id": 0, "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972381172.598, "dur": 3.471, + "args": { + "External id": 37482,"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": 4183437, "tid": 31318, + "ts": 658972381173.923, "dur": 1.724, + "args": { + "External id": 37483,"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": 4183437, "tid": 31318, + "ts": 658972381174.632, "dur": 0.948, + "args": { + "External id": 37484,"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": 4183437, "tid": 31318, + "ts": 658972381179.945, "dur": 4.831, + "args": { + "External id": 37485,"Record function id": 0, "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972381181.232, "dur": 3.116, + "args": { + "External id": 37486,"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": 4183437, "tid": 31318, + "ts": 658972381182.364, "dur": 1.551, + "args": { + "External id": 37487,"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": 4183437, "tid": 31318, + "ts": 658972381183.023, "dur": 0.810, + "args": { + "External id": 37488,"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": 4183437, "tid": 31318, + "ts": 658972381188.106, "dur": 3.698, + "args": { + "External id": 37489,"Record function id": 0, "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972381189.160, "dur": 2.208, + "args": { + "External id": 37490,"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": 4183437, "tid": 31318, + "ts": 658972381189.857, "dur": 1.074, + "args": { + "External id": 37491,"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": 4183437, "tid": 31318, + "ts": 658972381190.187, "dur": 0.679, + "args": { + "External id": 37492,"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": 4183437, "tid": 31318, + "ts": 658972381194.877, "dur": 3.860, + "args": { + "External id": 37493,"Record function id": 0, "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972381196.232, "dur": 2.068, + "args": { + "External id": 37494,"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": 4183437, "tid": 31318, + "ts": 658972381196.826, "dur": 1.043, + "args": { + "External id": 37495,"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": 4183437, "tid": 31318, + "ts": 658972381197.179, "dur": 0.624, + "args": { + "External id": 37496,"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": 4183437, "tid": 31318, + "ts": 658972381201.824, "dur": 3.381, + "args": { + "External id": 37497,"Record function id": 0, "Ev Idx": 4216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972381203.006, "dur": 1.760, + "args": { + "External id": 37498,"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": 4183437, "tid": 31318, + "ts": 658972381203.464, "dur": 0.883, + "args": { + "External id": 37499,"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": 4183437, "tid": 31318, + "ts": 658972381203.802, "dur": 0.477, + "args": { + "External id": 37500,"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": 4183437, "tid": 31318, + "ts": 658972381208.346, "dur": 3.447, + "args": { + "External id": 37501,"Record function id": 0, "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972381209.399, "dur": 1.968, + "args": { + "External id": 37502,"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": 4183437, "tid": 31318, + "ts": 658972381209.958, "dur": 1.005, + "args": { + "External id": 37503,"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": 4183437, "tid": 31318, + "ts": 658972381210.456, "dur": 0.439, + "args": { + "External id": 37504,"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": 4183437, "tid": 31318, + "ts": 658972381214.806, "dur": 4.086, + "args": { + "External id": 37505,"Record function id": 0, "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972381215.853, "dur": 2.619, + "args": { + "External id": 37506,"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": 4183437, "tid": 31318, + "ts": 658972381216.335, "dur": 1.709, + "args": { + "External id": 37507,"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": 4183437, "tid": 31318, + "ts": 658972381216.927, "dur": 1.055, + "args": { + "External id": 37508,"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": 4183437, "tid": 31318, + "ts": 658972381221.820, "dur": 6.823, + "args": { + "External id": 37509,"Record function id": 0, "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972381222.825, "dur": 5.379, + "args": { + "External id": 37510,"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": 4183437, "tid": 31318, + "ts": 658972381226.532, "dur": 1.251, + "args": { + "External id": 37511,"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": 4183437, "tid": 31318, + "ts": 658972381227.037, "dur": 0.681, + "args": { + "External id": 37512,"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": 4183437, "tid": 31318, + "ts": 658972381232.492, "dur": 14841.691, + "args": { + "External id": 37513,"Record function id": 0, "Sequence number": 459893, "Fwd thread id": 1, "Ev Idx": 4232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972381233.645, "dur": 14832.179, + "args": { + "External id": 37514,"Sequence number": 459893, "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": 4183437, "tid": 31318, "ts": 658972381233.645, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 4183437, "tid": 31318, + "ts": 658972381261.259, "dur": 53.062, + "args": { + "External id": 37515,"Record function id": 0, "Ev Idx": 4234 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 4183437, "tid": 31318, + "ts": 658972381322.963, "dur": 63.826, + "args": { + "External id": 37516,"Record function id": 0, "Ev Idx": 4235 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 4183437, "tid": 31318, + "ts": 658972381392.663, "dur": 14665.807, + "args": { + "External id": 37517,"Record function id": 0, "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972381480.053, "dur": 7.511, + "args": { + "External id": 37518,"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": 4183437, "tid": 31318, + "ts": 658972381497.433, "dur": 4.768, + "args": { + "External id": 37519,"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": 4183437, "tid": 31318, + "ts": 658972381515.888, "dur": 13880.074, + "args": { + "External id": 37520,"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": 4183437, "tid": 31318, + "ts": 658972381528.737, "dur": 13859.553, + "args": { + "External id": 37521,"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": 4183437, "tid": 31318, + "ts": 658972381558.295, "dur": 13.789, + "args": { + "External id": 37522,"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": 4183437, "tid": 31318, + "ts": 658972381577.121, "dur": 13776.696, + "args": { + "External id": 37523,"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": 4183437, "tid": 31318, + "ts": 658972381579.504, "dur": 13773.476, + "args": { + "External id": 37524,"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": 4183437, "tid": 31318, + "ts": 658972381583.173, "dur": 4.460, + "args": { + "External id": 37525,"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": 4183437, "tid": 31318, + "ts": 658972381589.241, "dur": 13760.225, + "args": { + "External id": 37526,"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": 4183437, "tid": 31318, + "ts": 658972395481.779, "dur": 9.703, + "args": { + "External id": 37527,"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": 4183437, "tid": 31318, + "ts": 658972395484.542, "dur": 6.559, + "args": { + "External id": 37528,"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": 4183437, "tid": 31318, + "ts": 658972395517.770, "dur": 280.257, + "args": { + "External id": 37529,"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": 4183437, "tid": 31318, + "ts": 658972395540.727, "dur": 252.139, + "args": { + "External id": 37530,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972395551.048, "dur": 236.867, + "args": { + "External id": 37531,"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": 4183437, "tid": 31318, + "ts": 658972395815.207, "dur": 2.009, + "args": { + "External id": 37532,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972395869.539, "dur": 6.312, + "args": { + "External id": 37533,"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": 4183437, "tid": 31318, + "ts": 658972395918.303, "dur": 1.137, + "args": { + "External id": 37534,"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": 4183437, "tid": 31318, + "ts": 658972395934.104, "dur": 1.309, + "args": { + "External id": 37535,"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": 4183437, "tid": 31318, + "ts": 658972395947.500, "dur": 1.154, + "args": { + "External id": 37536,"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": 4183437, "tid": 31318, + "ts": 658972395958.329, "dur": 1.141, + "args": { + "External id": 37537,"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": 4183437, "tid": 31318, + "ts": 658972395968.999, "dur": 1.095, + "args": { + "External id": 37538,"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": 4183437, "tid": 31318, + "ts": 658972395979.460, "dur": 0.800, + "args": { + "External id": 37539,"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": 4183437, "tid": 31318, + "ts": 658972395989.700, "dur": 1.357, + "args": { + "External id": 37540,"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": 4183437, "tid": 31318, + "ts": 658972395999.200, "dur": 1.374, + "args": { + "External id": 37541,"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": 4183437, "tid": 31318, + "ts": 658972396086.867, "dur": 2546.540, + "args": { + "External id": 37542,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 4183437, "tid": 31318, + "ts": 658972396105.067, "dur": 953.467, + "args": { + "External id": 37543,"Record function id": 0, "Ev Idx": 4262 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 4183437, "tid": 31318, + "ts": 658972396119.782, "dur": 307.263, + "args": { + "External id": 37544,"Record function id": 0, "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972396196.387, "dur": 4.174, + "args": { + "External id": 37545,"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": 4183437, "tid": 31318, + "ts": 658972396203.778, "dur": 0.944, + "args": { + "External id": 37546,"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": 4183437, "tid": 31318, + "ts": 658972396206.504, "dur": 0.958, + "args": { + "External id": 37547,"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": 4183437, "tid": 31318, + "ts": 658972396208.886, "dur": 0.690, + "args": { + "External id": 37548,"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": 4183437, "tid": 31318, + "ts": 658972396210.744, "dur": 0.674, + "args": { + "External id": 37549,"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": 4183437, "tid": 31318, + "ts": 658972396212.696, "dur": 0.815, + "args": { + "External id": 37550,"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": 4183437, "tid": 31318, + "ts": 658972396214.900, "dur": 0.853, + "args": { + "External id": 37551,"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": 4183437, "tid": 31318, + "ts": 658972396217.055, "dur": 1.004, + "args": { + "External id": 37552,"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": 4183437, "tid": 31318, + "ts": 658972396219.503, "dur": 1.256, + "args": { + "External id": 37553,"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": 4183437, "tid": 31318, + "ts": 658972396222.341, "dur": 0.912, + "args": { + "External id": 37554,"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": 4183437, "tid": 31318, + "ts": 658972396239.717, "dur": 156.935, + "args": { + "External id": 37555,"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": 4183437, "tid": 31318, + "ts": 658972396255.525, "dur": 136.794, + "args": { + "External id": 37556,"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": 4183437, "tid": 31318, + "ts": 658972396285.458, "dur": 14.364, + "args": { + "External id": 37557,"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": 4183437, "tid": 31318, + "ts": 658972396303.024, "dur": 61.468, + "args": { + "External id": 37558,"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": 4183437, "tid": 31318, + "ts": 658972396305.628, "dur": 58.539, + "args": { + "External id": 37559,"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": 4183437, "tid": 31318, + "ts": 658972396309.115, "dur": 5.494, + "args": { + "External id": 37560,"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": 4183437, "tid": 31318, + "ts": 658972396317.236, "dur": 46.211, + "args": { + "External id": 37561,"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": 4183437, "tid": 31318, + "ts": 658972396508.178, "dur": 543.071, + "args": { + "External id": 37562,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 4183437, "tid": 31318, + "ts": 658972396523.426, "dur": 516.680, + "args": { + "External id": 37563,"Record function id": 0, "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972396585.048, "dur": 4.544, + "args": { + "External id": 37564,"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": 4183437, "tid": 31318, + "ts": 658972396604.064, "dur": 21.233, + "args": { + "External id": 37565,"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": 4183437, "tid": 31318, + "ts": 658972396608.216, "dur": 1.454, + "args": { + "External id": 37566,"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": 4183437, "tid": 31318, + "ts": 658972396611.402, "dur": 0.713, + "args": { + "External id": 37567,"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": 4183437, "tid": 31318, + "ts": 658972396613.274, "dur": 0.599, + "args": { + "External id": 37568,"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": 4183437, "tid": 31318, + "ts": 658972396614.783, "dur": 0.419, + "args": { + "External id": 37569,"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": 4183437, "tid": 31318, + "ts": 658972396616.092, "dur": 0.698, + "args": { + "External id": 37570,"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": 4183437, "tid": 31318, + "ts": 658972396617.944, "dur": 0.439, + "args": { + "External id": 37571,"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": 4183437, "tid": 31318, + "ts": 658972396619.073, "dur": 0.177, + "args": { + "External id": 37572,"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": 4183437, "tid": 31318, + "ts": 658972396620.022, "dur": 0.668, + "args": { + "External id": 37573,"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": 4183437, "tid": 31318, + "ts": 658972396621.860, "dur": 0.360, + "args": { + "External id": 37574,"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": 4183437, "tid": 31318, + "ts": 658972396635.440, "dur": 69.684, + "args": { + "External id": 37575,"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": 4183437, "tid": 31318, + "ts": 658972396740.089, "dur": 96.332, + "args": { + "External id": 37576,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 31318, + "ts": 658972396750.654, "dur": 4.340, + "args": { + "External id": 37577,"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": 4183437, "tid": 31318, + "ts": 658972396759.560, "dur": 10.021, + "args": { + "External id": 37578,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 31318, + "ts": 658972396763.435, "dur": 5.729, + "args": { + "External id": 37579,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 31318, + "ts": 658972396766.584, "dur": 1.099, + "args": { + "External id": 37580,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972396776.270, "dur": 21.595, + "args": { + "External id": 37581,"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": 4183437, "tid": 31318, + "ts": 658972396778.411, "dur": 0.441, + "args": { + "External id": 37582,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 31318, + "ts": 658972396780.059, "dur": 1.001, + "args": { + "External id": 37583,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 31318, + "ts": 658972396782.480, "dur": 0.683, + "args": { + "External id": 37584,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 31318, + "ts": 658972396784.065, "dur": 0.200, + "args": { + "External id": 37585,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 31318, + "ts": 658972396784.923, "dur": 0.716, + "args": { + "External id": 37586,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 31318, + "ts": 658972396786.289, "dur": 0.439, + "args": { + "External id": 37587,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 31318, + "ts": 658972396787.463, "dur": 0.758, + "args": { + "External id": 37588,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 31318, + "ts": 658972396789.090, "dur": 0.764, + "args": { + "External id": 37589,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 31318, + "ts": 658972396791.174, "dur": 0.814, + "args": { + "External id": 37590,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 31318, + "ts": 658972396807.424, "dur": 21.343, + "args": { + "External id": 37591,"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": 4183437, "tid": 31318, + "ts": 658972396881.059, "dur": 99.527, + "args": { + "External id": 37592,"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": 4183437, "tid": 31318, + "ts": 658972396900.526, "dur": 76.413, + "args": { + "External id": 37593,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972396909.428, "dur": 63.757, + "args": { + "External id": 37594,"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": 4183437, "tid": 31318, + "ts": 658972396992.681, "dur": 1.724, + "args": { + "External id": 37595,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972397065.969, "dur": 1545.626, + "args": { + "External id": 37596,"Sequence number": 459892, "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": 4183437, "tid": 31318, "ts": 658972397065.969, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972397175.940, "dur": 119.881, + "args": { + "External id": 37597,"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": 4183437, "tid": 31318, + "ts": 658972397334.262, "dur": 40.607, + "args": { + "External id": 37598,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972397392.273, "dur": 44.061, + "args": { + "External id": 37599,"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": 4183437, "tid": 31318, + "ts": 658972397445.721, "dur": 27.061, + "args": { + "External id": 37600,"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": 4183437, "tid": 31318, + "ts": 658972397479.021, "dur": 36.563, + "args": { + "External id": 37601,"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": 4183437, "tid": 31318, + "ts": 658972397522.246, "dur": 21.639, + "args": { + "External id": 37602,"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": 4183437, "tid": 31318, + "ts": 658972397553.523, "dur": 28.756, + "args": { + "External id": 37603,"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": 4183437, "tid": 31318, + "ts": 658972397602.612, "dur": 25.393, + "args": { + "External id": 37604,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972397643.763, "dur": 69.638, + "args": { + "External id": 37605,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972397734.058, "dur": 23.457, + "args": { + "External id": 37606,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972397769.088, "dur": 14.358, + "args": { + "External id": 37607,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972397791.634, "dur": 43.845, + "args": { + "External id": 37608,"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": 4183437, "tid": 31318, + "ts": 658972397838.823, "dur": 33.308, + "args": { + "External id": 37609,"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": 4183437, "tid": 31318, + "ts": 658972397898.685, "dur": 168.654, + "args": { + "External id": 37610,"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": 4183437, "tid": 31318, + "ts": 658972397978.559, "dur": 5.839, + "args": { + "External id": 37611,"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": 4183437, "tid": 31318, + "ts": 658972397986.208, "dur": 2.856, + "args": { + "External id": 37612,"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": 4183437, "tid": 31318, + "ts": 658972398097.624, "dur": 22.197, + "args": { + "External id": 37613,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972398130.330, "dur": 13.912, + "args": { + "External id": 37614,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972398152.075, "dur": 42.740, + "args": { + "External id": 37615,"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": 4183437, "tid": 31318, + "ts": 658972398200.245, "dur": 30.606, + "args": { + "External id": 37616,"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": 4183437, "tid": 31318, + "ts": 658972398237.169, "dur": 45.952, + "args": { + "External id": 37617,"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": 4183437, "tid": 31318, + "ts": 658972398292.678, "dur": 32.182, + "args": { + "External id": 37618,"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": 4183437, "tid": 31318, + "ts": 658972398330.973, "dur": 26.682, + "args": { + "External id": 37619,"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": 4183437, "tid": 31318, + "ts": 658972398364.744, "dur": 29.210, + "args": { + "External id": 37620,"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": 4183437, "tid": 31318, + "ts": 658972398409.529, "dur": 21.733, + "args": { + "External id": 37621,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972398450.754, "dur": 22.341, + "args": { + "External id": 37622,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972398486.597, "dur": 15.781, + "args": { + "External id": 37623,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972398526.228, "dur": 22.353, + "args": { + "External id": 37624,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972398564.617, "dur": 17.998, + "args": { + "External id": 37625,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972398696.377, "dur": 18.079, + "args": { + "External id": 37626,"Record function id": 0, "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972398700.886, "dur": 12.347, + "args": { + "External id": 37627,"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": 4183437, "tid": 31318, + "ts": 658972398705.210, "dur": 6.800, + "args": { + "External id": 37628,"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": 4183437, "tid": 31318, + "ts": 658972398706.920, "dur": 4.844, + "args": { + "External id": 37629,"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": 4183437, "tid": 31318, + "ts": 658972398719.595, "dur": 4.850, + "args": { + "External id": 37630,"Record function id": 0, "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972398721.040, "dur": 2.975, + "args": { + "External id": 37631,"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": 4183437, "tid": 31318, + "ts": 658972398722.013, "dur": 1.540, + "args": { + "External id": 37632,"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": 4183437, "tid": 31318, + "ts": 658972398722.666, "dur": 0.822, + "args": { + "External id": 37633,"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": 4183437, "tid": 31318, + "ts": 658972398727.752, "dur": 4.154, + "args": { + "External id": 37634,"Record function id": 0, "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972398728.888, "dur": 2.514, + "args": { + "External id": 37635,"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": 4183437, "tid": 31318, + "ts": 658972398729.425, "dur": 1.559, + "args": { + "External id": 37636,"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": 4183437, "tid": 31318, + "ts": 658972398730.167, "dur": 0.750, + "args": { + "External id": 37637,"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": 4183437, "tid": 31318, + "ts": 658972398735.034, "dur": 3.921, + "args": { + "External id": 37638,"Record function id": 0, "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972398736.115, "dur": 2.430, + "args": { + "External id": 37639,"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": 4183437, "tid": 31318, + "ts": 658972398737.015, "dur": 1.113, + "args": { + "External id": 37640,"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": 4183437, "tid": 31318, + "ts": 658972398737.552, "dur": 0.502, + "args": { + "External id": 37641,"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": 4183437, "tid": 31318, + "ts": 658972398742.017, "dur": 3.749, + "args": { + "External id": 37642,"Record function id": 0, "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972398743.110, "dur": 2.211, + "args": { + "External id": 37643,"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": 4183437, "tid": 31318, + "ts": 658972398743.601, "dur": 1.276, + "args": { + "External id": 37644,"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": 4183437, "tid": 31318, + "ts": 658972398744.124, "dur": 0.689, + "args": { + "External id": 37645,"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": 4183437, "tid": 31318, + "ts": 658972398751.946, "dur": 5.270, + "args": { + "External id": 37646,"Record function id": 0, "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972398753.543, "dur": 3.193, + "args": { + "External id": 37647,"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": 4183437, "tid": 31318, + "ts": 658972398754.363, "dur": 1.877, + "args": { + "External id": 37648,"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": 4183437, "tid": 31318, + "ts": 658972398755.280, "dur": 0.895, + "args": { + "External id": 37649,"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": 4183437, "tid": 31318, + "ts": 658972398760.443, "dur": 4.101, + "args": { + "External id": 37650,"Record function id": 0, "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972398761.648, "dur": 2.458, + "args": { + "External id": 37651,"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": 4183437, "tid": 31318, + "ts": 658972398762.189, "dur": 1.505, + "args": { + "External id": 37652,"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": 4183437, "tid": 31318, + "ts": 658972398762.977, "dur": 0.655, + "args": { + "External id": 37653,"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": 4183437, "tid": 31318, + "ts": 658972398767.570, "dur": 3.935, + "args": { + "External id": 37654,"Record function id": 0, "Ev Idx": 4373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972398768.697, "dur": 2.368, + "args": { + "External id": 37655,"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": 4183437, "tid": 31318, + "ts": 658972398769.405, "dur": 1.227, + "args": { + "External id": 37656,"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": 4183437, "tid": 31318, + "ts": 658972398769.919, "dur": 0.649, + "args": { + "External id": 37657,"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": 4183437, "tid": 31318, + "ts": 658972398774.691, "dur": 3.075, + "args": { + "External id": 37658,"Record function id": 0, "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972398775.599, "dur": 1.733, + "args": { + "External id": 37659,"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": 4183437, "tid": 31318, + "ts": 658972398776.092, "dur": 0.820, + "args": { + "External id": 37660,"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": 4183437, "tid": 31318, + "ts": 658972398776.381, "dur": 0.467, + "args": { + "External id": 37661,"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": 4183437, "tid": 31318, + "ts": 658972398782.030, "dur": 14917.647, + "args": { + "External id": 37662,"Record function id": 0, "Sequence number": 459891, "Fwd thread id": 1, "Ev Idx": 4381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972398783.165, "dur": 14861.443, + "args": { + "External id": 37663,"Sequence number": 459891, "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": 4183437, "tid": 31318, "ts": 658972398783.165, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 4183437, "tid": 31318, + "ts": 658972398812.383, "dur": 34.694, + "args": { + "External id": 37664,"Record function id": 0, "Ev Idx": 4383 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 4183437, "tid": 31318, + "ts": 658972398854.784, "dur": 64.821, + "args": { + "External id": 37665,"Record function id": 0, "Ev Idx": 4384 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 4183437, "tid": 31318, + "ts": 658972398925.216, "dur": 14711.732, + "args": { + "External id": 37666,"Record function id": 0, "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972399011.679, "dur": 8.007, + "args": { + "External id": 37667,"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": 4183437, "tid": 31318, + "ts": 658972399028.912, "dur": 4.800, + "args": { + "External id": 37668,"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": 4183437, "tid": 31318, + "ts": 658972399047.387, "dur": 13935.679, + "args": { + "External id": 37669,"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": 4183437, "tid": 31318, + "ts": 658972399060.463, "dur": 13914.615, + "args": { + "External id": 37670,"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": 4183437, "tid": 31318, + "ts": 658972399085.617, "dur": 13.689, + "args": { + "External id": 37671,"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": 4183437, "tid": 31318, + "ts": 658972399104.344, "dur": 13837.106, + "args": { + "External id": 37672,"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": 4183437, "tid": 31318, + "ts": 658972399107.060, "dur": 13833.817, + "args": { + "External id": 37673,"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": 4183437, "tid": 31318, + "ts": 658972399110.466, "dur": 5.103, + "args": { + "External id": 37674,"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": 4183437, "tid": 31318, + "ts": 658972399117.333, "dur": 13820.166, + "args": { + "External id": 37675,"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": 4183437, "tid": 31318, + "ts": 658972413070.076, "dur": 9.881, + "args": { + "External id": 37676,"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": 4183437, "tid": 31318, + "ts": 658972413073.004, "dur": 6.539, + "args": { + "External id": 37677,"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": 4183437, "tid": 31318, + "ts": 658972413104.527, "dur": 266.840, + "args": { + "External id": 37678,"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": 4183437, "tid": 31318, + "ts": 658972413127.218, "dur": 239.423, + "args": { + "External id": 37679,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972413138.115, "dur": 223.658, + "args": { + "External id": 37680,"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": 4183437, "tid": 31318, + "ts": 658972413388.099, "dur": 2.031, + "args": { + "External id": 37681,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972413443.495, "dur": 5.792, + "args": { + "External id": 37682,"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": 4183437, "tid": 31318, + "ts": 658972413492.688, "dur": 1.453, + "args": { + "External id": 37683,"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": 4183437, "tid": 31318, + "ts": 658972413508.317, "dur": 1.376, + "args": { + "External id": 37684,"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": 4183437, "tid": 31318, + "ts": 658972413521.017, "dur": 1.018, + "args": { + "External id": 37685,"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": 4183437, "tid": 31318, + "ts": 658972413532.745, "dur": 0.918, + "args": { + "External id": 37686,"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": 4183437, "tid": 31318, + "ts": 658972413543.285, "dur": 1.135, + "args": { + "External id": 37687,"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": 4183437, "tid": 31318, + "ts": 658972413555.037, "dur": 1.456, + "args": { + "External id": 37688,"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": 4183437, "tid": 31318, + "ts": 658972413566.732, "dur": 0.913, + "args": { + "External id": 37689,"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": 4183437, "tid": 31318, + "ts": 658972413577.199, "dur": 1.274, + "args": { + "External id": 37690,"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": 4183437, "tid": 31318, + "ts": 658972413716.018, "dur": 1918.374, + "args": { + "External id": 37691,"Record function id": 0, "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 4183437, "tid": 31318, + "ts": 658972413739.273, "dur": 409.370, + "args": { + "External id": 37692,"Record function id": 0, "Ev Idx": 4411 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 4183437, "tid": 31318, + "ts": 658972413755.192, "dur": 297.224, + "args": { + "External id": 37693,"Record function id": 0, "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 31318, + "ts": 658972413842.163, "dur": 5.165, + "args": { + "External id": 37694,"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": 4183437, "tid": 31318, + "ts": 658972413851.003, "dur": 1.178, + "args": { + "External id": 37695,"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": 4183437, "tid": 31318, + "ts": 658972413854.093, "dur": 0.709, + "args": { + "External id": 37696,"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": 4183437, "tid": 31318, + "ts": 658972413856.140, "dur": 1.055, + "args": { + "External id": 37697,"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": 4183437, "tid": 31318, + "ts": 658972413858.674, "dur": 1.001, + "args": { + "External id": 37698,"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": 4183437, "tid": 31318, + "ts": 658972413861.290, "dur": 0.883, + "args": { + "External id": 37699,"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": 4183437, "tid": 31318, + "ts": 658972413863.783, "dur": 1.778, + "args": { + "External id": 37700,"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": 4183437, "tid": 31318, + "ts": 658972413867.054, "dur": 0.925, + "args": { + "External id": 37701,"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": 4183437, "tid": 31318, + "ts": 658972413869.321, "dur": 0.885, + "args": { + "External id": 37702,"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": 4183437, "tid": 31318, + "ts": 658972413871.634, "dur": 1.111, + "args": { + "External id": 37703,"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": 4183437, "tid": 31318, + "ts": 658972413889.197, "dur": 135.473, + "args": { + "External id": 37704,"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": 4183437, "tid": 31318, + "ts": 658972413905.396, "dur": 114.787, + "args": { + "External id": 37705,"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": 4183437, "tid": 31318, + "ts": 658972413917.167, "dur": 13.822, + "args": { + "External id": 37706,"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": 4183437, "tid": 31318, + "ts": 658972413933.693, "dur": 60.904, + "args": { + "External id": 37707,"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": 4183437, "tid": 31318, + "ts": 658972413936.556, "dur": 57.720, + "args": { + "External id": 37708,"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": 4183437, "tid": 31318, + "ts": 658972413940.050, "dur": 5.237, + "args": { + "External id": 37709,"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": 4183437, "tid": 31318, + "ts": 658972413946.890, "dur": 46.802, + "args": { + "External id": 37710,"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": 4183437, "tid": 31318, + "ts": 658972414155.269, "dur": 1458.515, + "args": { + "External id": 37711,"Sequence number": 459890, "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": 4183437, "tid": 31318, "ts": 658972414155.269, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 31318, + "ts": 658972414258.354, "dur": 116.740, + "args": { + "External id": 37712,"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": 4183437, "tid": 31318, + "ts": 658972414413.321, "dur": 38.497, + "args": { + "External id": 37713,"kernel_hash": "cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/mk/cmkeq4u5pisavuq2t7jgazatkrnieso6aqoamzahj5m3d6ifj3pb.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": 4183437, "tid": 31318, + "ts": 658972414468.694, "dur": 38.559, + "args": { + "External id": 37714,"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": 4183437, "tid": 31318, + "ts": 658972414515.520, "dur": 25.058, + "args": { + "External id": 37715,"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": 4183437, "tid": 31318, + "ts": 658972414546.655, "dur": 32.275, + "args": { + "External id": 37716,"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": 4183437, "tid": 31318, + "ts": 658972414585.272, "dur": 19.983, + "args": { + "External id": 37717,"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": 4183437, "tid": 31318, + "ts": 658972414612.497, "dur": 28.634, + "args": { + "External id": 37718,"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": 4183437, "tid": 31318, + "ts": 658972414701.888, "dur": 25.482, + "args": { + "External id": 37719,"kernel_hash": "cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/av/cav7qgx57xbavc6ssdhawospuahypfd4solvi2voaw5noe5weu4r.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": 4183437, "tid": 31318, + "ts": 658972414745.209, "dur": 26.758, + "args": { + "External id": 37720,"kernel_hash": "cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab", "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/dp/cdpn7rrycputverjz46ghiihs3stytwago5d5stbpivsr4f7asab.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": 4183437, "tid": 31318, + "ts": 658972414791.597, "dur": 18.621, + "args": { + "External id": 37721,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972414821.367, "dur": 15.336, + "args": { + "External id": 37722,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972414844.881, "dur": 41.150, + "args": { + "External id": 37723,"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": 4183437, "tid": 31318, + "ts": 658972414889.277, "dur": 30.742, + "args": { + "External id": 37724,"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": 4183437, "tid": 31318, + "ts": 658972414944.716, "dur": 167.250, + "args": { + "External id": 37725,"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": 4183437, "tid": 31318, + "ts": 658972415019.881, "dur": 6.553, + "args": { + "External id": 37726,"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": 4183437, "tid": 31318, + "ts": 658972415028.840, "dur": 2.677, + "args": { + "External id": 37727,"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": 4183437, "tid": 31318, + "ts": 658972415140.763, "dur": 24.596, + "args": { + "External id": 37728,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972415175.825, "dur": 15.005, + "args": { + "External id": 37729,"kernel_hash": "c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr", "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/4r/c4rx5antfp5u3c4pevhcbphzk2vpvoqjihguxnwf4btawsr5qemr.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": 4183437, "tid": 31318, + "ts": 658972415197.367, "dur": 40.202, + "args": { + "External id": 37730,"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": 4183437, "tid": 31318, + "ts": 658972415243.071, "dur": 45.999, + "args": { + "External id": 37731,"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": 4183437, "tid": 31318, + "ts": 658972415298.036, "dur": 31.047, + "args": { + "External id": 37732,"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": 4183437, "tid": 31318, + "ts": 658972415334.078, "dur": 28.134, + "args": { + "External id": 37733,"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": 4183437, "tid": 31318, + "ts": 658972415367.567, "dur": 27.106, + "args": { + "External id": 37734,"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": 4183437, "tid": 31318, + "ts": 658972415401.468, "dur": 27.295, + "args": { + "External id": 37735,"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": 4183437, "tid": 31318, + "ts": 658972415445.057, "dur": 23.315, + "args": { + "External id": 37736,"kernel_hash": "cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/ge/cgenyd3uslzu7odb2niq6o7wueb7jv5hiaj6wfn3bbislzkkxy3o.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": 4183437, "tid": 31318, + "ts": 658972415484.715, "dur": 24.000, + "args": { + "External id": 37737,"kernel_hash": "cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl", "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/r3/cr3xaaheqtqbxxoqp2csdm7scsofalg3wxjfri4mfi25uwllugrl.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": 4183437, "tid": 31318, + "ts": 658972415521.849, "dur": 15.706, + "args": { + "External id": 37738,"kernel_hash": "crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/ra/crascjkuvp5ihrdhcw3ozvc35kzdfmymcyhon4rem5klok7xhhbz.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": 4183437, "tid": 31318, + "ts": 658972415550.090, "dur": 13.155, + "args": { + "External id": 37739,"kernel_hash": "clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/lr/clrc6m7yd5lwsewwt3ekhxcarerttixuy3btf2brvn2bxg7u6vu2.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": 4183437, "tid": 31318, + "ts": 658972415572.726, "dur": 14.138, + "args": { + "External id": 37740,"kernel_hash": "crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rn/crnmasehmuoss525mx7jbflssxoydyirub5eljveqs3zu4dmxsd6.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": 4183437, "tid": 31318, + "ts": 658972415691.979, "dur": 18.327, + "args": { + "External id": 37741,"Record function id": 0, "Ev Idx": 4460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972415696.701, "dur": 12.243, + "args": { + "External id": 37742,"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": 4183437, "tid": 31318, + "ts": 658972415701.299, "dur": 6.296, + "args": { + "External id": 37743,"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": 4183437, "tid": 31318, + "ts": 658972415702.755, "dur": 4.575, + "args": { + "External id": 37744,"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": 4183437, "tid": 31318, + "ts": 658972415715.599, "dur": 8.158, + "args": { + "External id": 37745,"Record function id": 0, "Ev Idx": 4464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972415720.356, "dur": 2.956, + "args": { + "External id": 37746,"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": 4183437, "tid": 31318, + "ts": 658972415721.093, "dur": 1.759, + "args": { + "External id": 37747,"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": 4183437, "tid": 31318, + "ts": 658972415721.764, "dur": 1.022, + "args": { + "External id": 37748,"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": 4183437, "tid": 31318, + "ts": 658972415727.232, "dur": 5.266, + "args": { + "External id": 37749,"Record function id": 0, "Ev Idx": 4468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972415729.036, "dur": 2.994, + "args": { + "External id": 37750,"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": 4183437, "tid": 31318, + "ts": 658972415729.532, "dur": 1.879, + "args": { + "External id": 37751,"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": 4183437, "tid": 31318, + "ts": 658972415730.388, "dur": 0.944, + "args": { + "External id": 37752,"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": 4183437, "tid": 31318, + "ts": 658972415735.622, "dur": 4.306, + "args": { + "External id": 37753,"Record function id": 0, "Ev Idx": 4472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972415737.228, "dur": 2.286, + "args": { + "External id": 37754,"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": 4183437, "tid": 31318, + "ts": 658972415737.963, "dur": 1.093, + "args": { + "External id": 37755,"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": 4183437, "tid": 31318, + "ts": 658972415738.368, "dur": 0.620, + "args": { + "External id": 37756,"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": 4183437, "tid": 31318, + "ts": 658972415742.983, "dur": 3.641, + "args": { + "External id": 37757,"Record function id": 0, "Ev Idx": 4476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972415744.267, "dur": 1.876, + "args": { + "External id": 37758,"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": 4183437, "tid": 31318, + "ts": 658972415744.742, "dur": 0.968, + "args": { + "External id": 37759,"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": 4183437, "tid": 31318, + "ts": 658972415745.116, "dur": 0.528, + "args": { + "External id": 37760,"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": 4183437, "tid": 31318, + "ts": 658972415749.619, "dur": 3.567, + "args": { + "External id": 37761,"Record function id": 0, "Ev Idx": 4480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972415750.922, "dur": 1.837, + "args": { + "External id": 37762,"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": 4183437, "tid": 31318, + "ts": 658972415751.433, "dur": 0.903, + "args": { + "External id": 37763,"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": 4183437, "tid": 31318, + "ts": 658972415751.842, "dur": 0.429, + "args": { + "External id": 37764,"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": 4183437, "tid": 31318, + "ts": 658972415756.220, "dur": 3.437, + "args": { + "External id": 37765,"Record function id": 0, "Ev Idx": 4484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972415757.464, "dur": 1.769, + "args": { + "External id": 37766,"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": 4183437, "tid": 31318, + "ts": 658972415757.965, "dur": 0.830, + "args": { + "External id": 37767,"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": 4183437, "tid": 31318, + "ts": 658972415758.278, "dur": 0.454, + "args": { + "External id": 37768,"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": 4183437, "tid": 31318, + "ts": 658972415762.649, "dur": 3.986, + "args": { + "External id": 37769,"Record function id": 0, "Ev Idx": 4488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972415764.067, "dur": 2.156, + "args": { + "External id": 37770,"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": 4183437, "tid": 31318, + "ts": 658972415764.560, "dur": 1.233, + "args": { + "External id": 37771,"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": 4183437, "tid": 31318, + "ts": 658972415764.924, "dur": 0.805, + "args": { + "External id": 37772,"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": 4183437, "tid": 31318, + "ts": 658972415769.709, "dur": 3.734, + "args": { + "External id": 37773,"Record function id": 0, "Ev Idx": 4492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972415770.803, "dur": 2.205, + "args": { + "External id": 37774,"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": 4183437, "tid": 31318, + "ts": 658972415771.266, "dur": 1.312, + "args": { + "External id": 37775,"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": 4183437, "tid": 31318, + "ts": 658972415771.867, "dur": 0.642, + "args": { + "External id": 37776,"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": 4183437, "tid": 31318, + "ts": 658972415780.476, "dur": 15683.191, + "args": { + "External id": 37777,"Record function id": 0, "Sequence number": 459889, "Fwd thread id": 1, "Ev Idx": 4496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972415781.728, "dur": 15673.469, + "args": { + "External id": 37778,"Sequence number": 459889, "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": 4183437, "tid": 31318, "ts": 658972415781.728, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 4183437, "tid": 31318, + "ts": 658972415811.545, "dur": 39.109, + "args": { + "External id": 37779,"Record function id": 0, "Ev Idx": 4498 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 4183437, "tid": 31318, + "ts": 658972415857.594, "dur": 71.812, + "args": { + "External id": 37780,"Record function id": 0, "Ev Idx": 4499 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 4183437, "tid": 31318, + "ts": 658972415935.201, "dur": 15512.641, + "args": { + "External id": 37781,"Record function id": 0, "Ev Idx": 4500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972416029.365, "dur": 6.976, + "args": { + "External id": 37782,"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": 4183437, "tid": 31318, + "ts": 658972416045.738, "dur": 5.023, + "args": { + "External id": 37783,"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": 4183437, "tid": 31318, + "ts": 658972416064.847, "dur": 14727.112, + "args": { + "External id": 37784,"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": 4183437, "tid": 31318, + "ts": 658972416082.518, "dur": 14700.468, + "args": { + "External id": 37785,"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": 4183437, "tid": 31318, + "ts": 658972416111.894, "dur": 19.294, + "args": { + "External id": 37786,"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": 4183437, "tid": 31318, + "ts": 658972416136.749, "dur": 14611.431, + "args": { + "External id": 37787,"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": 4183437, "tid": 31318, + "ts": 658972416139.267, "dur": 14608.208, + "args": { + "External id": 37788,"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": 4183437, "tid": 31318, + "ts": 658972416142.889, "dur": 6.944, + "args": { + "External id": 37789,"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": 4183437, "tid": 31318, + "ts": 658972416151.375, "dur": 14593.294, + "args": { + "External id": 37790,"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": 4183437, "tid": 31318, + "ts": 658972430879.221, "dur": 9.641, + "args": { + "External id": 37791,"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": 4183437, "tid": 31318, + "ts": 658972430882.077, "dur": 6.399, + "args": { + "External id": 37792,"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": 4183437, "tid": 31318, + "ts": 658972430915.367, "dur": 253.022, + "args": { + "External id": 37793,"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": 4183437, "tid": 31318, + "ts": 658972430938.885, "dur": 225.760, + "args": { + "External id": 37794,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972430949.883, "dur": 210.143, + "args": { + "External id": 37795,"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": 4183437, "tid": 31318, + "ts": 658972431182.787, "dur": 2.089, + "args": { + "External id": 37796,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972431232.042, "dur": 6.003, + "args": { + "External id": 37797,"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": 4183437, "tid": 31318, + "ts": 658972431301.044, "dur": 2.011, + "args": { + "External id": 37798,"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": 4183437, "tid": 31318, + "ts": 658972431318.468, "dur": 2.141, + "args": { + "External id": 37799,"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": 4183437, "tid": 31318, + "ts": 658972431332.416, "dur": 0.935, + "args": { + "External id": 37800,"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": 4183437, "tid": 31318, + "ts": 658972431343.508, "dur": 0.729, + "args": { + "External id": 37801,"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": 4183437, "tid": 31318, + "ts": 658972431353.884, "dur": 0.855, + "args": { + "External id": 37802,"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": 4183437, "tid": 31318, + "ts": 658972431365.016, "dur": 0.966, + "args": { + "External id": 37803,"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": 4183437, "tid": 31318, + "ts": 658972431376.007, "dur": 0.932, + "args": { + "External id": 37804,"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": 4183437, "tid": 31318, + "ts": 658972431386.647, "dur": 0.815, + "args": { + "External id": 37805,"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": 4183437, "tid": 31318, + "ts": 658972431478.747, "dur": 302.282, + "args": { + "External id": 37806,"Record function id": 0, "Sequence number": 459888, "Fwd thread id": 1, "Ev Idx": 4525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183437, "tid": 31318, + "ts": 658972431481.591, "dur": 290.524, + "args": { + "External id": 37807,"Sequence number": 459888, "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": 4183437, "tid": 31318, "ts": 658972431481.591, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 4183437, "tid": 31318, + "ts": 658972431592.395, "dur": 42.799, + "args": { + "External id": 37808,"kernel_hash": "cotjgrudxaf32afunq4mlk3kj2pfdpgrwm4wnp4teclwrtsptuvz", "grid": "grid(32768000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "32768000"], "kernel_file": "/tmp/torchinductor_cvm/ot/cotjgrudxaf32afunq4mlk3kj2pfdpgrwm4wnp4teclwrtsptuvz.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": 4183437, "tid": 31318, + "ts": 658972431649.932, "dur": 66.498, + "args": { + "External id": 37809,"kernel_hash": "cvrih6upb6cmnqerscwgu3xs37rjvjj25oyo4jmzwkf5inz4myez", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/vr/cvrih6upb6cmnqerscwgu3xs37rjvjj25oyo4jmzwkf5inz4myez.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": 4183437, "tid": 31318, + "ts": 658972431736.332, "dur": 19.850, + "args": { + "External id": 37810,"kernel_hash": "cml7mmfjbpwuy3ek2fkd6pgkvjnqmqqop2yoqvwyiz4lt2prgof2", "grid": "grid(32768000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "32768000"], "kernel_file": "/tmp/torchinductor_cvm/ml/cml7mmfjbpwuy3ek2fkd6pgkvjnqmqqop2yoqvwyiz4lt2prgof2.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": 4183437, "tid": 31318, + "ts": 658972431792.955, "dur": 15.412, + "args": { + "External id": 37811,"Record function id": 0, "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183437, "tid": 31318, + "ts": 658972431796.829, "dur": 10.544, + "args": { + "External id": 37812,"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": 4183437, "tid": 31318, + "ts": 658972431800.839, "dur": 5.751, + "args": { + "External id": 37813,"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": 4183437, "tid": 31318, + "ts": 658972431802.375, "dur": 4.104, + "args": { + "External id": 37814,"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": 4183437, "tid": 31318, + "ts": 658972431829.821, "dur": 7790.630, + "args": { + "External id": 37815,"Record function id": 0, "Ev Idx": 4534 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 4183437, "tid": 31318, + "ts": 658972431848.900, "dur": 34.155, + "args": { + "External id": 37816,"Record function id": 0, "Ev Idx": 4535 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 4183437, "tid": 31318, + "ts": 658972431888.486, "dur": 244.179, + "args": { + "External id": 37817,"Record function id": 0, "Ev Idx": 4536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 4183437, "tid": 31318, + "ts": 658972432138.934, "dur": 7284.649, + "args": { + "External id": 37818,"Record function id": 0, "Ev Idx": 4537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 31318, + "ts": 658972432253.814, "dur": 7.841, + "args": { + "External id": 37819,"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": 4183437, "tid": 31318, + "ts": 658972432287.060, "dur": 5.349, + "args": { + "External id": 37820,"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": 4183437, "tid": 31318, + "ts": 658972432313.335, "dur": 5872.029, + "args": { + "External id": 37821,"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": 4183437, "tid": 31318, + "ts": 658972432331.547, "dur": 5843.658, + "args": { + "External id": 37822,"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": 4183437, "tid": 31318, + "ts": 658972432424.255, "dur": 12.795, + "args": { + "External id": 37823,"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": 4183437, "tid": 31318, + "ts": 658972432461.668, "dur": 5675.720, + "args": { + "External id": 37824,"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": 4183437, "tid": 31318, + "ts": 658972432464.475, "dur": 5672.134, + "args": { + "External id": 37825,"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": 4183437, "tid": 31318, + "ts": 658972432468.221, "dur": 6.998, + "args": { + "External id": 37826,"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": 4183437, "tid": 31318, + "ts": 658972432477.119, "dur": 5655.249, + "args": { + "External id": 37827,"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": 4183437, "tid": 31318, + "ts": 658972438312.569, "dur": 9.779, + "args": { + "External id": 37828,"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": 4183437, "tid": 31318, + "ts": 658972438315.593, "dur": 6.262, + "args": { + "External id": 37829,"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": 4183437, "tid": 31318, + "ts": 658972438348.981, "dur": 456.729, + "args": { + "External id": 37830,"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": 4183437, "tid": 31318, + "ts": 658972438372.438, "dur": 427.814, + "args": { + "External id": 37831,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 31318, + "ts": 658972438382.829, "dur": 412.112, + "args": { + "External id": 37832,"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": 4183437, "tid": 31318, + "ts": 658972438832.684, "dur": 2.290, + "args": { + "External id": 37833,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 31318, + "ts": 658972438896.086, "dur": 6.727, + "args": { + "External id": 37834,"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": 4183437, "tid": 31318, + "ts": 658972438944.700, "dur": 1.416, + "args": { + "External id": 37835,"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": 4183437, "tid": 31318, + "ts": 658972438960.571, "dur": 1.363, + "args": { + "External id": 37836,"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": 4183437, "tid": 31318, + "ts": 658972438974.752, "dur": 0.906, + "args": { + "External id": 37837,"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": 4183437, "tid": 31318, + "ts": 658972438985.292, "dur": 1.070, + "args": { + "External id": 37838,"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": 4183437, "tid": 31318, + "ts": 658972438997.520, "dur": 0.863, + "args": { + "External id": 37839,"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": 4183437, "tid": 31318, + "ts": 658972439007.520, "dur": 0.764, + "args": { + "External id": 37840,"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": 4183437, "tid": 31318, + "ts": 658972439018.586, "dur": 0.877, + "args": { + "External id": 37841,"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": 4183437, "tid": 31318, + "ts": 658972439030.373, "dur": 0.979, + "args": { + "External id": 37842,"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": 4183437, "tid": 31318, + "ts": 658972439041.194, "dur": 0.880, + "args": { + "External id": 37843,"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": 4183437, "tid": 31318, + "ts": 658972439051.931, "dur": 0.794, + "args": { + "External id": 37844,"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": 4183437, "tid": 31318, + "ts": 658972439062.669, "dur": 0.942, + "args": { + "External id": 37845,"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": 4183437, "tid": 31318, + "ts": 658972439072.963, "dur": 0.887, + "args": { + "External id": 37846,"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": 4183437, "tid": 31318, + "ts": 658972439083.184, "dur": 1.041, + "args": { + "External id": 37847,"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": 4183437, "tid": 31318, + "ts": 658972439093.825, "dur": 1.197, + "args": { + "External id": 37848,"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": 4183437, "tid": 31318, + "ts": 658972439105.198, "dur": 0.740, + "args": { + "External id": 37849,"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": 4183437, "tid": 31318, + "ts": 658972439115.471, "dur": 1.195, + "args": { + "External id": 37850,"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": 4183437, "tid": 31318, + "ts": 658972439127.309, "dur": 1.184, + "args": { + "External id": 37851,"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": 4183437, "tid": 31318, + "ts": 658972439138.010, "dur": 1.038, + "args": { + "External id": 37852,"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": 4183437, "tid": 31318, + "ts": 658972439148.333, "dur": 1.310, + "args": { + "External id": 37853,"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": 4183437, "tid": 31318, + "ts": 658972439158.570, "dur": 0.766, + "args": { + "External id": 37854,"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": 4183437, "tid": 31318, + "ts": 658972439169.096, "dur": 1.115, + "args": { + "External id": 37855,"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": 4183437, "tid": 31318, + "ts": 658972439179.709, "dur": 1.183, + "args": { + "External id": 37856,"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": 4183437, "tid": 31318, + "ts": 658972439190.040, "dur": 0.887, + "args": { + "External id": 37857,"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": 4183437, "tid": 31318, + "ts": 658972439199.257, "dur": 0.881, + "args": { + "External id": 37858,"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": 4183437, "tid": 31318, + "ts": 658972439209.468, "dur": 0.759, + "args": { + "External id": 37859,"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": 4183437, "tid": 31318, + "ts": 658972439219.319, "dur": 0.774, + "args": { + "External id": 37860,"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": 4183437, "tid": 31318, + "ts": 658972439229.508, "dur": 0.807, + "args": { + "External id": 37861,"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": 4183437, "tid": 31318, + "ts": 658972439239.261, "dur": 0.754, + "args": { + "External id": 37862,"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": 4183437, "tid": 31318, + "ts": 658972439249.431, "dur": 1.043, + "args": { + "External id": 37863,"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": 4183437, "tid": 31318, + "ts": 658972439260.427, "dur": 1.304, + "args": { + "External id": 37864,"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": 4183437, "tid": 31318, + "ts": 658972439288.809, "dur": 1.480, + "args": { + "External id": 37865,"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": 4183437, "tid": 31318, + "ts": 658972439300.235, "dur": 0.773, + "args": { + "External id": 37866,"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": 4183437, "tid": 31318, + "ts": 658972439310.572, "dur": 1.005, + "args": { + "External id": 37867,"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": 4183437, "tid": 31318, + "ts": 658972439321.345, "dur": 0.722, + "args": { + "External id": 37868,"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": 4183437, "tid": 31318, + "ts": 658972439331.551, "dur": 1.227, + "args": { + "External id": 37869,"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": 4183437, "tid": 31318, + "ts": 658972439341.919, "dur": 1.021, + "args": { + "External id": 37870,"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": 4183437, "tid": 31318, + "ts": 658972439352.115, "dur": 0.860, + "args": { + "External id": 37871,"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": 4183437, "tid": 31318, + "ts": 658972439362.445, "dur": 1.444, + "args": { + "External id": 37872,"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#2047", "pid": 4183437, "tid": 4183437, + "ts": 658971661444.046, "dur": 791869.047, + "args": { + "External id": 29185,"Record function id": 0, "Ev Idx": 4592 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 4183437, "tid": 4183437, + "ts": 658971661476.292, "dur": 405.763, + "args": { + "External id": 29186,"Record function id": 0, "Ev Idx": 4593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 4183437, "tid": 4183437, + "ts": 658971661921.129, "dur": 1939.854, + "args": { + "External id": 29187,"Record function id": 0, "Ev Idx": 4594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971662921.212, "dur": 7.552, + "args": { + "External id": 29188,"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": 4183437, "tid": 4183437, + "ts": 658971662947.833, "dur": 6.294, + "args": { + "External id": 29189,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971663372.334, "dur": 1.971, + "args": { + "External id": 29190,"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": 4183437, "tid": 4183437, + "ts": 658971663381.645, "dur": 2.380, + "args": { + "External id": 29191,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971663749.647, "dur": 1.819, + "args": { + "External id": 29192,"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": 4183437, "tid": 4183437, + "ts": 658971663756.895, "dur": 1.931, + "args": { + "External id": 29193,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971664256.796, "dur": 27.753, + "args": { + "External id": 29194,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971664278.101, "dur": 2.543, + "args": { + "External id": 29195,"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": 4183437, "tid": 4183437, + "ts": 658971664286.323, "dur": 4.606, + "args": { + "External id": 29196,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971664288.752, "dur": 1.054, + "args": { + "External id": 29197,"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": 4183437, "tid": 4183437, + "ts": 658971664315.323, "dur": 545.137, + "args": { + "External id": 29198,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971664322.835, "dur": 536.536, + "args": { + "External id": 29199,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971664330.696, "dur": 10.320, + "args": { + "External id": 29200,"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": 4183437, "tid": 4183437, + "ts": 658971664343.007, "dur": 514.661, + "args": { + "External id": 29201,"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": 4183437, "tid": 4183437, + "ts": 658971664352.856, "dur": 0.520, + "args": { + "External id": 29202,"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": 4183437, "tid": 4183437, + "ts": 658971664356.886, "dur": 10.182, + "args": { + "External id": 29203,"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": 4183437, "tid": 4183437, + "ts": 658971664362.839, "dur": 4.067, + "args": { + "External id": 29204,"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": 4183437, "tid": 4183437, + "ts": 658971664365.973, "dur": 0.676, + "args": { + "External id": 29205,"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": 4183437, "tid": 4183437, + "ts": 658971664368.997, "dur": 166.298, + "args": { + "External id": 29206,"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": 4183437, "tid": 4183437, + "ts": 658971664371.490, "dur": 163.494, + "args": { + "External id": 29207,"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": 4183437, "tid": 4183437, + "ts": 658971664374.235, "dur": 9.578, + "args": { + "External id": 29208,"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": 4183437, "tid": 4183437, + "ts": 658971664376.469, "dur": 6.840, + "args": { + "External id": 29209,"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": 4183437, "tid": 4183437, + "ts": 658971664384.476, "dur": 150.043, + "args": { + "External id": 29210,"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": 4183437, "tid": 4183437, + "ts": 658971664536.928, "dur": 316.006, + "args": { + "External id": 29211,"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": 4183437, "tid": 4183437, + "ts": 658971664879.027, "dur": 509.356, + "args": { + "External id": 29212,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971664881.326, "dur": 506.332, + "args": { + "External id": 29213,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971664888.775, "dur": 7.725, + "args": { + "External id": 29214,"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": 4183437, "tid": 4183437, + "ts": 658971664897.665, "dur": 486.430, + "args": { + "External id": 29215,"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": 4183437, "tid": 4183437, + "ts": 658971665417.437, "dur": 55.022, + "args": { + "External id": 29216,"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": 4183437, "tid": 4183437, + "ts": 658971665423.138, "dur": 5.600, + "args": { + "External id": 29217,"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": 4183437, "tid": 4183437, + "ts": 658971665431.130, "dur": 40.923, + "args": { + "External id": 29218,"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": 4183437, "tid": 4183437, + "ts": 658971665437.441, "dur": 6.316, + "args": { + "External id": 29219,"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": 4183437, "tid": 4183437, + "ts": 658971665487.310, "dur": 75.014, + "args": { + "External id": 29220,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971665492.786, "dur": 7.406, + "args": { + "External id": 29221,"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": 4183437, "tid": 4183437, + "ts": 658971665498.036, "dur": 1.853, + "args": { + "External id": 29222,"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": 4183437, "tid": 4183437, + "ts": 658971665501.048, "dur": 4.622, + "args": { + "External id": 29223,"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": 4183437, "tid": 4183437, + "ts": 658971665510.633, "dur": 4.065, + "args": { + "External id": 29224,"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": 4183437, "tid": 4183437, + "ts": 658971665517.442, "dur": 5.888, + "args": { + "External id": 29225,"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": 4183437, "tid": 4183437, + "ts": 658971665522.612, "dur": 0.506, + "args": { + "External id": 29226,"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": 4183437, "tid": 4183437, + "ts": 658971665524.005, "dur": 4.377, + "args": { + "External id": 29227,"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": 4183437, "tid": 4183437, + "ts": 658971665527.398, "dur": 0.876, + "args": { + "External id": 29228,"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": 4183437, "tid": 4183437, + "ts": 658971665530.341, "dur": 3.820, + "args": { + "External id": 29229,"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": 4183437, "tid": 4183437, + "ts": 658971665531.356, "dur": 2.696, + "args": { + "External id": 29230,"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": 4183437, "tid": 4183437, + "ts": 658971665532.872, "dur": 1.045, + "args": { + "External id": 29231,"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": 4183437, "tid": 4183437, + "ts": 658971665535.002, "dur": 26.640, + "args": { + "External id": 29232,"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": 4183437, "tid": 4183437, + "ts": 658971665571.216, "dur": 32.620, + "args": { + "External id": 29233,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971665573.041, "dur": 30.624, + "args": { + "External id": 29234,"Sequence number": 459888, "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": 4183437, "tid": 4183437, + "ts": 658971665579.916, "dur": 2.933, + "args": { + "External id": 29235,"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": 4183437, "tid": 4183437, + "ts": 658971665583.627, "dur": 19.629, + "args": { + "External id": 29236,"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": 4183437, "tid": 4183437, + "ts": 658971665749.884, "dur": 145.532, + "args": { + "External id": 29237,"Record function id": 0, "Ev Idx": 4644 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 4183437, "tid": 4183437, + "ts": 658971665829.481, "dur": 55.455, + "args": { + "External id": 29238,"Record function id": 0, "Ev Idx": 4645 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971665903.502, "dur": 42.080, + "args": { + "External id": 29239,"Record function id": 0, "Ev Idx": 4646 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 4183437, "tid": 4183437, + "ts": 658971665953.807, "dur": 8953.559, + "args": { + "External id": 29240,"Record function id": 0, "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 4183437, "tid": 4183437, + "ts": 658971665962.466, "dur": 1192.654, + "args": { + "External id": 29241,"Record function id": 0, "Ev Idx": 4648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971666067.097, "dur": 7.002, + "args": { + "External id": 29242,"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": 4183437, "tid": 4183437, + "ts": 658971666091.246, "dur": 116.202, + "args": { + "External id": 29243,"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": 4183437, "tid": 4183437, + "ts": 658971666096.892, "dur": 1.763, + "args": { + "External id": 29244,"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": 4183437, "tid": 4183437, + "ts": 658971666104.297, "dur": 0.294, + "args": { + "External id": 29245,"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": 4183437, "tid": 4183437, + "ts": 658971666105.559, "dur": 0.567, + "args": { + "External id": 29246,"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": 4183437, "tid": 4183437, + "ts": 658971666107.077, "dur": 1.947, + "args": { + "External id": 29247,"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": 4183437, "tid": 4183437, + "ts": 658971666112.192, "dur": 0.460, + "args": { + "External id": 29248,"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": 4183437, "tid": 4183437, + "ts": 658971666113.371, "dur": 0.160, + "args": { + "External id": 29249,"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": 4183437, "tid": 4183437, + "ts": 658971666114.346, "dur": 2.562, + "args": { + "External id": 29250,"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": 4183437, "tid": 4183437, + "ts": 658971666119.480, "dur": 0.364, + "args": { + "External id": 29251,"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": 4183437, "tid": 4183437, + "ts": 658971666120.612, "dur": 0.479, + "args": { + "External id": 29252,"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": 4183437, "tid": 4183437, + "ts": 658971666125.192, "dur": 0.537, + "args": { + "External id": 29253,"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": 4183437, "tid": 4183437, + "ts": 658971666126.558, "dur": 0.297, + "args": { + "External id": 29254,"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": 4183437, "tid": 4183437, + "ts": 658971666127.445, "dur": 1.480, + "args": { + "External id": 29255,"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": 4183437, "tid": 4183437, + "ts": 658971666132.698, "dur": 0.401, + "args": { + "External id": 29256,"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": 4183437, "tid": 4183437, + "ts": 658971666133.909, "dur": 0.181, + "args": { + "External id": 29257,"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": 4183437, "tid": 4183437, + "ts": 658971666134.762, "dur": 2.677, + "args": { + "External id": 29258,"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": 4183437, "tid": 4183437, + "ts": 658971666139.970, "dur": 0.167, + "args": { + "External id": 29259,"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": 4183437, "tid": 4183437, + "ts": 658971666140.835, "dur": 0.170, + "args": { + "External id": 29260,"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": 4183437, "tid": 4183437, + "ts": 658971666145.483, "dur": 0.162, + "args": { + "External id": 29261,"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": 4183437, "tid": 4183437, + "ts": 658971666146.495, "dur": 0.160, + "args": { + "External id": 29262,"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": 4183437, "tid": 4183437, + "ts": 658971666147.531, "dur": 1.166, + "args": { + "External id": 29263,"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": 4183437, "tid": 4183437, + "ts": 658971666151.677, "dur": 0.171, + "args": { + "External id": 29264,"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": 4183437, "tid": 4183437, + "ts": 658971666152.464, "dur": 0.158, + "args": { + "External id": 29265,"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": 4183437, "tid": 4183437, + "ts": 658971666153.317, "dur": 2.301, + "args": { + "External id": 29266,"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": 4183437, "tid": 4183437, + "ts": 658971666158.319, "dur": 0.155, + "args": { + "External id": 29267,"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": 4183437, "tid": 4183437, + "ts": 658971666159.282, "dur": 0.195, + "args": { + "External id": 29268,"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": 4183437, "tid": 4183437, + "ts": 658971666164.141, "dur": 0.175, + "args": { + "External id": 29269,"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": 4183437, "tid": 4183437, + "ts": 658971666164.976, "dur": 0.162, + "args": { + "External id": 29270,"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": 4183437, "tid": 4183437, + "ts": 658971666165.663, "dur": 1.312, + "args": { + "External id": 29271,"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": 4183437, "tid": 4183437, + "ts": 658971666169.744, "dur": 0.169, + "args": { + "External id": 29272,"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": 4183437, "tid": 4183437, + "ts": 658971666170.652, "dur": 0.233, + "args": { + "External id": 29273,"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": 4183437, "tid": 4183437, + "ts": 658971666171.702, "dur": 2.089, + "args": { + "External id": 29274,"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": 4183437, "tid": 4183437, + "ts": 658971666176.637, "dur": 0.220, + "args": { + "External id": 29275,"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": 4183437, "tid": 4183437, + "ts": 658971666177.539, "dur": 0.156, + "args": { + "External id": 29276,"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": 4183437, "tid": 4183437, + "ts": 658971666181.728, "dur": 0.169, + "args": { + "External id": 29277,"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": 4183437, "tid": 4183437, + "ts": 658971666182.772, "dur": 0.166, + "args": { + "External id": 29278,"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": 4183437, "tid": 4183437, + "ts": 658971666183.598, "dur": 1.220, + "args": { + "External id": 29279,"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": 4183437, "tid": 4183437, + "ts": 658971666187.933, "dur": 0.290, + "args": { + "External id": 29280,"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": 4183437, "tid": 4183437, + "ts": 658971666189.009, "dur": 0.162, + "args": { + "External id": 29281,"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": 4183437, "tid": 4183437, + "ts": 658971666189.878, "dur": 2.934, + "args": { + "External id": 29282,"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": 4183437, "tid": 4183437, + "ts": 658971666232.412, "dur": 65.916, + "args": { + "External id": 29283,"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": 4183437, "tid": 4183437, + "ts": 658971666368.260, "dur": 222.807, + "args": { + "External id": 29284,"Record function id": 0, "Concrete Inputs": ["", "", "14615680", "8", "1", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 4691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971666383.799, "dur": 5.497, + "args": { + "External id": 29285,"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": 4183437, "tid": 4183437, + "ts": 658971666396.508, "dur": 13.999, + "args": { + "External id": 29286,"Record function id": 0, "Concrete Inputs": ["", "0", "14615680", "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": 4183437, "tid": 4183437, + "ts": 658971666401.390, "dur": 8.682, + "args": { + "External id": 29287,"Record function id": 0, "Concrete Inputs": ["", "0", "14615680", "29231360", "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": 4183437, "tid": 4183437, + "ts": 658971666406.470, "dur": 0.686, + "args": { + "External id": 29288,"Record function id": 0, "Concrete Inputs": ["", "[14615680]", "[1]", "14615680"], "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": 4183437, "tid": 4183437, + "ts": 658971666418.440, "dur": 102.445, + "args": { + "External id": 29289,"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": 4183437, "tid": 4183437, + "ts": 658971666420.504, "dur": 0.230, + "args": { + "External id": 29290,"Record function id": 0, "Concrete Inputs": ["", "[4096000]", "[1]", "14615680"], "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": 4183437, "tid": 4183437, + "ts": 658971666422.022, "dur": 0.430, + "args": { + "External id": 29291,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "18711680"], "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": 4183437, "tid": 4183437, + "ts": 658971666424.725, "dur": 1.661, + "args": { + "External id": 29292,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "18711808"], "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": 4183437, "tid": 4183437, + "ts": 658971666427.192, "dur": 0.699, + "args": { + "External id": 29293,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "18842880"], "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": 4183437, "tid": 4183437, + "ts": 658971666430.133, "dur": 0.589, + "args": { + "External id": 29294,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "18973952"], "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": 4183437, "tid": 4183437, + "ts": 658971666431.314, "dur": 0.365, + "args": { + "External id": 29295,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "19105024"], "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": 4183437, "tid": 4183437, + "ts": 658971666432.597, "dur": 0.197, + "args": { + "External id": 29296,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "19236096"], "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": 4183437, "tid": 4183437, + "ts": 658971666434.853, "dur": 0.158, + "args": { + "External id": 29297,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "19236224"], "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": 4183437, "tid": 4183437, + "ts": 658971666435.766, "dur": 0.728, + "args": { + "External id": 29298,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "19596672"], "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": 4183437, "tid": 4183437, + "ts": 658971666437.279, "dur": 0.363, + "args": { + "External id": 29299,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "19957120"], "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": 4183437, "tid": 4183437, + "ts": 658971666439.913, "dur": 1.037, + "args": { + "External id": 29300,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "20317568"], "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": 4183437, "tid": 4183437, + "ts": 658971666441.801, "dur": 0.359, + "args": { + "External id": 29301,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "20317696"], "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": 4183437, "tid": 4183437, + "ts": 658971666444.571, "dur": 2.659, + "args": { + "External id": 29302,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "20448768"], "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": 4183437, "tid": 4183437, + "ts": 658971666448.049, "dur": 0.398, + "args": { + "External id": 29303,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "20579840"], "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": 4183437, "tid": 4183437, + "ts": 658971666449.128, "dur": 0.397, + "args": { + "External id": 29304,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "20710912"], "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": 4183437, "tid": 4183437, + "ts": 658971666453.645, "dur": 0.170, + "args": { + "External id": 29305,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "20841984"], "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": 4183437, "tid": 4183437, + "ts": 658971666454.480, "dur": 0.480, + "args": { + "External id": 29306,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "20842112"], "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": 4183437, "tid": 4183437, + "ts": 658971666455.826, "dur": 0.314, + "args": { + "External id": 29307,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "21202560"], "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": 4183437, "tid": 4183437, + "ts": 658971666460.186, "dur": 1.202, + "args": { + "External id": 29308,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "21563008"], "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": 4183437, "tid": 4183437, + "ts": 658971666461.969, "dur": 0.371, + "args": { + "External id": 29309,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "21923456"], "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": 4183437, "tid": 4183437, + "ts": 658971666464.294, "dur": 2.732, + "args": { + "External id": 29310,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "21923584"], "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": 4183437, "tid": 4183437, + "ts": 658971666467.828, "dur": 0.345, + "args": { + "External id": 29311,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "22054656"], "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": 4183437, "tid": 4183437, + "ts": 658971666468.950, "dur": 0.316, + "args": { + "External id": 29312,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "22185728"], "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": 4183437, "tid": 4183437, + "ts": 658971666473.474, "dur": 0.193, + "args": { + "External id": 29313,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "22316800"], "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": 4183437, "tid": 4183437, + "ts": 658971666474.259, "dur": 0.146, + "args": { + "External id": 29314,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "22447872"], "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": 4183437, "tid": 4183437, + "ts": 658971666476.270, "dur": 0.166, + "args": { + "External id": 29315,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "22448000"], "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": 4183437, "tid": 4183437, + "ts": 658971666479.352, "dur": 1.344, + "args": { + "External id": 29316,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "22808448"], "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": 4183437, "tid": 4183437, + "ts": 658971666482.312, "dur": 0.171, + "args": { + "External id": 29317,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "23168896"], "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": 4183437, "tid": 4183437, + "ts": 658971666483.886, "dur": 2.412, + "args": { + "External id": 29318,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "23529344"], "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": 4183437, "tid": 4183437, + "ts": 658971666487.487, "dur": 0.169, + "args": { + "External id": 29319,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "23529472"], "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": 4183437, "tid": 4183437, + "ts": 658971666489.109, "dur": 0.160, + "args": { + "External id": 29320,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "23660544"], "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": 4183437, "tid": 4183437, + "ts": 658971666493.390, "dur": 0.177, + "args": { + "External id": 29321,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "23791616"], "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": 4183437, "tid": 4183437, + "ts": 658971666495.027, "dur": 0.200, + "args": { + "External id": 29322,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "23922688"], "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": 4183437, "tid": 4183437, + "ts": 658971666496.616, "dur": 0.158, + "args": { + "External id": 29323,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "24053760"], "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": 4183437, "tid": 4183437, + "ts": 658971666500.045, "dur": 1.104, + "args": { + "External id": 29324,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "24053888"], "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": 4183437, "tid": 4183437, + "ts": 658971666502.794, "dur": 0.284, + "args": { + "External id": 29325,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "24414336"], "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": 4183437, "tid": 4183437, + "ts": 658971666504.462, "dur": 1.974, + "args": { + "External id": 29326,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "24774784"], "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": 4183437, "tid": 4183437, + "ts": 658971666507.647, "dur": 0.385, + "args": { + "External id": 29327,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "25135232"], "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": 4183437, "tid": 4183437, + "ts": 658971666509.332, "dur": 0.392, + "args": { + "External id": 29328,"Record function id": 0, "Concrete Inputs": ["", "[4096000]", "[1]", "25135360"], "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": 4183437, "tid": 4183437, + "ts": 658971666541.612, "dur": 34.238, + "args": { + "External id": 29329,"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": 4183437, "tid": 4183437, + "ts": 658971666647.821, "dur": 398.476, + "args": { + "External id": 29330,"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": 4183437, "tid": 4183437, + "ts": 658971666721.993, "dur": 318.830, + "args": { + "External id": 29331,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971666733.941, "dur": 301.706, + "args": { + "External id": 29332,"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": 4183437, "tid": 4183437, + "ts": 658971667069.192, "dur": 2.380, + "args": { + "External id": 29333,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 4183437, "tid": 4183437, + "ts": 658971667171.309, "dur": 7550.957, + "args": { + "External id": 29334,"Record function id": 0, "Ev Idx": 4741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971667380.104, "dur": 7.094, + "args": { + "External id": 29335,"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": 4183437, "tid": 4183437, + "ts": 658971667393.370, "dur": 0.982, + "args": { + "External id": 29336,"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": 4183437, "tid": 4183437, + "ts": 658971667396.679, "dur": 0.926, + "args": { + "External id": 29337,"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": 4183437, "tid": 4183437, + "ts": 658971667399.711, "dur": 2.049, + "args": { + "External id": 29338,"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": 4183437, "tid": 4183437, + "ts": 658971667406.044, "dur": 0.928, + "args": { + "External id": 29339,"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": 4183437, "tid": 4183437, + "ts": 658971667408.546, "dur": 0.878, + "args": { + "External id": 29340,"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": 4183437, "tid": 4183437, + "ts": 658971667411.037, "dur": 0.804, + "args": { + "External id": 29341,"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": 4183437, "tid": 4183437, + "ts": 658971667413.403, "dur": 1.617, + "args": { + "External id": 29342,"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": 4183437, "tid": 4183437, + "ts": 658971667418.468, "dur": 0.649, + "args": { + "External id": 29343,"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": 4183437, "tid": 4183437, + "ts": 658971667420.723, "dur": 0.781, + "args": { + "External id": 29344,"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": 4183437, "tid": 4183437, + "ts": 658971667423.132, "dur": 0.481, + "args": { + "External id": 29345,"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": 4183437, "tid": 4183437, + "ts": 658971667425.236, "dur": 1.718, + "args": { + "External id": 29346,"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": 4183437, "tid": 4183437, + "ts": 658971667430.150, "dur": 0.678, + "args": { + "External id": 29347,"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": 4183437, "tid": 4183437, + "ts": 658971667432.347, "dur": 0.511, + "args": { + "External id": 29348,"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": 4183437, "tid": 4183437, + "ts": 658971667434.416, "dur": 0.634, + "args": { + "External id": 29349,"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": 4183437, "tid": 4183437, + "ts": 658971667436.613, "dur": 1.735, + "args": { + "External id": 29350,"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": 4183437, "tid": 4183437, + "ts": 658971667442.369, "dur": 0.472, + "args": { + "External id": 29351,"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": 4183437, "tid": 4183437, + "ts": 658971667444.278, "dur": 0.700, + "args": { + "External id": 29352,"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": 4183437, "tid": 4183437, + "ts": 658971667446.933, "dur": 0.510, + "args": { + "External id": 29353,"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": 4183437, "tid": 4183437, + "ts": 658971667449.017, "dur": 1.511, + "args": { + "External id": 29354,"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": 4183437, "tid": 4183437, + "ts": 658971667453.996, "dur": 0.645, + "args": { + "External id": 29355,"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": 4183437, "tid": 4183437, + "ts": 658971667456.018, "dur": 0.647, + "args": { + "External id": 29356,"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": 4183437, "tid": 4183437, + "ts": 658971667458.013, "dur": 0.722, + "args": { + "External id": 29357,"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": 4183437, "tid": 4183437, + "ts": 658971667460.398, "dur": 1.376, + "args": { + "External id": 29358,"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": 4183437, "tid": 4183437, + "ts": 658971667472.180, "dur": 0.701, + "args": { + "External id": 29359,"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": 4183437, "tid": 4183437, + "ts": 658971667474.456, "dur": 0.706, + "args": { + "External id": 29360,"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": 4183437, "tid": 4183437, + "ts": 658971667476.852, "dur": 0.562, + "args": { + "External id": 29361,"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": 4183437, "tid": 4183437, + "ts": 658971667478.856, "dur": 1.676, + "args": { + "External id": 29362,"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": 4183437, "tid": 4183437, + "ts": 658971667484.609, "dur": 0.648, + "args": { + "External id": 29363,"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": 4183437, "tid": 4183437, + "ts": 658971667486.996, "dur": 0.657, + "args": { + "External id": 29364,"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": 4183437, "tid": 4183437, + "ts": 658971667489.477, "dur": 0.658, + "args": { + "External id": 29365,"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": 4183437, "tid": 4183437, + "ts": 658971667491.755, "dur": 1.792, + "args": { + "External id": 29366,"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": 4183437, "tid": 4183437, + "ts": 658971667497.205, "dur": 0.813, + "args": { + "External id": 29367,"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": 4183437, "tid": 4183437, + "ts": 658971667499.636, "dur": 0.650, + "args": { + "External id": 29368,"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": 4183437, "tid": 4183437, + "ts": 658971667501.896, "dur": 0.435, + "args": { + "External id": 29369,"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": 4183437, "tid": 4183437, + "ts": 658971667503.869, "dur": 1.513, + "args": { + "External id": 29370,"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": 4183437, "tid": 4183437, + "ts": 658971667508.703, "dur": 0.740, + "args": { + "External id": 29371,"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": 4183437, "tid": 4183437, + "ts": 658971667511.008, "dur": 0.664, + "args": { + "External id": 29372,"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": 4183437, "tid": 4183437, + "ts": 658971667513.614, "dur": 0.651, + "args": { + "External id": 29373,"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": 4183437, "tid": 4183437, + "ts": 658971667515.776, "dur": 1.383, + "args": { + "External id": 29374,"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": 4183437, "tid": 4183437, + "ts": 658971667548.620, "dur": 7092.387, + "args": { + "External id": 29375,"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": 4183437, "tid": 4183437, + "ts": 658971667573.023, "dur": 7057.913, + "args": { + "External id": 29376,"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": 4183437, "tid": 4183437, + "ts": 658971667595.341, "dur": 5.182, + "args": { + "External id": 29377,"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": 4183437, "tid": 4183437, + "ts": 658971667604.707, "dur": 6987.506, + "args": { + "External id": 29378,"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": 4183437, "tid": 4183437, + "ts": 658971667607.601, "dur": 6984.040, + "args": { + "External id": 29379,"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": 4183437, "tid": 4183437, + "ts": 658971667613.768, "dur": 7.164, + "args": { + "External id": 29380,"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": 4183437, "tid": 4183437, + "ts": 658971667622.607, "dur": 6965.326, + "args": { + "External id": 29381,"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": 4183437, "tid": 4183437, + "ts": 658971674989.813, "dur": 39.651, + "args": { + "External id": 29382,"Record function id": 0, "Ev Idx": 4789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 4183437, "tid": 4183437, + "ts": 658971675031.115, "dur": 207.592, + "args": { + "External id": 29383,"Record function id": 0, "Ev Idx": 4790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971675071.621, "dur": 158.104, + "args": { + "External id": 29384,"Sequence number": 459888, "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": 4183437, "tid": 4183437, "ts": 658971675071.621, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 4183437, "tid": 4183437, + "ts": 658971675144.609, "dur": 48.679, + "args": { + "External id": 29385,"kernel_hash": "cxiyymi3r3a3hepj6bdehtyy3l7cgvjeafvzenvgiyzl6dmji4aa", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/xi/cxiyymi3r3a3hepj6bdehtyy3l7cgvjeafvzenvgiyzl6dmji4aa.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": 4183437, "tid": 4183437, + "ts": 658971675318.519, "dur": 57.019, + "args": { + "External id": 29386,"Record function id": 0, "Ev Idx": 4793 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 4183437, "tid": 4183437, + "ts": 658971675386.859, "dur": 6997.022, + "args": { + "External id": 29387,"Record function id": 0, "Ev Idx": 4794 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 4183437, "tid": 4183437, + "ts": 658971675394.398, "dur": 828.762, + "args": { + "External id": 29388,"Record function id": 0, "Ev Idx": 4795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971675464.754, "dur": 12.256, + "args": { + "External id": 29389,"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": 4183437, "tid": 4183437, + "ts": 658971675489.952, "dur": 38.231, + "args": { + "External id": 29390,"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": 4183437, "tid": 4183437, + "ts": 658971675497.554, "dur": 2.382, + "args": { + "External id": 29391,"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": 4183437, "tid": 4183437, + "ts": 658971675501.952, "dur": 0.437, + "args": { + "External id": 29392,"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": 4183437, "tid": 4183437, + "ts": 658971675504.236, "dur": 2.376, + "args": { + "External id": 29393,"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": 4183437, "tid": 4183437, + "ts": 658971675508.327, "dur": 0.406, + "args": { + "External id": 29394,"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": 4183437, "tid": 4183437, + "ts": 658971675510.226, "dur": 0.246, + "args": { + "External id": 29395,"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": 4183437, "tid": 4183437, + "ts": 658971675513.636, "dur": 0.198, + "args": { + "External id": 29396,"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": 4183437, "tid": 4183437, + "ts": 658971675514.976, "dur": 0.358, + "args": { + "External id": 29397,"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": 4183437, "tid": 4183437, + "ts": 658971675516.552, "dur": 1.626, + "args": { + "External id": 29398,"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": 4183437, "tid": 4183437, + "ts": 658971675521.627, "dur": 0.527, + "args": { + "External id": 29399,"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": 4183437, "tid": 4183437, + "ts": 658971675538.964, "dur": 37.489, + "args": { + "External id": 29400,"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": 4183437, "tid": 4183437, + "ts": 658971675609.574, "dur": 151.226, + "args": { + "External id": 29401,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971675619.767, "dur": 4.016, + "args": { + "External id": 29402,"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": 4183437, "tid": 4183437, + "ts": 658971675629.431, "dur": 10.774, + "args": { + "External id": 29403,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971675634.131, "dur": 5.685, + "args": { + "External id": 29404,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971675638.159, "dur": 0.513, + "args": { + "External id": 29405,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971675646.710, "dur": 67.158, + "args": { + "External id": 29406,"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": 4183437, "tid": 4183437, + "ts": 658971675648.846, "dur": 0.590, + "args": { + "External id": 29407,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971675651.024, "dur": 38.005, + "args": { + "External id": 29408,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971675693.730, "dur": 0.208, + "args": { + "External id": 29409,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971675695.318, "dur": 0.553, + "args": { + "External id": 29410,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971675697.211, "dur": 3.636, + "args": { + "External id": 29411,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971675702.198, "dur": 0.393, + "args": { + "External id": 29412,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971675703.988, "dur": 0.374, + "args": { + "External id": 29413,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971675707.828, "dur": 0.194, + "args": { + "External id": 29414,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971675709.781, "dur": 0.234, + "args": { + "External id": 29415,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971675726.079, "dur": 25.829, + "args": { + "External id": 29416,"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": 4183437, "tid": 4183437, + "ts": 658971675813.729, "dur": 322.161, + "args": { + "External id": 29417,"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": 4183437, "tid": 4183437, + "ts": 658971675842.639, "dur": 289.082, + "args": { + "External id": 29418,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971675855.484, "dur": 271.365, + "args": { + "External id": 29419,"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": 4183437, "tid": 4183437, + "ts": 658971676158.659, "dur": 2.265, + "args": { + "External id": 29420,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 4183437, "tid": 4183437, + "ts": 658971676242.853, "dur": 5926.932, + "args": { + "External id": 29421,"Record function id": 0, "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971676358.513, "dur": 6.445, + "args": { + "External id": 29422,"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": 4183437, "tid": 4183437, + "ts": 658971676369.292, "dur": 0.782, + "args": { + "External id": 29423,"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": 4183437, "tid": 4183437, + "ts": 658971676371.724, "dur": 0.959, + "args": { + "External id": 29424,"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": 4183437, "tid": 4183437, + "ts": 658971676374.626, "dur": 1.562, + "args": { + "External id": 29425,"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": 4183437, "tid": 4183437, + "ts": 658971676377.752, "dur": 0.953, + "args": { + "External id": 29426,"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": 4183437, "tid": 4183437, + "ts": 658971676382.434, "dur": 0.974, + "args": { + "External id": 29427,"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": 4183437, "tid": 4183437, + "ts": 658971676385.124, "dur": 0.772, + "args": { + "External id": 29428,"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": 4183437, "tid": 4183437, + "ts": 658971676387.397, "dur": 2.308, + "args": { + "External id": 29429,"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": 4183437, "tid": 4183437, + "ts": 658971676391.078, "dur": 0.825, + "args": { + "External id": 29430,"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": 4183437, "tid": 4183437, + "ts": 658971676395.717, "dur": 0.706, + "args": { + "External id": 29431,"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": 4183437, "tid": 4183437, + "ts": 658971676414.398, "dur": 5715.327, + "args": { + "External id": 29432,"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": 4183437, "tid": 4183437, + "ts": 658971676430.581, "dur": 5692.544, + "args": { + "External id": 29433,"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": 4183437, "tid": 4183437, + "ts": 658971676446.786, "dur": 14.102, + "args": { + "External id": 29434,"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": 4183437, "tid": 4183437, + "ts": 658971676463.592, "dur": 5625.543, + "args": { + "External id": 29435,"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": 4183437, "tid": 4183437, + "ts": 658971676466.336, "dur": 5622.289, + "args": { + "External id": 29436,"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": 4183437, "tid": 4183437, + "ts": 658971676473.242, "dur": 7.549, + "args": { + "External id": 29437,"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": 4183437, "tid": 4183437, + "ts": 658971676482.669, "dur": 5602.839, + "args": { + "External id": 29438,"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": 4183437, "tid": 4183437, + "ts": 658971682329.410, "dur": 29.555, + "args": { + "External id": 29439,"Sequence number": 459889, "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": 4183437, "tid": 4183437, "ts": 658971682329.410, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971682345.752, "dur": 8.543, + "args": { + "External id": 29440,"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": 4183437, "tid": 4183437, + "ts": 658971682349.375, "dur": 4.510, + "args": { + "External id": 29441,"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": 4183437, "tid": 4183437, + "ts": 658971682425.505, "dur": 92.086, + "args": { + "External id": 29442,"Record function id": 0, "Ev Idx": 4849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971682519.361, "dur": 1117.565, + "args": { + "External id": 29443,"Record function id": 0, "Ev Idx": 4850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971682562.277, "dur": 1057.536, + "args": { + "External id": 29444,"Sequence number": 459890, "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": 4183437, "tid": 4183437, "ts": 658971682562.277, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971682629.944, "dur": 81.339, + "args": { + "External id": 29445,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971682728.455, "dur": 96.989, + "args": { + "External id": 29446,"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": 4183437, "tid": 4183437, + "ts": 658971682836.248, "dur": 36.287, + "args": { + "External id": 29447,"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": 4183437, "tid": 4183437, + "ts": 658971682882.302, "dur": 29.446, + "args": { + "External id": 29448,"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": 4183437, "tid": 4183437, + "ts": 658971682938.312, "dur": 27.607, + "args": { + "External id": 29449,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971682985.049, "dur": 17.886, + "args": { + "External id": 29450,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971683020.604, "dur": 126.810, + "args": { + "External id": 29451,"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": 4183437, "tid": 4183437, + "ts": 658971683070.046, "dur": 11.551, + "args": { + "External id": 29452,"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": 4183437, "tid": 4183437, + "ts": 658971683075.682, "dur": 5.175, + "args": { + "External id": 29453,"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": 4183437, "tid": 4183437, + "ts": 658971683084.541, "dur": 3.304, + "args": { + "External id": 29454,"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": 4183437, "tid": 4183437, + "ts": 658971683089.157, "dur": 0.945, + "args": { + "External id": 29455,"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": 4183437, "tid": 4183437, + "ts": 658971683092.969, "dur": 2.713, + "args": { + "External id": 29456,"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": 4183437, "tid": 4183437, + "ts": 658971683157.066, "dur": 42.801, + "args": { + "External id": 29457,"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": 4183437, "tid": 4183437, + "ts": 658971683231.902, "dur": 55.739, + "args": { + "External id": 29458,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971683298.258, "dur": 42.693, + "args": { + "External id": 29459,"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": 4183437, "tid": 4183437, + "ts": 658971683350.494, "dur": 32.209, + "args": { + "External id": 29460,"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": 4183437, "tid": 4183437, + "ts": 658971683405.632, "dur": 28.095, + "args": { + "External id": 29461,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971683439.348, "dur": 50.029, + "args": { + "External id": 29462,"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": 4183437, "tid": 4183437, + "ts": 658971683515.149, "dur": 19.925, + "args": { + "External id": 29463,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971683787.095, "dur": 114.207, + "args": { + "External id": 29464,"Record function id": 0, "Ev Idx": 4871 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971683998.535, "dur": 63.124, + "args": { + "External id": 29465,"Record function id": 0, "Ev Idx": 4872 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 4183437, "tid": 4183437, + "ts": 658971684076.562, "dur": 13843.784, + "args": { + "External id": 29466,"Record function id": 0, "Ev Idx": 4873 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 4183437, "tid": 4183437, + "ts": 658971684089.895, "dur": 1350.822, + "args": { + "External id": 29467,"Record function id": 0, "Ev Idx": 4874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971684188.917, "dur": 13.170, + "args": { + "External id": 29468,"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": 4183437, "tid": 4183437, + "ts": 658971684219.723, "dur": 82.533, + "args": { + "External id": 29469,"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": 4183437, "tid": 4183437, + "ts": 658971684226.996, "dur": 4.819, + "args": { + "External id": 29470,"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": 4183437, "tid": 4183437, + "ts": 658971684235.690, "dur": 0.639, + "args": { + "External id": 29471,"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": 4183437, "tid": 4183437, + "ts": 658971684239.069, "dur": 0.594, + "args": { + "External id": 29472,"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": 4183437, "tid": 4183437, + "ts": 658971684244.163, "dur": 0.404, + "args": { + "External id": 29473,"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": 4183437, "tid": 4183437, + "ts": 658971684246.518, "dur": 2.205, + "args": { + "External id": 29474,"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": 4183437, "tid": 4183437, + "ts": 658971684250.827, "dur": 0.356, + "args": { + "External id": 29475,"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": 4183437, "tid": 4183437, + "ts": 658971684256.270, "dur": 0.321, + "args": { + "External id": 29476,"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": 4183437, "tid": 4183437, + "ts": 658971684258.829, "dur": 0.493, + "args": { + "External id": 29477,"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": 4183437, "tid": 4183437, + "ts": 658971684291.442, "dur": 3.133, + "args": { + "External id": 29478,"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": 4183437, "tid": 4183437, + "ts": 658971684317.555, "dur": 62.099, + "args": { + "External id": 29479,"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": 4183437, "tid": 4183437, + "ts": 658971684438.793, "dur": 191.716, + "args": { + "External id": 29480,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971684457.543, "dur": 19.026, + "args": { + "External id": 29481,"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": 4183437, "tid": 4183437, + "ts": 658971684488.191, "dur": 15.397, + "args": { + "External id": 29482,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971684494.477, "dur": 8.553, + "args": { + "External id": 29483,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971684499.898, "dur": 1.027, + "args": { + "External id": 29484,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971684515.014, "dur": 37.594, + "args": { + "External id": 29485,"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": 4183437, "tid": 4183437, + "ts": 658971684518.525, "dur": 0.484, + "args": { + "External id": 29486,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971684521.823, "dur": 1.957, + "args": { + "External id": 29487,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971684526.124, "dur": 2.614, + "args": { + "External id": 29488,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971684530.798, "dur": 0.332, + "args": { + "External id": 29489,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971684533.355, "dur": 0.332, + "args": { + "External id": 29490,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971684538.155, "dur": 0.347, + "args": { + "External id": 29491,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971684540.380, "dur": 0.610, + "args": { + "External id": 29492,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971684542.705, "dur": 0.335, + "args": { + "External id": 29493,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971684547.171, "dur": 0.550, + "args": { + "External id": 29494,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971684572.192, "dur": 44.504, + "args": { + "External id": 29495,"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": 4183437, "tid": 4183437, + "ts": 658971684821.864, "dur": 482.825, + "args": { + "External id": 29496,"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": 4183437, "tid": 4183437, + "ts": 658971684862.245, "dur": 434.289, + "args": { + "External id": 29497,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971684877.853, "dur": 378.828, + "args": { + "External id": 29498,"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": 4183437, "tid": 4183437, + "ts": 658971685337.685, "dur": 4.249, + "args": { + "External id": 29499,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 4183437, "tid": 4183437, + "ts": 658971685469.941, "dur": 12118.128, + "args": { + "External id": 29500,"Record function id": 0, "Ev Idx": 4907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971685599.293, "dur": 7.710, + "args": { + "External id": 29501,"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": 4183437, "tid": 4183437, + "ts": 658971685613.352, "dur": 1.377, + "args": { + "External id": 29502,"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": 4183437, "tid": 4183437, + "ts": 658971685617.505, "dur": 1.326, + "args": { + "External id": 29503,"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": 4183437, "tid": 4183437, + "ts": 658971685621.309, "dur": 1.133, + "args": { + "External id": 29504,"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": 4183437, "tid": 4183437, + "ts": 658971685624.739, "dur": 0.934, + "args": { + "External id": 29505,"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": 4183437, "tid": 4183437, + "ts": 658971685629.972, "dur": 0.934, + "args": { + "External id": 29506,"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": 4183437, "tid": 4183437, + "ts": 658971685633.396, "dur": 1.266, + "args": { + "External id": 29507,"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": 4183437, "tid": 4183437, + "ts": 658971685637.281, "dur": 3.071, + "args": { + "External id": 29508,"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": 4183437, "tid": 4183437, + "ts": 658971685642.718, "dur": 0.742, + "args": { + "External id": 29509,"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": 4183437, "tid": 4183437, + "ts": 658971685648.020, "dur": 0.971, + "args": { + "External id": 29510,"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": 4183437, "tid": 4183437, + "ts": 658971685732.587, "dur": 11775.633, + "args": { + "External id": 29511,"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": 4183437, "tid": 4183437, + "ts": 658971685754.244, "dur": 11739.089, + "args": { + "External id": 29512,"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": 4183437, "tid": 4183437, + "ts": 658971685774.547, "dur": 17.397, + "args": { + "External id": 29513,"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": 4183437, "tid": 4183437, + "ts": 658971685796.227, "dur": 11634.064, + "args": { + "External id": 29514,"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": 4183437, "tid": 4183437, + "ts": 658971685799.768, "dur": 11628.743, + "args": { + "External id": 29515,"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": 4183437, "tid": 4183437, + "ts": 658971685807.324, "dur": 7.199, + "args": { + "External id": 29516,"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": 4183437, "tid": 4183437, + "ts": 658971685816.904, "dur": 11605.009, + "args": { + "External id": 29517,"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": 4183437, "tid": 4183437, + "ts": 658971697837.645, "dur": 43.899, + "args": { + "External id": 29518,"Sequence number": 459891, "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": 4183437, "tid": 4183437, "ts": 658971697837.645, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971697860.170, "dur": 14.997, + "args": { + "External id": 29519,"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": 4183437, "tid": 4183437, + "ts": 658971697866.875, "dur": 7.749, + "args": { + "External id": 29520,"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": 4183437, "tid": 4183437, + "ts": 658971697974.757, "dur": 107.755, + "args": { + "External id": 29521,"Record function id": 0, "Ev Idx": 4928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971698085.785, "dur": 1167.201, + "args": { + "External id": 29522,"Record function id": 0, "Ev Idx": 4929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971698131.849, "dur": 1107.386, + "args": { + "External id": 29523,"Sequence number": 459892, "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": 4183437, "tid": 4183437, "ts": 658971698131.849, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971698216.559, "dur": 73.453, + "args": { + "External id": 29524,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971698310.392, "dur": 93.961, + "args": { + "External id": 29525,"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": 4183437, "tid": 4183437, + "ts": 658971698412.293, "dur": 36.128, + "args": { + "External id": 29526,"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": 4183437, "tid": 4183437, + "ts": 658971698454.085, "dur": 30.235, + "args": { + "External id": 29527,"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": 4183437, "tid": 4183437, + "ts": 658971698515.899, "dur": 27.739, + "args": { + "External id": 29528,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971698562.533, "dur": 19.298, + "args": { + "External id": 29529,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971698598.774, "dur": 187.080, + "args": { + "External id": 29530,"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": 4183437, "tid": 4183437, + "ts": 658971698648.539, "dur": 62.045, + "args": { + "External id": 29531,"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": 4183437, "tid": 4183437, + "ts": 658971698700.018, "dur": 9.400, + "args": { + "External id": 29532,"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": 4183437, "tid": 4183437, + "ts": 658971698713.958, "dur": 4.146, + "args": { + "External id": 29533,"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": 4183437, "tid": 4183437, + "ts": 658971698719.348, "dur": 3.288, + "args": { + "External id": 29534,"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": 4183437, "tid": 4183437, + "ts": 658971698725.407, "dur": 2.491, + "args": { + "External id": 29535,"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": 4183437, "tid": 4183437, + "ts": 658971698797.608, "dur": 54.450, + "args": { + "External id": 29536,"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": 4183437, "tid": 4183437, + "ts": 658971698882.318, "dur": 30.556, + "args": { + "External id": 29537,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971698920.965, "dur": 39.133, + "args": { + "External id": 29538,"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": 4183437, "tid": 4183437, + "ts": 658971698966.825, "dur": 49.531, + "args": { + "External id": 29539,"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": 4183437, "tid": 4183437, + "ts": 658971699041.833, "dur": 25.510, + "args": { + "External id": 29540,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971699072.948, "dur": 54.587, + "args": { + "External id": 29541,"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": 4183437, "tid": 4183437, + "ts": 658971699147.954, "dur": 21.911, + "args": { + "External id": 29542,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971699341.790, "dur": 77.658, + "args": { + "External id": 29543,"Record function id": 0, "Ev Idx": 4950 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971699495.897, "dur": 48.857, + "args": { + "External id": 29544,"Record function id": 0, "Ev Idx": 4951 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 4183437, "tid": 4183437, + "ts": 658971699553.791, "dur": 9391.153, + "args": { + "External id": 29545,"Record function id": 0, "Ev Idx": 4952 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 4183437, "tid": 4183437, + "ts": 658971699562.350, "dur": 924.990, + "args": { + "External id": 29546,"Record function id": 0, "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971699643.938, "dur": 9.253, + "args": { + "External id": 29547,"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": 4183437, "tid": 4183437, + "ts": 658971699707.444, "dur": 36.902, + "args": { + "External id": 29548,"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": 4183437, "tid": 4183437, + "ts": 658971699713.102, "dur": 2.554, + "args": { + "External id": 29549,"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": 4183437, "tid": 4183437, + "ts": 658971699720.045, "dur": 0.532, + "args": { + "External id": 29550,"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": 4183437, "tid": 4183437, + "ts": 658971699722.460, "dur": 0.415, + "args": { + "External id": 29551,"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": 4183437, "tid": 4183437, + "ts": 658971699724.369, "dur": 0.631, + "args": { + "External id": 29552,"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": 4183437, "tid": 4183437, + "ts": 658971699728.101, "dur": 0.189, + "args": { + "External id": 29553,"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": 4183437, "tid": 4183437, + "ts": 658971699729.447, "dur": 0.579, + "args": { + "External id": 29554,"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": 4183437, "tid": 4183437, + "ts": 658971699731.335, "dur": 3.687, + "args": { + "External id": 29555,"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": 4183437, "tid": 4183437, + "ts": 658971699735.977, "dur": 0.500, + "args": { + "External id": 29556,"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": 4183437, "tid": 4183437, + "ts": 658971699737.702, "dur": 0.332, + "args": { + "External id": 29557,"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": 4183437, "tid": 4183437, + "ts": 658971699756.073, "dur": 45.011, + "args": { + "External id": 29558,"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": 4183437, "tid": 4183437, + "ts": 658971699838.232, "dur": 114.324, + "args": { + "External id": 29559,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971699851.665, "dur": 4.963, + "args": { + "External id": 29560,"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": 4183437, "tid": 4183437, + "ts": 658971699862.195, "dur": 9.864, + "args": { + "External id": 29561,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971699866.857, "dur": 4.806, + "args": { + "External id": 29562,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971699870.054, "dur": 0.420, + "args": { + "External id": 29563,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971699878.970, "dur": 29.352, + "args": { + "External id": 29564,"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": 4183437, "tid": 4183437, + "ts": 658971699880.721, "dur": 2.906, + "args": { + "External id": 29565,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971699885.025, "dur": 0.374, + "args": { + "External id": 29566,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971699886.889, "dur": 0.361, + "args": { + "External id": 29567,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971699891.219, "dur": 1.349, + "args": { + "External id": 29568,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971699893.626, "dur": 0.174, + "args": { + "External id": 29569,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971699895.182, "dur": 0.171, + "args": { + "External id": 29570,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971699898.987, "dur": 0.217, + "args": { + "External id": 29571,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971699900.332, "dur": 0.263, + "args": { + "External id": 29572,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971699902.044, "dur": 2.409, + "args": { + "External id": 29573,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971699919.473, "dur": 25.248, + "args": { + "External id": 29574,"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": 4183437, "tid": 4183437, + "ts": 658971700007.580, "dur": 381.541, + "args": { + "External id": 29575,"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": 4183437, "tid": 4183437, + "ts": 658971700040.326, "dur": 343.497, + "args": { + "External id": 29576,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971700051.355, "dur": 326.623, + "args": { + "External id": 29577,"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": 4183437, "tid": 4183437, + "ts": 658971700414.439, "dur": 2.708, + "args": { + "External id": 29578,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 4183437, "tid": 4183437, + "ts": 658971700508.545, "dur": 8230.591, + "args": { + "External id": 29579,"Record function id": 0, "Ev Idx": 4986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971700600.217, "dur": 6.262, + "args": { + "External id": 29580,"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": 4183437, "tid": 4183437, + "ts": 658971700610.474, "dur": 1.104, + "args": { + "External id": 29581,"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": 4183437, "tid": 4183437, + "ts": 658971700613.587, "dur": 2.080, + "args": { + "External id": 29582,"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": 4183437, "tid": 4183437, + "ts": 658971700617.649, "dur": 0.934, + "args": { + "External id": 29583,"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": 4183437, "tid": 4183437, + "ts": 658971700620.013, "dur": 0.837, + "args": { + "External id": 29584,"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": 4183437, "tid": 4183437, + "ts": 658971700625.037, "dur": 0.733, + "args": { + "External id": 29585,"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": 4183437, "tid": 4183437, + "ts": 658971700627.381, "dur": 0.959, + "args": { + "External id": 29586,"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": 4183437, "tid": 4183437, + "ts": 658971700630.027, "dur": 1.863, + "args": { + "External id": 29587,"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": 4183437, "tid": 4183437, + "ts": 658971700633.336, "dur": 0.761, + "args": { + "External id": 29588,"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": 4183437, "tid": 4183437, + "ts": 658971700637.294, "dur": 0.666, + "args": { + "External id": 29589,"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": 4183437, "tid": 4183437, + "ts": 658971700694.466, "dur": 7991.825, + "args": { + "External id": 29590,"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": 4183437, "tid": 4183437, + "ts": 658971700712.214, "dur": 7939.466, + "args": { + "External id": 29591,"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": 4183437, "tid": 4183437, + "ts": 658971700730.592, "dur": 15.129, + "args": { + "External id": 29592,"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": 4183437, "tid": 4183437, + "ts": 658971700749.017, "dur": 7864.889, + "args": { + "External id": 29593,"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": 4183437, "tid": 4183437, + "ts": 658971700751.516, "dur": 7861.651, + "args": { + "External id": 29594,"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": 4183437, "tid": 4183437, + "ts": 658971700758.200, "dur": 5.342, + "args": { + "External id": 29595,"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": 4183437, "tid": 4183437, + "ts": 658971700765.309, "dur": 7844.342, + "args": { + "External id": 29596,"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": 4183437, "tid": 4183437, + "ts": 658971708887.942, "dur": 31.362, + "args": { + "External id": 29597,"Sequence number": 459893, "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": 4183437, "tid": 4183437, "ts": 658971708887.942, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971708904.795, "dur": 9.731, + "args": { + "External id": 29598,"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": 4183437, "tid": 4183437, + "ts": 658971708908.888, "dur": 5.464, + "args": { + "External id": 29599,"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": 4183437, "tid": 4183437, + "ts": 658971708984.873, "dur": 82.054, + "args": { + "External id": 29600,"Record function id": 0, "Ev Idx": 5007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971709068.374, "dur": 1070.120, + "args": { + "External id": 29601,"Record function id": 0, "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971709107.664, "dur": 1017.329, + "args": { + "External id": 29602,"Sequence number": 459894, "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": 4183437, "tid": 4183437, "ts": 658971709107.664, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971709179.328, "dur": 42.255, + "args": { + "External id": 29603,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971709235.019, "dur": 110.452, + "args": { + "External id": 29604,"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": 4183437, "tid": 4183437, + "ts": 658971709359.315, "dur": 38.037, + "args": { + "External id": 29605,"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": 4183437, "tid": 4183437, + "ts": 658971709406.027, "dur": 29.532, + "args": { + "External id": 29606,"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": 4183437, "tid": 4183437, + "ts": 658971709462.988, "dur": 26.744, + "args": { + "External id": 29607,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971709510.333, "dur": 15.001, + "args": { + "External id": 29608,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971709542.951, "dur": 163.298, + "args": { + "External id": 29609,"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": 4183437, "tid": 4183437, + "ts": 658971709592.163, "dur": 12.993, + "args": { + "External id": 29610,"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": 4183437, "tid": 4183437, + "ts": 658971709597.120, "dur": 7.343, + "args": { + "External id": 29611,"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": 4183437, "tid": 4183437, + "ts": 658971709608.015, "dur": 3.571, + "args": { + "External id": 29612,"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": 4183437, "tid": 4183437, + "ts": 658971709613.229, "dur": 1.021, + "args": { + "External id": 29613,"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": 4183437, "tid": 4183437, + "ts": 658971709616.669, "dur": 3.504, + "args": { + "External id": 29614,"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": 4183437, "tid": 4183437, + "ts": 658971709718.286, "dur": 52.601, + "args": { + "External id": 29615,"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": 4183437, "tid": 4183437, + "ts": 658971709800.606, "dur": 26.132, + "args": { + "External id": 29616,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971709835.271, "dur": 37.751, + "args": { + "External id": 29617,"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": 4183437, "tid": 4183437, + "ts": 658971709881.296, "dur": 32.962, + "args": { + "External id": 29618,"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": 4183437, "tid": 4183437, + "ts": 658971709937.397, "dur": 25.234, + "args": { + "External id": 29619,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971709968.150, "dur": 44.787, + "args": { + "External id": 29620,"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": 4183437, "tid": 4183437, + "ts": 658971710034.657, "dur": 18.345, + "args": { + "External id": 29621,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971710201.236, "dur": 92.657, + "args": { + "External id": 29622,"Record function id": 0, "Ev Idx": 5029 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971710372.928, "dur": 48.730, + "args": { + "External id": 29623,"Record function id": 0, "Ev Idx": 5030 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 4183437, "tid": 4183437, + "ts": 658971710430.794, "dur": 8884.260, + "args": { + "External id": 29624,"Record function id": 0, "Ev Idx": 5031 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 4183437, "tid": 4183437, + "ts": 658971710439.851, "dur": 949.219, + "args": { + "External id": 29625,"Record function id": 0, "Ev Idx": 5032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971710517.771, "dur": 9.264, + "args": { + "External id": 29626,"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": 4183437, "tid": 4183437, + "ts": 658971710539.880, "dur": 42.193, + "args": { + "External id": 29627,"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": 4183437, "tid": 4183437, + "ts": 658971710545.638, "dur": 2.274, + "args": { + "External id": 29628,"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": 4183437, "tid": 4183437, + "ts": 658971710552.569, "dur": 0.558, + "args": { + "External id": 29629,"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": 4183437, "tid": 4183437, + "ts": 658971710554.723, "dur": 0.692, + "args": { + "External id": 29630,"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": 4183437, "tid": 4183437, + "ts": 658971710561.718, "dur": 0.414, + "args": { + "External id": 29631,"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": 4183437, "tid": 4183437, + "ts": 658971710565.620, "dur": 0.556, + "args": { + "External id": 29632,"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": 4183437, "tid": 4183437, + "ts": 658971710567.293, "dur": 0.241, + "args": { + "External id": 29633,"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": 4183437, "tid": 4183437, + "ts": 658971710569.087, "dur": 3.438, + "args": { + "External id": 29634,"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": 4183437, "tid": 4183437, + "ts": 658971710573.987, "dur": 0.377, + "args": { + "External id": 29635,"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": 4183437, "tid": 4183437, + "ts": 658971710575.642, "dur": 0.384, + "args": { + "External id": 29636,"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": 4183437, "tid": 4183437, + "ts": 658971710592.852, "dur": 43.927, + "args": { + "External id": 29637,"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": 4183437, "tid": 4183437, + "ts": 658971710712.866, "dur": 135.196, + "args": { + "External id": 29638,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971710727.484, "dur": 6.414, + "args": { + "External id": 29639,"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": 4183437, "tid": 4183437, + "ts": 658971710740.220, "dur": 10.937, + "args": { + "External id": 29640,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971710744.886, "dur": 5.876, + "args": { + "External id": 29641,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971710748.348, "dur": 0.886, + "args": { + "External id": 29642,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971710758.696, "dur": 28.722, + "args": { + "External id": 29643,"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": 4183437, "tid": 4183437, + "ts": 658971710760.847, "dur": 2.640, + "args": { + "External id": 29644,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971710764.606, "dur": 0.457, + "args": { + "External id": 29645,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971710766.178, "dur": 0.407, + "args": { + "External id": 29646,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971710770.029, "dur": 1.327, + "args": { + "External id": 29647,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971710772.420, "dur": 0.253, + "args": { + "External id": 29648,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971710774.053, "dur": 0.160, + "args": { + "External id": 29649,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971710778.010, "dur": 0.281, + "args": { + "External id": 29650,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971710779.067, "dur": 0.337, + "args": { + "External id": 29651,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971710780.423, "dur": 2.756, + "args": { + "External id": 29652,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971710811.276, "dur": 28.501, + "args": { + "External id": 29653,"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": 4183437, "tid": 4183437, + "ts": 658971710905.179, "dur": 381.367, + "args": { + "External id": 29654,"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": 4183437, "tid": 4183437, + "ts": 658971710935.631, "dur": 345.246, + "args": { + "External id": 29655,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971710948.051, "dur": 306.004, + "args": { + "External id": 29656,"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": 4183437, "tid": 4183437, + "ts": 658971711313.511, "dur": 2.703, + "args": { + "External id": 29657,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 4183437, "tid": 4183437, + "ts": 658971711410.960, "dur": 7677.879, + "args": { + "External id": 29658,"Record function id": 0, "Ev Idx": 5065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971711506.762, "dur": 6.034, + "args": { + "External id": 29659,"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": 4183437, "tid": 4183437, + "ts": 658971711516.168, "dur": 1.078, + "args": { + "External id": 29660,"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": 4183437, "tid": 4183437, + "ts": 658971711519.907, "dur": 2.431, + "args": { + "External id": 29661,"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": 4183437, "tid": 4183437, + "ts": 658971711524.063, "dur": 0.988, + "args": { + "External id": 29662,"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": 4183437, "tid": 4183437, + "ts": 658971711526.762, "dur": 0.808, + "args": { + "External id": 29663,"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": 4183437, "tid": 4183437, + "ts": 658971711531.223, "dur": 1.160, + "args": { + "External id": 29664,"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": 4183437, "tid": 4183437, + "ts": 658971711534.043, "dur": 0.768, + "args": { + "External id": 29665,"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": 4183437, "tid": 4183437, + "ts": 658971711536.391, "dur": 1.499, + "args": { + "External id": 29666,"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": 4183437, "tid": 4183437, + "ts": 658971711539.590, "dur": 0.713, + "args": { + "External id": 29667,"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": 4183437, "tid": 4183437, + "ts": 658971711543.911, "dur": 0.752, + "args": { + "External id": 29668,"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": 4183437, "tid": 4183437, + "ts": 658971711563.616, "dur": 7475.556, + "args": { + "External id": 29669,"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": 4183437, "tid": 4183437, + "ts": 658971711580.840, "dur": 7449.616, + "args": { + "External id": 29670,"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": 4183437, "tid": 4183437, + "ts": 658971711595.929, "dur": 14.262, + "args": { + "External id": 29671,"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": 4183437, "tid": 4183437, + "ts": 658971711613.033, "dur": 7380.112, + "args": { + "External id": 29672,"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": 4183437, "tid": 4183437, + "ts": 658971711615.943, "dur": 7376.466, + "args": { + "External id": 29673,"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": 4183437, "tid": 4183437, + "ts": 658971711621.958, "dur": 5.680, + "args": { + "External id": 29674,"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": 4183437, "tid": 4183437, + "ts": 658971711629.622, "dur": 7359.182, + "args": { + "External id": 29675,"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": 4183437, "tid": 4183437, + "ts": 658971719229.656, "dur": 56.889, + "args": { + "External id": 29676,"Sequence number": 459895, "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": 4183437, "tid": 4183437, "ts": 658971719229.656, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971719252.828, "dur": 28.401, + "args": { + "External id": 29677,"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": 4183437, "tid": 4183437, + "ts": 658971719257.937, "dur": 22.821, + "args": { + "External id": 29678,"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": 4183437, "tid": 4183437, + "ts": 658971719357.068, "dur": 81.422, + "args": { + "External id": 29679,"Record function id": 0, "Ev Idx": 5086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971719440.432, "dur": 1331.997, + "args": { + "External id": 29680,"Record function id": 0, "Ev Idx": 5087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971719483.428, "dur": 1265.985, + "args": { + "External id": 29681,"Sequence number": 459896, "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": 4183437, "tid": 4183437, "ts": 658971719483.428, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971719556.544, "dur": 44.576, + "args": { + "External id": 29682,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971719614.158, "dur": 132.248, + "args": { + "External id": 29683,"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": 4183437, "tid": 4183437, + "ts": 658971719764.149, "dur": 38.804, + "args": { + "External id": 29684,"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": 4183437, "tid": 4183437, + "ts": 658971719808.769, "dur": 29.350, + "args": { + "External id": 29685,"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": 4183437, "tid": 4183437, + "ts": 658971719868.631, "dur": 29.986, + "args": { + "External id": 29686,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971719915.087, "dur": 15.380, + "args": { + "External id": 29687,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971719947.475, "dur": 132.383, + "args": { + "External id": 29688,"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": 4183437, "tid": 4183437, + "ts": 658971719998.502, "dur": 11.495, + "args": { + "External id": 29689,"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": 4183437, "tid": 4183437, + "ts": 658971720003.519, "dur": 5.587, + "args": { + "External id": 29690,"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": 4183437, "tid": 4183437, + "ts": 658971720013.177, "dur": 4.658, + "args": { + "External id": 29691,"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": 4183437, "tid": 4183437, + "ts": 658971720020.091, "dur": 0.771, + "args": { + "External id": 29692,"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": 4183437, "tid": 4183437, + "ts": 658971720025.707, "dur": 3.557, + "args": { + "External id": 29693,"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": 4183437, "tid": 4183437, + "ts": 658971720091.165, "dur": 45.063, + "args": { + "External id": 29694,"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": 4183437, "tid": 4183437, + "ts": 658971720165.689, "dur": 29.732, + "args": { + "External id": 29695,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971720203.700, "dur": 48.987, + "args": { + "External id": 29696,"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": 4183437, "tid": 4183437, + "ts": 658971720321.260, "dur": 73.634, + "args": { + "External id": 29697,"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": 4183437, "tid": 4183437, + "ts": 658971720435.878, "dur": 46.645, + "args": { + "External id": 29698,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971720491.984, "dur": 49.240, + "args": { + "External id": 29699,"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": 4183437, "tid": 4183437, + "ts": 658971720567.057, "dur": 29.213, + "args": { + "External id": 29700,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971720859.065, "dur": 97.812, + "args": { + "External id": 29701,"Record function id": 0, "Ev Idx": 5108 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971721051.761, "dur": 63.348, + "args": { + "External id": 29702,"Record function id": 0, "Ev Idx": 5109 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 4183437, "tid": 4183437, + "ts": 658971721126.694, "dur": 9249.208, + "args": { + "External id": 29703,"Record function id": 0, "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 4183437, "tid": 4183437, + "ts": 658971721137.051, "dur": 1161.589, + "args": { + "External id": 29704,"Record function id": 0, "Ev Idx": 5111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971721236.605, "dur": 13.149, + "args": { + "External id": 29705,"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": 4183437, "tid": 4183437, + "ts": 658971721299.250, "dur": 48.678, + "args": { + "External id": 29706,"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": 4183437, "tid": 4183437, + "ts": 658971721306.318, "dur": 2.747, + "args": { + "External id": 29707,"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": 4183437, "tid": 4183437, + "ts": 658971721315.307, "dur": 0.621, + "args": { + "External id": 29708,"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": 4183437, "tid": 4183437, + "ts": 658971721318.558, "dur": 0.378, + "args": { + "External id": 29709,"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": 4183437, "tid": 4183437, + "ts": 658971721321.216, "dur": 0.422, + "args": { + "External id": 29710,"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": 4183437, "tid": 4183437, + "ts": 658971721325.950, "dur": 0.526, + "args": { + "External id": 29711,"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": 4183437, "tid": 4183437, + "ts": 658971721328.586, "dur": 0.364, + "args": { + "External id": 29712,"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": 4183437, "tid": 4183437, + "ts": 658971721331.034, "dur": 4.478, + "args": { + "External id": 29713,"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": 4183437, "tid": 4183437, + "ts": 658971721337.765, "dur": 0.313, + "args": { + "External id": 29714,"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": 4183437, "tid": 4183437, + "ts": 658971721340.873, "dur": 0.295, + "args": { + "External id": 29715,"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": 4183437, "tid": 4183437, + "ts": 658971721364.218, "dur": 61.172, + "args": { + "External id": 29716,"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": 4183437, "tid": 4183437, + "ts": 658971721474.754, "dur": 173.469, + "args": { + "External id": 29717,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971721493.513, "dur": 7.793, + "args": { + "External id": 29718,"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": 4183437, "tid": 4183437, + "ts": 658971721509.278, "dur": 16.167, + "args": { + "External id": 29719,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971721515.747, "dur": 9.186, + "args": { + "External id": 29720,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971721521.531, "dur": 0.810, + "args": { + "External id": 29721,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971721537.014, "dur": 42.238, + "args": { + "External id": 29722,"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": 4183437, "tid": 4183437, + "ts": 658971721540.182, "dur": 3.013, + "args": { + "External id": 29723,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971721545.821, "dur": 0.589, + "args": { + "External id": 29724,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971721548.848, "dur": 0.400, + "args": { + "External id": 29725,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971721554.153, "dur": 1.813, + "args": { + "External id": 29726,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971721558.066, "dur": 0.393, + "args": { + "External id": 29727,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971721560.727, "dur": 0.273, + "args": { + "External id": 29728,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971721566.007, "dur": 0.569, + "args": { + "External id": 29729,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971721569.092, "dur": 0.320, + "args": { + "External id": 29730,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971721571.338, "dur": 2.736, + "args": { + "External id": 29731,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971721596.092, "dur": 39.479, + "args": { + "External id": 29732,"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": 4183437, "tid": 4183437, + "ts": 658971721772.555, "dur": 400.500, + "args": { + "External id": 29733,"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": 4183437, "tid": 4183437, + "ts": 658971721815.298, "dur": 352.389, + "args": { + "External id": 29734,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971721829.393, "dur": 332.057, + "args": { + "External id": 29735,"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": 4183437, "tid": 4183437, + "ts": 658971722197.598, "dur": 2.396, + "args": { + "External id": 29736,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 4183437, "tid": 4183437, + "ts": 658971722322.546, "dur": 7748.423, + "args": { + "External id": 29737,"Record function id": 0, "Ev Idx": 5144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971722418.054, "dur": 6.855, + "args": { + "External id": 29738,"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": 4183437, "tid": 4183437, + "ts": 658971722428.332, "dur": 0.928, + "args": { + "External id": 29739,"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": 4183437, "tid": 4183437, + "ts": 658971722431.110, "dur": 1.912, + "args": { + "External id": 29740,"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": 4183437, "tid": 4183437, + "ts": 658971722434.953, "dur": 0.558, + "args": { + "External id": 29741,"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": 4183437, "tid": 4183437, + "ts": 658971722436.734, "dur": 0.815, + "args": { + "External id": 29742,"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": 4183437, "tid": 4183437, + "ts": 658971722438.757, "dur": 0.799, + "args": { + "External id": 29743,"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": 4183437, "tid": 4183437, + "ts": 658971722443.483, "dur": 0.748, + "args": { + "External id": 29744,"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": 4183437, "tid": 4183437, + "ts": 658971722445.677, "dur": 1.732, + "args": { + "External id": 29745,"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": 4183437, "tid": 4183437, + "ts": 658971722448.759, "dur": 0.459, + "args": { + "External id": 29746,"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": 4183437, "tid": 4183437, + "ts": 658971722451.000, "dur": 0.482, + "args": { + "External id": 29747,"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": 4183437, "tid": 4183437, + "ts": 658971722472.498, "dur": 7521.657, + "args": { + "External id": 29748,"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": 4183437, "tid": 4183437, + "ts": 658971722489.606, "dur": 7490.046, + "args": { + "External id": 29749,"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": 4183437, "tid": 4183437, + "ts": 658971722510.160, "dur": 14.358, + "args": { + "External id": 29750,"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": 4183437, "tid": 4183437, + "ts": 658971722527.455, "dur": 7389.862, + "args": { + "External id": 29751,"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": 4183437, "tid": 4183437, + "ts": 658971722530.066, "dur": 7385.804, + "args": { + "External id": 29752,"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": 4183437, "tid": 4183437, + "ts": 658971722536.629, "dur": 4.860, + "args": { + "External id": 29753,"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": 4183437, "tid": 4183437, + "ts": 658971722543.254, "dur": 7365.947, + "args": { + "External id": 29754,"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": 4183437, "tid": 4183437, + "ts": 658971730289.685, "dur": 47.691, + "args": { + "External id": 29755,"Sequence number": 459897, "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": 4183437, "tid": 4183437, "ts": 658971730289.685, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971730315.410, "dur": 15.358, + "args": { + "External id": 29756,"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": 4183437, "tid": 4183437, + "ts": 658971730321.733, "dur": 8.390, + "args": { + "External id": 29757,"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": 4183437, "tid": 4183437, + "ts": 658971730422.910, "dur": 84.446, + "args": { + "External id": 29758,"Record function id": 0, "Ev Idx": 5165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971730508.931, "dur": 1132.835, + "args": { + "External id": 29759,"Record function id": 0, "Ev Idx": 5166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971730554.801, "dur": 1068.473, + "args": { + "External id": 29760,"Sequence number": 459898, "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": 4183437, "tid": 4183437, "ts": 658971730554.801, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971730629.271, "dur": 93.545, + "args": { + "External id": 29761,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971730740.167, "dur": 97.160, + "args": { + "External id": 29762,"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": 4183437, "tid": 4183437, + "ts": 658971730847.162, "dur": 36.676, + "args": { + "External id": 29763,"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": 4183437, "tid": 4183437, + "ts": 658971730893.994, "dur": 31.371, + "args": { + "External id": 29764,"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": 4183437, "tid": 4183437, + "ts": 658971730953.519, "dur": 26.753, + "args": { + "External id": 29765,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971730998.218, "dur": 15.905, + "args": { + "External id": 29766,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971731032.675, "dur": 131.117, + "args": { + "External id": 29767,"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": 4183437, "tid": 4183437, + "ts": 658971731081.713, "dur": 11.846, + "args": { + "External id": 29768,"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": 4183437, "tid": 4183437, + "ts": 658971731087.058, "dur": 5.683, + "args": { + "External id": 29769,"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": 4183437, "tid": 4183437, + "ts": 658971731096.483, "dur": 6.058, + "args": { + "External id": 29770,"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": 4183437, "tid": 4183437, + "ts": 658971731103.986, "dur": 0.766, + "args": { + "External id": 29771,"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": 4183437, "tid": 4183437, + "ts": 658971731107.276, "dur": 3.573, + "args": { + "External id": 29772,"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": 4183437, "tid": 4183437, + "ts": 658971731173.916, "dur": 41.886, + "args": { + "External id": 29773,"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": 4183437, "tid": 4183437, + "ts": 658971731245.810, "dur": 55.111, + "args": { + "External id": 29774,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971731312.701, "dur": 41.537, + "args": { + "External id": 29775,"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": 4183437, "tid": 4183437, + "ts": 658971731362.285, "dur": 33.238, + "args": { + "External id": 29776,"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": 4183437, "tid": 4183437, + "ts": 658971731420.190, "dur": 28.040, + "args": { + "External id": 29777,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971731454.236, "dur": 47.487, + "args": { + "External id": 29778,"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": 4183437, "tid": 4183437, + "ts": 658971731522.288, "dur": 18.424, + "args": { + "External id": 29779,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971731766.762, "dur": 103.497, + "args": { + "External id": 29780,"Record function id": 0, "Ev Idx": 5187 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971731967.292, "dur": 63.905, + "args": { + "External id": 29781,"Record function id": 0, "Ev Idx": 5188 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 4183437, "tid": 4183437, + "ts": 658971732043.740, "dur": 9375.098, + "args": { + "External id": 29782,"Record function id": 0, "Ev Idx": 5189 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 4183437, "tid": 4183437, + "ts": 658971732055.489, "dur": 1165.752, + "args": { + "External id": 29783,"Record function id": 0, "Ev Idx": 5190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971732147.918, "dur": 11.496, + "args": { + "External id": 29784,"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": 4183437, "tid": 4183437, + "ts": 658971732173.596, "dur": 41.143, + "args": { + "External id": 29785,"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": 4183437, "tid": 4183437, + "ts": 658971732179.451, "dur": 2.440, + "args": { + "External id": 29786,"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": 4183437, "tid": 4183437, + "ts": 658971732186.985, "dur": 0.366, + "args": { + "External id": 29787,"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": 4183437, "tid": 4183437, + "ts": 658971732189.008, "dur": 0.229, + "args": { + "External id": 29788,"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": 4183437, "tid": 4183437, + "ts": 658971732190.994, "dur": 0.266, + "args": { + "External id": 29789,"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": 4183437, "tid": 4183437, + "ts": 658971732195.021, "dur": 0.282, + "args": { + "External id": 29790,"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": 4183437, "tid": 4183437, + "ts": 658971732197.203, "dur": 0.681, + "args": { + "External id": 29791,"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": 4183437, "tid": 4183437, + "ts": 658971732199.904, "dur": 4.228, + "args": { + "External id": 29792,"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": 4183437, "tid": 4183437, + "ts": 658971732206.197, "dur": 0.328, + "args": { + "External id": 29793,"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": 4183437, "tid": 4183437, + "ts": 658971732208.228, "dur": 0.334, + "args": { + "External id": 29794,"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": 4183437, "tid": 4183437, + "ts": 658971732226.285, "dur": 66.147, + "args": { + "External id": 29795,"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": 4183437, "tid": 4183437, + "ts": 658971732331.098, "dur": 125.258, + "args": { + "External id": 29796,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971732345.138, "dur": 5.464, + "args": { + "External id": 29797,"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": 4183437, "tid": 4183437, + "ts": 658971732356.908, "dur": 11.195, + "args": { + "External id": 29798,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971732361.427, "dur": 6.250, + "args": { + "External id": 29799,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971732365.315, "dur": 0.740, + "args": { + "External id": 29800,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971732375.565, "dur": 29.518, + "args": { + "External id": 29801,"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": 4183437, "tid": 4183437, + "ts": 658971732377.805, "dur": 2.596, + "args": { + "External id": 29802,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971732382.211, "dur": 0.198, + "args": { + "External id": 29803,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971732384.085, "dur": 0.216, + "args": { + "External id": 29804,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971732388.428, "dur": 1.682, + "args": { + "External id": 29805,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971732391.411, "dur": 0.192, + "args": { + "External id": 29806,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971732393.195, "dur": 0.163, + "args": { + "External id": 29807,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971732395.916, "dur": 0.156, + "args": { + "External id": 29808,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971732397.379, "dur": 0.144, + "args": { + "External id": 29809,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971732398.676, "dur": 2.385, + "args": { + "External id": 29810,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971732420.197, "dur": 27.853, + "args": { + "External id": 29811,"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": 4183437, "tid": 4183437, + "ts": 658971732512.415, "dur": 587.817, + "args": { + "External id": 29812,"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": 4183437, "tid": 4183437, + "ts": 658971732543.757, "dur": 549.374, + "args": { + "External id": 29813,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971732556.398, "dur": 528.917, + "args": { + "External id": 29814,"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": 4183437, "tid": 4183437, + "ts": 658971733132.399, "dur": 3.151, + "args": { + "External id": 29815,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 4183437, "tid": 4183437, + "ts": 658971733248.287, "dur": 7885.542, + "args": { + "External id": 29816,"Record function id": 0, "Ev Idx": 5223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971733405.914, "dur": 8.691, + "args": { + "External id": 29817,"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": 4183437, "tid": 4183437, + "ts": 658971733419.997, "dur": 1.373, + "args": { + "External id": 29818,"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": 4183437, "tid": 4183437, + "ts": 658971733424.073, "dur": 3.069, + "args": { + "External id": 29819,"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": 4183437, "tid": 4183437, + "ts": 658971733429.662, "dur": 1.249, + "args": { + "External id": 29820,"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": 4183437, "tid": 4183437, + "ts": 658971733433.123, "dur": 1.117, + "args": { + "External id": 29821,"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": 4183437, "tid": 4183437, + "ts": 658971733436.531, "dur": 1.369, + "args": { + "External id": 29822,"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": 4183437, "tid": 4183437, + "ts": 658971733443.598, "dur": 1.208, + "args": { + "External id": 29823,"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": 4183437, "tid": 4183437, + "ts": 658971733447.212, "dur": 2.312, + "args": { + "External id": 29824,"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": 4183437, "tid": 4183437, + "ts": 658971733452.273, "dur": 1.163, + "args": { + "External id": 29825,"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": 4183437, "tid": 4183437, + "ts": 658971733455.554, "dur": 0.762, + "args": { + "External id": 29826,"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": 4183437, "tid": 4183437, + "ts": 658971733483.258, "dur": 7581.072, + "args": { + "External id": 29827,"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": 4183437, "tid": 4183437, + "ts": 658971733513.917, "dur": 7536.882, + "args": { + "External id": 29828,"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": 4183437, "tid": 4183437, + "ts": 658971733531.573, "dur": 18.414, + "args": { + "External id": 29829,"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": 4183437, "tid": 4183437, + "ts": 658971733554.148, "dur": 7443.009, + "args": { + "External id": 29830,"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": 4183437, "tid": 4183437, + "ts": 658971733557.232, "dur": 7438.476, + "args": { + "External id": 29831,"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": 4183437, "tid": 4183437, + "ts": 658971733564.203, "dur": 6.564, + "args": { + "External id": 29832,"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": 4183437, "tid": 4183437, + "ts": 658971733573.293, "dur": 7416.519, + "args": { + "External id": 29833,"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": 4183437, "tid": 4183437, + "ts": 658971741338.104, "dur": 42.961, + "args": { + "External id": 29834,"Sequence number": 459899, "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": 4183437, "tid": 4183437, "ts": 658971741338.104, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971741361.273, "dur": 13.930, + "args": { + "External id": 29835,"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": 4183437, "tid": 4183437, + "ts": 658971741367.209, "dur": 7.385, + "args": { + "External id": 29836,"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": 4183437, "tid": 4183437, + "ts": 658971741470.520, "dur": 106.300, + "args": { + "External id": 29837,"Record function id": 0, "Ev Idx": 5244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971741579.528, "dur": 1497.553, + "args": { + "External id": 29838,"Record function id": 0, "Ev Idx": 5245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971741639.759, "dur": 1421.406, + "args": { + "External id": 29839,"Sequence number": 459900, "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": 4183437, "tid": 4183437, "ts": 658971741639.759, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971741771.719, "dur": 60.078, + "args": { + "External id": 29840,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971741850.443, "dur": 104.779, + "args": { + "External id": 29841,"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": 4183437, "tid": 4183437, + "ts": 658971741967.211, "dur": 49.422, + "args": { + "External id": 29842,"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": 4183437, "tid": 4183437, + "ts": 658971742031.949, "dur": 42.846, + "args": { + "External id": 29843,"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": 4183437, "tid": 4183437, + "ts": 658971742117.079, "dur": 37.248, + "args": { + "External id": 29844,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971742180.728, "dur": 22.877, + "args": { + "External id": 29845,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971742238.093, "dur": 225.208, + "args": { + "External id": 29846,"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": 4183437, "tid": 4183437, + "ts": 658971742324.891, "dur": 24.612, + "args": { + "External id": 29847,"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": 4183437, "tid": 4183437, + "ts": 658971742332.298, "dur": 15.687, + "args": { + "External id": 29848,"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": 4183437, "tid": 4183437, + "ts": 658971742353.267, "dur": 6.011, + "args": { + "External id": 29849,"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": 4183437, "tid": 4183437, + "ts": 658971742363.031, "dur": 1.684, + "args": { + "External id": 29850,"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": 4183437, "tid": 4183437, + "ts": 658971742369.070, "dur": 5.426, + "args": { + "External id": 29851,"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": 4183437, "tid": 4183437, + "ts": 658971742483.112, "dur": 102.012, + "args": { + "External id": 29852,"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": 4183437, "tid": 4183437, + "ts": 658971742640.372, "dur": 86.791, + "args": { + "External id": 29853,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971742745.537, "dur": 59.574, + "args": { + "External id": 29854,"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": 4183437, "tid": 4183437, + "ts": 658971742815.723, "dur": 34.093, + "args": { + "External id": 29855,"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": 4183437, "tid": 4183437, + "ts": 658971742876.262, "dur": 27.693, + "args": { + "External id": 29856,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971742910.124, "dur": 33.394, + "args": { + "External id": 29857,"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": 4183437, "tid": 4183437, + "ts": 658971742967.904, "dur": 18.886, + "args": { + "External id": 29858,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971743144.797, "dur": 76.272, + "args": { + "External id": 29859,"Record function id": 0, "Ev Idx": 5266 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971743312.603, "dur": 48.576, + "args": { + "External id": 29860,"Record function id": 0, "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 4183437, "tid": 4183437, + "ts": 658971743370.414, "dur": 8812.522, + "args": { + "External id": 29861,"Record function id": 0, "Ev Idx": 5268 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 4183437, "tid": 4183437, + "ts": 658971743378.573, "dur": 920.157, + "args": { + "External id": 29862,"Record function id": 0, "Ev Idx": 5269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971743457.543, "dur": 10.143, + "args": { + "External id": 29863,"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": 4183437, "tid": 4183437, + "ts": 658971743481.125, "dur": 34.845, + "args": { + "External id": 29864,"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": 4183437, "tid": 4183437, + "ts": 658971743486.359, "dur": 2.496, + "args": { + "External id": 29865,"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": 4183437, "tid": 4183437, + "ts": 658971743493.716, "dur": 0.653, + "args": { + "External id": 29866,"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": 4183437, "tid": 4183437, + "ts": 658971743495.729, "dur": 0.242, + "args": { + "External id": 29867,"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": 4183437, "tid": 4183437, + "ts": 658971743497.376, "dur": 0.249, + "args": { + "External id": 29868,"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": 4183437, "tid": 4183437, + "ts": 658971743501.056, "dur": 0.498, + "args": { + "External id": 29869,"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": 4183437, "tid": 4183437, + "ts": 658971743502.447, "dur": 0.398, + "args": { + "External id": 29870,"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": 4183437, "tid": 4183437, + "ts": 658971743504.449, "dur": 3.158, + "args": { + "External id": 29871,"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": 4183437, "tid": 4183437, + "ts": 658971743508.593, "dur": 0.204, + "args": { + "External id": 29872,"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": 4183437, "tid": 4183437, + "ts": 658971743510.052, "dur": 0.182, + "args": { + "External id": 29873,"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": 4183437, "tid": 4183437, + "ts": 658971743527.329, "dur": 42.898, + "args": { + "External id": 29874,"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": 4183437, "tid": 4183437, + "ts": 658971743603.969, "dur": 160.957, + "args": { + "External id": 29875,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971743616.646, "dur": 3.916, + "args": { + "External id": 29876,"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": 4183437, "tid": 4183437, + "ts": 658971743626.258, "dur": 9.717, + "args": { + "External id": 29877,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971743630.556, "dur": 4.979, + "args": { + "External id": 29878,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971743633.810, "dur": 0.609, + "args": { + "External id": 29879,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971743642.619, "dur": 69.949, + "args": { + "External id": 29880,"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": 4183437, "tid": 4183437, + "ts": 658971743644.818, "dur": 2.611, + "args": { + "External id": 29881,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971743648.502, "dur": 0.316, + "args": { + "External id": 29882,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971743650.395, "dur": 0.185, + "args": { + "External id": 29883,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971743691.113, "dur": 1.997, + "args": { + "External id": 29884,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971743695.822, "dur": 0.193, + "args": { + "External id": 29885,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971743697.654, "dur": 0.177, + "args": { + "External id": 29886,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971743701.924, "dur": 0.343, + "args": { + "External id": 29887,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971743703.674, "dur": 0.155, + "args": { + "External id": 29888,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971743705.429, "dur": 2.544, + "args": { + "External id": 29889,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971743727.417, "dur": 28.357, + "args": { + "External id": 29890,"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": 4183437, "tid": 4183437, + "ts": 658971743822.445, "dur": 368.662, + "args": { + "External id": 29891,"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": 4183437, "tid": 4183437, + "ts": 658971743853.498, "dur": 333.182, + "args": { + "External id": 29892,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971743864.138, "dur": 316.796, + "args": { + "External id": 29893,"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": 4183437, "tid": 4183437, + "ts": 658971744212.534, "dur": 2.204, + "args": { + "External id": 29894,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 4183437, "tid": 4183437, + "ts": 658971744321.737, "dur": 7603.840, + "args": { + "External id": 29895,"Record function id": 0, "Ev Idx": 5302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971744417.156, "dur": 6.026, + "args": { + "External id": 29896,"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": 4183437, "tid": 4183437, + "ts": 658971744426.491, "dur": 1.027, + "args": { + "External id": 29897,"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": 4183437, "tid": 4183437, + "ts": 658971744429.222, "dur": 2.883, + "args": { + "External id": 29898,"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": 4183437, "tid": 4183437, + "ts": 658971744434.065, "dur": 0.806, + "args": { + "External id": 29899,"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": 4183437, "tid": 4183437, + "ts": 658971744436.232, "dur": 0.722, + "args": { + "External id": 29900,"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": 4183437, "tid": 4183437, + "ts": 658971744438.310, "dur": 0.833, + "args": { + "External id": 29901,"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": 4183437, "tid": 4183437, + "ts": 658971744442.479, "dur": 0.797, + "args": { + "External id": 29902,"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": 4183437, "tid": 4183437, + "ts": 658971744444.822, "dur": 1.679, + "args": { + "External id": 29903,"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": 4183437, "tid": 4183437, + "ts": 658971744447.925, "dur": 0.993, + "args": { + "External id": 29904,"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": 4183437, "tid": 4183437, + "ts": 658971744450.300, "dur": 0.726, + "args": { + "External id": 29905,"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": 4183437, "tid": 4183437, + "ts": 658971744470.396, "dur": 7383.232, + "args": { + "External id": 29906,"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": 4183437, "tid": 4183437, + "ts": 658971744486.214, "dur": 7353.924, + "args": { + "External id": 29907,"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": 4183437, "tid": 4183437, + "ts": 658971744500.716, "dur": 15.461, + "args": { + "External id": 29908,"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": 4183437, "tid": 4183437, + "ts": 658971744518.834, "dur": 7266.026, + "args": { + "External id": 29909,"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": 4183437, "tid": 4183437, + "ts": 658971744521.560, "dur": 7261.740, + "args": { + "External id": 29910,"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": 4183437, "tid": 4183437, + "ts": 658971744528.107, "dur": 7.565, + "args": { + "External id": 29911,"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": 4183437, "tid": 4183437, + "ts": 658971744537.873, "dur": 7239.034, + "args": { + "External id": 29912,"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": 4183437, "tid": 4183437, + "ts": 658971752107.182, "dur": 42.431, + "args": { + "External id": 29913,"Sequence number": 459901, "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": 4183437, "tid": 4183437, "ts": 658971752107.182, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971752131.589, "dur": 12.777, + "args": { + "External id": 29914,"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": 4183437, "tid": 4183437, + "ts": 658971752137.064, "dur": 6.827, + "args": { + "External id": 29915,"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": 4183437, "tid": 4183437, + "ts": 658971752231.836, "dur": 126.587, + "args": { + "External id": 29916,"Record function id": 0, "Ev Idx": 5323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971752363.109, "dur": 1507.218, + "args": { + "External id": 29917,"Record function id": 0, "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971752419.685, "dur": 1429.201, + "args": { + "External id": 29918,"Sequence number": 459902, "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": 4183437, "tid": 4183437, "ts": 658971752419.685, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971752507.603, "dur": 56.656, + "args": { + "External id": 29919,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971752581.793, "dur": 156.418, + "args": { + "External id": 29920,"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": 4183437, "tid": 4183437, + "ts": 658971752759.710, "dur": 57.030, + "args": { + "External id": 29921,"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": 4183437, "tid": 4183437, + "ts": 658971752830.415, "dur": 40.944, + "args": { + "External id": 29922,"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": 4183437, "tid": 4183437, + "ts": 658971752914.814, "dur": 41.436, + "args": { + "External id": 29923,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971752982.580, "dur": 22.271, + "args": { + "External id": 29924,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971753030.192, "dur": 167.024, + "args": { + "External id": 29925,"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": 4183437, "tid": 4183437, + "ts": 658971753091.884, "dur": 15.053, + "args": { + "External id": 29926,"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": 4183437, "tid": 4183437, + "ts": 658971753098.307, "dur": 7.585, + "args": { + "External id": 29927,"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": 4183437, "tid": 4183437, + "ts": 658971753110.928, "dur": 7.297, + "args": { + "External id": 29928,"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": 4183437, "tid": 4183437, + "ts": 658971753119.929, "dur": 1.924, + "args": { + "External id": 29929,"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": 4183437, "tid": 4183437, + "ts": 658971753125.265, "dur": 5.494, + "args": { + "External id": 29930,"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": 4183437, "tid": 4183437, + "ts": 658971753212.481, "dur": 81.755, + "args": { + "External id": 29931,"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": 4183437, "tid": 4183437, + "ts": 658971753344.098, "dur": 42.758, + "args": { + "External id": 29932,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971753400.588, "dur": 67.546, + "args": { + "External id": 29933,"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": 4183437, "tid": 4183437, + "ts": 658971753480.536, "dur": 46.898, + "args": { + "External id": 29934,"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": 4183437, "tid": 4183437, + "ts": 658971753558.720, "dur": 35.374, + "args": { + "External id": 29935,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971753602.520, "dur": 43.976, + "args": { + "External id": 29936,"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": 4183437, "tid": 4183437, + "ts": 658971753717.994, "dur": 30.306, + "args": { + "External id": 29937,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971753950.137, "dur": 97.333, + "args": { + "External id": 29938,"Record function id": 0, "Ev Idx": 5345 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971754142.495, "dur": 62.045, + "args": { + "External id": 29939,"Record function id": 0, "Ev Idx": 5346 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 4183437, "tid": 4183437, + "ts": 658971754217.089, "dur": 8852.939, + "args": { + "External id": 29940,"Record function id": 0, "Ev Idx": 5347 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 4183437, "tid": 4183437, + "ts": 658971754228.897, "dur": 1209.652, + "args": { + "External id": 29941,"Record function id": 0, "Ev Idx": 5348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971754354.427, "dur": 13.339, + "args": { + "External id": 29942,"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": 4183437, "tid": 4183437, + "ts": 658971754386.713, "dur": 44.868, + "args": { + "External id": 29943,"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": 4183437, "tid": 4183437, + "ts": 658971754393.652, "dur": 2.643, + "args": { + "External id": 29944,"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": 4183437, "tid": 4183437, + "ts": 658971754401.360, "dur": 0.507, + "args": { + "External id": 29945,"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": 4183437, "tid": 4183437, + "ts": 658971754403.629, "dur": 0.940, + "args": { + "External id": 29946,"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": 4183437, "tid": 4183437, + "ts": 658971754406.516, "dur": 0.545, + "args": { + "External id": 29947,"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": 4183437, "tid": 4183437, + "ts": 658971754410.845, "dur": 0.560, + "args": { + "External id": 29948,"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": 4183437, "tid": 4183437, + "ts": 658971754412.963, "dur": 0.548, + "args": { + "External id": 29949,"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": 4183437, "tid": 4183437, + "ts": 658971754415.218, "dur": 4.081, + "args": { + "External id": 29950,"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": 4183437, "tid": 4183437, + "ts": 658971754421.621, "dur": 0.492, + "args": { + "External id": 29951,"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": 4183437, "tid": 4183437, + "ts": 658971754423.892, "dur": 0.303, + "args": { + "External id": 29952,"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": 4183437, "tid": 4183437, + "ts": 658971754446.311, "dur": 56.142, + "args": { + "External id": 29953,"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": 4183437, "tid": 4183437, + "ts": 658971754549.895, "dur": 202.393, + "args": { + "External id": 29954,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971754563.942, "dur": 6.260, + "args": { + "External id": 29955,"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": 4183437, "tid": 4183437, + "ts": 658971754578.090, "dur": 13.010, + "args": { + "External id": 29956,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971754583.429, "dur": 7.131, + "args": { + "External id": 29957,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971754588.043, "dur": 0.659, + "args": { + "External id": 29958,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971754601.362, "dur": 37.763, + "args": { + "External id": 29959,"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": 4183437, "tid": 4183437, + "ts": 658971754603.882, "dur": 2.563, + "args": { + "External id": 29960,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971754608.548, "dur": 0.447, + "args": { + "External id": 29961,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971754610.938, "dur": 0.436, + "args": { + "External id": 29962,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971754615.806, "dur": 2.214, + "args": { + "External id": 29963,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971754619.671, "dur": 0.403, + "args": { + "External id": 29964,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971754621.852, "dur": 0.410, + "args": { + "External id": 29965,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971754626.917, "dur": 0.404, + "args": { + "External id": 29966,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971754629.347, "dur": 0.557, + "args": { + "External id": 29967,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971754631.408, "dur": 2.613, + "args": { + "External id": 29968,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971754698.680, "dur": 39.446, + "args": { + "External id": 29969,"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": 4183437, "tid": 4183437, + "ts": 658971754833.278, "dur": 471.350, + "args": { + "External id": 29970,"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": 4183437, "tid": 4183437, + "ts": 658971754868.671, "dur": 428.408, + "args": { + "External id": 29971,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971754882.030, "dur": 405.867, + "args": { + "External id": 29972,"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": 4183437, "tid": 4183437, + "ts": 658971755337.641, "dur": 4.088, + "args": { + "External id": 29973,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 4183437, "tid": 4183437, + "ts": 658971755467.514, "dur": 7321.007, + "args": { + "External id": 29974,"Record function id": 0, "Ev Idx": 5381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971755598.495, "dur": 7.891, + "args": { + "External id": 29975,"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": 4183437, "tid": 4183437, + "ts": 658971755611.156, "dur": 1.598, + "args": { + "External id": 29976,"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": 4183437, "tid": 4183437, + "ts": 658971755615.536, "dur": 3.213, + "args": { + "External id": 29977,"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": 4183437, "tid": 4183437, + "ts": 658971755623.093, "dur": 0.971, + "args": { + "External id": 29978,"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": 4183437, "tid": 4183437, + "ts": 658971755626.471, "dur": 0.764, + "args": { + "External id": 29979,"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": 4183437, "tid": 4183437, + "ts": 658971755629.524, "dur": 1.076, + "args": { + "External id": 29980,"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": 4183437, "tid": 4183437, + "ts": 658971755633.011, "dur": 1.244, + "args": { + "External id": 29981,"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": 4183437, "tid": 4183437, + "ts": 658971755639.391, "dur": 2.531, + "args": { + "External id": 29982,"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": 4183437, "tid": 4183437, + "ts": 658971755644.193, "dur": 0.754, + "args": { + "External id": 29983,"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": 4183437, "tid": 4183437, + "ts": 658971755647.331, "dur": 1.007, + "args": { + "External id": 29984,"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": 4183437, "tid": 4183437, + "ts": 658971755718.073, "dur": 6995.931, + "args": { + "External id": 29985,"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": 4183437, "tid": 4183437, + "ts": 658971755740.496, "dur": 6898.235, + "args": { + "External id": 29986,"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": 4183437, "tid": 4183437, + "ts": 658971755757.999, "dur": 19.282, + "args": { + "External id": 29987,"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": 4183437, "tid": 4183437, + "ts": 658971755783.124, "dur": 6796.582, + "args": { + "External id": 29988,"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": 4183437, "tid": 4183437, + "ts": 658971755786.451, "dur": 6791.728, + "args": { + "External id": 29989,"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": 4183437, "tid": 4183437, + "ts": 658971755793.711, "dur": 10.039, + "args": { + "External id": 29990,"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": 4183437, "tid": 4183437, + "ts": 658971755806.063, "dur": 6765.966, + "args": { + "External id": 29991,"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": 4183437, "tid": 4183437, + "ts": 658971762986.807, "dur": 46.812, + "args": { + "External id": 29992,"Sequence number": 459903, "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": 4183437, "tid": 4183437, "ts": 658971762986.807, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971763014.045, "dur": 14.005, + "args": { + "External id": 29993,"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": 4183437, "tid": 4183437, + "ts": 658971763019.810, "dur": 7.650, + "args": { + "External id": 29994,"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": 4183437, "tid": 4183437, + "ts": 658971763120.282, "dur": 106.419, + "args": { + "External id": 29995,"Record function id": 0, "Ev Idx": 5402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971763229.523, "dur": 1381.248, + "args": { + "External id": 29996,"Record function id": 0, "Ev Idx": 5403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971763318.981, "dur": 1275.298, + "args": { + "External id": 29997,"Sequence number": 459904, "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": 4183437, "tid": 4183437, "ts": 658971763318.981, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971763413.848, "dur": 68.079, + "args": { + "External id": 29998,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971763500.503, "dur": 117.432, + "args": { + "External id": 29999,"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": 4183437, "tid": 4183437, + "ts": 658971763633.391, "dur": 115.969, + "args": { + "External id": 30000,"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": 4183437, "tid": 4183437, + "ts": 658971763768.533, "dur": 49.682, + "args": { + "External id": 30001,"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": 4183437, "tid": 4183437, + "ts": 658971763856.753, "dur": 39.609, + "args": { + "External id": 30002,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971763924.056, "dur": 21.365, + "args": { + "External id": 30003,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971763968.356, "dur": 145.903, + "args": { + "External id": 30004,"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": 4183437, "tid": 4183437, + "ts": 658971764022.699, "dur": 13.414, + "args": { + "External id": 30005,"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": 4183437, "tid": 4183437, + "ts": 658971764028.386, "dur": 6.968, + "args": { + "External id": 30006,"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": 4183437, "tid": 4183437, + "ts": 658971764039.304, "dur": 6.237, + "args": { + "External id": 30007,"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": 4183437, "tid": 4183437, + "ts": 658971764051.422, "dur": 1.137, + "args": { + "External id": 30008,"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": 4183437, "tid": 4183437, + "ts": 658971764054.982, "dur": 4.413, + "args": { + "External id": 30009,"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": 4183437, "tid": 4183437, + "ts": 658971764125.193, "dur": 52.939, + "args": { + "External id": 30010,"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": 4183437, "tid": 4183437, + "ts": 658971764213.647, "dur": 31.610, + "args": { + "External id": 30011,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971764253.949, "dur": 85.596, + "args": { + "External id": 30012,"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": 4183437, "tid": 4183437, + "ts": 658971764351.736, "dur": 35.496, + "args": { + "External id": 30013,"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": 4183437, "tid": 4183437, + "ts": 658971764411.882, "dur": 29.256, + "args": { + "External id": 30014,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971764446.615, "dur": 32.547, + "args": { + "External id": 30015,"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": 4183437, "tid": 4183437, + "ts": 658971764501.598, "dur": 17.591, + "args": { + "External id": 30016,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971764722.528, "dur": 82.746, + "args": { + "External id": 30017,"Record function id": 0, "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971764884.166, "dur": 48.020, + "args": { + "External id": 30018,"Record function id": 0, "Ev Idx": 5425 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 4183437, "tid": 4183437, + "ts": 658971764941.252, "dur": 8238.675, + "args": { + "External id": 30019,"Record function id": 0, "Ev Idx": 5426 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 4183437, "tid": 4183437, + "ts": 658971764949.725, "dur": 948.848, + "args": { + "External id": 30020,"Record function id": 0, "Ev Idx": 5427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971765036.150, "dur": 10.217, + "args": { + "External id": 30021,"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": 4183437, "tid": 4183437, + "ts": 658971765059.575, "dur": 37.805, + "args": { + "External id": 30022,"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": 4183437, "tid": 4183437, + "ts": 658971765065.130, "dur": 2.228, + "args": { + "External id": 30023,"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": 4183437, "tid": 4183437, + "ts": 658971765072.615, "dur": 0.630, + "args": { + "External id": 30024,"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": 4183437, "tid": 4183437, + "ts": 658971765074.793, "dur": 0.588, + "args": { + "External id": 30025,"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": 4183437, "tid": 4183437, + "ts": 658971765076.841, "dur": 0.458, + "args": { + "External id": 30026,"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": 4183437, "tid": 4183437, + "ts": 658971765080.081, "dur": 0.214, + "args": { + "External id": 30027,"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": 4183437, "tid": 4183437, + "ts": 658971765081.595, "dur": 0.266, + "args": { + "External id": 30028,"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": 4183437, "tid": 4183437, + "ts": 658971765083.155, "dur": 4.081, + "args": { + "External id": 30029,"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": 4183437, "tid": 4183437, + "ts": 658971765088.703, "dur": 0.212, + "args": { + "External id": 30030,"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": 4183437, "tid": 4183437, + "ts": 658971765090.342, "dur": 0.274, + "args": { + "External id": 30031,"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": 4183437, "tid": 4183437, + "ts": 658971765108.328, "dur": 45.348, + "args": { + "External id": 30032,"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": 4183437, "tid": 4183437, + "ts": 658971765189.137, "dur": 140.986, + "args": { + "External id": 30033,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971765199.907, "dur": 4.177, + "args": { + "External id": 30034,"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": 4183437, "tid": 4183437, + "ts": 658971765209.711, "dur": 10.043, + "args": { + "External id": 30035,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971765214.025, "dur": 5.292, + "args": { + "External id": 30036,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971765217.411, "dur": 0.683, + "args": { + "External id": 30037,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971765226.811, "dur": 33.742, + "args": { + "External id": 30038,"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": 4183437, "tid": 4183437, + "ts": 658971765229.347, "dur": 2.635, + "args": { + "External id": 30039,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971765233.479, "dur": 0.461, + "args": { + "External id": 30040,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971765235.494, "dur": 0.499, + "args": { + "External id": 30041,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971765240.625, "dur": 1.915, + "args": { + "External id": 30042,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971765244.176, "dur": 0.280, + "args": { + "External id": 30043,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971765246.630, "dur": 0.526, + "args": { + "External id": 30044,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971765250.463, "dur": 0.289, + "args": { + "External id": 30045,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971765252.169, "dur": 0.351, + "args": { + "External id": 30046,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971765253.857, "dur": 2.803, + "args": { + "External id": 30047,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971765293.950, "dur": 27.385, + "args": { + "External id": 30048,"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": 4183437, "tid": 4183437, + "ts": 658971765384.569, "dur": 412.366, + "args": { + "External id": 30049,"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": 4183437, "tid": 4183437, + "ts": 658971765415.436, "dur": 376.239, + "args": { + "External id": 30050,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971765426.077, "dur": 359.626, + "args": { + "External id": 30051,"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": 4183437, "tid": 4183437, + "ts": 658971765821.848, "dur": 2.529, + "args": { + "External id": 30052,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 4183437, "tid": 4183437, + "ts": 658971765918.863, "dur": 7066.856, + "args": { + "External id": 30053,"Record function id": 0, "Ev Idx": 5460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971766013.666, "dur": 6.363, + "args": { + "External id": 30054,"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": 4183437, "tid": 4183437, + "ts": 658971766023.353, "dur": 1.132, + "args": { + "External id": 30055,"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": 4183437, "tid": 4183437, + "ts": 658971766026.271, "dur": 2.777, + "args": { + "External id": 30056,"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": 4183437, "tid": 4183437, + "ts": 658971766030.741, "dur": 0.878, + "args": { + "External id": 30057,"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": 4183437, "tid": 4183437, + "ts": 658971766032.920, "dur": 1.394, + "args": { + "External id": 30058,"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": 4183437, "tid": 4183437, + "ts": 658971766035.746, "dur": 0.568, + "args": { + "External id": 30059,"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": 4183437, "tid": 4183437, + "ts": 658971766039.761, "dur": 1.087, + "args": { + "External id": 30060,"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": 4183437, "tid": 4183437, + "ts": 658971766042.908, "dur": 2.377, + "args": { + "External id": 30061,"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": 4183437, "tid": 4183437, + "ts": 658971766046.468, "dur": 0.955, + "args": { + "External id": 30062,"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": 4183437, "tid": 4183437, + "ts": 658971766049.441, "dur": 0.842, + "args": { + "External id": 30063,"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": 4183437, "tid": 4183437, + "ts": 658971766079.317, "dur": 6867.301, + "args": { + "External id": 30064,"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": 4183437, "tid": 4183437, + "ts": 658971766096.765, "dur": 6843.276, + "args": { + "External id": 30065,"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": 4183437, "tid": 4183437, + "ts": 658971766109.786, "dur": 15.668, + "args": { + "External id": 30066,"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": 4183437, "tid": 4183437, + "ts": 658971766128.474, "dur": 6779.156, + "args": { + "External id": 30067,"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": 4183437, "tid": 4183437, + "ts": 658971766131.353, "dur": 6775.705, + "args": { + "External id": 30068,"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": 4183437, "tid": 4183437, + "ts": 658971766138.343, "dur": 7.587, + "args": { + "External id": 30069,"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": 4183437, "tid": 4183437, + "ts": 658971766147.614, "dur": 6756.563, + "args": { + "External id": 30070,"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": 4183437, "tid": 4183437, + "ts": 658971773124.632, "dur": 31.065, + "args": { + "External id": 30071,"Sequence number": 459905, "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": 4183437, "tid": 4183437, "ts": 658971773124.632, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971773142.865, "dur": 8.205, + "args": { + "External id": 30072,"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": 4183437, "tid": 4183437, + "ts": 658971773146.720, "dur": 4.172, + "args": { + "External id": 30073,"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": 4183437, "tid": 4183437, + "ts": 658971773219.652, "dur": 101.134, + "args": { + "External id": 30074,"Record function id": 0, "Ev Idx": 5481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971773323.988, "dur": 1087.353, + "args": { + "External id": 30075,"Record function id": 0, "Ev Idx": 5482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971773366.833, "dur": 1030.517, + "args": { + "External id": 30076,"Sequence number": 459906, "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": 4183437, "tid": 4183437, "ts": 658971773366.833, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971773433.025, "dur": 42.308, + "args": { + "External id": 30077,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971773488.952, "dur": 90.277, + "args": { + "External id": 30078,"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": 4183437, "tid": 4183437, + "ts": 658971773589.333, "dur": 35.115, + "args": { + "External id": 30079,"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": 4183437, "tid": 4183437, + "ts": 658971773633.751, "dur": 70.050, + "args": { + "External id": 30080,"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": 4183437, "tid": 4183437, + "ts": 658971773734.188, "dur": 27.056, + "args": { + "External id": 30081,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971773777.944, "dur": 17.168, + "args": { + "External id": 30082,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971773813.600, "dur": 131.943, + "args": { + "External id": 30083,"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": 4183437, "tid": 4183437, + "ts": 658971773864.202, "dur": 11.784, + "args": { + "External id": 30084,"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": 4183437, "tid": 4183437, + "ts": 658971773869.431, "dur": 5.819, + "args": { + "External id": 30085,"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": 4183437, "tid": 4183437, + "ts": 658971773878.757, "dur": 6.622, + "args": { + "External id": 30086,"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": 4183437, "tid": 4183437, + "ts": 658971773887.075, "dur": 1.376, + "args": { + "External id": 30087,"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": 4183437, "tid": 4183437, + "ts": 658971773890.769, "dur": 4.723, + "args": { + "External id": 30088,"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": 4183437, "tid": 4183437, + "ts": 658971773955.691, "dur": 51.579, + "args": { + "External id": 30089,"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": 4183437, "tid": 4183437, + "ts": 658971774036.607, "dur": 29.854, + "args": { + "External id": 30090,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971774075.455, "dur": 38.118, + "args": { + "External id": 30091,"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": 4183437, "tid": 4183437, + "ts": 658971774122.757, "dur": 32.323, + "args": { + "External id": 30092,"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": 4183437, "tid": 4183437, + "ts": 658971774177.830, "dur": 27.599, + "args": { + "External id": 30093,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971774210.896, "dur": 67.336, + "args": { + "External id": 30094,"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": 4183437, "tid": 4183437, + "ts": 658971774302.605, "dur": 20.939, + "args": { + "External id": 30095,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971774473.572, "dur": 75.868, + "args": { + "External id": 30096,"Record function id": 0, "Ev Idx": 5503 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971774623.038, "dur": 86.662, + "args": { + "External id": 30097,"Record function id": 0, "Ev Idx": 5504 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 4183437, "tid": 4183437, + "ts": 658971774720.818, "dur": 8350.152, + "args": { + "External id": 30098,"Record function id": 0, "Ev Idx": 5505 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 4183437, "tid": 4183437, + "ts": 658971774729.493, "dur": 889.748, + "args": { + "External id": 30099,"Record function id": 0, "Ev Idx": 5506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971774808.366, "dur": 10.056, + "args": { + "External id": 30100,"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": 4183437, "tid": 4183437, + "ts": 658971774831.795, "dur": 37.232, + "args": { + "External id": 30101,"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": 4183437, "tid": 4183437, + "ts": 658971774837.325, "dur": 2.205, + "args": { + "External id": 30102,"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": 4183437, "tid": 4183437, + "ts": 658971774844.783, "dur": 0.365, + "args": { + "External id": 30103,"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": 4183437, "tid": 4183437, + "ts": 658971774846.158, "dur": 0.455, + "args": { + "External id": 30104,"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": 4183437, "tid": 4183437, + "ts": 658971774848.381, "dur": 0.465, + "args": { + "External id": 30105,"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": 4183437, "tid": 4183437, + "ts": 658971774852.000, "dur": 0.753, + "args": { + "External id": 30106,"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": 4183437, "tid": 4183437, + "ts": 658971774854.633, "dur": 0.321, + "args": { + "External id": 30107,"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": 4183437, "tid": 4183437, + "ts": 658971774855.953, "dur": 3.865, + "args": { + "External id": 30108,"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": 4183437, "tid": 4183437, + "ts": 658971774861.186, "dur": 0.271, + "args": { + "External id": 30109,"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": 4183437, "tid": 4183437, + "ts": 658971774862.423, "dur": 0.361, + "args": { + "External id": 30110,"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": 4183437, "tid": 4183437, + "ts": 658971774880.102, "dur": 41.693, + "args": { + "External id": 30111,"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": 4183437, "tid": 4183437, + "ts": 658971774954.368, "dur": 126.862, + "args": { + "External id": 30112,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971774965.217, "dur": 4.437, + "args": { + "External id": 30113,"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": 4183437, "tid": 4183437, + "ts": 658971774975.457, "dur": 9.477, + "args": { + "External id": 30114,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971774979.708, "dur": 4.829, + "args": { + "External id": 30115,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971774982.922, "dur": 0.458, + "args": { + "External id": 30116,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971774991.753, "dur": 34.156, + "args": { + "External id": 30117,"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": 4183437, "tid": 4183437, + "ts": 658971774993.600, "dur": 2.408, + "args": { + "External id": 30118,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971775000.877, "dur": 0.623, + "args": { + "External id": 30119,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971775002.833, "dur": 0.613, + "args": { + "External id": 30120,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971775007.001, "dur": 2.079, + "args": { + "External id": 30121,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971775010.159, "dur": 0.259, + "args": { + "External id": 30122,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971775012.060, "dur": 2.309, + "args": { + "External id": 30123,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971775015.828, "dur": 0.344, + "args": { + "External id": 30124,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971775017.768, "dur": 0.285, + "args": { + "External id": 30125,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971775021.536, "dur": 0.200, + "args": { + "External id": 30126,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971775047.848, "dur": 24.938, + "args": { + "External id": 30127,"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": 4183437, "tid": 4183437, + "ts": 658971775134.411, "dur": 388.354, + "args": { + "External id": 30128,"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": 4183437, "tid": 4183437, + "ts": 658971775163.284, "dur": 354.018, + "args": { + "External id": 30129,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971775175.032, "dur": 336.642, + "args": { + "External id": 30130,"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": 4183437, "tid": 4183437, + "ts": 658971775546.627, "dur": 2.503, + "args": { + "External id": 30131,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 4183437, "tid": 4183437, + "ts": 658971775640.656, "dur": 7240.452, + "args": { + "External id": 30132,"Record function id": 0, "Ev Idx": 5539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971775782.235, "dur": 6.742, + "args": { + "External id": 30133,"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": 4183437, "tid": 4183437, + "ts": 658971775792.473, "dur": 1.274, + "args": { + "External id": 30134,"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": 4183437, "tid": 4183437, + "ts": 658971775795.545, "dur": 3.088, + "args": { + "External id": 30135,"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": 4183437, "tid": 4183437, + "ts": 658971775800.250, "dur": 1.076, + "args": { + "External id": 30136,"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": 4183437, "tid": 4183437, + "ts": 658971775802.635, "dur": 0.965, + "args": { + "External id": 30137,"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": 4183437, "tid": 4183437, + "ts": 658971775806.909, "dur": 1.190, + "args": { + "External id": 30138,"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": 4183437, "tid": 4183437, + "ts": 658971775809.771, "dur": 0.822, + "args": { + "External id": 30139,"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": 4183437, "tid": 4183437, + "ts": 658971775812.403, "dur": 2.543, + "args": { + "External id": 30140,"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": 4183437, "tid": 4183437, + "ts": 658971775816.551, "dur": 0.817, + "args": { + "External id": 30141,"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": 4183437, "tid": 4183437, + "ts": 658971775820.550, "dur": 0.802, + "args": { + "External id": 30142,"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": 4183437, "tid": 4183437, + "ts": 658971775840.956, "dur": 7003.188, + "args": { + "External id": 30143,"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": 4183437, "tid": 4183437, + "ts": 658971775857.534, "dur": 6980.592, + "args": { + "External id": 30144,"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": 4183437, "tid": 4183437, + "ts": 658971775872.368, "dur": 14.790, + "args": { + "External id": 30145,"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": 4183437, "tid": 4183437, + "ts": 658971775889.842, "dur": 6916.586, + "args": { + "External id": 30146,"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": 4183437, "tid": 4183437, + "ts": 658971775892.760, "dur": 6913.118, + "args": { + "External id": 30147,"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": 4183437, "tid": 4183437, + "ts": 658971775899.325, "dur": 7.556, + "args": { + "External id": 30148,"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": 4183437, "tid": 4183437, + "ts": 658971775908.704, "dur": 6894.409, + "args": { + "External id": 30149,"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": 4183437, "tid": 4183437, + "ts": 658971783015.124, "dur": 27.957, + "args": { + "External id": 30150,"Sequence number": 459907, "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": 4183437, "tid": 4183437, "ts": 658971783015.124, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971783031.504, "dur": 6.647, + "args": { + "External id": 30151,"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": 4183437, "tid": 4183437, + "ts": 658971783034.451, "dur": 3.495, + "args": { + "External id": 30152,"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": 4183437, "tid": 4183437, + "ts": 658971783109.028, "dur": 85.433, + "args": { + "External id": 30153,"Record function id": 0, "Ev Idx": 5560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971783196.242, "dur": 1094.436, + "args": { + "External id": 30154,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971783235.281, "dur": 1024.943, + "args": { + "External id": 30155,"Sequence number": 459908, "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": 4183437, "tid": 4183437, "ts": 658971783235.281, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971783318.510, "dur": 43.384, + "args": { + "External id": 30156,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971783375.658, "dur": 88.955, + "args": { + "External id": 30157,"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": 4183437, "tid": 4183437, + "ts": 658971783474.818, "dur": 35.101, + "args": { + "External id": 30158,"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": 4183437, "tid": 4183437, + "ts": 658971783518.742, "dur": 30.742, + "args": { + "External id": 30159,"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": 4183437, "tid": 4183437, + "ts": 658971783572.344, "dur": 26.147, + "args": { + "External id": 30160,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971783616.133, "dur": 14.015, + "args": { + "External id": 30161,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971783648.728, "dur": 174.768, + "args": { + "External id": 30162,"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": 4183437, "tid": 4183437, + "ts": 658971783736.787, "dur": 13.503, + "args": { + "External id": 30163,"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": 4183437, "tid": 4183437, + "ts": 658971783742.106, "dur": 7.212, + "args": { + "External id": 30164,"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": 4183437, "tid": 4183437, + "ts": 658971783753.439, "dur": 6.060, + "args": { + "External id": 30165,"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": 4183437, "tid": 4183437, + "ts": 658971783760.850, "dur": 1.496, + "args": { + "External id": 30166,"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": 4183437, "tid": 4183437, + "ts": 658971783764.998, "dur": 4.824, + "args": { + "External id": 30167,"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": 4183437, "tid": 4183437, + "ts": 658971783834.370, "dur": 52.976, + "args": { + "External id": 30168,"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": 4183437, "tid": 4183437, + "ts": 658971783919.608, "dur": 26.746, + "args": { + "External id": 30169,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971783962.111, "dur": 38.143, + "args": { + "External id": 30170,"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": 4183437, "tid": 4183437, + "ts": 658971784009.317, "dur": 31.661, + "args": { + "External id": 30171,"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": 4183437, "tid": 4183437, + "ts": 658971784064.297, "dur": 25.628, + "args": { + "External id": 30172,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971784095.578, "dur": 50.708, + "args": { + "External id": 30173,"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": 4183437, "tid": 4183437, + "ts": 658971784167.369, "dur": 20.983, + "args": { + "External id": 30174,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971784355.100, "dur": 76.997, + "args": { + "External id": 30175,"Record function id": 0, "Ev Idx": 5582 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971784507.346, "dur": 46.168, + "args": { + "External id": 30176,"Record function id": 0, "Ev Idx": 5583 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 4183437, "tid": 4183437, + "ts": 658971784562.307, "dur": 8524.021, + "args": { + "External id": 30177,"Record function id": 0, "Ev Idx": 5584 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 4183437, "tid": 4183437, + "ts": 658971784571.504, "dur": 932.298, + "args": { + "External id": 30178,"Record function id": 0, "Ev Idx": 5585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971784687.644, "dur": 11.617, + "args": { + "External id": 30179,"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": 4183437, "tid": 4183437, + "ts": 658971784715.127, "dur": 36.770, + "args": { + "External id": 30180,"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": 4183437, "tid": 4183437, + "ts": 658971784720.827, "dur": 2.266, + "args": { + "External id": 30181,"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": 4183437, "tid": 4183437, + "ts": 658971784728.307, "dur": 0.476, + "args": { + "External id": 30182,"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": 4183437, "tid": 4183437, + "ts": 658971784730.419, "dur": 0.579, + "args": { + "External id": 30183,"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": 4183437, "tid": 4183437, + "ts": 658971784732.500, "dur": 0.472, + "args": { + "External id": 30184,"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": 4183437, "tid": 4183437, + "ts": 658971784735.782, "dur": 0.427, + "args": { + "External id": 30185,"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": 4183437, "tid": 4183437, + "ts": 658971784737.497, "dur": 0.397, + "args": { + "External id": 30186,"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": 4183437, "tid": 4183437, + "ts": 658971784739.074, "dur": 3.485, + "args": { + "External id": 30187,"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": 4183437, "tid": 4183437, + "ts": 658971784744.080, "dur": 0.236, + "args": { + "External id": 30188,"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": 4183437, "tid": 4183437, + "ts": 658971784745.785, "dur": 0.455, + "args": { + "External id": 30189,"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": 4183437, "tid": 4183437, + "ts": 658971784763.566, "dur": 42.993, + "args": { + "External id": 30190,"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": 4183437, "tid": 4183437, + "ts": 658971784841.324, "dur": 113.825, + "args": { + "External id": 30191,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971784852.658, "dur": 4.625, + "args": { + "External id": 30192,"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": 4183437, "tid": 4183437, + "ts": 658971784863.050, "dur": 9.941, + "args": { + "External id": 30193,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971784867.568, "dur": 5.033, + "args": { + "External id": 30194,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971784870.914, "dur": 0.458, + "args": { + "External id": 30195,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971784879.626, "dur": 32.144, + "args": { + "External id": 30196,"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": 4183437, "tid": 4183437, + "ts": 658971784881.611, "dur": 2.927, + "args": { + "External id": 30197,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971784885.894, "dur": 0.557, + "args": { + "External id": 30198,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971784887.701, "dur": 0.585, + "args": { + "External id": 30199,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971784892.834, "dur": 2.177, + "args": { + "External id": 30200,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971784896.208, "dur": 0.533, + "args": { + "External id": 30201,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971784897.966, "dur": 0.333, + "args": { + "External id": 30202,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971784901.778, "dur": 0.170, + "args": { + "External id": 30203,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971784903.410, "dur": 0.158, + "args": { + "External id": 30204,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971784904.935, "dur": 2.516, + "args": { + "External id": 30205,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971784924.251, "dur": 22.054, + "args": { + "External id": 30206,"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": 4183437, "tid": 4183437, + "ts": 658971785010.110, "dur": 400.092, + "args": { + "External id": 30207,"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": 4183437, "tid": 4183437, + "ts": 658971785036.557, "dur": 367.912, + "args": { + "External id": 30208,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971785071.627, "dur": 327.011, + "args": { + "External id": 30209,"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": 4183437, "tid": 4183437, + "ts": 658971785430.794, "dur": 2.312, + "args": { + "External id": 30210,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 4183437, "tid": 4183437, + "ts": 658971785524.287, "dur": 7376.541, + "args": { + "External id": 30211,"Record function id": 0, "Ev Idx": 5618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971785623.279, "dur": 6.236, + "args": { + "External id": 30212,"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": 4183437, "tid": 4183437, + "ts": 658971785632.733, "dur": 1.446, + "args": { + "External id": 30213,"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": 4183437, "tid": 4183437, + "ts": 658971785635.863, "dur": 2.686, + "args": { + "External id": 30214,"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": 4183437, "tid": 4183437, + "ts": 658971785640.082, "dur": 0.867, + "args": { + "External id": 30215,"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": 4183437, "tid": 4183437, + "ts": 658971785642.778, "dur": 0.836, + "args": { + "External id": 30216,"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": 4183437, "tid": 4183437, + "ts": 658971785645.482, "dur": 0.743, + "args": { + "External id": 30217,"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": 4183437, "tid": 4183437, + "ts": 658971785648.058, "dur": 0.900, + "args": { + "External id": 30218,"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": 4183437, "tid": 4183437, + "ts": 658971785685.992, "dur": 2.678, + "args": { + "External id": 30219,"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": 4183437, "tid": 4183437, + "ts": 658971785692.553, "dur": 0.849, + "args": { + "External id": 30220,"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": 4183437, "tid": 4183437, + "ts": 658971785695.695, "dur": 0.672, + "args": { + "External id": 30221,"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": 4183437, "tid": 4183437, + "ts": 658971785716.633, "dur": 7147.997, + "args": { + "External id": 30222,"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": 4183437, "tid": 4183437, + "ts": 658971785732.731, "dur": 7125.204, + "args": { + "External id": 30223,"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": 4183437, "tid": 4183437, + "ts": 658971785748.344, "dur": 15.425, + "args": { + "External id": 30224,"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": 4183437, "tid": 4183437, + "ts": 658971785766.673, "dur": 7059.646, + "args": { + "External id": 30225,"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": 4183437, "tid": 4183437, + "ts": 658971785769.420, "dur": 7056.369, + "args": { + "External id": 30226,"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": 4183437, "tid": 4183437, + "ts": 658971785775.850, "dur": 7.946, + "args": { + "External id": 30227,"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": 4183437, "tid": 4183437, + "ts": 658971785785.736, "dur": 7037.097, + "args": { + "External id": 30228,"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": 4183437, "tid": 4183437, + "ts": 658971793033.010, "dur": 28.618, + "args": { + "External id": 30229,"Sequence number": 459909, "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": 4183437, "tid": 4183437, "ts": 658971793033.010, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971793049.712, "dur": 7.313, + "args": { + "External id": 30230,"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": 4183437, "tid": 4183437, + "ts": 658971793052.785, "dur": 4.034, + "args": { + "External id": 30231,"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": 4183437, "tid": 4183437, + "ts": 658971793125.324, "dur": 83.654, + "args": { + "External id": 30232,"Record function id": 0, "Ev Idx": 5639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971793210.755, "dur": 1096.156, + "args": { + "External id": 30233,"Record function id": 0, "Ev Idx": 5640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971793249.901, "dur": 1041.139, + "args": { + "External id": 30234,"Sequence number": 459910, "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": 4183437, "tid": 4183437, "ts": 658971793249.901, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971793335.285, "dur": 42.765, + "args": { + "External id": 30235,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971793391.342, "dur": 90.234, + "args": { + "External id": 30236,"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": 4183437, "tid": 4183437, + "ts": 658971793491.204, "dur": 35.957, + "args": { + "External id": 30237,"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": 4183437, "tid": 4183437, + "ts": 658971793535.020, "dur": 29.946, + "args": { + "External id": 30238,"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": 4183437, "tid": 4183437, + "ts": 658971793589.573, "dur": 23.399, + "args": { + "External id": 30239,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971793629.822, "dur": 15.238, + "args": { + "External id": 30240,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971793699.942, "dur": 136.329, + "args": { + "External id": 30241,"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": 4183437, "tid": 4183437, + "ts": 658971793750.253, "dur": 13.494, + "args": { + "External id": 30242,"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": 4183437, "tid": 4183437, + "ts": 658971793755.705, "dur": 7.021, + "args": { + "External id": 30243,"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": 4183437, "tid": 4183437, + "ts": 658971793766.770, "dur": 5.581, + "args": { + "External id": 30244,"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": 4183437, "tid": 4183437, + "ts": 658971793773.739, "dur": 1.283, + "args": { + "External id": 30245,"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": 4183437, "tid": 4183437, + "ts": 658971793777.469, "dur": 5.127, + "args": { + "External id": 30246,"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": 4183437, "tid": 4183437, + "ts": 658971793848.411, "dur": 51.770, + "args": { + "External id": 30247,"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": 4183437, "tid": 4183437, + "ts": 658971793932.675, "dur": 27.700, + "args": { + "External id": 30248,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971793970.588, "dur": 39.291, + "args": { + "External id": 30249,"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": 4183437, "tid": 4183437, + "ts": 658971794019.229, "dur": 32.836, + "args": { + "External id": 30250,"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": 4183437, "tid": 4183437, + "ts": 658971794074.030, "dur": 28.498, + "args": { + "External id": 30251,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971794108.599, "dur": 50.117, + "args": { + "External id": 30252,"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": 4183437, "tid": 4183437, + "ts": 658971794180.270, "dur": 18.479, + "args": { + "External id": 30253,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971794371.936, "dur": 75.879, + "args": { + "External id": 30254,"Record function id": 0, "Ev Idx": 5661 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971794522.444, "dur": 46.674, + "args": { + "External id": 30255,"Record function id": 0, "Ev Idx": 5662 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 4183437, "tid": 4183437, + "ts": 658971794578.120, "dur": 8521.492, + "args": { + "External id": 30256,"Record function id": 0, "Ev Idx": 5663 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 4183437, "tid": 4183437, + "ts": 658971794587.196, "dur": 964.348, + "args": { + "External id": 30257,"Record function id": 0, "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971794708.180, "dur": 10.410, + "args": { + "External id": 30258,"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": 4183437, "tid": 4183437, + "ts": 658971794732.493, "dur": 38.621, + "args": { + "External id": 30259,"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": 4183437, "tid": 4183437, + "ts": 658971794738.744, "dur": 2.378, + "args": { + "External id": 30260,"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": 4183437, "tid": 4183437, + "ts": 658971794746.983, "dur": 0.531, + "args": { + "External id": 30261,"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": 4183437, "tid": 4183437, + "ts": 658971794748.481, "dur": 0.497, + "args": { + "External id": 30262,"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": 4183437, "tid": 4183437, + "ts": 658971794750.227, "dur": 0.219, + "args": { + "External id": 30263,"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": 4183437, "tid": 4183437, + "ts": 658971794753.647, "dur": 0.303, + "args": { + "External id": 30264,"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": 4183437, "tid": 4183437, + "ts": 658971794755.789, "dur": 0.386, + "args": { + "External id": 30265,"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": 4183437, "tid": 4183437, + "ts": 658971794757.433, "dur": 3.929, + "args": { + "External id": 30266,"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": 4183437, "tid": 4183437, + "ts": 658971794763.011, "dur": 0.430, + "args": { + "External id": 30267,"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": 4183437, "tid": 4183437, + "ts": 658971794764.753, "dur": 0.391, + "args": { + "External id": 30268,"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": 4183437, "tid": 4183437, + "ts": 658971794785.417, "dur": 43.923, + "args": { + "External id": 30269,"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": 4183437, "tid": 4183437, + "ts": 658971794862.819, "dur": 109.426, + "args": { + "External id": 30270,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971794873.430, "dur": 6.169, + "args": { + "External id": 30271,"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": 4183437, "tid": 4183437, + "ts": 658971794885.284, "dur": 9.780, + "args": { + "External id": 30272,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971794889.657, "dur": 4.936, + "args": { + "External id": 30273,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971794892.918, "dur": 0.485, + "args": { + "External id": 30274,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971794901.687, "dur": 28.872, + "args": { + "External id": 30275,"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": 4183437, "tid": 4183437, + "ts": 658971794903.720, "dur": 0.473, + "args": { + "External id": 30276,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971794905.881, "dur": 2.476, + "args": { + "External id": 30277,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971794909.448, "dur": 0.406, + "args": { + "External id": 30278,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971794911.891, "dur": 1.519, + "args": { + "External id": 30279,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971794917.822, "dur": 0.318, + "args": { + "External id": 30280,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971794919.704, "dur": 0.532, + "args": { + "External id": 30281,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971794921.361, "dur": 0.396, + "args": { + "External id": 30282,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971794925.046, "dur": 0.500, + "args": { + "External id": 30283,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971794926.431, "dur": 0.399, + "args": { + "External id": 30284,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971794942.812, "dur": 21.567, + "args": { + "External id": 30285,"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": 4183437, "tid": 4183437, + "ts": 658971795026.894, "dur": 426.057, + "args": { + "External id": 30286,"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": 4183437, "tid": 4183437, + "ts": 658971795054.090, "dur": 393.393, + "args": { + "External id": 30287,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971795064.370, "dur": 375.758, + "args": { + "External id": 30288,"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": 4183437, "tid": 4183437, + "ts": 658971795476.023, "dur": 2.770, + "args": { + "External id": 30289,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 4183437, "tid": 4183437, + "ts": 658971795571.759, "dur": 7337.608, + "args": { + "External id": 30290,"Record function id": 0, "Ev Idx": 5697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971795717.371, "dur": 6.800, + "args": { + "External id": 30291,"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": 4183437, "tid": 4183437, + "ts": 658971795727.606, "dur": 1.214, + "args": { + "External id": 30292,"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": 4183437, "tid": 4183437, + "ts": 658971795730.888, "dur": 2.285, + "args": { + "External id": 30293,"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": 4183437, "tid": 4183437, + "ts": 658971795734.811, "dur": 0.925, + "args": { + "External id": 30294,"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": 4183437, "tid": 4183437, + "ts": 658971795737.784, "dur": 0.849, + "args": { + "External id": 30295,"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": 4183437, "tid": 4183437, + "ts": 658971795740.172, "dur": 1.034, + "args": { + "External id": 30296,"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": 4183437, "tid": 4183437, + "ts": 658971795743.161, "dur": 0.912, + "args": { + "External id": 30297,"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": 4183437, "tid": 4183437, + "ts": 658971795745.830, "dur": 2.192, + "args": { + "External id": 30298,"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": 4183437, "tid": 4183437, + "ts": 658971795749.933, "dur": 0.640, + "args": { + "External id": 30299,"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": 4183437, "tid": 4183437, + "ts": 658971795752.687, "dur": 0.944, + "args": { + "External id": 30300,"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": 4183437, "tid": 4183437, + "ts": 658971795772.482, "dur": 7100.791, + "args": { + "External id": 30301,"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": 4183437, "tid": 4183437, + "ts": 658971795788.825, "dur": 7078.144, + "args": { + "External id": 30302,"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": 4183437, "tid": 4183437, + "ts": 658971795803.471, "dur": 14.264, + "args": { + "External id": 30303,"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": 4183437, "tid": 4183437, + "ts": 658971795820.728, "dur": 7015.973, + "args": { + "External id": 30304,"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": 4183437, "tid": 4183437, + "ts": 658971795823.584, "dur": 7012.620, + "args": { + "External id": 30305,"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": 4183437, "tid": 4183437, + "ts": 658971795829.937, "dur": 5.814, + "args": { + "External id": 30306,"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": 4183437, "tid": 4183437, + "ts": 658971795837.700, "dur": 6995.518, + "args": { + "External id": 30307,"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": 4183437, "tid": 4183437, + "ts": 658971803046.055, "dur": 29.669, + "args": { + "External id": 30308,"Sequence number": 459911, "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": 4183437, "tid": 4183437, "ts": 658971803046.055, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971803063.961, "dur": 6.851, + "args": { + "External id": 30309,"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": 4183437, "tid": 4183437, + "ts": 658971803066.625, "dur": 3.955, + "args": { + "External id": 30310,"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": 4183437, "tid": 4183437, + "ts": 658971803138.298, "dur": 82.651, + "args": { + "External id": 30311,"Record function id": 0, "Ev Idx": 5718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971803222.507, "dur": 1078.686, + "args": { + "External id": 30312,"Record function id": 0, "Ev Idx": 5719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971803274.903, "dur": 1011.472, + "args": { + "External id": 30313,"Sequence number": 459912, "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": 4183437, "tid": 4183437, "ts": 658971803274.903, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971803342.545, "dur": 42.580, + "args": { + "External id": 30314,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971803398.316, "dur": 91.775, + "args": { + "External id": 30315,"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": 4183437, "tid": 4183437, + "ts": 658971803499.187, "dur": 34.692, + "args": { + "External id": 30316,"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": 4183437, "tid": 4183437, + "ts": 658971803542.806, "dur": 29.276, + "args": { + "External id": 30317,"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": 4183437, "tid": 4183437, + "ts": 658971803595.552, "dur": 25.226, + "args": { + "External id": 30318,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971803637.504, "dur": 48.929, + "args": { + "External id": 30319,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971803708.862, "dur": 135.459, + "args": { + "External id": 30320,"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": 4183437, "tid": 4183437, + "ts": 658971803759.875, "dur": 12.978, + "args": { + "External id": 30321,"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": 4183437, "tid": 4183437, + "ts": 658971803764.873, "dur": 7.115, + "args": { + "External id": 30322,"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": 4183437, "tid": 4183437, + "ts": 658971803775.926, "dur": 6.200, + "args": { + "External id": 30323,"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": 4183437, "tid": 4183437, + "ts": 658971803783.529, "dur": 1.480, + "args": { + "External id": 30324,"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": 4183437, "tid": 4183437, + "ts": 658971803787.355, "dur": 3.882, + "args": { + "External id": 30325,"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": 4183437, "tid": 4183437, + "ts": 658971803855.005, "dur": 52.915, + "args": { + "External id": 30326,"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": 4183437, "tid": 4183437, + "ts": 658971803939.968, "dur": 32.682, + "args": { + "External id": 30327,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971803981.066, "dur": 37.852, + "args": { + "External id": 30328,"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": 4183437, "tid": 4183437, + "ts": 658971804028.250, "dur": 32.233, + "args": { + "External id": 30329,"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": 4183437, "tid": 4183437, + "ts": 658971804082.051, "dur": 27.054, + "args": { + "External id": 30330,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971804115.350, "dur": 41.142, + "args": { + "External id": 30331,"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": 4183437, "tid": 4183437, + "ts": 658971804177.690, "dur": 20.256, + "args": { + "External id": 30332,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971804365.718, "dur": 77.892, + "args": { + "External id": 30333,"Record function id": 0, "Ev Idx": 5740 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971804518.677, "dur": 47.739, + "args": { + "External id": 30334,"Record function id": 0, "Ev Idx": 5741 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 4183437, "tid": 4183437, + "ts": 658971804575.640, "dur": 8767.931, + "args": { + "External id": 30335,"Record function id": 0, "Ev Idx": 5742 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 4183437, "tid": 4183437, + "ts": 658971804584.195, "dur": 920.614, + "args": { + "External id": 30336,"Record function id": 0, "Ev Idx": 5743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971804713.886, "dur": 10.574, + "args": { + "External id": 30337,"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": 4183437, "tid": 4183437, + "ts": 658971804740.917, "dur": 37.527, + "args": { + "External id": 30338,"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": 4183437, "tid": 4183437, + "ts": 658971804746.470, "dur": 2.181, + "args": { + "External id": 30339,"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": 4183437, "tid": 4183437, + "ts": 658971804753.398, "dur": 0.734, + "args": { + "External id": 30340,"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": 4183437, "tid": 4183437, + "ts": 658971804755.524, "dur": 0.625, + "args": { + "External id": 30341,"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": 4183437, "tid": 4183437, + "ts": 658971804757.383, "dur": 2.816, + "args": { + "External id": 30342,"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": 4183437, "tid": 4183437, + "ts": 658971804761.764, "dur": 0.376, + "args": { + "External id": 30343,"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": 4183437, "tid": 4183437, + "ts": 658971804763.667, "dur": 0.379, + "args": { + "External id": 30344,"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": 4183437, "tid": 4183437, + "ts": 658971804768.030, "dur": 0.439, + "args": { + "External id": 30345,"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": 4183437, "tid": 4183437, + "ts": 658971804770.071, "dur": 0.444, + "args": { + "External id": 30346,"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": 4183437, "tid": 4183437, + "ts": 658971804771.742, "dur": 0.604, + "args": { + "External id": 30347,"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": 4183437, "tid": 4183437, + "ts": 658971804789.608, "dur": 41.163, + "args": { + "External id": 30348,"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": 4183437, "tid": 4183437, + "ts": 658971804865.269, "dur": 112.038, + "args": { + "External id": 30349,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971804875.850, "dur": 4.367, + "args": { + "External id": 30350,"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": 4183437, "tid": 4183437, + "ts": 658971804886.074, "dur": 12.265, + "args": { + "External id": 30351,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971804890.322, "dur": 7.514, + "args": { + "External id": 30352,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971804893.556, "dur": 3.075, + "args": { + "External id": 30353,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971804905.300, "dur": 29.502, + "args": { + "External id": 30354,"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": 4183437, "tid": 4183437, + "ts": 658971804907.148, "dur": 0.784, + "args": { + "External id": 30355,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971804909.536, "dur": 1.282, + "args": { + "External id": 30356,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971804912.228, "dur": 0.821, + "args": { + "External id": 30357,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971804916.706, "dur": 0.880, + "args": { + "External id": 30358,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971804918.676, "dur": 0.541, + "args": { + "External id": 30359,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971804920.866, "dur": 2.426, + "args": { + "External id": 30360,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971804924.916, "dur": 0.647, + "args": { + "External id": 30361,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971804926.965, "dur": 0.391, + "args": { + "External id": 30362,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971804930.405, "dur": 0.485, + "args": { + "External id": 30363,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971804945.862, "dur": 22.947, + "args": { + "External id": 30364,"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": 4183437, "tid": 4183437, + "ts": 658971805033.444, "dur": 378.258, + "args": { + "External id": 30365,"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": 4183437, "tid": 4183437, + "ts": 658971805060.447, "dur": 345.688, + "args": { + "External id": 30366,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971805071.272, "dur": 328.911, + "args": { + "External id": 30367,"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": 4183437, "tid": 4183437, + "ts": 658971805432.211, "dur": 2.670, + "args": { + "External id": 30368,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 4183437, "tid": 4183437, + "ts": 658971805526.798, "dur": 7608.516, + "args": { + "External id": 30369,"Record function id": 0, "Ev Idx": 5776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971805625.353, "dur": 6.247, + "args": { + "External id": 30370,"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": 4183437, "tid": 4183437, + "ts": 658971805634.877, "dur": 1.533, + "args": { + "External id": 30371,"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": 4183437, "tid": 4183437, + "ts": 658971805638.058, "dur": 1.181, + "args": { + "External id": 30372,"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": 4183437, "tid": 4183437, + "ts": 658971805641.309, "dur": 1.234, + "args": { + "External id": 30373,"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": 4183437, "tid": 4183437, + "ts": 658971805644.438, "dur": 1.373, + "args": { + "External id": 30374,"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": 4183437, "tid": 4183437, + "ts": 658971805647.678, "dur": 0.997, + "args": { + "External id": 30375,"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": 4183437, "tid": 4183437, + "ts": 658971805687.481, "dur": 2.101, + "args": { + "External id": 30376,"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": 4183437, "tid": 4183437, + "ts": 658971805693.720, "dur": 1.990, + "args": { + "External id": 30377,"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": 4183437, "tid": 4183437, + "ts": 658971805697.862, "dur": 1.201, + "args": { + "External id": 30378,"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": 4183437, "tid": 4183437, + "ts": 658971805701.076, "dur": 1.027, + "args": { + "External id": 30379,"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": 4183437, "tid": 4183437, + "ts": 658971805721.017, "dur": 7376.224, + "args": { + "External id": 30380,"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": 4183437, "tid": 4183437, + "ts": 658971805736.770, "dur": 7353.724, + "args": { + "External id": 30381,"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": 4183437, "tid": 4183437, + "ts": 658971805750.780, "dur": 14.282, + "args": { + "External id": 30382,"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": 4183437, "tid": 4183437, + "ts": 658971805767.704, "dur": 7290.114, + "args": { + "External id": 30383,"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": 4183437, "tid": 4183437, + "ts": 658971805770.511, "dur": 7286.789, + "args": { + "External id": 30384,"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": 4183437, "tid": 4183437, + "ts": 658971805777.037, "dur": 7.043, + "args": { + "External id": 30385,"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": 4183437, "tid": 4183437, + "ts": 658971805785.997, "dur": 7268.311, + "args": { + "External id": 30386,"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": 4183437, "tid": 4183437, + "ts": 658971813286.805, "dur": 29.301, + "args": { + "External id": 30387,"Sequence number": 459913, "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": 4183437, "tid": 4183437, "ts": 658971813286.805, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971813302.893, "dur": 8.312, + "args": { + "External id": 30388,"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": 4183437, "tid": 4183437, + "ts": 658971813306.127, "dur": 4.653, + "args": { + "External id": 30389,"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": 4183437, "tid": 4183437, + "ts": 658971813381.785, "dur": 84.364, + "args": { + "External id": 30390,"Record function id": 0, "Ev Idx": 5797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971813467.822, "dur": 1058.690, + "args": { + "External id": 30391,"Record function id": 0, "Ev Idx": 5798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971813509.414, "dur": 1003.752, + "args": { + "External id": 30392,"Sequence number": 459914, "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": 4183437, "tid": 4183437, "ts": 658971813509.414, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971813576.672, "dur": 41.382, + "args": { + "External id": 30393,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971813630.767, "dur": 124.428, + "args": { + "External id": 30394,"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": 4183437, "tid": 4183437, + "ts": 658971813768.457, "dur": 37.565, + "args": { + "External id": 30395,"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": 4183437, "tid": 4183437, + "ts": 658971813816.277, "dur": 30.032, + "args": { + "External id": 30396,"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": 4183437, "tid": 4183437, + "ts": 658971813872.350, "dur": 26.882, + "args": { + "External id": 30397,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971813917.567, "dur": 14.822, + "args": { + "External id": 30398,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971813949.891, "dur": 128.064, + "args": { + "External id": 30399,"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": 4183437, "tid": 4183437, + "ts": 658971813998.374, "dur": 11.878, + "args": { + "External id": 30400,"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": 4183437, "tid": 4183437, + "ts": 658971814003.394, "dur": 6.102, + "args": { + "External id": 30401,"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": 4183437, "tid": 4183437, + "ts": 658971814012.972, "dur": 6.248, + "args": { + "External id": 30402,"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": 4183437, "tid": 4183437, + "ts": 658971814020.826, "dur": 1.737, + "args": { + "External id": 30403,"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": 4183437, "tid": 4183437, + "ts": 658971814024.901, "dur": 3.233, + "args": { + "External id": 30404,"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": 4183437, "tid": 4183437, + "ts": 658971814089.124, "dur": 43.201, + "args": { + "External id": 30405,"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": 4183437, "tid": 4183437, + "ts": 658971814162.550, "dur": 27.952, + "args": { + "External id": 30406,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971814198.856, "dur": 37.097, + "args": { + "External id": 30407,"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": 4183437, "tid": 4183437, + "ts": 658971814245.266, "dur": 47.432, + "args": { + "External id": 30408,"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": 4183437, "tid": 4183437, + "ts": 658971814327.488, "dur": 29.133, + "args": { + "External id": 30409,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971814365.362, "dur": 44.105, + "args": { + "External id": 30410,"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": 4183437, "tid": 4183437, + "ts": 658971814427.840, "dur": 18.773, + "args": { + "External id": 30411,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971814588.213, "dur": 113.395, + "args": { + "External id": 30412,"Record function id": 0, "Ev Idx": 5819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971814780.566, "dur": 48.669, + "args": { + "External id": 30413,"Record function id": 0, "Ev Idx": 5820 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 4183437, "tid": 4183437, + "ts": 658971814838.543, "dur": 8726.368, + "args": { + "External id": 30414,"Record function id": 0, "Ev Idx": 5821 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 4183437, "tid": 4183437, + "ts": 658971814848.229, "dur": 901.026, + "args": { + "External id": 30415,"Record function id": 0, "Ev Idx": 5822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971814927.190, "dur": 9.831, + "args": { + "External id": 30416,"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": 4183437, "tid": 4183437, + "ts": 658971814950.970, "dur": 37.104, + "args": { + "External id": 30417,"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": 4183437, "tid": 4183437, + "ts": 658971814956.637, "dur": 2.206, + "args": { + "External id": 30418,"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": 4183437, "tid": 4183437, + "ts": 658971814964.352, "dur": 1.081, + "args": { + "External id": 30419,"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": 4183437, "tid": 4183437, + "ts": 658971814966.614, "dur": 0.665, + "args": { + "External id": 30420,"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": 4183437, "tid": 4183437, + "ts": 658971814968.894, "dur": 0.636, + "args": { + "External id": 30421,"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": 4183437, "tid": 4183437, + "ts": 658971814972.393, "dur": 0.491, + "args": { + "External id": 30422,"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": 4183437, "tid": 4183437, + "ts": 658971814974.576, "dur": 0.668, + "args": { + "External id": 30423,"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": 4183437, "tid": 4183437, + "ts": 658971814976.178, "dur": 2.083, + "args": { + "External id": 30424,"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": 4183437, "tid": 4183437, + "ts": 658971814979.782, "dur": 0.443, + "args": { + "External id": 30425,"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": 4183437, "tid": 4183437, + "ts": 658971814981.427, "dur": 0.496, + "args": { + "External id": 30426,"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": 4183437, "tid": 4183437, + "ts": 658971814999.974, "dur": 40.809, + "args": { + "External id": 30427,"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": 4183437, "tid": 4183437, + "ts": 658971815074.052, "dur": 112.928, + "args": { + "External id": 30428,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971815085.029, "dur": 4.965, + "args": { + "External id": 30429,"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": 4183437, "tid": 4183437, + "ts": 658971815095.838, "dur": 10.258, + "args": { + "External id": 30430,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971815100.369, "dur": 5.292, + "args": { + "External id": 30431,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971815103.716, "dur": 0.779, + "args": { + "External id": 30432,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971815113.093, "dur": 31.422, + "args": { + "External id": 30433,"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": 4183437, "tid": 4183437, + "ts": 658971815115.221, "dur": 3.282, + "args": { + "External id": 30434,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971815119.966, "dur": 0.693, + "args": { + "External id": 30435,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971815121.887, "dur": 0.598, + "args": { + "External id": 30436,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971815126.220, "dur": 0.494, + "args": { + "External id": 30437,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971815128.121, "dur": 0.540, + "args": { + "External id": 30438,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971815130.146, "dur": 0.555, + "args": { + "External id": 30439,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971815134.292, "dur": 0.600, + "args": { + "External id": 30440,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971815136.057, "dur": 0.469, + "args": { + "External id": 30441,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971815137.765, "dur": 2.623, + "args": { + "External id": 30442,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971815157.375, "dur": 21.864, + "args": { + "External id": 30443,"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": 4183437, "tid": 4183437, + "ts": 658971815237.688, "dur": 379.334, + "args": { + "External id": 30444,"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": 4183437, "tid": 4183437, + "ts": 658971815279.807, "dur": 332.008, + "args": { + "External id": 30445,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971815292.266, "dur": 314.094, + "args": { + "External id": 30446,"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": 4183437, "tid": 4183437, + "ts": 658971815637.848, "dur": 2.272, + "args": { + "External id": 30447,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 4183437, "tid": 4183437, + "ts": 658971815772.683, "dur": 7596.592, + "args": { + "External id": 30448,"Record function id": 0, "Ev Idx": 5855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971815878.641, "dur": 6.594, + "args": { + "External id": 30449,"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": 4183437, "tid": 4183437, + "ts": 658971815888.595, "dur": 1.520, + "args": { + "External id": 30450,"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": 4183437, "tid": 4183437, + "ts": 658971815892.197, "dur": 1.255, + "args": { + "External id": 30451,"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": 4183437, "tid": 4183437, + "ts": 658971815895.084, "dur": 1.096, + "args": { + "External id": 30452,"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": 4183437, "tid": 4183437, + "ts": 658971815897.799, "dur": 1.503, + "args": { + "External id": 30453,"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": 4183437, "tid": 4183437, + "ts": 658971815901.520, "dur": 1.441, + "args": { + "External id": 30454,"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": 4183437, "tid": 4183437, + "ts": 658971815905.035, "dur": 1.045, + "args": { + "External id": 30455,"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": 4183437, "tid": 4183437, + "ts": 658971815907.884, "dur": 2.106, + "args": { + "External id": 30456,"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": 4183437, "tid": 4183437, + "ts": 658971815911.715, "dur": 0.933, + "args": { + "External id": 30457,"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": 4183437, "tid": 4183437, + "ts": 658971815914.820, "dur": 0.719, + "args": { + "External id": 30458,"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": 4183437, "tid": 4183437, + "ts": 658971815933.968, "dur": 7397.241, + "args": { + "External id": 30459,"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": 4183437, "tid": 4183437, + "ts": 658971815949.766, "dur": 7374.348, + "args": { + "External id": 30460,"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": 4183437, "tid": 4183437, + "ts": 658971815965.447, "dur": 14.707, + "args": { + "External id": 30461,"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": 4183437, "tid": 4183437, + "ts": 658971815982.738, "dur": 7309.065, + "args": { + "External id": 30462,"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": 4183437, "tid": 4183437, + "ts": 658971815985.646, "dur": 7305.651, + "args": { + "External id": 30463,"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": 4183437, "tid": 4183437, + "ts": 658971815991.416, "dur": 7.386, + "args": { + "External id": 30464,"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": 4183437, "tid": 4183437, + "ts": 658971816000.901, "dur": 7287.585, + "args": { + "External id": 30465,"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": 4183437, "tid": 4183437, + "ts": 658971823510.904, "dur": 28.658, + "args": { + "External id": 30466,"Sequence number": 459915, "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": 4183437, "tid": 4183437, "ts": 658971823510.904, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971823526.627, "dur": 7.998, + "args": { + "External id": 30467,"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": 4183437, "tid": 4183437, + "ts": 658971823529.892, "dur": 4.473, + "args": { + "External id": 30468,"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": 4183437, "tid": 4183437, + "ts": 658971823603.610, "dur": 115.826, + "args": { + "External id": 30469,"Record function id": 0, "Ev Idx": 5876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971823722.738, "dur": 1087.972, + "args": { + "External id": 30470,"Record function id": 0, "Ev Idx": 5877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971823766.296, "dur": 1028.783, + "args": { + "External id": 30471,"Sequence number": 459916, "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": 4183437, "tid": 4183437, "ts": 658971823766.296, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971823836.030, "dur": 44.073, + "args": { + "External id": 30472,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971823893.230, "dur": 89.663, + "args": { + "External id": 30473,"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": 4183437, "tid": 4183437, + "ts": 658971823991.738, "dur": 34.888, + "args": { + "External id": 30474,"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": 4183437, "tid": 4183437, + "ts": 658971824036.323, "dur": 29.858, + "args": { + "External id": 30475,"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": 4183437, "tid": 4183437, + "ts": 658971824091.108, "dur": 27.344, + "args": { + "External id": 30476,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971824136.487, "dur": 15.258, + "args": { + "External id": 30477,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971824167.903, "dur": 147.821, + "args": { + "External id": 30478,"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": 4183437, "tid": 4183437, + "ts": 658971824218.071, "dur": 11.416, + "args": { + "External id": 30479,"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": 4183437, "tid": 4183437, + "ts": 658971824222.840, "dur": 5.865, + "args": { + "External id": 30480,"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": 4183437, "tid": 4183437, + "ts": 658971824232.275, "dur": 5.891, + "args": { + "External id": 30481,"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": 4183437, "tid": 4183437, + "ts": 658971824239.663, "dur": 1.530, + "args": { + "External id": 30482,"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": 4183437, "tid": 4183437, + "ts": 658971824243.689, "dur": 3.483, + "args": { + "External id": 30483,"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": 4183437, "tid": 4183437, + "ts": 658971824328.298, "dur": 48.363, + "args": { + "External id": 30484,"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": 4183437, "tid": 4183437, + "ts": 658971824408.163, "dur": 29.824, + "args": { + "External id": 30485,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971824446.147, "dur": 38.959, + "args": { + "External id": 30486,"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": 4183437, "tid": 4183437, + "ts": 658971824495.808, "dur": 32.430, + "args": { + "External id": 30487,"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": 4183437, "tid": 4183437, + "ts": 658971824550.731, "dur": 27.236, + "args": { + "External id": 30488,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971824584.259, "dur": 54.214, + "args": { + "External id": 30489,"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": 4183437, "tid": 4183437, + "ts": 658971824695.574, "dur": 22.334, + "args": { + "External id": 30490,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971824876.915, "dur": 77.179, + "args": { + "External id": 30491,"Record function id": 0, "Ev Idx": 5898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971825026.543, "dur": 46.931, + "args": { + "External id": 30492,"Record function id": 0, "Ev Idx": 5899 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 4183437, "tid": 4183437, + "ts": 658971825082.032, "dur": 8609.442, + "args": { + "External id": 30493,"Record function id": 0, "Ev Idx": 5900 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 4183437, "tid": 4183437, + "ts": 658971825090.845, "dur": 843.434, + "args": { + "External id": 30494,"Record function id": 0, "Ev Idx": 5901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971825171.815, "dur": 9.438, + "args": { + "External id": 30495,"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": 4183437, "tid": 4183437, + "ts": 658971825194.317, "dur": 44.698, + "args": { + "External id": 30496,"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": 4183437, "tid": 4183437, + "ts": 658971825204.190, "dur": 2.871, + "args": { + "External id": 30497,"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": 4183437, "tid": 4183437, + "ts": 658971825211.421, "dur": 0.708, + "args": { + "External id": 30498,"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": 4183437, "tid": 4183437, + "ts": 658971825213.318, "dur": 0.555, + "args": { + "External id": 30499,"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": 4183437, "tid": 4183437, + "ts": 658971825215.317, "dur": 2.434, + "args": { + "External id": 30500,"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": 4183437, "tid": 4183437, + "ts": 658971825218.865, "dur": 0.761, + "args": { + "External id": 30501,"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": 4183437, "tid": 4183437, + "ts": 658971825223.056, "dur": 0.502, + "args": { + "External id": 30502,"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": 4183437, "tid": 4183437, + "ts": 658971825226.747, "dur": 0.473, + "args": { + "External id": 30503,"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": 4183437, "tid": 4183437, + "ts": 658971825228.325, "dur": 0.700, + "args": { + "External id": 30504,"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": 4183437, "tid": 4183437, + "ts": 658971825230.308, "dur": 2.741, + "args": { + "External id": 30505,"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": 4183437, "tid": 4183437, + "ts": 658971825250.047, "dur": 54.778, + "args": { + "External id": 30506,"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": 4183437, "tid": 4183437, + "ts": 658971825341.905, "dur": 109.150, + "args": { + "External id": 30507,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971825353.410, "dur": 5.495, + "args": { + "External id": 30508,"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": 4183437, "tid": 4183437, + "ts": 658971825364.660, "dur": 11.145, + "args": { + "External id": 30509,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971825369.104, "dur": 6.269, + "args": { + "External id": 30510,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971825372.914, "dur": 0.858, + "args": { + "External id": 30511,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971825382.767, "dur": 26.886, + "args": { + "External id": 30512,"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": 4183437, "tid": 4183437, + "ts": 658971825384.702, "dur": 0.758, + "args": { + "External id": 30513,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971825386.888, "dur": 0.643, + "args": { + "External id": 30514,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971825388.836, "dur": 2.431, + "args": { + "External id": 30515,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971825392.547, "dur": 0.606, + "args": { + "External id": 30516,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971825394.113, "dur": 0.624, + "args": { + "External id": 30517,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971825398.213, "dur": 0.628, + "args": { + "External id": 30518,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971825400.086, "dur": 0.460, + "args": { + "External id": 30519,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971825401.646, "dur": 0.606, + "args": { + "External id": 30520,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971825405.506, "dur": 0.558, + "args": { + "External id": 30521,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971825421.025, "dur": 21.788, + "args": { + "External id": 30522,"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": 4183437, "tid": 4183437, + "ts": 658971825504.152, "dur": 335.127, + "args": { + "External id": 30523,"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": 4183437, "tid": 4183437, + "ts": 658971825528.588, "dur": 305.256, + "args": { + "External id": 30524,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971825538.956, "dur": 289.469, + "args": { + "External id": 30525,"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": 4183437, "tid": 4183437, + "ts": 658971825859.875, "dur": 2.471, + "args": { + "External id": 30526,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 4183437, "tid": 4183437, + "ts": 658971825955.764, "dur": 7519.142, + "args": { + "External id": 30527,"Record function id": 0, "Ev Idx": 5934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971826056.919, "dur": 6.356, + "args": { + "External id": 30528,"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": 4183437, "tid": 4183437, + "ts": 658971826066.875, "dur": 1.148, + "args": { + "External id": 30529,"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": 4183437, "tid": 4183437, + "ts": 658971826069.895, "dur": 1.072, + "args": { + "External id": 30530,"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": 4183437, "tid": 4183437, + "ts": 658971826072.761, "dur": 1.153, + "args": { + "External id": 30531,"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": 4183437, "tid": 4183437, + "ts": 658971826075.358, "dur": 1.334, + "args": { + "External id": 30532,"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": 4183437, "tid": 4183437, + "ts": 658971826078.585, "dur": 1.174, + "args": { + "External id": 30533,"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": 4183437, "tid": 4183437, + "ts": 658971826081.561, "dur": 1.158, + "args": { + "External id": 30534,"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": 4183437, "tid": 4183437, + "ts": 658971826084.564, "dur": 1.991, + "args": { + "External id": 30535,"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": 4183437, "tid": 4183437, + "ts": 658971826088.258, "dur": 0.969, + "args": { + "External id": 30536,"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": 4183437, "tid": 4183437, + "ts": 658971826090.837, "dur": 0.844, + "args": { + "External id": 30537,"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": 4183437, "tid": 4183437, + "ts": 658971826109.814, "dur": 7328.429, + "args": { + "External id": 30538,"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": 4183437, "tid": 4183437, + "ts": 658971826125.349, "dur": 7306.535, + "args": { + "External id": 30539,"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": 4183437, "tid": 4183437, + "ts": 658971826138.679, "dur": 14.006, + "args": { + "External id": 30540,"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": 4183437, "tid": 4183437, + "ts": 658971826155.709, "dur": 7245.088, + "args": { + "External id": 30541,"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": 4183437, "tid": 4183437, + "ts": 658971826158.247, "dur": 7241.941, + "args": { + "External id": 30542,"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": 4183437, "tid": 4183437, + "ts": 658971826164.216, "dur": 7.538, + "args": { + "External id": 30543,"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": 4183437, "tid": 4183437, + "ts": 658971826173.783, "dur": 7223.111, + "args": { + "External id": 30544,"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": 4183437, "tid": 4183437, + "ts": 658971833609.378, "dur": 27.321, + "args": { + "External id": 30545,"Sequence number": 459917, "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": 4183437, "tid": 4183437, "ts": 658971833609.378, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971833624.155, "dur": 7.627, + "args": { + "External id": 30546,"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": 4183437, "tid": 4183437, + "ts": 658971833627.342, "dur": 4.207, + "args": { + "External id": 30547,"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": 4183437, "tid": 4183437, + "ts": 658971833732.611, "dur": 81.552, + "args": { + "External id": 30548,"Record function id": 0, "Ev Idx": 5955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971833815.965, "dur": 1071.974, + "args": { + "External id": 30549,"Record function id": 0, "Ev Idx": 5956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971833856.575, "dur": 1017.468, + "args": { + "External id": 30550,"Sequence number": 459918, "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": 4183437, "tid": 4183437, "ts": 658971833856.575, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971833923.799, "dur": 41.800, + "args": { + "External id": 30551,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971833978.897, "dur": 90.101, + "args": { + "External id": 30552,"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": 4183437, "tid": 4183437, + "ts": 658971834077.743, "dur": 35.169, + "args": { + "External id": 30553,"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": 4183437, "tid": 4183437, + "ts": 658971834122.372, "dur": 30.218, + "args": { + "External id": 30554,"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": 4183437, "tid": 4183437, + "ts": 658971834176.389, "dur": 25.502, + "args": { + "External id": 30555,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971834219.489, "dur": 15.240, + "args": { + "External id": 30556,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971834250.943, "dur": 156.100, + "args": { + "External id": 30557,"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": 4183437, "tid": 4183437, + "ts": 658971834324.303, "dur": 12.858, + "args": { + "External id": 30558,"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": 4183437, "tid": 4183437, + "ts": 658971834329.559, "dur": 6.706, + "args": { + "External id": 30559,"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": 4183437, "tid": 4183437, + "ts": 658971834339.817, "dur": 6.018, + "args": { + "External id": 30560,"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": 4183437, "tid": 4183437, + "ts": 658971834347.214, "dur": 1.486, + "args": { + "External id": 30561,"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": 4183437, "tid": 4183437, + "ts": 658971834351.407, "dur": 2.843, + "args": { + "External id": 30562,"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": 4183437, "tid": 4183437, + "ts": 658971834418.702, "dur": 49.588, + "args": { + "External id": 30563,"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": 4183437, "tid": 4183437, + "ts": 658971834498.561, "dur": 30.434, + "args": { + "External id": 30564,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971834537.435, "dur": 38.862, + "args": { + "External id": 30565,"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": 4183437, "tid": 4183437, + "ts": 658971834585.229, "dur": 33.348, + "args": { + "External id": 30566,"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": 4183437, "tid": 4183437, + "ts": 658971834639.608, "dur": 63.993, + "args": { + "External id": 30567,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971834712.644, "dur": 51.796, + "args": { + "External id": 30568,"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": 4183437, "tid": 4183437, + "ts": 658971834787.120, "dur": 17.967, + "args": { + "External id": 30569,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971834952.565, "dur": 74.376, + "args": { + "External id": 30570,"Record function id": 0, "Ev Idx": 5977 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971835102.143, "dur": 46.700, + "args": { + "External id": 30571,"Record function id": 0, "Ev Idx": 5978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 4183437, "tid": 4183437, + "ts": 658971835157.610, "dur": 8902.410, + "args": { + "External id": 30572,"Record function id": 0, "Ev Idx": 5979 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 4183437, "tid": 4183437, + "ts": 658971835166.219, "dur": 907.505, + "args": { + "External id": 30573,"Record function id": 0, "Ev Idx": 5980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971835245.638, "dur": 9.078, + "args": { + "External id": 30574,"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": 4183437, "tid": 4183437, + "ts": 658971835287.366, "dur": 37.383, + "args": { + "External id": 30575,"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": 4183437, "tid": 4183437, + "ts": 658971835293.198, "dur": 2.315, + "args": { + "External id": 30576,"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": 4183437, "tid": 4183437, + "ts": 658971835300.304, "dur": 0.412, + "args": { + "External id": 30577,"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": 4183437, "tid": 4183437, + "ts": 658971835301.924, "dur": 0.662, + "args": { + "External id": 30578,"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": 4183437, "tid": 4183437, + "ts": 658971835304.258, "dur": 0.817, + "args": { + "External id": 30579,"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": 4183437, "tid": 4183437, + "ts": 658971835308.076, "dur": 0.881, + "args": { + "External id": 30580,"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": 4183437, "tid": 4183437, + "ts": 658971835309.971, "dur": 0.606, + "args": { + "External id": 30581,"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": 4183437, "tid": 4183437, + "ts": 658971835311.897, "dur": 2.732, + "args": { + "External id": 30582,"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": 4183437, "tid": 4183437, + "ts": 658971835316.132, "dur": 0.535, + "args": { + "External id": 30583,"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": 4183437, "tid": 4183437, + "ts": 658971835317.944, "dur": 0.720, + "args": { + "External id": 30584,"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": 4183437, "tid": 4183437, + "ts": 658971835336.626, "dur": 40.114, + "args": { + "External id": 30585,"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": 4183437, "tid": 4183437, + "ts": 658971835411.429, "dur": 121.185, + "args": { + "External id": 30586,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971835422.788, "dur": 5.880, + "args": { + "External id": 30587,"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": 4183437, "tid": 4183437, + "ts": 658971835434.364, "dur": 10.207, + "args": { + "External id": 30588,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971835438.797, "dur": 5.343, + "args": { + "External id": 30589,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971835442.055, "dur": 0.907, + "args": { + "External id": 30590,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971835451.520, "dur": 30.499, + "args": { + "External id": 30591,"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": 4183437, "tid": 4183437, + "ts": 658971835453.609, "dur": 2.869, + "args": { + "External id": 30592,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971835457.928, "dur": 0.864, + "args": { + "External id": 30593,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971835460.147, "dur": 0.640, + "args": { + "External id": 30594,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971835464.494, "dur": 0.521, + "args": { + "External id": 30595,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971835466.122, "dur": 0.786, + "args": { + "External id": 30596,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971835468.040, "dur": 0.781, + "args": { + "External id": 30597,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971835472.368, "dur": 1.008, + "args": { + "External id": 30598,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971835474.631, "dur": 0.449, + "args": { + "External id": 30599,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971835476.226, "dur": 1.928, + "args": { + "External id": 30600,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971835501.996, "dur": 21.579, + "args": { + "External id": 30601,"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": 4183437, "tid": 4183437, + "ts": 658971835586.641, "dur": 393.338, + "args": { + "External id": 30602,"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": 4183437, "tid": 4183437, + "ts": 658971835612.058, "dur": 363.082, + "args": { + "External id": 30603,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971835624.487, "dur": 344.723, + "args": { + "External id": 30604,"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": 4183437, "tid": 4183437, + "ts": 658971836001.061, "dur": 2.378, + "args": { + "External id": 30605,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 4183437, "tid": 4183437, + "ts": 658971836094.237, "dur": 7778.952, + "args": { + "External id": 30606,"Record function id": 0, "Ev Idx": 6013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971836189.869, "dur": 5.831, + "args": { + "External id": 30607,"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": 4183437, "tid": 4183437, + "ts": 658971836199.223, "dur": 1.346, + "args": { + "External id": 30608,"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": 4183437, "tid": 4183437, + "ts": 658971836202.519, "dur": 1.326, + "args": { + "External id": 30609,"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": 4183437, "tid": 4183437, + "ts": 658971836205.597, "dur": 1.263, + "args": { + "External id": 30610,"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": 4183437, "tid": 4183437, + "ts": 658971836208.495, "dur": 1.226, + "args": { + "External id": 30611,"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": 4183437, "tid": 4183437, + "ts": 658971836211.665, "dur": 1.049, + "args": { + "External id": 30612,"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": 4183437, "tid": 4183437, + "ts": 658971836215.272, "dur": 1.092, + "args": { + "External id": 30613,"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": 4183437, "tid": 4183437, + "ts": 658971836218.324, "dur": 2.172, + "args": { + "External id": 30614,"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": 4183437, "tid": 4183437, + "ts": 658971836222.302, "dur": 1.153, + "args": { + "External id": 30615,"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": 4183437, "tid": 4183437, + "ts": 658971836225.402, "dur": 1.016, + "args": { + "External id": 30616,"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": 4183437, "tid": 4183437, + "ts": 658971836243.636, "dur": 7592.226, + "args": { + "External id": 30617,"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": 4183437, "tid": 4183437, + "ts": 658971836258.701, "dur": 7570.189, + "args": { + "External id": 30618,"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": 4183437, "tid": 4183437, + "ts": 658971836291.828, "dur": 15.137, + "args": { + "External id": 30619,"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": 4183437, "tid": 4183437, + "ts": 658971836310.379, "dur": 7485.880, + "args": { + "External id": 30620,"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": 4183437, "tid": 4183437, + "ts": 658971836313.222, "dur": 7482.514, + "args": { + "External id": 30621,"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": 4183437, "tid": 4183437, + "ts": 658971836320.432, "dur": 7.598, + "args": { + "External id": 30622,"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": 4183437, "tid": 4183437, + "ts": 658971836330.016, "dur": 7462.685, + "args": { + "External id": 30623,"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": 4183437, "tid": 4183437, + "ts": 658971844005.584, "dur": 30.202, + "args": { + "External id": 30624,"Sequence number": 459919, "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": 4183437, "tid": 4183437, "ts": 658971844005.584, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971844023.225, "dur": 7.786, + "args": { + "External id": 30625,"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": 4183437, "tid": 4183437, + "ts": 658971844026.532, "dur": 4.236, + "args": { + "External id": 30626,"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": 4183437, "tid": 4183437, + "ts": 658971844098.483, "dur": 81.038, + "args": { + "External id": 30627,"Record function id": 0, "Ev Idx": 6034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971844181.086, "dur": 1064.182, + "args": { + "External id": 30628,"Record function id": 0, "Ev Idx": 6035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971844223.374, "dur": 1008.068, + "args": { + "External id": 30629,"Sequence number": 459920, "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": 4183437, "tid": 4183437, "ts": 658971844223.374, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971844306.044, "dur": 42.877, + "args": { + "External id": 30630,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971844363.262, "dur": 88.350, + "args": { + "External id": 30631,"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": 4183437, "tid": 4183437, + "ts": 658971844460.126, "dur": 35.088, + "args": { + "External id": 30632,"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": 4183437, "tid": 4183437, + "ts": 658971844503.862, "dur": 28.430, + "args": { + "External id": 30633,"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": 4183437, "tid": 4183437, + "ts": 658971844555.315, "dur": 23.865, + "args": { + "External id": 30634,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971844596.839, "dur": 14.606, + "args": { + "External id": 30635,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971844628.068, "dur": 172.352, + "args": { + "External id": 30636,"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": 4183437, "tid": 4183437, + "ts": 658971844715.852, "dur": 13.839, + "args": { + "External id": 30637,"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": 4183437, "tid": 4183437, + "ts": 658971844721.337, "dur": 7.260, + "args": { + "External id": 30638,"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": 4183437, "tid": 4183437, + "ts": 658971844733.094, "dur": 5.635, + "args": { + "External id": 30639,"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": 4183437, "tid": 4183437, + "ts": 658971844740.087, "dur": 1.606, + "args": { + "External id": 30640,"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": 4183437, "tid": 4183437, + "ts": 658971844744.043, "dur": 3.145, + "args": { + "External id": 30641,"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": 4183437, "tid": 4183437, + "ts": 658971844811.302, "dur": 55.845, + "args": { + "External id": 30642,"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": 4183437, "tid": 4183437, + "ts": 658971844898.259, "dur": 31.622, + "args": { + "External id": 30643,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971844938.367, "dur": 37.866, + "args": { + "External id": 30644,"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": 4183437, "tid": 4183437, + "ts": 658971844985.470, "dur": 32.367, + "args": { + "External id": 30645,"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": 4183437, "tid": 4183437, + "ts": 658971845039.004, "dur": 26.889, + "args": { + "External id": 30646,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971845072.163, "dur": 45.349, + "args": { + "External id": 30647,"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": 4183437, "tid": 4183437, + "ts": 658971845138.547, "dur": 19.751, + "args": { + "External id": 30648,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971845328.703, "dur": 78.462, + "args": { + "External id": 30649,"Record function id": 0, "Ev Idx": 6056 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971845483.153, "dur": 47.342, + "args": { + "External id": 30650,"Record function id": 0, "Ev Idx": 6057 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 4183437, "tid": 4183437, + "ts": 658971845539.020, "dur": 8886.163, + "args": { + "External id": 30651,"Record function id": 0, "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 4183437, "tid": 4183437, + "ts": 658971845548.102, "dur": 977.032, + "args": { + "External id": 30652,"Record function id": 0, "Ev Idx": 6059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971845631.517, "dur": 9.366, + "args": { + "External id": 30653,"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": 4183437, "tid": 4183437, + "ts": 658971845690.004, "dur": 37.822, + "args": { + "External id": 30654,"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": 4183437, "tid": 4183437, + "ts": 658971845695.693, "dur": 2.340, + "args": { + "External id": 30655,"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": 4183437, "tid": 4183437, + "ts": 658971845702.877, "dur": 0.494, + "args": { + "External id": 30656,"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": 4183437, "tid": 4183437, + "ts": 658971845705.146, "dur": 0.769, + "args": { + "External id": 30657,"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": 4183437, "tid": 4183437, + "ts": 658971845707.301, "dur": 0.487, + "args": { + "External id": 30658,"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": 4183437, "tid": 4183437, + "ts": 658971845710.985, "dur": 0.735, + "args": { + "External id": 30659,"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": 4183437, "tid": 4183437, + "ts": 658971845713.401, "dur": 0.847, + "args": { + "External id": 30660,"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": 4183437, "tid": 4183437, + "ts": 658971845715.701, "dur": 2.714, + "args": { + "External id": 30661,"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": 4183437, "tid": 4183437, + "ts": 658971845719.566, "dur": 0.741, + "args": { + "External id": 30662,"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": 4183437, "tid": 4183437, + "ts": 658971845721.527, "dur": 0.570, + "args": { + "External id": 30663,"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": 4183437, "tid": 4183437, + "ts": 658971845741.616, "dur": 41.652, + "args": { + "External id": 30664,"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": 4183437, "tid": 4183437, + "ts": 658971845819.131, "dur": 113.285, + "args": { + "External id": 30665,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971845830.331, "dur": 7.102, + "args": { + "External id": 30666,"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": 4183437, "tid": 4183437, + "ts": 658971845843.665, "dur": 11.025, + "args": { + "External id": 30667,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971845847.989, "dur": 6.245, + "args": { + "External id": 30668,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971845851.861, "dur": 1.116, + "args": { + "External id": 30669,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971845861.211, "dur": 29.981, + "args": { + "External id": 30670,"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": 4183437, "tid": 4183437, + "ts": 658971845863.237, "dur": 0.835, + "args": { + "External id": 30671,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971845865.524, "dur": 2.728, + "args": { + "External id": 30672,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971845869.810, "dur": 0.804, + "args": { + "External id": 30673,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971845872.065, "dur": 0.565, + "args": { + "External id": 30674,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971845876.480, "dur": 0.912, + "args": { + "External id": 30675,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971845878.461, "dur": 0.762, + "args": { + "External id": 30676,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971845880.382, "dur": 0.763, + "args": { + "External id": 30677,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971845884.063, "dur": 0.975, + "args": { + "External id": 30678,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971845886.383, "dur": 0.774, + "args": { + "External id": 30679,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971845902.468, "dur": 21.593, + "args": { + "External id": 30680,"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": 4183437, "tid": 4183437, + "ts": 658971845987.559, "dur": 439.196, + "args": { + "External id": 30681,"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": 4183437, "tid": 4183437, + "ts": 658971846013.256, "dur": 407.442, + "args": { + "External id": 30682,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971846023.732, "dur": 391.147, + "args": { + "External id": 30683,"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": 4183437, "tid": 4183437, + "ts": 658971846450.154, "dur": 3.042, + "args": { + "External id": 30684,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 4183437, "tid": 4183437, + "ts": 658971846545.908, "dur": 7668.279, + "args": { + "External id": 30685,"Record function id": 0, "Ev Idx": 6092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971846647.930, "dur": 40.613, + "args": { + "External id": 30686,"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": 4183437, "tid": 4183437, + "ts": 658971846694.949, "dur": 1.863, + "args": { + "External id": 30687,"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": 4183437, "tid": 4183437, + "ts": 658971846698.809, "dur": 1.211, + "args": { + "External id": 30688,"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": 4183437, "tid": 4183437, + "ts": 658971846701.947, "dur": 1.185, + "args": { + "External id": 30689,"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": 4183437, "tid": 4183437, + "ts": 658971846705.100, "dur": 1.169, + "args": { + "External id": 30690,"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": 4183437, "tid": 4183437, + "ts": 658971846708.277, "dur": 1.104, + "args": { + "External id": 30691,"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": 4183437, "tid": 4183437, + "ts": 658971846711.329, "dur": 1.290, + "args": { + "External id": 30692,"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": 4183437, "tid": 4183437, + "ts": 658971846714.709, "dur": 2.188, + "args": { + "External id": 30693,"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": 4183437, "tid": 4183437, + "ts": 658971846718.676, "dur": 0.963, + "args": { + "External id": 30694,"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": 4183437, "tid": 4183437, + "ts": 658971846721.307, "dur": 0.909, + "args": { + "External id": 30695,"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": 4183437, "tid": 4183437, + "ts": 658971846741.465, "dur": 7432.587, + "args": { + "External id": 30696,"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": 4183437, "tid": 4183437, + "ts": 658971846757.873, "dur": 7409.528, + "args": { + "External id": 30697,"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": 4183437, "tid": 4183437, + "ts": 658971846773.655, "dur": 14.294, + "args": { + "External id": 30698,"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": 4183437, "tid": 4183437, + "ts": 658971846790.916, "dur": 7341.696, + "args": { + "External id": 30699,"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": 4183437, "tid": 4183437, + "ts": 658971846793.683, "dur": 7338.366, + "args": { + "External id": 30700,"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": 4183437, "tid": 4183437, + "ts": 658971846799.789, "dur": 8.250, + "args": { + "External id": 30701,"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": 4183437, "tid": 4183437, + "ts": 658971846809.657, "dur": 7319.672, + "args": { + "External id": 30702,"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": 4183437, "tid": 4183437, + "ts": 658971854370.959, "dur": 28.214, + "args": { + "External id": 30703,"Sequence number": 459921, "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": 4183437, "tid": 4183437, "ts": 658971854370.959, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971854386.470, "dur": 7.966, + "args": { + "External id": 30704,"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": 4183437, "tid": 4183437, + "ts": 658971854389.619, "dur": 4.399, + "args": { + "External id": 30705,"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": 4183437, "tid": 4183437, + "ts": 658971854466.211, "dur": 82.274, + "args": { + "External id": 30706,"Record function id": 0, "Ev Idx": 6113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971854550.106, "dur": 1087.335, + "args": { + "External id": 30707,"Record function id": 0, "Ev Idx": 6114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971854589.690, "dur": 1033.429, + "args": { + "External id": 30708,"Sequence number": 459922, "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": 4183437, "tid": 4183437, "ts": 658971854589.690, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971854682.642, "dur": 45.529, + "args": { + "External id": 30709,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971854743.426, "dur": 92.995, + "args": { + "External id": 30710,"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": 4183437, "tid": 4183437, + "ts": 658971854844.953, "dur": 36.103, + "args": { + "External id": 30711,"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": 4183437, "tid": 4183437, + "ts": 658971854890.314, "dur": 30.114, + "args": { + "External id": 30712,"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": 4183437, "tid": 4183437, + "ts": 658971854948.867, "dur": 27.952, + "args": { + "External id": 30713,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971854992.910, "dur": 16.260, + "args": { + "External id": 30714,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971855026.068, "dur": 135.166, + "args": { + "External id": 30715,"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": 4183437, "tid": 4183437, + "ts": 658971855078.584, "dur": 11.992, + "args": { + "External id": 30716,"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": 4183437, "tid": 4183437, + "ts": 658971855083.487, "dur": 6.098, + "args": { + "External id": 30717,"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": 4183437, "tid": 4183437, + "ts": 658971855093.371, "dur": 5.726, + "args": { + "External id": 30718,"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": 4183437, "tid": 4183437, + "ts": 658971855100.341, "dur": 1.524, + "args": { + "External id": 30719,"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": 4183437, "tid": 4183437, + "ts": 658971855104.623, "dur": 4.540, + "args": { + "External id": 30720,"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": 4183437, "tid": 4183437, + "ts": 658971855192.438, "dur": 45.881, + "args": { + "External id": 30721,"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": 4183437, "tid": 4183437, + "ts": 658971855284.795, "dur": 33.003, + "args": { + "External id": 30722,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971855327.756, "dur": 40.945, + "args": { + "External id": 30723,"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": 4183437, "tid": 4183437, + "ts": 658971855377.608, "dur": 31.960, + "args": { + "External id": 30724,"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": 4183437, "tid": 4183437, + "ts": 658971855431.874, "dur": 25.871, + "args": { + "External id": 30725,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971855463.789, "dur": 51.999, + "args": { + "External id": 30726,"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": 4183437, "tid": 4183437, + "ts": 658971855535.527, "dur": 18.397, + "args": { + "External id": 30727,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971855740.448, "dur": 74.977, + "args": { + "External id": 30728,"Record function id": 0, "Ev Idx": 6135 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971855891.193, "dur": 46.534, + "args": { + "External id": 30729,"Record function id": 0, "Ev Idx": 6136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 4183437, "tid": 4183437, + "ts": 658971855946.485, "dur": 8679.320, + "args": { + "External id": 30730,"Record function id": 0, "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 4183437, "tid": 4183437, + "ts": 658971855954.991, "dur": 910.248, + "args": { + "External id": 30731,"Record function id": 0, "Ev Idx": 6138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971856036.361, "dur": 9.644, + "args": { + "External id": 30732,"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": 4183437, "tid": 4183437, + "ts": 658971856059.730, "dur": 37.349, + "args": { + "External id": 30733,"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": 4183437, "tid": 4183437, + "ts": 658971856065.363, "dur": 2.273, + "args": { + "External id": 30734,"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": 4183437, "tid": 4183437, + "ts": 658971856072.111, "dur": 0.663, + "args": { + "External id": 30735,"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": 4183437, "tid": 4183437, + "ts": 658971856073.995, "dur": 0.649, + "args": { + "External id": 30736,"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": 4183437, "tid": 4183437, + "ts": 658971856075.923, "dur": 0.747, + "args": { + "External id": 30737,"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": 4183437, "tid": 4183437, + "ts": 658971856080.308, "dur": 0.790, + "args": { + "External id": 30738,"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": 4183437, "tid": 4183437, + "ts": 658971856083.076, "dur": 0.787, + "args": { + "External id": 30739,"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": 4183437, "tid": 4183437, + "ts": 658971856085.009, "dur": 2.585, + "args": { + "External id": 30740,"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": 4183437, "tid": 4183437, + "ts": 658971856088.976, "dur": 0.942, + "args": { + "External id": 30741,"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": 4183437, "tid": 4183437, + "ts": 658971856091.096, "dur": 0.549, + "args": { + "External id": 30742,"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": 4183437, "tid": 4183437, + "ts": 658971856108.116, "dur": 39.456, + "args": { + "External id": 30743,"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": 4183437, "tid": 4183437, + "ts": 658971856180.569, "dur": 131.200, + "args": { + "External id": 30744,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971856190.838, "dur": 4.889, + "args": { + "External id": 30745,"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": 4183437, "tid": 4183437, + "ts": 658971856201.162, "dur": 10.034, + "args": { + "External id": 30746,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971856205.579, "dur": 5.173, + "args": { + "External id": 30747,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971856208.978, "dur": 0.616, + "args": { + "External id": 30748,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971856218.264, "dur": 30.108, + "args": { + "External id": 30749,"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": 4183437, "tid": 4183437, + "ts": 658971856220.268, "dur": 2.511, + "args": { + "External id": 30750,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971856224.329, "dur": 0.555, + "args": { + "External id": 30751,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971856225.612, "dur": 0.723, + "args": { + "External id": 30752,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971856229.635, "dur": 0.843, + "args": { + "External id": 30753,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971856231.545, "dur": 0.764, + "args": { + "External id": 30754,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971856233.860, "dur": 0.793, + "args": { + "External id": 30755,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971856237.835, "dur": 0.856, + "args": { + "External id": 30756,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971856240.289, "dur": 0.650, + "args": { + "External id": 30757,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971856241.892, "dur": 2.560, + "args": { + "External id": 30758,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971856275.972, "dur": 25.860, + "args": { + "External id": 30759,"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": 4183437, "tid": 4183437, + "ts": 658971856368.166, "dur": 399.977, + "args": { + "External id": 30760,"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": 4183437, "tid": 4183437, + "ts": 658971856393.302, "dur": 369.751, + "args": { + "External id": 30761,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971856403.542, "dur": 353.610, + "args": { + "External id": 30762,"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": 4183437, "tid": 4183437, + "ts": 658971856788.546, "dur": 2.858, + "args": { + "External id": 30763,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 4183437, "tid": 4183437, + "ts": 658971856886.450, "dur": 7554.578, + "args": { + "External id": 30764,"Record function id": 0, "Ev Idx": 6171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971856988.253, "dur": 6.561, + "args": { + "External id": 30765,"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": 4183437, "tid": 4183437, + "ts": 658971856998.672, "dur": 1.559, + "args": { + "External id": 30766,"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": 4183437, "tid": 4183437, + "ts": 658971857001.913, "dur": 1.127, + "args": { + "External id": 30767,"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": 4183437, "tid": 4183437, + "ts": 658971857004.901, "dur": 0.948, + "args": { + "External id": 30768,"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": 4183437, "tid": 4183437, + "ts": 658971857007.179, "dur": 1.213, + "args": { + "External id": 30769,"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": 4183437, "tid": 4183437, + "ts": 658971857009.999, "dur": 1.105, + "args": { + "External id": 30770,"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": 4183437, "tid": 4183437, + "ts": 658971857013.282, "dur": 1.464, + "args": { + "External id": 30771,"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": 4183437, "tid": 4183437, + "ts": 658971857016.820, "dur": 2.449, + "args": { + "External id": 30772,"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": 4183437, "tid": 4183437, + "ts": 658971857020.687, "dur": 0.871, + "args": { + "External id": 30773,"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": 4183437, "tid": 4183437, + "ts": 658971857023.362, "dur": 0.953, + "args": { + "External id": 30774,"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": 4183437, "tid": 4183437, + "ts": 658971857041.319, "dur": 7363.596, + "args": { + "External id": 30775,"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": 4183437, "tid": 4183437, + "ts": 658971857056.460, "dur": 7341.829, + "args": { + "External id": 30776,"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": 4183437, "tid": 4183437, + "ts": 658971857071.870, "dur": 14.509, + "args": { + "External id": 30777,"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": 4183437, "tid": 4183437, + "ts": 658971857089.072, "dur": 7278.336, + "args": { + "External id": 30778,"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": 4183437, "tid": 4183437, + "ts": 658971857091.883, "dur": 7274.898, + "args": { + "External id": 30779,"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": 4183437, "tid": 4183437, + "ts": 658971857098.521, "dur": 7.222, + "args": { + "External id": 30780,"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": 4183437, "tid": 4183437, + "ts": 658971857107.243, "dur": 7256.678, + "args": { + "External id": 30781,"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": 4183437, "tid": 4183437, + "ts": 658971864574.251, "dur": 27.264, + "args": { + "External id": 30782,"Sequence number": 459923, "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": 4183437, "tid": 4183437, "ts": 658971864574.251, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971864589.710, "dur": 7.093, + "args": { + "External id": 30783,"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": 4183437, "tid": 4183437, + "ts": 658971864592.599, "dur": 3.955, + "args": { + "External id": 30784,"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": 4183437, "tid": 4183437, + "ts": 658971864693.791, "dur": 82.935, + "args": { + "External id": 30785,"Record function id": 0, "Ev Idx": 6192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971864779.019, "dur": 1076.213, + "args": { + "External id": 30786,"Record function id": 0, "Ev Idx": 6193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971864820.789, "dur": 1019.773, + "args": { + "External id": 30787,"Sequence number": 459924, "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": 4183437, "tid": 4183437, "ts": 658971864820.789, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971864892.662, "dur": 42.342, + "args": { + "External id": 30788,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971864948.268, "dur": 87.902, + "args": { + "External id": 30789,"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": 4183437, "tid": 4183437, + "ts": 658971865045.237, "dur": 34.792, + "args": { + "External id": 30790,"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": 4183437, "tid": 4183437, + "ts": 658971865089.692, "dur": 31.101, + "args": { + "External id": 30791,"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": 4183437, "tid": 4183437, + "ts": 658971865144.507, "dur": 27.734, + "args": { + "External id": 30792,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971865189.748, "dur": 15.369, + "args": { + "External id": 30793,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971865221.398, "dur": 150.149, + "args": { + "External id": 30794,"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": 4183437, "tid": 4183437, + "ts": 658971865288.492, "dur": 12.849, + "args": { + "External id": 30795,"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": 4183437, "tid": 4183437, + "ts": 658971865293.530, "dur": 6.869, + "args": { + "External id": 30796,"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": 4183437, "tid": 4183437, + "ts": 658971865304.313, "dur": 5.919, + "args": { + "External id": 30797,"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": 4183437, "tid": 4183437, + "ts": 658971865311.595, "dur": 1.300, + "args": { + "External id": 30798,"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": 4183437, "tid": 4183437, + "ts": 658971865315.280, "dur": 2.731, + "args": { + "External id": 30799,"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": 4183437, "tid": 4183437, + "ts": 658971865382.190, "dur": 48.231, + "args": { + "External id": 30800,"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": 4183437, "tid": 4183437, + "ts": 658971865460.591, "dur": 28.705, + "args": { + "External id": 30801,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971865497.631, "dur": 37.902, + "args": { + "External id": 30802,"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": 4183437, "tid": 4183437, + "ts": 658971865544.460, "dur": 32.368, + "args": { + "External id": 30803,"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": 4183437, "tid": 4183437, + "ts": 658971865597.767, "dur": 29.816, + "args": { + "External id": 30804,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971865632.981, "dur": 86.654, + "args": { + "External id": 30805,"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": 4183437, "tid": 4183437, + "ts": 658971865745.122, "dur": 21.122, + "args": { + "External id": 30806,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971865918.763, "dur": 76.612, + "args": { + "External id": 30807,"Record function id": 0, "Ev Idx": 6214 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971866069.519, "dur": 47.791, + "args": { + "External id": 30808,"Record function id": 0, "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 4183437, "tid": 4183437, + "ts": 658971866126.934, "dur": 8653.089, + "args": { + "External id": 30809,"Record function id": 0, "Ev Idx": 6216 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 4183437, "tid": 4183437, + "ts": 658971866135.739, "dur": 908.507, + "args": { + "External id": 30810,"Record function id": 0, "Ev Idx": 6217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971866213.886, "dur": 8.850, + "args": { + "External id": 30811,"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": 4183437, "tid": 4183437, + "ts": 658971866235.823, "dur": 54.081, + "args": { + "External id": 30812,"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": 4183437, "tid": 4183437, + "ts": 658971866241.180, "dur": 2.070, + "args": { + "External id": 30813,"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": 4183437, "tid": 4183437, + "ts": 658971866247.869, "dur": 0.840, + "args": { + "External id": 30814,"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": 4183437, "tid": 4183437, + "ts": 658971866249.782, "dur": 0.805, + "args": { + "External id": 30815,"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": 4183437, "tid": 4183437, + "ts": 658971866251.538, "dur": 0.784, + "args": { + "External id": 30816,"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": 4183437, "tid": 4183437, + "ts": 658971866254.934, "dur": 1.000, + "args": { + "External id": 30817,"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": 4183437, "tid": 4183437, + "ts": 658971866257.360, "dur": 0.759, + "args": { + "External id": 30818,"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": 4183437, "tid": 4183437, + "ts": 658971866259.103, "dur": 20.510, + "args": { + "External id": 30819,"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": 4183437, "tid": 4183437, + "ts": 658971866282.145, "dur": 0.700, + "args": { + "External id": 30820,"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": 4183437, "tid": 4183437, + "ts": 658971866283.534, "dur": 0.794, + "args": { + "External id": 30821,"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": 4183437, "tid": 4183437, + "ts": 658971866301.792, "dur": 42.283, + "args": { + "External id": 30822,"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": 4183437, "tid": 4183437, + "ts": 658971866379.175, "dur": 110.649, + "args": { + "External id": 30823,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971866392.778, "dur": 6.434, + "args": { + "External id": 30824,"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": 4183437, "tid": 4183437, + "ts": 658971866404.822, "dur": 10.008, + "args": { + "External id": 30825,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971866409.085, "dur": 5.208, + "args": { + "External id": 30826,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971866412.247, "dur": 0.753, + "args": { + "External id": 30827,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971866421.865, "dur": 27.566, + "args": { + "External id": 30828,"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": 4183437, "tid": 4183437, + "ts": 658971866423.909, "dur": 0.619, + "args": { + "External id": 30829,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971866425.750, "dur": 2.510, + "args": { + "External id": 30830,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971866429.312, "dur": 0.794, + "args": { + "External id": 30831,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971866431.005, "dur": 0.812, + "args": { + "External id": 30832,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971866435.015, "dur": 0.638, + "args": { + "External id": 30833,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971866436.482, "dur": 0.824, + "args": { + "External id": 30834,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971866438.526, "dur": 0.741, + "args": { + "External id": 30835,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971866442.951, "dur": 0.750, + "args": { + "External id": 30836,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971866444.920, "dur": 0.684, + "args": { + "External id": 30837,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971866459.328, "dur": 22.467, + "args": { + "External id": 30838,"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": 4183437, "tid": 4183437, + "ts": 658971866544.315, "dur": 405.740, + "args": { + "External id": 30839,"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": 4183437, "tid": 4183437, + "ts": 658971866570.414, "dur": 374.097, + "args": { + "External id": 30840,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971866580.922, "dur": 357.679, + "args": { + "External id": 30841,"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": 4183437, "tid": 4183437, + "ts": 658971866971.889, "dur": 2.405, + "args": { + "External id": 30842,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 4183437, "tid": 4183437, + "ts": 658971867064.452, "dur": 7501.238, + "args": { + "External id": 30843,"Record function id": 0, "Ev Idx": 6250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971867164.643, "dur": 6.658, + "args": { + "External id": 30844,"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": 4183437, "tid": 4183437, + "ts": 658971867174.451, "dur": 1.636, + "args": { + "External id": 30845,"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": 4183437, "tid": 4183437, + "ts": 658971867178.070, "dur": 1.135, + "args": { + "External id": 30846,"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": 4183437, "tid": 4183437, + "ts": 658971867180.904, "dur": 1.369, + "args": { + "External id": 30847,"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": 4183437, "tid": 4183437, + "ts": 658971867184.150, "dur": 0.868, + "args": { + "External id": 30848,"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": 4183437, "tid": 4183437, + "ts": 658971867186.476, "dur": 1.141, + "args": { + "External id": 30849,"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": 4183437, "tid": 4183437, + "ts": 658971867189.644, "dur": 0.931, + "args": { + "External id": 30850,"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": 4183437, "tid": 4183437, + "ts": 658971867192.898, "dur": 2.081, + "args": { + "External id": 30851,"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": 4183437, "tid": 4183437, + "ts": 658971867196.906, "dur": 0.944, + "args": { + "External id": 30852,"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": 4183437, "tid": 4183437, + "ts": 658971867199.480, "dur": 0.772, + "args": { + "External id": 30853,"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": 4183437, "tid": 4183437, + "ts": 658971867218.004, "dur": 7311.736, + "args": { + "External id": 30854,"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": 4183437, "tid": 4183437, + "ts": 658971867233.320, "dur": 7289.803, + "args": { + "External id": 30855,"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": 4183437, "tid": 4183437, + "ts": 658971867248.445, "dur": 29.433, + "args": { + "External id": 30856,"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": 4183437, "tid": 4183437, + "ts": 658971867281.865, "dur": 7208.783, + "args": { + "External id": 30857,"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": 4183437, "tid": 4183437, + "ts": 658971867284.487, "dur": 7205.548, + "args": { + "External id": 30858,"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": 4183437, "tid": 4183437, + "ts": 658971867290.837, "dur": 6.018, + "args": { + "External id": 30859,"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": 4183437, "tid": 4183437, + "ts": 658971867298.689, "dur": 7188.424, + "args": { + "External id": 30860,"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": 4183437, "tid": 4183437, + "ts": 658971874724.544, "dur": 29.411, + "args": { + "External id": 30861,"Sequence number": 459925, "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": 4183437, "tid": 4183437, "ts": 658971874724.544, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971874741.177, "dur": 7.946, + "args": { + "External id": 30862,"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": 4183437, "tid": 4183437, + "ts": 658971874744.317, "dur": 4.434, + "args": { + "External id": 30863,"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": 4183437, "tid": 4183437, + "ts": 658971874818.683, "dur": 80.207, + "args": { + "External id": 30864,"Record function id": 0, "Ev Idx": 6271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971874900.508, "dur": 1111.857, + "args": { + "External id": 30865,"Record function id": 0, "Ev Idx": 6272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971874939.754, "dur": 1058.518, + "args": { + "External id": 30866,"Sequence number": 459926, "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": 4183437, "tid": 4183437, "ts": 658971874939.754, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971875010.830, "dur": 42.426, + "args": { + "External id": 30867,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971875068.834, "dur": 92.505, + "args": { + "External id": 30868,"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": 4183437, "tid": 4183437, + "ts": 658971875169.733, "dur": 36.357, + "args": { + "External id": 30869,"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": 4183437, "tid": 4183437, + "ts": 658971875212.821, "dur": 30.843, + "args": { + "External id": 30870,"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": 4183437, "tid": 4183437, + "ts": 658971875286.880, "dur": 29.955, + "args": { + "External id": 30871,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971875334.341, "dur": 19.412, + "args": { + "External id": 30872,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971875368.821, "dur": 134.585, + "args": { + "External id": 30873,"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": 4183437, "tid": 4183437, + "ts": 658971875420.979, "dur": 12.630, + "args": { + "External id": 30874,"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": 4183437, "tid": 4183437, + "ts": 658971875425.892, "dur": 6.955, + "args": { + "External id": 30875,"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": 4183437, "tid": 4183437, + "ts": 658971875436.462, "dur": 4.048, + "args": { + "External id": 30876,"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": 4183437, "tid": 4183437, + "ts": 658971875441.733, "dur": 3.872, + "args": { + "External id": 30877,"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": 4183437, "tid": 4183437, + "ts": 658971875448.140, "dur": 2.826, + "args": { + "External id": 30878,"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": 4183437, "tid": 4183437, + "ts": 658971875513.597, "dur": 50.333, + "args": { + "External id": 30879,"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": 4183437, "tid": 4183437, + "ts": 658971875595.386, "dur": 30.156, + "args": { + "External id": 30880,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971875634.047, "dur": 78.118, + "args": { + "External id": 30881,"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": 4183437, "tid": 4183437, + "ts": 658971875723.354, "dur": 54.384, + "args": { + "External id": 30882,"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": 4183437, "tid": 4183437, + "ts": 658971875802.937, "dur": 36.262, + "args": { + "External id": 30883,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971875845.617, "dur": 44.781, + "args": { + "External id": 30884,"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": 4183437, "tid": 4183437, + "ts": 658971875908.532, "dur": 21.042, + "args": { + "External id": 30885,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971876076.039, "dur": 73.372, + "args": { + "External id": 30886,"Record function id": 0, "Ev Idx": 6293 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183437, "tid": 4183437, + "ts": 658971876224.503, "dur": 67.875, + "args": { + "External id": 30887,"Record function id": 0, "Ev Idx": 6294 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 4183437, "tid": 4183437, + "ts": 658971876303.097, "dur": 8402.249, + "args": { + "External id": 30888,"Record function id": 0, "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 4183437, "tid": 4183437, + "ts": 658971876312.361, "dur": 878.401, + "args": { + "External id": 30889,"Record function id": 0, "Ev Idx": 6296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971876398.075, "dur": 9.636, + "args": { + "External id": 30890,"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": 4183437, "tid": 4183437, + "ts": 658971876421.038, "dur": 38.030, + "args": { + "External id": 30891,"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": 4183437, "tid": 4183437, + "ts": 658971876426.536, "dur": 2.423, + "args": { + "External id": 30892,"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": 4183437, "tid": 4183437, + "ts": 658971876434.240, "dur": 0.534, + "args": { + "External id": 30893,"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": 4183437, "tid": 4183437, + "ts": 658971876435.653, "dur": 0.571, + "args": { + "External id": 30894,"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": 4183437, "tid": 4183437, + "ts": 658971876437.188, "dur": 0.654, + "args": { + "External id": 30895,"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": 4183437, "tid": 4183437, + "ts": 658971876441.127, "dur": 0.559, + "args": { + "External id": 30896,"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": 4183437, "tid": 4183437, + "ts": 658971876443.520, "dur": 0.748, + "args": { + "External id": 30897,"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": 4183437, "tid": 4183437, + "ts": 658971876445.629, "dur": 2.751, + "args": { + "External id": 30898,"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": 4183437, "tid": 4183437, + "ts": 658971876449.856, "dur": 0.672, + "args": { + "External id": 30899,"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": 4183437, "tid": 4183437, + "ts": 658971876451.867, "dur": 1.176, + "args": { + "External id": 30900,"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": 4183437, "tid": 4183437, + "ts": 658971876471.268, "dur": 40.198, + "args": { + "External id": 30901,"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": 4183437, "tid": 4183437, + "ts": 658971876544.375, "dur": 148.271, + "args": { + "External id": 30902,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "1", "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": 4183437, "tid": 4183437, + "ts": 658971876554.893, "dur": 4.695, + "args": { + "External id": 30903,"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": 4183437, "tid": 4183437, + "ts": 658971876565.266, "dur": 10.440, + "args": { + "External id": 30904,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "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": 4183437, "tid": 4183437, + "ts": 658971876569.670, "dur": 5.614, + "args": { + "External id": 30905,"Record function id": 0, "Concrete Inputs": ["", "0", "1605888", "3211776", "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": 4183437, "tid": 4183437, + "ts": 658971876573.153, "dur": 0.856, + "args": { + "External id": 30906,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971876582.369, "dur": 30.633, + "args": { + "External id": 30907,"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": 4183437, "tid": 4183437, + "ts": 658971876584.186, "dur": 3.073, + "args": { + "External id": 30908,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "1605888"], "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": 4183437, "tid": 4183437, + "ts": 658971876588.846, "dur": 0.654, + "args": { + "External id": 30909,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1606016"], "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": 4183437, "tid": 4183437, + "ts": 658971876590.519, "dur": 0.844, + "args": { + "External id": 30910,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1737088"], "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": 4183437, "tid": 4183437, + "ts": 658971876594.944, "dur": 0.435, + "args": { + "External id": 30911,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1868160"], "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": 4183437, "tid": 4183437, + "ts": 658971876596.108, "dur": 0.518, + "args": { + "External id": 30912,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "1999232"], "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": 4183437, "tid": 4183437, + "ts": 658971876598.252, "dur": 0.540, + "args": { + "External id": 30913,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "2130304"], "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": 4183437, "tid": 4183437, + "ts": 658971876602.460, "dur": 0.615, + "args": { + "External id": 30914,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2130432"], "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": 4183437, "tid": 4183437, + "ts": 658971876604.412, "dur": 0.672, + "args": { + "External id": 30915,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2490880"], "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": 4183437, "tid": 4183437, + "ts": 658971876606.636, "dur": 2.342, + "args": { + "External id": 30916,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "2851328"], "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": 4183437, "tid": 4183437, + "ts": 658971876625.290, "dur": 22.870, + "args": { + "External id": 30917,"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": 4183437, "tid": 4183437, + "ts": 658971876752.522, "dur": 353.148, + "args": { + "External id": 30918,"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": 4183437, "tid": 4183437, + "ts": 658971876778.201, "dur": 322.546, + "args": { + "External id": 30919,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658971876788.573, "dur": 305.354, + "args": { + "External id": 30920,"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": 4183437, "tid": 4183437, + "ts": 658971877124.236, "dur": 2.019, + "args": { + "External id": 30921,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 4183437, "tid": 4183437, + "ts": 658971877211.179, "dur": 7278.252, + "args": { + "External id": 30922,"Record function id": 0, "Ev Idx": 6329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971877327.749, "dur": 6.542, + "args": { + "External id": 30923,"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": 4183437, "tid": 4183437, + "ts": 658971877345.134, "dur": 2.051, + "args": { + "External id": 30924,"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": 4183437, "tid": 4183437, + "ts": 658971877349.279, "dur": 1.185, + "args": { + "External id": 30925,"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": 4183437, "tid": 4183437, + "ts": 658971877352.074, "dur": 1.110, + "args": { + "External id": 30926,"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": 4183437, "tid": 4183437, + "ts": 658971877354.493, "dur": 0.912, + "args": { + "External id": 30927,"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": 4183437, "tid": 4183437, + "ts": 658971877356.798, "dur": 0.995, + "args": { + "External id": 30928,"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": 4183437, "tid": 4183437, + "ts": 658971877359.993, "dur": 0.806, + "args": { + "External id": 30929,"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": 4183437, "tid": 4183437, + "ts": 658971877362.444, "dur": 1.669, + "args": { + "External id": 30930,"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": 4183437, "tid": 4183437, + "ts": 658971877365.765, "dur": 0.874, + "args": { + "External id": 30931,"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": 4183437, "tid": 4183437, + "ts": 658971877368.651, "dur": 0.778, + "args": { + "External id": 30932,"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": 4183437, "tid": 4183437, + "ts": 658971877388.461, "dur": 7065.150, + "args": { + "External id": 30933,"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": 4183437, "tid": 4183437, + "ts": 658971877404.891, "dur": 7042.427, + "args": { + "External id": 30934,"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": 4183437, "tid": 4183437, + "ts": 658971877418.119, "dur": 13.837, + "args": { + "External id": 30935,"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": 4183437, "tid": 4183437, + "ts": 658971877434.745, "dur": 6981.874, + "args": { + "External id": 30936,"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": 4183437, "tid": 4183437, + "ts": 658971877437.351, "dur": 6978.660, + "args": { + "External id": 30937,"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": 4183437, "tid": 4183437, + "ts": 658971877443.569, "dur": 5.654, + "args": { + "External id": 30938,"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": 4183437, "tid": 4183437, + "ts": 658971877450.901, "dur": 6962.303, + "args": { + "External id": 30939,"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": 4183437, "tid": 4183437, + "ts": 658971884623.115, "dur": 55.013, + "args": { + "External id": 30940,"Sequence number": 459927, "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": 4183437, "tid": 4183437, "ts": 658971884623.115, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183437, "tid": 4183437, + "ts": 658971884640.873, "dur": 7.110, + "args": { + "External id": 30941,"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": 4183437, "tid": 4183437, + "ts": 658971884643.734, "dur": 4.084, + "args": { + "External id": 30942,"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": 4183437, "tid": 4183437, + "ts": 658971884745.599, "dur": 83.871, + "args": { + "External id": 30943,"Record function id": 0, "Ev Idx": 6350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183437, "tid": 4183437, + "ts": 658971884831.041, "dur": 1040.196, + "args": { + "External id": 30944,"Record function id": 0, "Ev Idx": 6351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971884870.834, "dur": 985.904, + "args": { + "External id": 30945,"Sequence number": 459928, "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": 4183437, "tid": 4183437, "ts": 658971884870.834, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971884936.358, "dur": 42.089, + "args": { + "External id": 30946,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971884992.730, "dur": 85.318, + "args": { + "External id": 30947,"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": 4183437, "tid": 4183437, + "ts": 658971885086.328, "dur": 35.755, + "args": { + "External id": 30948,"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": 4183437, "tid": 4183437, + "ts": 658971885131.069, "dur": 28.934, + "args": { + "External id": 30949,"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": 4183437, "tid": 4183437, + "ts": 658971885182.175, "dur": 25.509, + "args": { + "External id": 30950,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971885224.887, "dur": 13.931, + "args": { + "External id": 30951,"kernel_hash": "cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr", "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/yd/cydduboj2466efscuk3tvkfbe5yvbhb5sxk5ulill6a3ww53gqhr.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": 4183437, "tid": 4183437, + "ts": 658971885254.600, "dur": 145.897, + "args": { + "External id": 30952,"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": 4183437, "tid": 4183437, + "ts": 658971885322.921, "dur": 12.943, + "args": { + "External id": 30953,"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": 4183437, "tid": 4183437, + "ts": 658971885328.038, "dur": 6.628, + "args": { + "External id": 30954,"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": 4183437, "tid": 4183437, + "ts": 658971885338.671, "dur": 3.985, + "args": { + "External id": 30955,"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": 4183437, "tid": 4183437, + "ts": 658971885344.001, "dur": 1.290, + "args": { + "External id": 30956,"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": 4183437, "tid": 4183437, + "ts": 658971885347.656, "dur": 2.640, + "args": { + "External id": 30957,"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": 4183437, "tid": 4183437, + "ts": 658971885410.222, "dur": 45.906, + "args": { + "External id": 30958,"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": 4183437, "tid": 4183437, + "ts": 658971885488.227, "dur": 28.968, + "args": { + "External id": 30959,"kernel_hash": "cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqifafngnqnvapsab5siu56mw52zzjo53qtn65cxzop3bd35fgmw.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": 4183437, "tid": 4183437, + "ts": 658971885524.720, "dur": 37.660, + "args": { + "External id": 30960,"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": 4183437, "tid": 4183437, + "ts": 658971885570.639, "dur": 32.153, + "args": { + "External id": 30961,"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": 4183437, "tid": 4183437, + "ts": 658971885624.266, "dur": 26.168, + "args": { + "External id": 30962,"kernel_hash": "ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/kw/ckwwntckieq3ujjoz2jzpcsfvzcsxrne4hwwslnwpv4nc5kcwnol.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": 4183437, "tid": 4183437, + "ts": 658971885693.687, "dur": 48.213, + "args": { + "External id": 30963,"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": 4183437, "tid": 4183437, + "ts": 658971885765.082, "dur": 19.648, + "args": { + "External id": 30964,"kernel_hash": "crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/rk/crkw22lzzvcp6shulid26hbxgcu364bptxf5kjq47n4bnjtgzozt.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": 4183437, "tid": 4183437, + "ts": 658971885937.661, "dur": 33.436, + "args": { + "External id": 30965,"Record function id": 0, "Ev Idx": 6372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971886053.425, "dur": 304.965, + "args": { + "External id": 30966,"Sequence number": 459929, "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": 4183437, "tid": 4183437, "ts": 658971886053.425, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971886086.776, "dur": 7.556, + "args": { + "External id": 30967,"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": 4183437, "tid": 4183437, + "ts": 658971886088.955, "dur": 5.169, + "args": { + "External id": 30968,"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": 4183437, "tid": 4183437, + "ts": 658971886103.832, "dur": 11.878, + "args": { + "External id": 30969,"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": 4183437, "tid": 4183437, + "ts": 658971886107.034, "dur": 8.097, + "args": { + "External id": 30970,"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": 4183437, "tid": 4183437, + "ts": 658971886122.749, "dur": 4.169, + "args": { + "External id": 30971,"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": 4183437, "tid": 4183437, + "ts": 658971886335.978, "dur": 7.384, + "args": { + "External id": 30972,"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": 4183437, "tid": 4183437, + "ts": 658971886339.519, "dur": 3.468, + "args": { + "External id": 30973,"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": 4183437, "tid": 4183437, + "ts": 658971886388.555, "dur": 129.242, + "args": { + "External id": 30974,"Sequence number": 459930, "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": 4183437, "tid": 4183437, + "ts": 658971886391.697, "dur": 15.388, + "args": { + "External id": 30975,"Sequence number": 459930, "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": 4183437, "tid": 4183437, "ts": 658971886391.697, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971886399.351, "dur": 6.133, + "args": { + "External id": 30976,"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": 4183437, "tid": 4183437, + "ts": 658971886403.108, "dur": 1.901, + "args": { + "External id": 30977,"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": 4183437, "tid": 4183437, + "ts": 658971886410.353, "dur": 107.092, + "args": { + "External id": 30978,"Sequence number": 459931, "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": 4183437, "tid": 4183437, + "ts": 658971886413.819, "dur": 5.106, + "args": { + "External id": 30979,"Sequence number": 459931, "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": 4183437, "tid": 4183437, + "ts": 658971886415.158, "dur": 3.621, + "args": { + "External id": 30980,"Sequence number": 459931, "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": 4183437, "tid": 4183437, "ts": 658971886415.158, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971886420.749, "dur": 84.889, + "args": { + "External id": 30981,"Sequence number": 459932, "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": 4183437, "tid": 4183437, "ts": 658971886420.749, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971886509.953, "dur": 6.417, + "args": { + "External id": 30982,"Sequence number": 459933, "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": 4183437, "tid": 4183437, "ts": 658971886509.953, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971886527.987, "dur": 62.999, + "args": { + "External id": 30983,"Sequence number": 459934, "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": 4183437, "tid": 4183437, + "ts": 658971886528.990, "dur": 6.887, + "args": { + "External id": 30984,"Sequence number": 459934, "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": 4183437, "tid": 4183437, "ts": 658971886528.990, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971886531.218, "dur": 3.411, + "args": { + "External id": 30985,"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": 4183437, "tid": 4183437, + "ts": 658971886533.422, "dur": 0.994, + "args": { + "External id": 30986,"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": 4183437, "tid": 4183437, + "ts": 658971886536.809, "dur": 53.881, + "args": { + "External id": 30987,"Sequence number": 459935, "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": 4183437, "tid": 4183437, + "ts": 658971886538.488, "dur": 5.478, + "args": { + "External id": 30988,"Sequence number": 459935, "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": 4183437, "tid": 4183437, + "ts": 658971886539.375, "dur": 4.384, + "args": { + "External id": 30989,"Sequence number": 459935, "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": 4183437, "tid": 4183437, "ts": 658971886539.375, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971886544.597, "dur": 39.616, + "args": { + "External id": 30990,"Sequence number": 459936, "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": 4183437, "tid": 4183437, "ts": 658971886544.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971886585.853, "dur": 4.402, + "args": { + "External id": 30991,"Sequence number": 459937, "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": 4183437, "tid": 4183437, "ts": 658971886585.853, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971886600.813, "dur": 98.528, + "args": { + "External id": 30992,"Sequence number": 459938, "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": 4183437, "tid": 4183437, + "ts": 658971886601.443, "dur": 6.033, + "args": { + "External id": 30993,"Sequence number": 459938, "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": 4183437, "tid": 4183437, "ts": 658971886601.443, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971886603.420, "dur": 2.866, + "args": { + "External id": 30994,"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": 4183437, "tid": 4183437, + "ts": 658971886605.330, "dur": 0.812, + "args": { + "External id": 30995,"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": 4183437, "tid": 4183437, + "ts": 658971886608.236, "dur": 90.861, + "args": { + "External id": 30996,"Sequence number": 459939, "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": 4183437, "tid": 4183437, + "ts": 658971886609.936, "dur": 4.719, + "args": { + "External id": 30997,"Sequence number": 459939, "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": 4183437, "tid": 4183437, + "ts": 658971886610.753, "dur": 3.748, + "args": { + "External id": 30998,"Sequence number": 459939, "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": 4183437, "tid": 4183437, "ts": 658971886610.753, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971886615.253, "dur": 75.467, + "args": { + "External id": 30999,"Sequence number": 459940, "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": 4183437, "tid": 4183437, "ts": 658971886615.253, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971886693.821, "dur": 4.826, + "args": { + "External id": 31000,"Sequence number": 459941, "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": 4183437, "tid": 4183437, "ts": 658971886693.821, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971886724.933, "dur": 4.775, + "args": { + "External id": 31001,"Sequence number": 459942, "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": 4183437, "tid": 4183437, + "ts": 658971886726.192, "dur": 3.384, + "args": { + "External id": 31002,"Sequence number": 459942, "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": 4183437, "tid": 4183437, "ts": 658971886726.192, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971886739.053, "dur": 5.139, + "args": { + "External id": 31003,"Sequence number": 459943, "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": 4183437, "tid": 4183437, + "ts": 658971886740.335, "dur": 3.724, + "args": { + "External id": 31004,"Sequence number": 459943, "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": 4183437, "tid": 4183437, "ts": 658971886740.335, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971886748.137, "dur": 3.049, + "args": { + "External id": 31005,"Sequence number": 459944, "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": 4183437, "tid": 4183437, + "ts": 658971886749.186, "dur": 1.862, + "args": { + "External id": 31006,"Sequence number": 459944, "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": 4183437, "tid": 4183437, "ts": 658971886749.186, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971886787.471, "dur": 180.804, + "args": { + "External id": 31007,"Sequence number": 459945, "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": 4183437, "tid": 4183437, "ts": 658971886787.471, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 4183437, + "ts": 658971886810.105, "dur": 9.293, + "args": { + "External id": 31008,"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": 4183437, "tid": 4183437, + "ts": 658971886812.891, "dur": 6.054, + "args": { + "External id": 31009,"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": 4183437, "tid": 4183437, + "ts": 658971886982.701, "dur": 111.743, + "args": { + "External id": 31010,"Sequence number": 459946, "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": 4183437, "tid": 4183437, "ts": 658971886982.701, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 4183437, + "ts": 658971886997.339, "dur": 9.394, + "args": { + "External id": 31011,"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": 4183437, "tid": 4183437, + "ts": 658971887000.076, "dur": 6.337, + "args": { + "External id": 31012,"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": 4183437, "tid": 4183437, + "ts": 658971887126.356, "dur": 200.081, + "args": { + "External id": 31013,"Sequence number": 459947, "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": 4183437, "tid": 4183437, "ts": 658971887126.356, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183437, "tid": 4183437, + "ts": 658971887157.463, "dur": 137.646, + "args": { + "External id": 31014,"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": 4183437, "tid": 4183437, + "ts": 658971887205.825, "dur": 7.450, + "args": { + "External id": 31015,"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": 4183437, "tid": 4183437, + "ts": 658971887207.971, "dur": 4.767, + "args": { + "External id": 31016,"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": 4183437, "tid": 4183437, + "ts": 658971887215.917, "dur": 3.802, + "args": { + "External id": 31017,"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": 4183437, "tid": 4183437, + "ts": 658971887221.437, "dur": 1.323, + "args": { + "External id": 31018,"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": 4183437, "tid": 4183437, + "ts": 658971887225.393, "dur": 5.005, + "args": { + "External id": 31019,"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": 4183437, "tid": 4183437, + "ts": 658971887310.190, "dur": 5.864, + "args": { + "External id": 31020,"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": 4183437, "tid": 4183437, + "ts": 658971887331.661, "dur": 6.224, + "args": { + "External id": 31021,"Sequence number": 459948, "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": 4183437, "tid": 4183437, + "ts": 658971887333.127, "dur": 4.545, + "args": { + "External id": 31022,"Sequence number": 459948, "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": 4183437, "tid": 4183437, "ts": 658971887333.127, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971887351.279, "dur": 105.455, + "args": { + "External id": 31023,"Sequence number": 459949, "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": 4183437, "tid": 4183437, + "ts": 658971887353.101, "dur": 9.468, + "args": { + "External id": 31024,"Sequence number": 459949, "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": 4183437, "tid": 4183437, "ts": 658971887353.101, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971887356.134, "dur": 5.099, + "args": { + "External id": 31025,"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": 4183437, "tid": 4183437, + "ts": 658971887359.144, "dur": 1.803, + "args": { + "External id": 31026,"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": 4183437, "tid": 4183437, + "ts": 658971887363.998, "dur": 92.375, + "args": { + "External id": 31027,"Sequence number": 459950, "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": 4183437, "tid": 4183437, + "ts": 658971887366.181, "dur": 6.242, + "args": { + "External id": 31028,"Sequence number": 459950, "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": 4183437, "tid": 4183437, + "ts": 658971887367.353, "dur": 4.876, + "args": { + "External id": 31029,"Sequence number": 459950, "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": 4183437, "tid": 4183437, "ts": 658971887367.353, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971887373.518, "dur": 76.349, + "args": { + "External id": 31030,"Sequence number": 459951, "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": 4183437, "tid": 4183437, "ts": 658971887373.518, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971887452.119, "dur": 3.508, + "args": { + "External id": 31031,"Sequence number": 459952, "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": 4183437, "tid": 4183437, "ts": 658971887452.119, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971887492.799, "dur": 276.356, + "args": { + "External id": 31032,"Sequence number": 459953, "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": 4183437, "tid": 4183437, "ts": 658971887492.799, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971887512.379, "dur": 3.114, + "args": { + "External id": 31033,"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": 4183437, "tid": 4183437, + "ts": 658971887513.642, "dur": 1.631, + "args": { + "External id": 31034,"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": 4183437, "tid": 4183437, + "ts": 658971887521.922, "dur": 3.856, + "args": { + "External id": 31035,"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": 4183437, "tid": 4183437, + "ts": 658971887523.426, "dur": 2.240, + "args": { + "External id": 31036,"Record 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": 4183437, "tid": 4183437, + "ts": 658971887524.619, "dur": 0.940, + "args": { + "External id": 31037,"Record 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": 4183437, "tid": 4183437, + "ts": 658971887533.379, "dur": 8.109, + "args": { + "External id": 31038,"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": 4183437, "tid": 4183437, + "ts": 658971887536.079, "dur": 5.106, + "args": { + "External id": 31039,"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": 4183437, "tid": 4183437, + "ts": 658971887547.921, "dur": 3.349, + "args": { + "External id": 31040,"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": 4183437, "tid": 4183437, + "ts": 658971887554.826, "dur": 4.316, + "args": { + "External id": 31041,"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": 4183437, "tid": 4183437, + "ts": 658971887741.502, "dur": 8.110, + "args": { + "External id": 31042,"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": 4183437, "tid": 4183437, + "ts": 658971887742.788, "dur": 6.312, + "args": { + "External id": 31043,"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": 4183437, "tid": 4183437, + "ts": 658971887752.763, "dur": 2.316, + "args": { + "External id": 31044,"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": 4183437, "tid": 4183437, + "ts": 658971887753.764, "dur": 1.147, + "args": { + "External id": 31045,"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": 4183437, "tid": 4183437, + "ts": 658971887793.270, "dur": 116.885, + "args": { + "External id": 31046,"Sequence number": 459954, "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": 4183437, "tid": 4183437, + "ts": 658971887794.595, "dur": 9.349, + "args": { + "External id": 31047,"Sequence number": 459954, "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": 4183437, "tid": 4183437, "ts": 658971887794.595, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971887798.306, "dur": 4.575, + "args": { + "External id": 31048,"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": 4183437, "tid": 4183437, + "ts": 658971887800.826, "dur": 1.686, + "args": { + "External id": 31049,"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": 4183437, "tid": 4183437, + "ts": 658971887805.357, "dur": 104.502, + "args": { + "External id": 31050,"Sequence number": 459955, "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": 4183437, "tid": 4183437, + "ts": 658971887807.288, "dur": 6.193, + "args": { + "External id": 31051,"Sequence number": 459955, "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": 4183437, "tid": 4183437, + "ts": 658971887808.450, "dur": 4.880, + "args": { + "External id": 31052,"Sequence number": 459955, "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": 4183437, "tid": 4183437, "ts": 658971887808.450, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971887814.641, "dur": 89.493, + "args": { + "External id": 31053,"Sequence number": 459956, "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": 4183437, "tid": 4183437, "ts": 658971887814.641, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971887906.217, "dur": 2.957, + "args": { + "External id": 31054,"Sequence number": 459957, "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": 4183437, "tid": 4183437, "ts": 658971887906.217, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971887919.924, "dur": 68.607, + "args": { + "External id": 31055,"Sequence number": 459958, "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": 4183437, "tid": 4183437, + "ts": 658971887920.770, "dur": 8.312, + "args": { + "External id": 31056,"Sequence number": 459958, "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": 4183437, "tid": 4183437, "ts": 658971887920.770, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971887922.460, "dur": 5.193, + "args": { + "External id": 31057,"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": 4183437, "tid": 4183437, + "ts": 658971887926.214, "dur": 1.270, + "args": { + "External id": 31058,"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": 4183437, "tid": 4183437, + "ts": 658971887930.026, "dur": 58.135, + "args": { + "External id": 31059,"Sequence number": 459959, "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": 4183437, "tid": 4183437, + "ts": 658971887931.394, "dur": 5.463, + "args": { + "External id": 31060,"Sequence number": 459959, "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": 4183437, "tid": 4183437, + "ts": 658971887932.510, "dur": 4.090, + "args": { + "External id": 31061,"Sequence number": 459959, "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": 4183437, "tid": 4183437, "ts": 658971887932.510, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971887937.486, "dur": 43.251, + "args": { + "External id": 31062,"Sequence number": 459960, "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": 4183437, "tid": 4183437, "ts": 658971887937.486, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971887983.225, "dur": 4.562, + "args": { + "External id": 31063,"Sequence number": 459961, "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": 4183437, "tid": 4183437, "ts": 658971887983.225, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971888012.074, "dur": 152.897, + "args": { + "External id": 31064,"Sequence number": 459962, "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": 4183437, "tid": 4183437, "ts": 658971888012.074, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971888055.634, "dur": 3.947, + "args": { + "External id": 31065,"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": 4183437, "tid": 4183437, + "ts": 658971888096.909, "dur": 53.916, + "args": { + "External id": 31066,"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": 4183437, "tid": 4183437, + "ts": 658971888097.677, "dur": 4.744, + "args": { + "External id": 31067,"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": 4183437, "tid": 4183437, + "ts": 658971888098.851, "dur": 2.725, + "args": { + "External id": 31068,"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": 4183437, "tid": 4183437, + "ts": 658971888100.637, "dur": 0.692, + "args": { + "External id": 31069,"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": 4183437, "tid": 4183437, + "ts": 658971888103.369, "dur": 47.116, + "args": { + "External id": 31070,"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": 4183437, "tid": 4183437, + "ts": 658971888104.816, "dur": 2.921, + "args": { + "External id": 31071,"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": 4183437, "tid": 4183437, + "ts": 658971888105.903, "dur": 1.690, + "args": { + "External id": 31072,"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": 4183437, "tid": 4183437, + "ts": 658971888108.449, "dur": 38.716, + "args": { + "External id": 31073,"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": 4183437, "tid": 4183437, + "ts": 658971888148.856, "dur": 1.019, + "args": { + "External id": 31074,"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": 4183437, "tid": 4183437, + "ts": 658971888175.008, "dur": 30.246, + "args": { + "External id": 31075,"Sequence number": 459963, "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": 4183437, "tid": 4183437, "ts": 658971888175.008, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971888240.341, "dur": 393.089, + "args": { + "External id": 31076,"Sequence number": 459964, "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": 4183437, "tid": 4183437, "ts": 658971888240.341, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971888260.234, "dur": 44.625, + "args": { + "External id": 31077,"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": 4183437, "tid": 4183437, + "ts": 658971888301.198, "dur": 3.046, + "args": { + "External id": 31078,"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": 4183437, "tid": 4183437, + "ts": 658971888332.275, "dur": 25.297, + "args": { + "External id": 31079,"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": 4183437, "tid": 4183437, + "ts": 658971888350.872, "dur": 6.034, + "args": { + "External id": 31080,"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": 4183437, "tid": 4183437, + "ts": 658971888382.305, "dur": 4.301, + "args": { + "External id": 31081,"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": 4183437, "tid": 4183437, + "ts": 658971888613.541, "dur": 7.489, + "args": { + "External id": 31082,"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": 4183437, "tid": 4183437, + "ts": 658971888617.394, "dur": 3.139, + "args": { + "External id": 31083,"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": 4183437, "tid": 4183437, + "ts": 658971888689.754, "dur": 101.791, + "args": { + "External id": 31084,"Sequence number": 459965, "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": 4183437, "tid": 4183437, + "ts": 658971888691.086, "dur": 10.758, + "args": { + "External id": 31085,"Sequence number": 459965, "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": 4183437, "tid": 4183437, "ts": 658971888691.086, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971888695.633, "dur": 4.473, + "args": { + "External id": 31086,"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": 4183437, "tid": 4183437, + "ts": 658971888698.087, "dur": 1.681, + "args": { + "External id": 31087,"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": 4183437, "tid": 4183437, + "ts": 658971888702.910, "dur": 88.421, + "args": { + "External id": 31088,"Sequence number": 459966, "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": 4183437, "tid": 4183437, + "ts": 658971888705.146, "dur": 4.769, + "args": { + "External id": 31089,"Sequence number": 459966, "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": 4183437, "tid": 4183437, + "ts": 658971888706.438, "dur": 3.320, + "args": { + "External id": 31090,"Sequence number": 459966, "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": 4183437, "tid": 4183437, "ts": 658971888706.438, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971888711.075, "dur": 73.732, + "args": { + "External id": 31091,"Sequence number": 459967, "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": 4183437, "tid": 4183437, "ts": 658971888711.075, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971888787.066, "dur": 3.399, + "args": { + "External id": 31092,"Sequence number": 459968, "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": 4183437, "tid": 4183437, "ts": 658971888787.066, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971888802.224, "dur": 71.886, + "args": { + "External id": 31093,"Sequence number": 459969, "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": 4183437, "tid": 4183437, + "ts": 658971888802.971, "dur": 8.681, + "args": { + "External id": 31094,"Sequence number": 459969, "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": 4183437, "tid": 4183437, "ts": 658971888802.971, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971888807.452, "dur": 2.979, + "args": { + "External id": 31095,"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": 4183437, "tid": 4183437, + "ts": 658971888809.329, "dur": 0.951, + "args": { + "External id": 31096,"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": 4183437, "tid": 4183437, + "ts": 658971888812.414, "dur": 61.318, + "args": { + "External id": 31097,"Sequence number": 459970, "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": 4183437, "tid": 4183437, + "ts": 658971888813.927, "dur": 5.325, + "args": { + "External id": 31098,"Sequence number": 459970, "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": 4183437, "tid": 4183437, + "ts": 658971888814.884, "dur": 4.161, + "args": { + "External id": 31099,"Sequence number": 459970, "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": 4183437, "tid": 4183437, "ts": 658971888814.884, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971888820.055, "dur": 47.397, + "args": { + "External id": 31100,"Sequence number": 459971, "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": 4183437, "tid": 4183437, "ts": 658971888820.055, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971888869.179, "dur": 4.109, + "args": { + "External id": 31101,"Sequence number": 459972, "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": 4183437, "tid": 4183437, "ts": 658971888869.179, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971888882.084, "dur": 57.702, + "args": { + "External id": 31102,"Sequence number": 459973, "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": 4183437, "tid": 4183437, + "ts": 658971888882.718, "dur": 5.678, + "args": { + "External id": 31103,"Sequence number": 459973, "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": 4183437, "tid": 4183437, "ts": 658971888882.718, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971888884.496, "dur": 2.464, + "args": { + "External id": 31104,"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": 4183437, "tid": 4183437, + "ts": 658971888886.124, "dur": 0.709, + "args": { + "External id": 31105,"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": 4183437, "tid": 4183437, + "ts": 658971888889.290, "dur": 50.283, + "args": { + "External id": 31106,"Sequence number": 459974, "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": 4183437, "tid": 4183437, + "ts": 658971888890.229, "dur": 5.387, + "args": { + "External id": 31107,"Sequence number": 459974, "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": 4183437, "tid": 4183437, + "ts": 658971888891.647, "dur": 3.809, + "args": { + "External id": 31108,"Sequence number": 459974, "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": 4183437, "tid": 4183437, "ts": 658971888891.647, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971888896.149, "dur": 37.743, + "args": { + "External id": 31109,"Sequence number": 459975, "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": 4183437, "tid": 4183437, "ts": 658971888896.149, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971888935.792, "dur": 3.226, + "args": { + "External id": 31110,"Sequence number": 459976, "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": 4183437, "tid": 4183437, "ts": 658971888935.792, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971888956.619, "dur": 3.951, + "args": { + "External id": 31111,"Sequence number": 459977, "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": 4183437, "tid": 4183437, + "ts": 658971888957.330, "dur": 3.117, + "args": { + "External id": 31112,"Sequence number": 459977, "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": 4183437, "tid": 4183437, "ts": 658971888957.330, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971888967.089, "dur": 5.532, + "args": { + "External id": 31113,"Sequence number": 459978, "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": 4183437, "tid": 4183437, + "ts": 658971888968.468, "dur": 4.037, + "args": { + "External id": 31114,"Sequence number": 459978, "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": 4183437, "tid": 4183437, "ts": 658971888968.468, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971888976.790, "dur": 5.509, + "args": { + "External id": 31115,"Sequence number": 459979, "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": 4183437, "tid": 4183437, + "ts": 658971888977.879, "dur": 4.286, + "args": { + "External id": 31116,"Sequence number": 459979, "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": 4183437, "tid": 4183437, "ts": 658971888977.879, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971889011.492, "dur": 158.387, + "args": { + "External id": 31117,"Sequence number": 459980, "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": 4183437, "tid": 4183437, "ts": 658971889011.492, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 4183437, + "ts": 658971889030.955, "dur": 8.080, + "args": { + "External id": 31118,"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": 4183437, "tid": 4183437, + "ts": 658971889033.707, "dur": 4.892, + "args": { + "External id": 31119,"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": 4183437, "tid": 4183437, + "ts": 658971889181.854, "dur": 124.425, + "args": { + "External id": 31120,"Sequence number": 459981, "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": 4183437, "tid": 4183437, "ts": 658971889181.854, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 4183437, + "ts": 658971889195.167, "dur": 6.438, + "args": { + "External id": 31121,"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": 4183437, "tid": 4183437, + "ts": 658971889196.823, "dur": 4.449, + "args": { + "External id": 31122,"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": 4183437, "tid": 4183437, + "ts": 658971889336.090, "dur": 176.003, + "args": { + "External id": 31123,"Sequence number": 459982, "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": 4183437, "tid": 4183437, "ts": 658971889336.090, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183437, "tid": 4183437, + "ts": 658971889362.647, "dur": 126.021, + "args": { + "External id": 31124,"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": 4183437, "tid": 4183437, + "ts": 658971889412.391, "dur": 7.709, + "args": { + "External id": 31125,"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": 4183437, "tid": 4183437, + "ts": 658971889414.607, "dur": 5.010, + "args": { + "External id": 31126,"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": 4183437, "tid": 4183437, + "ts": 658971889422.860, "dur": 3.422, + "args": { + "External id": 31127,"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": 4183437, "tid": 4183437, + "ts": 658971889427.774, "dur": 1.317, + "args": { + "External id": 31128,"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": 4183437, "tid": 4183437, + "ts": 658971889433.507, "dur": 3.066, + "args": { + "External id": 31129,"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": 4183437, "tid": 4183437, + "ts": 658971889499.532, "dur": 4.083, + "args": { + "External id": 31130,"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": 4183437, "tid": 4183437, + "ts": 658971889516.784, "dur": 5.649, + "args": { + "External id": 31131,"Sequence number": 459983, "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": 4183437, "tid": 4183437, + "ts": 658971889518.247, "dur": 4.031, + "args": { + "External id": 31132,"Sequence number": 459983, "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": 4183437, "tid": 4183437, "ts": 658971889518.247, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971889535.001, "dur": 96.014, + "args": { + "External id": 31133,"Sequence number": 459984, "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": 4183437, "tid": 4183437, + "ts": 658971889536.505, "dur": 8.392, + "args": { + "External id": 31134,"Sequence number": 459984, "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": 4183437, "tid": 4183437, "ts": 658971889536.505, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971889539.475, "dur": 4.279, + "args": { + "External id": 31135,"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": 4183437, "tid": 4183437, + "ts": 658971889542.080, "dur": 1.422, + "args": { + "External id": 31136,"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": 4183437, "tid": 4183437, + "ts": 658971889545.998, "dur": 84.757, + "args": { + "External id": 31137,"Sequence number": 459985, "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": 4183437, "tid": 4183437, + "ts": 658971889548.453, "dur": 3.830, + "args": { + "External id": 31138,"Sequence number": 459985, "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": 4183437, "tid": 4183437, + "ts": 658971889549.558, "dur": 2.577, + "args": { + "External id": 31139,"Sequence number": 459985, "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": 4183437, "tid": 4183437, "ts": 658971889549.558, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971889553.374, "dur": 71.205, + "args": { + "External id": 31140,"Sequence number": 459986, "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": 4183437, "tid": 4183437, "ts": 658971889553.374, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971889626.959, "dur": 3.179, + "args": { + "External id": 31141,"Sequence number": 459987, "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": 4183437, "tid": 4183437, "ts": 658971889626.959, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971889701.560, "dur": 216.285, + "args": { + "External id": 31142,"Sequence number": 459988, "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": 4183437, "tid": 4183437, "ts": 658971889701.560, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971889723.831, "dur": 4.339, + "args": { + "External id": 31143,"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": 4183437, "tid": 4183437, + "ts": 658971889725.471, "dur": 2.428, + "args": { + "External id": 31144,"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": 4183437, "tid": 4183437, + "ts": 658971889732.042, "dur": 3.301, + "args": { + "External id": 31145,"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": 4183437, "tid": 4183437, + "ts": 658971889733.099, "dur": 2.124, + "args": { + "External id": 31146,"Record 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": 4183437, "tid": 4183437, + "ts": 658971889733.995, "dur": 1.034, + "args": { + "External id": 31147,"Record 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": 4183437, "tid": 4183437, + "ts": 658971889742.648, "dur": 7.862, + "args": { + "External id": 31148,"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": 4183437, "tid": 4183437, + "ts": 658971889744.837, "dur": 5.316, + "args": { + "External id": 31149,"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": 4183437, "tid": 4183437, + "ts": 658971889756.535, "dur": 3.470, + "args": { + "External id": 31150,"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": 4183437, "tid": 4183437, + "ts": 658971889763.308, "dur": 2.753, + "args": { + "External id": 31151,"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": 4183437, "tid": 4183437, + "ts": 658971889894.999, "dur": 5.315, + "args": { + "External id": 31152,"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": 4183437, "tid": 4183437, + "ts": 658971889897.950, "dur": 2.028, + "args": { + "External id": 31153,"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": 4183437, "tid": 4183437, + "ts": 658971889903.463, "dur": 2.247, + "args": { + "External id": 31154,"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": 4183437, "tid": 4183437, + "ts": 658971889904.570, "dur": 1.006, + "args": { + "External id": 31155,"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": 4183437, "tid": 4183437, + "ts": 658971889935.440, "dur": 107.685, + "args": { + "External id": 31156,"Sequence number": 459989, "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": 4183437, "tid": 4183437, + "ts": 658971889936.614, "dur": 7.004, + "args": { + "External id": 31157,"Sequence number": 459989, "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": 4183437, "tid": 4183437, "ts": 658971889936.614, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971889938.787, "dur": 3.672, + "args": { + "External id": 31158,"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": 4183437, "tid": 4183437, + "ts": 658971889940.833, "dur": 1.375, + "args": { + "External id": 31159,"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": 4183437, "tid": 4183437, + "ts": 658971889944.534, "dur": 98.302, + "args": { + "External id": 31160,"Sequence number": 459990, "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": 4183437, "tid": 4183437, + "ts": 658971889945.938, "dur": 5.420, + "args": { + "External id": 31161,"Sequence number": 459990, "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": 4183437, "tid": 4183437, + "ts": 658971889946.963, "dur": 4.235, + "args": { + "External id": 31162,"Sequence number": 459990, "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": 4183437, "tid": 4183437, "ts": 658971889946.963, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971889952.251, "dur": 67.186, + "args": { + "External id": 31163,"Sequence number": 459991, "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": 4183437, "tid": 4183437, "ts": 658971889952.251, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971890036.874, "dur": 5.369, + "args": { + "External id": 31164,"Sequence number": 459992, "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": 4183437, "tid": 4183437, "ts": 658971890036.874, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971890052.113, "dur": 62.792, + "args": { + "External id": 31165,"Sequence number": 459993, "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": 4183437, "tid": 4183437, + "ts": 658971890052.796, "dur": 5.976, + "args": { + "External id": 31166,"Sequence number": 459993, "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": 4183437, "tid": 4183437, "ts": 658971890052.796, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971890054.613, "dur": 3.016, + "args": { + "External id": 31167,"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": 4183437, "tid": 4183437, + "ts": 658971890056.515, "dur": 0.972, + "args": { + "External id": 31168,"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": 4183437, "tid": 4183437, + "ts": 658971890059.422, "dur": 55.184, + "args": { + "External id": 31169,"Sequence number": 459994, "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": 4183437, "tid": 4183437, + "ts": 658971890060.341, "dur": 4.743, + "args": { + "External id": 31170,"Sequence number": 459994, "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": 4183437, "tid": 4183437, + "ts": 658971890061.574, "dur": 3.380, + "args": { + "External id": 31171,"Sequence number": 459994, "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": 4183437, "tid": 4183437, "ts": 658971890061.574, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971890065.628, "dur": 44.867, + "args": { + "External id": 31172,"Sequence number": 459995, "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": 4183437, "tid": 4183437, "ts": 658971890065.628, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971890111.931, "dur": 2.337, + "args": { + "External id": 31173,"Sequence number": 459996, "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": 4183437, "tid": 4183437, "ts": 658971890111.931, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971890135.978, "dur": 168.582, + "args": { + "External id": 31174,"Sequence number": 459997, "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": 4183437, "tid": 4183437, "ts": 658971890135.978, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971890172.881, "dur": 3.990, + "args": { + "External id": 31175,"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": 4183437, "tid": 4183437, + "ts": 658971890210.393, "dur": 78.757, + "args": { + "External id": 31176,"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": 4183437, "tid": 4183437, + "ts": 658971890211.062, "dur": 6.797, + "args": { + "External id": 31177,"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": 4183437, "tid": 4183437, + "ts": 658971890212.115, "dur": 4.910, + "args": { + "External id": 31178,"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": 4183437, "tid": 4183437, + "ts": 658971890216.077, "dur": 0.696, + "args": { + "External id": 31179,"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": 4183437, "tid": 4183437, + "ts": 658971890218.619, "dur": 70.094, + "args": { + "External id": 31180,"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": 4183437, "tid": 4183437, + "ts": 658971890220.020, "dur": 2.537, + "args": { + "External id": 31181,"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": 4183437, "tid": 4183437, + "ts": 658971890221.040, "dur": 1.367, + "args": { + "External id": 31182,"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": 4183437, "tid": 4183437, + "ts": 658971890223.417, "dur": 60.033, + "args": { + "External id": 31183,"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": 4183437, "tid": 4183437, + "ts": 658971890286.715, "dur": 1.256, + "args": { + "External id": 31184,"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": 4183437, "tid": 4183437, + "ts": 658971890314.652, "dur": 29.992, + "args": { + "External id": 31185,"Sequence number": 459998, "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": 4183437, "tid": 4183437, "ts": 658971890314.652, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971890382.587, "dur": 185.768, + "args": { + "External id": 31186,"Sequence number": 459999, "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": 4183437, "tid": 4183437, "ts": 658971890382.587, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971890402.438, "dur": 3.570, + "args": { + "External id": 31187,"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": 4183437, "tid": 4183437, + "ts": 658971890403.549, "dur": 2.262, + "args": { + "External id": 31188,"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": 4183437, "tid": 4183437, + "ts": 658971890413.839, "dur": 7.780, + "args": { + "External id": 31189,"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": 4183437, "tid": 4183437, + "ts": 658971890416.724, "dur": 4.484, + "args": { + "External id": 31190,"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": 4183437, "tid": 4183437, + "ts": 658971890427.915, "dur": 3.161, + "args": { + "External id": 31191,"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": 4183437, "tid": 4183437, + "ts": 658971890553.794, "dur": 3.107, + "args": { + "External id": 31192,"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": 4183437, "tid": 4183437, + "ts": 658971890554.665, "dur": 1.982, + "args": { + "External id": 31193,"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": 4183437, "tid": 4183437, + "ts": 658971890587.775, "dur": 130.643, + "args": { + "External id": 31194,"Sequence number": 460000, "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": 4183437, "tid": 4183437, + "ts": 658971890589.232, "dur": 7.120, + "args": { + "External id": 31195,"Sequence number": 460000, "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": 4183437, "tid": 4183437, "ts": 658971890589.232, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971890591.432, "dur": 3.914, + "args": { + "External id": 31196,"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": 4183437, "tid": 4183437, + "ts": 658971890593.678, "dur": 1.486, + "args": { + "External id": 31197,"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": 4183437, "tid": 4183437, + "ts": 658971890597.466, "dur": 120.408, + "args": { + "External id": 31198,"Sequence number": 460001, "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": 4183437, "tid": 4183437, + "ts": 658971890599.393, "dur": 4.486, + "args": { + "External id": 31199,"Sequence number": 460001, "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": 4183437, "tid": 4183437, + "ts": 658971890600.705, "dur": 3.004, + "args": { + "External id": 31200,"Sequence number": 460001, "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": 4183437, "tid": 4183437, "ts": 658971890600.705, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971890604.853, "dur": 100.852, + "args": { + "External id": 31201,"Sequence number": 460002, "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": 4183437, "tid": 4183437, "ts": 658971890604.853, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971890709.036, "dur": 8.081, + "args": { + "External id": 31202,"Sequence number": 460003, "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": 4183437, "tid": 4183437, "ts": 658971890709.036, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971890728.911, "dur": 64.552, + "args": { + "External id": 31203,"Sequence number": 460004, "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": 4183437, "tid": 4183437, + "ts": 658971890729.854, "dur": 6.065, + "args": { + "External id": 31204,"Sequence number": 460004, "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": 4183437, "tid": 4183437, "ts": 658971890729.854, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971890731.947, "dur": 2.848, + "args": { + "External id": 31205,"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": 4183437, "tid": 4183437, + "ts": 658971890733.830, "dur": 0.782, + "args": { + "External id": 31206,"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": 4183437, "tid": 4183437, + "ts": 658971890736.466, "dur": 56.709, + "args": { + "External id": 31207,"Sequence number": 460005, "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": 4183437, "tid": 4183437, + "ts": 658971890737.585, "dur": 3.753, + "args": { + "External id": 31208,"Sequence number": 460005, "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": 4183437, "tid": 4183437, + "ts": 658971890738.810, "dur": 2.383, + "args": { + "External id": 31209,"Sequence number": 460005, "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": 4183437, "tid": 4183437, "ts": 658971890738.810, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971890741.858, "dur": 47.391, + "args": { + "External id": 31210,"Sequence number": 460006, "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": 4183437, "tid": 4183437, "ts": 658971890741.858, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971890790.838, "dur": 2.003, + "args": { + "External id": 31211,"Sequence number": 460007, "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": 4183437, "tid": 4183437, "ts": 658971890790.838, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971890801.577, "dur": 54.813, + "args": { + "External id": 31212,"Sequence number": 460008, "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": 4183437, "tid": 4183437, + "ts": 658971890802.236, "dur": 5.641, + "args": { + "External id": 31213,"Sequence number": 460008, "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": 4183437, "tid": 4183437, "ts": 658971890802.236, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971890804.114, "dur": 2.653, + "args": { + "External id": 31214,"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": 4183437, "tid": 4183437, + "ts": 658971890805.637, "dur": 1.010, + "args": { + "External id": 31215,"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": 4183437, "tid": 4183437, + "ts": 658971890808.609, "dur": 47.512, + "args": { + "External id": 31216,"Sequence number": 460009, "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": 4183437, "tid": 4183437, + "ts": 658971890809.612, "dur": 4.471, + "args": { + "External id": 31217,"Sequence number": 460009, "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": 4183437, "tid": 4183437, + "ts": 658971890810.457, "dur": 3.479, + "args": { + "External id": 31218,"Sequence number": 460009, "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": 4183437, "tid": 4183437, "ts": 658971890810.457, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971890814.556, "dur": 37.560, + "args": { + "External id": 31219,"Sequence number": 460010, "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": 4183437, "tid": 4183437, "ts": 658971890814.556, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971890853.885, "dur": 1.931, + "args": { + "External id": 31220,"Sequence number": 460011, "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": 4183437, "tid": 4183437, "ts": 658971890853.885, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971890872.445, "dur": 3.996, + "args": { + "External id": 31221,"Sequence number": 460012, "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": 4183437, "tid": 4183437, + "ts": 658971890873.523, "dur": 2.802, + "args": { + "External id": 31222,"Sequence number": 460012, "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": 4183437, "tid": 4183437, "ts": 658971890873.523, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971890882.892, "dur": 6.112, + "args": { + "External id": 31223,"Sequence number": 460013, "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": 4183437, "tid": 4183437, + "ts": 658971890884.235, "dur": 4.601, + "args": { + "External id": 31224,"Sequence number": 460013, "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": 4183437, "tid": 4183437, "ts": 658971890884.235, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971890893.388, "dur": 2.792, + "args": { + "External id": 31225,"Sequence number": 460014, "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": 4183437, "tid": 4183437, + "ts": 658971890894.188, "dur": 1.758, + "args": { + "External id": 31226,"Sequence number": 460014, "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": 4183437, "tid": 4183437, "ts": 658971890894.188, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971890924.401, "dur": 154.434, + "args": { + "External id": 31227,"Sequence number": 460015, "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": 4183437, "tid": 4183437, "ts": 658971890924.401, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 4183437, + "ts": 658971890944.521, "dur": 8.324, + "args": { + "External id": 31228,"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": 4183437, "tid": 4183437, + "ts": 658971890946.881, "dur": 5.576, + "args": { + "External id": 31229,"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": 4183437, "tid": 4183437, + "ts": 658971891090.822, "dur": 103.421, + "args": { + "External id": 31230,"Sequence number": 460016, "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": 4183437, "tid": 4183437, "ts": 658971891090.822, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 4183437, + "ts": 658971891104.271, "dur": 6.325, + "args": { + "External id": 31231,"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": 4183437, "tid": 4183437, + "ts": 658971891106.283, "dur": 3.980, + "args": { + "External id": 31232,"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": 4183437, "tid": 4183437, + "ts": 658971891242.862, "dur": 201.497, + "args": { + "External id": 31233,"Sequence number": 460017, "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": 4183437, "tid": 4183437, "ts": 658971891242.862, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183437, "tid": 4183437, + "ts": 658971891287.151, "dur": 130.802, + "args": { + "External id": 31234,"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": 4183437, "tid": 4183437, + "ts": 658971891336.113, "dur": 10.709, + "args": { + "External id": 31235,"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": 4183437, "tid": 4183437, + "ts": 658971891338.338, "dur": 7.680, + "args": { + "External id": 31236,"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": 4183437, "tid": 4183437, + "ts": 658971891351.429, "dur": 3.971, + "args": { + "External id": 31237,"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": 4183437, "tid": 4183437, + "ts": 658971891356.547, "dur": 1.039, + "args": { + "External id": 31238,"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": 4183437, "tid": 4183437, + "ts": 658971891359.814, "dur": 3.129, + "args": { + "External id": 31239,"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": 4183437, "tid": 4183437, + "ts": 658971891429.289, "dur": 5.132, + "args": { + "External id": 31240,"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": 4183437, "tid": 4183437, + "ts": 658971891448.989, "dur": 6.143, + "args": { + "External id": 31241,"Sequence number": 460018, "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": 4183437, "tid": 4183437, + "ts": 658971891450.471, "dur": 4.468, + "args": { + "External id": 31242,"Sequence number": 460018, "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": 4183437, "tid": 4183437, "ts": 658971891450.471, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971891468.493, "dur": 102.678, + "args": { + "External id": 31243,"Sequence number": 460019, "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": 4183437, "tid": 4183437, + "ts": 658971891469.704, "dur": 9.318, + "args": { + "External id": 31244,"Sequence number": 460019, "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": 4183437, "tid": 4183437, "ts": 658971891469.704, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971891474.024, "dur": 4.011, + "args": { + "External id": 31245,"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": 4183437, "tid": 4183437, + "ts": 658971891476.246, "dur": 1.543, + "args": { + "External id": 31246,"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": 4183437, "tid": 4183437, + "ts": 658971891480.245, "dur": 90.577, + "args": { + "External id": 31247,"Sequence number": 460020, "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": 4183437, "tid": 4183437, + "ts": 658971891482.257, "dur": 3.373, + "args": { + "External id": 31248,"Sequence number": 460020, "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": 4183437, "tid": 4183437, + "ts": 658971891483.245, "dur": 2.253, + "args": { + "External id": 31249,"Sequence number": 460020, "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": 4183437, "tid": 4183437, "ts": 658971891483.245, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971891486.579, "dur": 75.894, + "args": { + "External id": 31250,"Sequence number": 460021, "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": 4183437, "tid": 4183437, "ts": 658971891486.579, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971891564.857, "dur": 5.307, + "args": { + "External id": 31251,"Sequence number": 460022, "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": 4183437, "tid": 4183437, "ts": 658971891564.857, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971891604.760, "dur": 247.146, + "args": { + "External id": 31252,"Sequence number": 460023, "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": 4183437, "tid": 4183437, "ts": 658971891604.760, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971891622.995, "dur": 2.660, + "args": { + "External id": 31253,"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": 4183437, "tid": 4183437, + "ts": 658971891623.698, "dur": 1.619, + "args": { + "External id": 31254,"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": 4183437, "tid": 4183437, + "ts": 658971891629.495, "dur": 3.261, + "args": { + "External id": 31255,"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": 4183437, "tid": 4183437, + "ts": 658971891630.517, "dur": 2.135, + "args": { + "External id": 31256,"Record 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": 4183437, "tid": 4183437, + "ts": 658971891631.566, "dur": 0.965, + "args": { + "External id": 31257,"Record 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": 4183437, "tid": 4183437, + "ts": 658971891639.830, "dur": 6.246, + "args": { + "External id": 31258,"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": 4183437, "tid": 4183437, + "ts": 658971891641.651, "dur": 4.138, + "args": { + "External id": 31259,"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": 4183437, "tid": 4183437, + "ts": 658971891652.279, "dur": 38.929, + "args": { + "External id": 31260,"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": 4183437, "tid": 4183437, + "ts": 658971891698.053, "dur": 4.397, + "args": { + "External id": 31261,"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": 4183437, "tid": 4183437, + "ts": 658971891828.825, "dur": 3.865, + "args": { + "External id": 31262,"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": 4183437, "tid": 4183437, + "ts": 658971891829.778, "dur": 2.658, + "args": { + "External id": 31263,"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": 4183437, "tid": 4183437, + "ts": 658971891835.260, "dur": 1.810, + "args": { + "External id": 31264,"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": 4183437, "tid": 4183437, + "ts": 658971891835.954, "dur": 0.992, + "args": { + "External id": 31265,"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": 4183437, "tid": 4183437, + "ts": 658971891871.361, "dur": 95.455, + "args": { + "External id": 31266,"Sequence number": 460024, "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": 4183437, "tid": 4183437, + "ts": 658971891872.334, "dur": 7.454, + "args": { + "External id": 31267,"Sequence number": 460024, "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": 4183437, "tid": 4183437, "ts": 658971891872.334, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971891874.967, "dur": 3.474, + "args": { + "External id": 31268,"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": 4183437, "tid": 4183437, + "ts": 658971891876.880, "dur": 1.288, + "args": { + "External id": 31269,"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": 4183437, "tid": 4183437, + "ts": 658971891880.734, "dur": 85.783, + "args": { + "External id": 31270,"Sequence number": 460025, "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": 4183437, "tid": 4183437, + "ts": 658971891882.692, "dur": 3.486, + "args": { + "External id": 31271,"Sequence number": 460025, "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": 4183437, "tid": 4183437, + "ts": 658971891883.736, "dur": 2.298, + "args": { + "External id": 31272,"Sequence number": 460025, "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": 4183437, "tid": 4183437, "ts": 658971891883.736, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971891886.951, "dur": 71.719, + "args": { + "External id": 31273,"Sequence number": 460026, "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": 4183437, "tid": 4183437, "ts": 658971891886.951, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971891960.881, "dur": 4.990, + "args": { + "External id": 31274,"Sequence number": 460027, "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": 4183437, "tid": 4183437, "ts": 658971891960.881, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971891974.663, "dur": 63.796, + "args": { + "External id": 31275,"Sequence number": 460028, "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": 4183437, "tid": 4183437, + "ts": 658971891976.041, "dur": 5.403, + "args": { + "External id": 31276,"Sequence number": 460028, "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": 4183437, "tid": 4183437, "ts": 658971891976.041, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971891977.903, "dur": 2.362, + "args": { + "External id": 31277,"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": 4183437, "tid": 4183437, + "ts": 658971891979.378, "dur": 0.755, + "args": { + "External id": 31278,"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": 4183437, "tid": 4183437, + "ts": 658971891982.134, "dur": 56.035, + "args": { + "External id": 31279,"Sequence number": 460029, "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": 4183437, "tid": 4183437, + "ts": 658971891983.463, "dur": 6.329, + "args": { + "External id": 31280,"Sequence number": 460029, "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": 4183437, "tid": 4183437, + "ts": 658971891984.543, "dur": 5.078, + "args": { + "External id": 31281,"Sequence number": 460029, "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": 4183437, "tid": 4183437, "ts": 658971891984.543, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971891990.397, "dur": 41.557, + "args": { + "External id": 31282,"Sequence number": 460030, "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": 4183437, "tid": 4183437, "ts": 658971891990.397, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971892033.706, "dur": 3.990, + "args": { + "External id": 31283,"Sequence number": 460031, "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": 4183437, "tid": 4183437, "ts": 658971892033.706, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971892058.872, "dur": 139.641, + "args": { + "External id": 31284,"Sequence number": 460032, "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": 4183437, "tid": 4183437, "ts": 658971892058.872, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971892095.935, "dur": 3.712, + "args": { + "External id": 31285,"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": 4183437, "tid": 4183437, + "ts": 658971892132.198, "dur": 54.444, + "args": { + "External id": 31286,"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": 4183437, "tid": 4183437, + "ts": 658971892132.853, "dur": 5.015, + "args": { + "External id": 31287,"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": 4183437, "tid": 4183437, + "ts": 658971892133.859, "dur": 3.137, + "args": { + "External id": 31288,"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": 4183437, "tid": 4183437, + "ts": 658971892135.742, "dur": 0.927, + "args": { + "External id": 31289,"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": 4183437, "tid": 4183437, + "ts": 658971892138.674, "dur": 47.658, + "args": { + "External id": 31290,"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": 4183437, "tid": 4183437, + "ts": 658971892140.272, "dur": 2.561, + "args": { + "External id": 31291,"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": 4183437, "tid": 4183437, + "ts": 658971892141.542, "dur": 1.168, + "args": { + "External id": 31292,"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": 4183437, "tid": 4183437, + "ts": 658971892143.520, "dur": 39.266, + "args": { + "External id": 31293,"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": 4183437, "tid": 4183437, + "ts": 658971892184.625, "dur": 1.175, + "args": { + "External id": 31294,"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": 4183437, "tid": 4183437, + "ts": 658971892207.049, "dur": 25.738, + "args": { + "External id": 31295,"Sequence number": 460033, "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": 4183437, "tid": 4183437, "ts": 658971892207.049, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971892285.154, "dur": 186.295, + "args": { + "External id": 31296,"Sequence number": 460034, "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": 4183437, "tid": 4183437, "ts": 658971892285.154, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971892304.680, "dur": 4.231, + "args": { + "External id": 31297,"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": 4183437, "tid": 4183437, + "ts": 658971892305.944, "dur": 2.719, + "args": { + "External id": 31298,"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": 4183437, "tid": 4183437, + "ts": 658971892317.192, "dur": 8.030, + "args": { + "External id": 31299,"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": 4183437, "tid": 4183437, + "ts": 658971892319.782, "dur": 5.002, + "args": { + "External id": 31300,"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": 4183437, "tid": 4183437, + "ts": 658971892330.871, "dur": 3.106, + "args": { + "External id": 31301,"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": 4183437, "tid": 4183437, + "ts": 658971892455.764, "dur": 3.111, + "args": { + "External id": 31302,"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": 4183437, "tid": 4183437, + "ts": 658971892456.617, "dur": 1.939, + "args": { + "External id": 31303,"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": 4183437, "tid": 4183437, + "ts": 658971892490.994, "dur": 83.145, + "args": { + "External id": 31304,"Sequence number": 460035, "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": 4183437, "tid": 4183437, + "ts": 658971892491.833, "dur": 6.708, + "args": { + "External id": 31305,"Sequence number": 460035, "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": 4183437, "tid": 4183437, "ts": 658971892491.833, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971892494.129, "dur": 3.229, + "args": { + "External id": 31306,"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": 4183437, "tid": 4183437, + "ts": 658971892495.826, "dur": 1.295, + "args": { + "External id": 31307,"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": 4183437, "tid": 4183437, + "ts": 658971892499.668, "dur": 74.133, + "args": { + "External id": 31308,"Sequence number": 460036, "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": 4183437, "tid": 4183437, + "ts": 658971892501.234, "dur": 3.430, + "args": { + "External id": 31309,"Sequence number": 460036, "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": 4183437, "tid": 4183437, + "ts": 658971892502.003, "dur": 2.538, + "args": { + "External id": 31310,"Sequence number": 460036, "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": 4183437, "tid": 4183437, "ts": 658971892502.003, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971892505.417, "dur": 63.051, + "args": { + "External id": 31311,"Sequence number": 460037, "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": 4183437, "tid": 4183437, "ts": 658971892505.417, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971892570.571, "dur": 2.469, + "args": { + "External id": 31312,"Sequence number": 460038, "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": 4183437, "tid": 4183437, "ts": 658971892570.571, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971892582.626, "dur": 56.282, + "args": { + "External id": 31313,"Sequence number": 460039, "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": 4183437, "tid": 4183437, + "ts": 658971892583.318, "dur": 5.490, + "args": { + "External id": 31314,"Sequence number": 460039, "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": 4183437, "tid": 4183437, "ts": 658971892583.318, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971892585.247, "dur": 2.501, + "args": { + "External id": 31315,"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": 4183437, "tid": 4183437, + "ts": 658971892586.684, "dur": 0.839, + "args": { + "External id": 31316,"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": 4183437, "tid": 4183437, + "ts": 658971892589.467, "dur": 49.143, + "args": { + "External id": 31317,"Sequence number": 460040, "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": 4183437, "tid": 4183437, + "ts": 658971892590.394, "dur": 3.012, + "args": { + "External id": 31318,"Sequence number": 460040, "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": 4183437, "tid": 4183437, + "ts": 658971892591.144, "dur": 2.126, + "args": { + "External id": 31319,"Sequence number": 460040, "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": 4183437, "tid": 4183437, "ts": 658971892591.144, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971892594.014, "dur": 38.902, + "args": { + "External id": 31320,"Sequence number": 460041, "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": 4183437, "tid": 4183437, "ts": 658971892594.014, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971892634.274, "dur": 3.974, + "args": { + "External id": 31321,"Sequence number": 460042, "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": 4183437, "tid": 4183437, "ts": 658971892634.274, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971892645.364, "dur": 111.976, + "args": { + "External id": 31322,"Sequence number": 460043, "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": 4183437, "tid": 4183437, + "ts": 658971892646.089, "dur": 6.901, + "args": { + "External id": 31323,"Sequence number": 460043, "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": 4183437, "tid": 4183437, "ts": 658971892646.089, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971892647.703, "dur": 4.194, + "args": { + "External id": 31324,"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": 4183437, "tid": 4183437, + "ts": 658971892648.844, "dur": 2.829, + "args": { + "External id": 31325,"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": 4183437, "tid": 4183437, + "ts": 658971892690.649, "dur": 66.332, + "args": { + "External id": 31326,"Sequence number": 460044, "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": 4183437, "tid": 4183437, + "ts": 658971892692.962, "dur": 6.107, + "args": { + "External id": 31327,"Sequence number": 460044, "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": 4183437, "tid": 4183437, + "ts": 658971892694.255, "dur": 4.589, + "args": { + "External id": 31328,"Sequence number": 460044, "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": 4183437, "tid": 4183437, "ts": 658971892694.255, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971892699.731, "dur": 51.494, + "args": { + "External id": 31329,"Sequence number": 460045, "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": 4183437, "tid": 4183437, "ts": 658971892699.731, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971892752.732, "dur": 3.768, + "args": { + "External id": 31330,"Sequence number": 460046, "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": 4183437, "tid": 4183437, "ts": 658971892752.732, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971892774.383, "dur": 4.352, + "args": { + "External id": 31331,"Sequence number": 460047, "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": 4183437, "tid": 4183437, + "ts": 658971892775.529, "dur": 3.045, + "args": { + "External id": 31332,"Sequence number": 460047, "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": 4183437, "tid": 4183437, "ts": 658971892775.529, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971892785.220, "dur": 3.236, + "args": { + "External id": 31333,"Sequence number": 460048, "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": 4183437, "tid": 4183437, + "ts": 658971892786.441, "dur": 1.887, + "args": { + "External id": 31334,"Sequence number": 460048, "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": 4183437, "tid": 4183437, "ts": 658971892786.441, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971892792.846, "dur": 2.757, + "args": { + "External id": 31335,"Sequence number": 460049, "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": 4183437, "tid": 4183437, + "ts": 658971892793.815, "dur": 1.672, + "args": { + "External id": 31336,"Sequence number": 460049, "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": 4183437, "tid": 4183437, "ts": 658971892793.815, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971892823.866, "dur": 156.048, + "args": { + "External id": 31337,"Sequence number": 460050, "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": 4183437, "tid": 4183437, "ts": 658971892823.866, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 4183437, + "ts": 658971892842.652, "dur": 10.830, + "args": { + "External id": 31338,"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": 4183437, "tid": 4183437, + "ts": 658971892845.603, "dur": 7.405, + "args": { + "External id": 31339,"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": 4183437, "tid": 4183437, + "ts": 658971892998.611, "dur": 105.023, + "args": { + "External id": 31340,"Sequence number": 460051, "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": 4183437, "tid": 4183437, "ts": 658971892998.611, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183437, "tid": 4183437, + "ts": 658971893012.029, "dur": 7.761, + "args": { + "External id": 31341,"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": 4183437, "tid": 4183437, + "ts": 658971893015.190, "dur": 4.227, + "args": { + "External id": 31342,"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": 4183437, "tid": 4183437, + "ts": 658971893129.104, "dur": 197.406, + "args": { + "External id": 31343,"Sequence number": 460052, "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": 4183437, "tid": 4183437, "ts": 658971893129.104, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183437, "tid": 4183437, + "ts": 658971893157.333, "dur": 141.461, + "args": { + "External id": 31344,"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": 4183437, "tid": 4183437, + "ts": 658971893205.323, "dur": 6.816, + "args": { + "External id": 31345,"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": 4183437, "tid": 4183437, + "ts": 658971893207.409, "dur": 4.240, + "args": { + "External id": 31346,"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": 4183437, "tid": 4183437, + "ts": 658971893214.589, "dur": 3.891, + "args": { + "External id": 31347,"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": 4183437, "tid": 4183437, + "ts": 658971893219.542, "dur": 1.652, + "args": { + "External id": 31348,"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": 4183437, "tid": 4183437, + "ts": 658971893223.603, "dur": 4.128, + "args": { + "External id": 31349,"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": 4183437, "tid": 4183437, + "ts": 658971893311.877, "dur": 4.510, + "args": { + "External id": 31350,"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": 4183437, "tid": 4183437, + "ts": 658971893331.291, "dur": 5.716, + "args": { + "External id": 31351,"Sequence number": 460053, "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": 4183437, "tid": 4183437, + "ts": 658971893332.660, "dur": 4.220, + "args": { + "External id": 31352,"Sequence number": 460053, "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": 4183437, "tid": 4183437, "ts": 658971893332.660, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971893349.760, "dur": 98.666, + "args": { + "External id": 31353,"Sequence number": 460054, "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": 4183437, "tid": 4183437, + "ts": 658971893351.119, "dur": 8.044, + "args": { + "External id": 31354,"Sequence number": 460054, "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": 4183437, "tid": 4183437, "ts": 658971893351.119, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971893354.086, "dur": 4.123, + "args": { + "External id": 31355,"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": 4183437, "tid": 4183437, + "ts": 658971893356.352, "dur": 1.588, + "args": { + "External id": 31356,"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": 4183437, "tid": 4183437, + "ts": 658971893360.668, "dur": 87.443, + "args": { + "External id": 31357,"Sequence number": 460055, "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": 4183437, "tid": 4183437, + "ts": 658971893362.317, "dur": 2.836, + "args": { + "External id": 31358,"Sequence number": 460055, "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": 4183437, "tid": 4183437, + "ts": 658971893363.126, "dur": 1.883, + "args": { + "External id": 31359,"Sequence number": 460055, "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": 4183437, "tid": 4183437, "ts": 658971893363.126, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971893366.210, "dur": 76.101, + "args": { + "External id": 31360,"Sequence number": 460056, "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": 4183437, "tid": 4183437, "ts": 658971893366.210, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971893444.389, "dur": 3.059, + "args": { + "External id": 31361,"Sequence number": 460057, "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": 4183437, "tid": 4183437, "ts": 658971893444.389, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971893482.134, "dur": 237.776, + "args": { + "External id": 31362,"Sequence number": 460058, "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": 4183437, "tid": 4183437, "ts": 658971893482.134, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183437, "tid": 4183437, + "ts": 658971893499.105, "dur": 3.114, + "args": { + "External id": 31363,"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": 4183437, "tid": 4183437, + "ts": 658971893500.431, "dur": 1.673, + "args": { + "External id": 31364,"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": 4183437, "tid": 4183437, + "ts": 658971893505.744, "dur": 2.893, + "args": { + "External id": 31365,"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": 4183437, "tid": 4183437, + "ts": 658971893506.834, "dur": 1.691, + "args": { + "External id": 31366,"Record 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": 4183437, "tid": 4183437, + "ts": 658971893507.487, "dur": 0.908, + "args": { + "External id": 31367,"Record 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": 4183437, "tid": 4183437, + "ts": 658971893515.524, "dur": 7.027, + "args": { + "External id": 31368,"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": 4183437, "tid": 4183437, + "ts": 658971893517.906, "dur": 4.351, + "args": { + "External id": 31369,"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": 4183437, "tid": 4183437, + "ts": 658971893528.764, "dur": 3.365, + "args": { + "External id": 31370,"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": 4183437, "tid": 4183437, + "ts": 658971893535.340, "dur": 3.004, + "args": { + "External id": 31371,"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": 4183437, "tid": 4183437, + "ts": 658971893694.070, "dur": 6.511, + "args": { + "External id": 31372,"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": 4183437, "tid": 4183437, + "ts": 658971893695.078, "dur": 5.056, + "args": { + "External id": 31373,"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": 4183437, "tid": 4183437, + "ts": 658971893704.288, "dur": 2.213, + "args": { + "External id": 31374,"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": 4183437, "tid": 4183437, + "ts": 658971893705.374, "dur": 1.018, + "args": { + "External id": 31375,"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": 4183437, "tid": 4183437, + "ts": 658971893738.776, "dur": 93.345, + "args": { + "External id": 31376,"Sequence number": 460059, "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": 4183437, "tid": 4183437, + "ts": 658971893740.113, "dur": 7.528, + "args": { + "External id": 31377,"Sequence number": 460059, "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": 4183437, "tid": 4183437, "ts": 658971893740.113, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971893742.683, "dur": 3.774, + "args": { + "External id": 31378,"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": 4183437, "tid": 4183437, + "ts": 658971893744.618, "dur": 1.601, + "args": { + "External id": 31379,"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": 4183437, "tid": 4183437, + "ts": 658971893748.514, "dur": 83.264, + "args": { + "External id": 31380,"Sequence number": 460060, "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": 4183437, "tid": 4183437, + "ts": 658971893750.191, "dur": 5.645, + "args": { + "External id": 31381,"Sequence number": 460060, "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": 4183437, "tid": 4183437, + "ts": 658971893751.226, "dur": 4.380, + "args": { + "External id": 31382,"Sequence number": 460060, "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": 4183437, "tid": 4183437, "ts": 658971893751.226, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971893756.686, "dur": 69.728, + "args": { + "External id": 31383,"Sequence number": 460061, "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": 4183437, "tid": 4183437, "ts": 658971893756.686, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971893828.375, "dur": 2.889, + "args": { + "External id": 31384,"Sequence number": 460062, "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": 4183437, "tid": 4183437, "ts": 658971893828.375, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183437, "tid": 4183437, + "ts": 658971893840.677, "dur": 69.437, + "args": { + "External id": 31385,"Sequence number": 460063, "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": 4183437, "tid": 4183437, + "ts": 658971893841.370, "dur": 10.746, + "args": { + "External id": 31386,"Sequence number": 460063, "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": 4183437, "tid": 4183437, "ts": 658971893841.370, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183437, "tid": 4183437, + "ts": 658971893846.168, "dur": 4.624, + "args": { + "External id": 31387,"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": 4183437, "tid": 4183437, + "ts": 658971893849.651, "dur": 0.964, + "args": { + "External id": 31388,"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": 4183437, "tid": 4183437, + "ts": 658971893852.766, "dur": 57.098, + "args": { + "External id": 31389,"Sequence number": 460064, "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": 4183437, "tid": 4183437, + "ts": 658971893853.727, "dur": 4.455, + "args": { + "External id": 31390,"Sequence number": 460064, "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": 4183437, "tid": 4183437, + "ts": 658971893854.724, "dur": 3.314, + "args": { + "External id": 31391,"Sequence number": 460064, "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": 4183437, "tid": 4183437, "ts": 658971893854.724, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183437, "tid": 4183437, + "ts": 658971893858.934, "dur": 42.234, + "args": { + "External id": 31392,"Sequence number": 460065, "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": 4183437, "tid": 4183437, "ts": 658971893858.934, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183437, "tid": 4183437, + "ts": 658971893902.889, "dur": 6.645, + "args": { + "External id": 31393,"Sequence number": 460066, "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": 4183437, "tid": 4183437, "ts": 658971893902.889, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971893929.588, "dur": 138.946, + "args": { + "External id": 31394,"Sequence number": 460067, "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": 4183437, "tid": 4183437, "ts": 658971893929.588, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183437, "tid": 4183437, + "ts": 658971893966.482, "dur": 4.042, + "args": { + "External id": 31395,"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": 4183437, "tid": 4183437, + "ts": 658971894002.984, "dur": 53.659, + "args": { + "External id": 31396,"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": 4183437, "tid": 4183437, + "ts": 658971894003.572, "dur": 4.511, + "args": { + "External id": 31397,"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": 4183437, "tid": 4183437, + "ts": 658971894004.734, "dur": 2.500, + "args": { + "External id": 31398,"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": 4183437, "tid": 4183437, + "ts": 658971894006.295, "dur": 0.775, + "args": { + "External id": 31399,"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": 4183437, "tid": 4183437, + "ts": 658971894008.923, "dur": 47.439, + "args": { + "External id": 31400,"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": 4183437, "tid": 4183437, + "ts": 658971894010.434, "dur": 2.138, + "args": { + "External id": 31401,"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": 4183437, "tid": 4183437, + "ts": 658971894011.369, "dur": 1.093, + "args": { + "External id": 31402,"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": 4183437, "tid": 4183437, + "ts": 658971894013.157, "dur": 39.457, + "args": { + "External id": 31403,"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": 4183437, "tid": 4183437, + "ts": 658971894054.692, "dur": 1.135, + "args": { + "External id": 31404,"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": 4183437, "tid": 4183437, + "ts": 658971894076.514, "dur": 26.662, + "args": { + "External id": 31405,"Sequence number": 460068, "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": 4183437, "tid": 4183437, "ts": 658971894076.514, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 4183437, "tid": 4183437, + "ts": 658971894120.349, "dur": 41.931, + "args": { + "External id": 31406,"Sequence number": 460069, "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": 4183437, "tid": 4183437, "ts": 658971894120.349, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 4183437, "tid": 4183437, + "ts": 658971894127.800, "dur": 29.592, + "args": { + "External id": 31407,"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": 4183437, "tid": 4183437, + "ts": 658971894158.920, "dur": 1.878, + "args": { + "External id": 31408,"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": 4183437, "tid": 4183437, + "ts": 658971894196.919, "dur": 91.565, + "args": { + "External id": 31409,"Record function id": 0, "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 4183437, "tid": 4183437, + "ts": 658971894290.763, "dur": 193.464, + "args": { + "External id": 31410,"Record function id": 0, "Ev Idx": 6817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183437, "tid": 4183437, + "ts": 658971894329.970, "dur": 145.794, + "args": { + "External id": 31411,"Sequence number": 460070, "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": 4183437, "tid": 4183437, "ts": 658971894329.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183437, "tid": 4183437, + "ts": 658971894397.609, "dur": 39.679, + "args": { + "External id": 31412,"kernel_hash": "cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/bz/cbzso6w6hywh6tshw4koysopsifasmv3jfwqhf6xmgi5t3amn2td.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": 4183437, "tid": 4183437, + "ts": 658971894565.020, "dur": 38.168, + "args": { + "External id": 31413,"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": 4183437, "tid": 4183437, + "ts": 658971894567.806, "dur": 4.805, + "args": { + "External id": 31414,"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": 4183437, "tid": 4183437, + "ts": 658971894575.282, "dur": 27.561, + "args": { + "External id": 31415,"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": 4183437, "tid": 4183437, + "ts": 658971894577.848, "dur": 24.451, + "args": { + "External id": 31416,"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": 4183437, "tid": 4183437, + "ts": 658971894607.206, "dur": 19.297, + "args": { + "External id": 31417,"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": 4183437, "tid": 4183437, + "ts": 658971894608.152, "dur": 2.513, + "args": { + "External id": 31418,"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": 4183437, "tid": 4183437, + "ts": 658971894611.344, "dur": 14.884, + "args": { + "External id": 31419,"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": 4183437, "tid": 4183437, + "ts": 658971894612.102, "dur": 13.763, + "args": { + "External id": 31420,"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": 4183437, "tid": 4183437, + "ts": 658971894629.405, "dur": 16.444, + "args": { + "External id": 31421,"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": 4183437, "tid": 4183437, + "ts": 658971894630.200, "dur": 2.368, + "args": { + "External id": 31422,"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": 4183437, "tid": 4183437, + "ts": 658971894633.084, "dur": 12.536, + "args": { + "External id": 31423,"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": 4183437, "tid": 4183437, + "ts": 658971894634.155, "dur": 10.962, + "args": { + "External id": 31424,"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": 4183437, "tid": 4183437, + "ts": 658971894695.075, "dur": 0.814, + "args": { + "External id": 31425,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894705.776, "dur": 9.156, + "args": { + "External id": 31426,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894711.090, "dur": 2.162, + "args": { + "External id": 31427,"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": 4183437, "tid": 4183437, + "ts": 658971894721.624, "dur": 6.278, + "args": { + "External id": 31428,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894725.182, "dur": 0.885, + "args": { + "External id": 31429,"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": 4183437, "tid": 4183437, + "ts": 658971894729.263, "dur": 2.934, + "args": { + "External id": 31430,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894730.773, "dur": 0.682, + "args": { + "External id": 31431,"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": 4183437, "tid": 4183437, + "ts": 658971894733.794, "dur": 2.832, + "args": { + "External id": 31432,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894735.371, "dur": 0.660, + "args": { + "External id": 31433,"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": 4183437, "tid": 4183437, + "ts": 658971894739.848, "dur": 3.204, + "args": { + "External id": 31434,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894741.518, "dur": 0.986, + "args": { + "External id": 31435,"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": 4183437, "tid": 4183437, + "ts": 658971894744.091, "dur": 2.784, + "args": { + "External id": 31436,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894745.389, "dur": 0.678, + "args": { + "External id": 31437,"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": 4183437, "tid": 4183437, + "ts": 658971894748.144, "dur": 2.396, + "args": { + "External id": 31438,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894749.266, "dur": 0.731, + "args": { + "External id": 31439,"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": 4183437, "tid": 4183437, + "ts": 658971894754.810, "dur": 4.498, + "args": { + "External id": 31440,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894757.733, "dur": 0.763, + "args": { + "External id": 31441,"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": 4183437, "tid": 4183437, + "ts": 658971894763.116, "dur": 2.744, + "args": { + "External id": 31442,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894764.700, "dur": 0.565, + "args": { + "External id": 31443,"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": 4183437, "tid": 4183437, + "ts": 658971894769.134, "dur": 7.306, + "args": { + "External id": 31444,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894774.390, "dur": 0.913, + "args": { + "External id": 31445,"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": 4183437, "tid": 4183437, + "ts": 658971894777.758, "dur": 2.654, + "args": { + "External id": 31446,"Sequence number": 460071, "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": 4183437, "tid": 4183437, + "ts": 658971894779.226, "dur": 0.618, + "args": { + "External id": 31447,"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": 4183437, "tid": 4183437, + "ts": 658971894782.948, "dur": 5.771, + "args": { + "External id": 31448,"Sequence number": 460071, "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": 4183437, "tid": 4183437, "ts": 658971894782.948, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971894786.442, "dur": 0.658, + "args": { + "External id": 31449,"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": 4183437, "tid": 4183437, + "ts": 658971894789.929, "dur": 4.552, + "args": { + "External id": 31450,"Sequence number": 460072, "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": 4183437, "tid": 4183437, "ts": 658971894789.929, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971894792.672, "dur": 1.016, + "args": { + "External id": 31451,"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": 4183437, "tid": 4183437, + "ts": 658971894795.552, "dur": 4.887, + "args": { + "External id": 31452,"Sequence number": 460073, "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": 4183437, "tid": 4183437, "ts": 658971894795.552, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971894798.997, "dur": 0.551, + "args": { + "External id": 31453,"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": 4183437, "tid": 4183437, + "ts": 658971894801.571, "dur": 4.398, + "args": { + "External id": 31454,"Sequence number": 460074, "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": 4183437, "tid": 4183437, "ts": 658971894801.571, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971894804.059, "dur": 1.123, + "args": { + "External id": 31455,"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": 4183437, "tid": 4183437, + "ts": 658971894809.628, "dur": 45.258, + "args": { + "External id": 31456,"Sequence number": 460075, "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": 4183437, "tid": 4183437, + "ts": 658971894811.994, "dur": 42.612, + "args": { + "External id": 31457,"Sequence number": 460075, "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": 4183437, "tid": 4183437, + "ts": 658971894815.116, "dur": 8.524, + "args": { + "External id": 31458,"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": 4183437, "tid": 4183437, + "ts": 658971894817.150, "dur": 5.898, + "args": { + "External id": 31459,"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": 4183437, "tid": 4183437, + "ts": 658971894825.068, "dur": 29.059, + "args": { + "External id": 31460,"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": 4183437, "tid": 4183437, + "ts": 658971894881.079, "dur": 4.568, + "args": { + "External id": 31461,"Sequence number": 460075, "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": 4183437, "tid": 4183437, "ts": 658971894881.079, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971894887.850, "dur": 1.400, + "args": { + "External id": 31462,"Sequence number": 460076, "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": 4183437, "tid": 4183437, + "ts": 658971894915.669, "dur": 21208.707, + "args": { + "External id": 31463,"Sequence number": 460076, "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": 4183437, "tid": 4183437, "ts": 658971894915.669, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183437, "tid": 4183437, + "ts": 658971894930.368, "dur": 28.552, + "args": { + "External id": 31464,"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": 4183437, "tid": 4183437, + "ts": 658971894931.141, "dur": 27.549, + "args": { + "External id": 31465,"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": 4183437, "tid": 4183437, + "ts": 658971894932.721, "dur": 5.378, + "args": { + "External id": 31466,"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": 4183437, "tid": 4183437, + "ts": 658971894934.052, "dur": 3.694, + "args": { + "External id": 31467,"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": 4183437, "tid": 4183437, + "ts": 658971894938.777, "dur": 19.413, + "args": { + "External id": 31468,"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": 4183437, "tid": 4183437, + "ts": 658971894976.488, "dur": 32.564, + "args": { + "External id": 31469,"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": 4183437, "tid": 4183437, + "ts": 658971894984.246, "dur": 6.697, + "args": { + "External id": 31470,"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": 4183437, "tid": 4183437, + "ts": 658971894986.476, "dur": 4.083, + "args": { + "External id": 31471,"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": 4183437, "tid": 4183437, + "ts": 658971894991.770, "dur": 17.053, + "args": { + "External id": 31472,"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": 4183437, "tid": 4183437, + "ts": 658971894992.954, "dur": 15.431, + "args": { + "External id": 31473,"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": 4183437, "tid": 4183437, + "ts": 658971895013.225, "dur": 20.987, + "args": { + "External id": 31474,"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": 4183437, "tid": 4183437, + "ts": 658971895014.048, "dur": 4.275, + "args": { + "External id": 31475,"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": 4183437, "tid": 4183437, + "ts": 658971895015.288, "dur": 2.778, + "args": { + "External id": 31476,"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": 4183437, "tid": 4183437, + "ts": 658971895019.023, "dur": 14.986, + "args": { + "External id": 31477,"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": 4183437, "tid": 4183437, + "ts": 658971895019.725, "dur": 13.843, + "args": { + "External id": 31478,"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": 4183437, "tid": 4183437, + "ts": 658971895038.814, "dur": 16.270, + "args": { + "External id": 31479,"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": 4183437, "tid": 4183437, + "ts": 658971895039.902, "dur": 2.314, + "args": { + "External id": 31480,"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": 4183437, "tid": 4183437, + "ts": 658971895042.751, "dur": 12.076, + "args": { + "External id": 31481,"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": 4183437, "tid": 4183437, + "ts": 658971895043.438, "dur": 11.063, + "args": { + "External id": 31482,"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": 4183437, "tid": 4183437, + "ts": 658971895062.037, "dur": 29.653, + "args": { + "External id": 31483,"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": 4183437, "tid": 4183437, + "ts": 658971895096.664, "dur": 67.234, + "args": { + "External id": 31484,"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": 4183437, "tid": 4183437, + "ts": 658971895099.958, "dur": 63.451, + "args": { + "External id": 31485,"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": 4183437, "tid": 4183437, + "ts": 658971895106.509, "dur": 1.649, + "args": { + "External id": 31486,"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": 4183437, "tid": 4183437, + "ts": 658971895109.838, "dur": 29.043, + "args": { + "External id": 31487,"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": 4183437, "tid": 4183437, + "ts": 658971895113.813, "dur": 24.832, + "args": { + "External id": 31488,"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": 4183437, "tid": 4183437, + "ts": 658971895116.210, "dur": 2.958, + "args": { + "External id": 31489,"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": 4183437, "tid": 4183437, + "ts": 658971895120.263, "dur": 17.960, + "args": { + "External id": 31490,"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": 4183437, "tid": 4183437, + "ts": 658971895168.864, "dur": 15161.343, + "args": { + "External id": 31491,"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": 4183437, "tid": 4183437, + "ts": 658971895171.076, "dur": 15157.806, + "args": { + "External id": 31492,"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": 4183437, "tid": 4183437, + "ts": 658971910341.903, "dur": 6.990, + "args": { + "External id": 31493,"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": 4183437, "tid": 4183437, + "ts": 658971910346.127, "dur": 1.011, + "args": { + "External id": 31494,"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": 4183437, "tid": 4183437, + "ts": 658971910354.113, "dur": 111.011, + "args": { + "External id": 31495,"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": 4183437, "tid": 4183437, + "ts": 658971910355.649, "dur": 6.775, + "args": { + "External id": 31496,"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": 4183437, "tid": 4183437, + "ts": 658971910357.909, "dur": 3.426, + "args": { + "External id": 31497,"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": 4183437, "tid": 4183437, + "ts": 658971910360.011, "dur": 1.059, + "args": { + "External id": 31498,"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": 4183437, "tid": 4183437, + "ts": 658971910363.654, "dur": 100.742, + "args": { + "External id": 31499,"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": 4183437, "tid": 4183437, + "ts": 658971910365.507, "dur": 97.932, + "args": { + "External id": 31500,"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": 4183437, "tid": 4183437, + "ts": 658971910468.734, "dur": 4.216, + "args": { + "External id": 31501,"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": 4183437, "tid": 4183437, + "ts": 658971910470.848, "dur": 0.793, + "args": { + "External id": 31502,"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": 4183437, "tid": 4183437, + "ts": 658971910482.141, "dur": 3.673, + "args": { + "External id": 31503,"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": 4183437, "tid": 4183437, + "ts": 658971910497.134, "dur": 7.199, + "args": { + "External id": 31504,"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": 4183437, "tid": 4183437, + "ts": 658971910499.914, "dur": 4.163, + "args": { + "External id": 31505,"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": 4183437, "tid": 4183437, + "ts": 658971910650.616, "dur": 266.907, + "args": { + "External id": 31506,"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": 4183437, "tid": 4183437, + "ts": 658971910682.257, "dur": 6.359, + "args": { + "External id": 31507,"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": 4183437, "tid": 4183437, + "ts": 658971910691.543, "dur": 225.380, + "args": { + "External id": 31508,"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": 4183437, "tid": 4183437, + "ts": 658971910694.716, "dur": 0.682, + "args": { + "External id": 31509,"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": 4183437, "tid": 4183437, + "ts": 658971910698.594, "dur": 31.299, + "args": { + "External id": 31510,"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": 4183437, "tid": 4183437, + "ts": 658971910732.761, "dur": 6.025, + "args": { + "External id": 31511,"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": 4183437, "tid": 4183437, + "ts": 658971910737.463, "dur": 0.823, + "args": { + "External id": 31512,"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": 4183437, "tid": 4183437, + "ts": 658971910740.570, "dur": 26.898, + "args": { + "External id": 31513,"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": 4183437, "tid": 4183437, + "ts": 658971910741.758, "dur": 1.112, + "args": { + "External id": 31514,"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": 4183437, "tid": 4183437, + "ts": 658971910745.036, "dur": 22.152, + "args": { + "External id": 31515,"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": 4183437, "tid": 4183437, + "ts": 658971910749.563, "dur": 3.508, + "args": { + "External id": 31516,"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": 4183437, "tid": 4183437, + "ts": 658971910769.849, "dur": 25.114, + "args": { + "External id": 31517,"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": 4183437, "tid": 4183437, + "ts": 658971910797.573, "dur": 17.719, + "args": { + "External id": 31518,"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": 4183437, "tid": 4183437, + "ts": 658971910819.216, "dur": 18.619, + "args": { + "External id": 31519,"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": 4183437, "tid": 4183437, + "ts": 658971910840.783, "dur": 15.918, + "args": { + "External id": 31520,"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": 4183437, "tid": 4183437, + "ts": 658971910860.125, "dur": 23.389, + "args": { + "External id": 31521,"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": 4183437, "tid": 4183437, + "ts": 658971910864.840, "dur": 1.406, + "args": { + "External id": 31522,"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": 4183437, "tid": 4183437, + "ts": 658971910868.472, "dur": 0.882, + "args": { + "External id": 31523,"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": 4183437, "tid": 4183437, + "ts": 658971910886.644, "dur": 14.836, + "args": { + "External id": 31524,"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": 4183437, "tid": 4183437, + "ts": 658971910904.375, "dur": 11.551, + "args": { + "External id": 31525,"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": 4183437, "tid": 4183437, + "ts": 658971910925.919, "dur": 2.582, + "args": { + "External id": 31526,"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": 4183437, "tid": 4183437, + "ts": 658971910935.519, "dur": 4.621, + "args": { + "External id": 31527,"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": 4183437, "tid": 4183437, + "ts": 658971910938.240, "dur": 0.926, + "args": { + "External id": 31528,"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": 4183437, "tid": 4183437, + "ts": 658971911030.242, "dur": 65.381, + "args": { + "External id": 31529,"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": 4183437, "tid": 4183437, + "ts": 658971911100.957, "dur": 4.695, + "args": { + "External id": 31530,"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": 4183437, "tid": 4183437, + "ts": 658971911103.585, "dur": 0.983, + "args": { + "External id": 31531,"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": 4183437, "tid": 4183437, + "ts": 658971911107.318, "dur": 30.591, + "args": { + "External id": 31532,"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": 4183437, "tid": 4183437, + "ts": 658971911143.893, "dur": 6.569, + "args": { + "External id": 31533,"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": 4183437, "tid": 4183437, + "ts": 658971911145.754, "dur": 3.975, + "args": { + "External id": 31534,"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": 4183437, "tid": 4183437, + "ts": 658971911147.741, "dur": 1.711, + "args": { + "External id": 31535,"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": 4183437, "tid": 4183437, + "ts": 658971911154.711, "dur": 54.375, + "args": { + "External id": 31536,"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": 4183437, "tid": 4183437, + "ts": 658971911155.970, "dur": 52.545, + "args": { + "External id": 31537,"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": 4183437, "tid": 4183437, + "ts": 658971911214.635, "dur": 19.634, + "args": { + "External id": 31538,"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": 4183437, "tid": 4183437, + "ts": 658971911240.731, "dur": 3.763, + "args": { + "External id": 31539,"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": 4183437, "tid": 4183437, + "ts": 658971911242.869, "dur": 0.672, + "args": { + "External id": 31540,"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": 4183437, "tid": 4183437, + "ts": 658971911249.211, "dur": 78.903, + "args": { + "External id": 31541,"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": 4183437, "tid": 4183437, + "ts": 658971911250.196, "dur": 10.146, + "args": { + "External id": 31542,"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": 4183437, "tid": 4183437, + "ts": 658971911251.148, "dur": 8.537, + "args": { + "External id": 31543,"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": 4183437, "tid": 4183437, + "ts": 658971911258.175, "dur": 1.347, + "args": { + "External id": 31544,"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": 4183437, "tid": 4183437, + "ts": 658971911261.000, "dur": 66.436, + "args": { + "External id": 31545,"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": 4183437, "tid": 4183437, + "ts": 658971911277.365, "dur": 49.274, + "args": { + "External id": 31546,"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": 4183437, "tid": 4183437, + "ts": 658971911333.231, "dur": 5.125, + "args": { + "External id": 31547,"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": 4183437, "tid": 4183437, + "ts": 658971911335.571, "dur": 1.375, + "args": { + "External id": 31548,"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": 4183437, "tid": 4183437, + "ts": 658971911345.439, "dur": 2.040, + "args": { + "External id": 31549,"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": 4183437, "tid": 4183437, + "ts": 658971911356.111, "dur": 8.435, + "args": { + "External id": 31550,"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": 4183437, "tid": 4183437, + "ts": 658971911358.348, "dur": 5.888, + "args": { + "External id": 31551,"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": 4183437, "tid": 4183437, + "ts": 658971911467.897, "dur": 291.398, + "args": { + "External id": 31552,"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": 4183437, "tid": 4183437, + "ts": 658971911470.204, "dur": 1.978, + "args": { + "External id": 31553,"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": 4183437, "tid": 4183437, + "ts": 658971911473.722, "dur": 284.879, + "args": { + "External id": 31554,"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": 4183437, "tid": 4183437, + "ts": 658971911476.156, "dur": 0.477, + "args": { + "External id": 31555,"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": 4183437, "tid": 4183437, + "ts": 658971911478.070, "dur": 32.100, + "args": { + "External id": 31556,"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": 4183437, "tid": 4183437, + "ts": 658971911512.179, "dur": 3.414, + "args": { + "External id": 31557,"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": 4183437, "tid": 4183437, + "ts": 658971911514.475, "dur": 0.858, + "args": { + "External id": 31558,"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": 4183437, "tid": 4183437, + "ts": 658971911516.907, "dur": 32.249, + "args": { + "External id": 31559,"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": 4183437, "tid": 4183437, + "ts": 658971911518.027, "dur": 1.540, + "args": { + "External id": 31560,"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": 4183437, "tid": 4183437, + "ts": 658971911520.996, "dur": 27.757, + "args": { + "External id": 31561,"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": 4183437, "tid": 4183437, + "ts": 658971911526.838, "dur": 3.182, + "args": { + "External id": 31562,"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": 4183437, "tid": 4183437, + "ts": 658971911551.019, "dur": 41.862, + "args": { + "External id": 31563,"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": 4183437, "tid": 4183437, + "ts": 658971911594.484, "dur": 39.660, + "args": { + "External id": 31564,"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": 4183437, "tid": 4183437, + "ts": 658971911637.269, "dur": 50.378, + "args": { + "External id": 31565,"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": 4183437, "tid": 4183437, + "ts": 658971911690.458, "dur": 15.297, + "args": { + "External id": 31566,"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": 4183437, "tid": 4183437, + "ts": 658971911708.595, "dur": 22.066, + "args": { + "External id": 31567,"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": 4183437, "tid": 4183437, + "ts": 658971911710.814, "dur": 2.209, + "args": { + "External id": 31568,"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": 4183437, "tid": 4183437, + "ts": 658971911715.422, "dur": 0.931, + "args": { + "External id": 31569,"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": 4183437, "tid": 4183437, + "ts": 658971911732.406, "dur": 11.772, + "args": { + "External id": 31570,"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": 4183437, "tid": 4183437, + "ts": 658971911745.824, "dur": 11.797, + "args": { + "External id": 31571,"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": 4183437, "tid": 4183437, + "ts": 658971911767.499, "dur": 2.557, + "args": { + "External id": 31572,"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": 4183437, "tid": 4183437, + "ts": 658971911780.235, "dur": 3.784, + "args": { + "External id": 31573,"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": 4183437, "tid": 4183437, + "ts": 658971911782.426, "dur": 0.770, + "args": { + "External id": 31574,"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": 4183437, "tid": 4183437, + "ts": 658971911861.150, "dur": 49.044, + "args": { + "External id": 31575,"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": 4183437, "tid": 4183437, + "ts": 658971911914.988, "dur": 5.339, + "args": { + "External id": 31576,"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": 4183437, "tid": 4183437, + "ts": 658971911917.959, "dur": 1.311, + "args": { + "External id": 31577,"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": 4183437, "tid": 4183437, + "ts": 658971911922.040, "dur": 24.031, + "args": { + "External id": 31578,"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": 4183437, "tid": 4183437, + "ts": 658971911950.991, "dur": 12.252, + "args": { + "External id": 31579,"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": 4183437, "tid": 4183437, + "ts": 658971911958.244, "dur": 4.235, + "args": { + "External id": 31580,"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": 4183437, "tid": 4183437, + "ts": 658971911961.255, "dur": 1.015, + "args": { + "External id": 31581,"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": 4183437, "tid": 4183437, + "ts": 658971911966.182, "dur": 43.422, + "args": { + "External id": 31582,"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": 4183437, "tid": 4183437, + "ts": 658971911967.594, "dur": 41.377, + "args": { + "External id": 31583,"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": 4183437, "tid": 4183437, + "ts": 658971912013.758, "dur": 14.090, + "args": { + "External id": 31584,"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": 4183437, "tid": 4183437, + "ts": 658971912033.318, "dur": 3.740, + "args": { + "External id": 31585,"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": 4183437, "tid": 4183437, + "ts": 658971912035.524, "dur": 0.730, + "args": { + "External id": 31586,"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": 4183437, "tid": 4183437, + "ts": 658971912041.105, "dur": 50.631, + "args": { + "External id": 31587,"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": 4183437, "tid": 4183437, + "ts": 658971912041.986, "dur": 6.652, + "args": { + "External id": 31588,"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": 4183437, "tid": 4183437, + "ts": 658971912043.063, "dur": 4.865, + "args": { + "External id": 31589,"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": 4183437, "tid": 4183437, + "ts": 658971912044.461, "dur": 3.235, + "args": { + "External id": 31590,"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": 4183437, "tid": 4183437, + "ts": 658971912049.304, "dur": 41.803, + "args": { + "External id": 31591,"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": 4183437, "tid": 4183437, + "ts": 658971912050.304, "dur": 40.257, + "args": { + "External id": 31592,"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": 4183437, "tid": 4183437, + "ts": 658971912096.012, "dur": 3.891, + "args": { + "External id": 31593,"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": 4183437, "tid": 4183437, + "ts": 658971912097.747, "dur": 0.885, + "args": { + "External id": 31594,"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": 4183437, "tid": 4183437, + "ts": 658971912105.333, "dur": 1.640, + "args": { + "External id": 31595,"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": 4183437, "tid": 4183437, + "ts": 658971912114.705, "dur": 5.924, + "args": { + "External id": 31596,"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": 4183437, "tid": 4183437, + "ts": 658971912116.823, "dur": 3.532, + "args": { + "External id": 31597,"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": 4183437, "tid": 4183437, + "ts": 658971912206.923, "dur": 198.785, + "args": { + "External id": 31598,"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": 4183437, "tid": 4183437, + "ts": 658971912209.738, "dur": 2.146, + "args": { + "External id": 31599,"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": 4183437, "tid": 4183437, + "ts": 658971912213.160, "dur": 192.066, + "args": { + "External id": 31600,"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": 4183437, "tid": 4183437, + "ts": 658971912214.896, "dur": 0.491, + "args": { + "External id": 31601,"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": 4183437, "tid": 4183437, + "ts": 658971912218.996, "dur": 19.603, + "args": { + "External id": 31602,"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": 4183437, "tid": 4183437, + "ts": 658971912240.131, "dur": 3.619, + "args": { + "External id": 31603,"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": 4183437, "tid": 4183437, + "ts": 658971912242.476, "dur": 1.010, + "args": { + "External id": 31604,"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": 4183437, "tid": 4183437, + "ts": 658971912244.696, "dur": 40.880, + "args": { + "External id": 31605,"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": 4183437, "tid": 4183437, + "ts": 658971912245.798, "dur": 3.553, + "args": { + "External id": 31606,"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": 4183437, "tid": 4183437, + "ts": 658971912250.593, "dur": 34.407, + "args": { + "External id": 31607,"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": 4183437, "tid": 4183437, + "ts": 658971912253.333, "dur": 2.184, + "args": { + "External id": 31608,"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": 4183437, "tid": 4183437, + "ts": 658971912287.772, "dur": 21.886, + "args": { + "External id": 31609,"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": 4183437, "tid": 4183437, + "ts": 658971912311.403, "dur": 12.738, + "args": { + "External id": 31610,"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": 4183437, "tid": 4183437, + "ts": 658971912326.942, "dur": 12.803, + "args": { + "External id": 31611,"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": 4183437, "tid": 4183437, + "ts": 658971912341.369, "dur": 11.755, + "args": { + "External id": 31612,"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": 4183437, "tid": 4183437, + "ts": 658971912355.406, "dur": 21.768, + "args": { + "External id": 31613,"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": 4183437, "tid": 4183437, + "ts": 658971912357.420, "dur": 1.171, + "args": { + "External id": 31614,"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": 4183437, "tid": 4183437, + "ts": 658971912360.789, "dur": 1.262, + "args": { + "External id": 31615,"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": 4183437, "tid": 4183437, + "ts": 658971912378.989, "dur": 12.019, + "args": { + "External id": 31616,"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": 4183437, "tid": 4183437, + "ts": 658971912392.277, "dur": 11.685, + "args": { + "External id": 31617,"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": 4183437, "tid": 4183437, + "ts": 658971912413.124, "dur": 2.259, + "args": { + "External id": 31618,"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": 4183437, "tid": 4183437, + "ts": 658971912424.689, "dur": 3.548, + "args": { + "External id": 31619,"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": 4183437, "tid": 4183437, + "ts": 658971912426.788, "dur": 0.557, + "args": { + "External id": 31620,"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": 4183437, "tid": 4183437, + "ts": 658971912500.879, "dur": 47.697, + "args": { + "External id": 31621,"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": 4183437, "tid": 4183437, + "ts": 658971912553.255, "dur": 5.053, + "args": { + "External id": 31622,"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": 4183437, "tid": 4183437, + "ts": 658971912555.825, "dur": 1.275, + "args": { + "External id": 31623,"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": 4183437, "tid": 4183437, + "ts": 658971912559.788, "dur": 24.993, + "args": { + "External id": 31624,"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": 4183437, "tid": 4183437, + "ts": 658971912589.595, "dur": 6.858, + "args": { + "External id": 31625,"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": 4183437, "tid": 4183437, + "ts": 658971912591.378, "dur": 4.444, + "args": { + "External id": 31626,"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": 4183437, "tid": 4183437, + "ts": 658971912593.031, "dur": 2.540, + "args": { + "External id": 31627,"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": 4183437, "tid": 4183437, + "ts": 658971912599.145, "dur": 42.939, + "args": { + "External id": 31628,"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": 4183437, "tid": 4183437, + "ts": 658971912600.302, "dur": 41.109, + "args": { + "External id": 31629,"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": 4183437, "tid": 4183437, + "ts": 658971912645.844, "dur": 52.731, + "args": { + "External id": 31630,"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": 4183437, "tid": 4183437, + "ts": 658971912706.980, "dur": 5.275, + "args": { + "External id": 31631,"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": 4183437, "tid": 4183437, + "ts": 658971912709.967, "dur": 1.095, + "args": { + "External id": 31632,"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": 4183437, "tid": 4183437, + "ts": 658971912717.089, "dur": 54.639, + "args": { + "External id": 31633,"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": 4183437, "tid": 4183437, + "ts": 658971912717.866, "dur": 4.058, + "args": { + "External id": 31634,"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": 4183437, "tid": 4183437, + "ts": 658971912719.048, "dur": 2.281, + "args": { + "External id": 31635,"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": 4183437, "tid": 4183437, + "ts": 658971912720.357, "dur": 0.792, + "args": { + "External id": 31636,"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": 4183437, "tid": 4183437, + "ts": 658971912722.660, "dur": 48.600, + "args": { + "External id": 31637,"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": 4183437, "tid": 4183437, + "ts": 658971912723.571, "dur": 47.171, + "args": { + "External id": 31638,"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": 4183437, "tid": 4183437, + "ts": 658971912775.787, "dur": 3.766, + "args": { + "External id": 31639,"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": 4183437, "tid": 4183437, + "ts": 658971912777.824, "dur": 0.608, + "args": { + "External id": 31640,"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": 4183437, "tid": 4183437, + "ts": 658971912786.000, "dur": 1.980, + "args": { + "External id": 31641,"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": 4183437, "tid": 4183437, + "ts": 658971912796.625, "dur": 7.181, + "args": { + "External id": 31642,"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": 4183437, "tid": 4183437, + "ts": 658971912798.734, "dur": 4.803, + "args": { + "External id": 31643,"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": 4183437, "tid": 4183437, + "ts": 658971912895.590, "dur": 181.705, + "args": { + "External id": 31644,"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": 4183437, "tid": 4183437, + "ts": 658971912897.544, "dur": 2.579, + "args": { + "External id": 31645,"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": 4183437, "tid": 4183437, + "ts": 658971912904.306, "dur": 172.435, + "args": { + "External id": 31646,"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": 4183437, "tid": 4183437, + "ts": 658971912905.582, "dur": 0.447, + "args": { + "External id": 31647,"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": 4183437, "tid": 4183437, + "ts": 658971912907.521, "dur": 21.713, + "args": { + "External id": 31648,"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": 4183437, "tid": 4183437, + "ts": 658971912930.714, "dur": 5.941, + "args": { + "External id": 31649,"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": 4183437, "tid": 4183437, + "ts": 658971912933.216, "dur": 3.111, + "args": { + "External id": 31650,"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": 4183437, "tid": 4183437, + "ts": 658971912937.650, "dur": 19.928, + "args": { + "External id": 31651,"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": 4183437, "tid": 4183437, + "ts": 658971912938.627, "dur": 1.545, + "args": { + "External id": 31652,"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": 4183437, "tid": 4183437, + "ts": 658971912941.223, "dur": 16.075, + "args": { + "External id": 31653,"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": 4183437, "tid": 4183437, + "ts": 658971912943.824, "dur": 2.417, + "args": { + "External id": 31654,"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": 4183437, "tid": 4183437, + "ts": 658971912959.105, "dur": 19.316, + "args": { + "External id": 31655,"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": 4183437, "tid": 4183437, + "ts": 658971912979.856, "dur": 13.222, + "args": { + "External id": 31656,"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": 4183437, "tid": 4183437, + "ts": 658971912996.111, "dur": 12.967, + "args": { + "External id": 31657,"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": 4183437, "tid": 4183437, + "ts": 658971913010.758, "dur": 14.118, + "args": { + "External id": 31658,"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": 4183437, "tid": 4183437, + "ts": 658971913026.834, "dur": 22.108, + "args": { + "External id": 31659,"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": 4183437, "tid": 4183437, + "ts": 658971913028.958, "dur": 1.539, + "args": { + "External id": 31660,"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": 4183437, "tid": 4183437, + "ts": 658971913032.340, "dur": 2.690, + "args": { + "External id": 31661,"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": 4183437, "tid": 4183437, + "ts": 658971913051.034, "dur": 12.704, + "args": { + "External id": 31662,"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": 4183437, "tid": 4183437, + "ts": 658971913064.872, "dur": 10.979, + "args": { + "External id": 31663,"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": 4183437, "tid": 4183437, + "ts": 658971913083.441, "dur": 1.737, + "args": { + "External id": 31664,"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": 4183437, "tid": 4183437, + "ts": 658971913093.540, "dur": 3.149, + "args": { + "External id": 31665,"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": 4183437, "tid": 4183437, + "ts": 658971913095.450, "dur": 0.453, + "args": { + "External id": 31666,"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": 4183437, "tid": 4183437, + "ts": 658971913163.151, "dur": 42.863, + "args": { + "External id": 31667,"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": 4183437, "tid": 4183437, + "ts": 658971913210.234, "dur": 4.284, + "args": { + "External id": 31668,"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": 4183437, "tid": 4183437, + "ts": 658971913212.813, "dur": 0.748, + "args": { + "External id": 31669,"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": 4183437, "tid": 4183437, + "ts": 658971913215.972, "dur": 25.336, + "args": { + "External id": 31670,"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": 4183437, "tid": 4183437, + "ts": 658971913245.549, "dur": 4.978, + "args": { + "External id": 31671,"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": 4183437, "tid": 4183437, + "ts": 658971913246.787, "dur": 3.082, + "args": { + "External id": 31672,"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": 4183437, "tid": 4183437, + "ts": 658971913248.427, "dur": 1.250, + "args": { + "External id": 31673,"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": 4183437, "tid": 4183437, + "ts": 658971913252.811, "dur": 65.695, + "args": { + "External id": 31674,"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": 4183437, "tid": 4183437, + "ts": 658971913253.987, "dur": 63.376, + "args": { + "External id": 31675,"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": 4183437, "tid": 4183437, + "ts": 658971913323.798, "dur": 17.488, + "args": { + "External id": 31676,"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": 4183437, "tid": 4183437, + "ts": 658971913347.795, "dur": 4.431, + "args": { + "External id": 31677,"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": 4183437, "tid": 4183437, + "ts": 658971913350.255, "dur": 0.903, + "args": { + "External id": 31678,"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": 4183437, "tid": 4183437, + "ts": 658971913356.424, "dur": 48.425, + "args": { + "External id": 31679,"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": 4183437, "tid": 4183437, + "ts": 658971913357.269, "dur": 4.276, + "args": { + "External id": 31680,"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": 4183437, "tid": 4183437, + "ts": 658971913358.380, "dur": 2.612, + "args": { + "External id": 31681,"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": 4183437, "tid": 4183437, + "ts": 658971913360.104, "dur": 0.748, + "args": { + "External id": 31682,"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": 4183437, "tid": 4183437, + "ts": 658971913362.131, "dur": 42.228, + "args": { + "External id": 31683,"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": 4183437, "tid": 4183437, + "ts": 658971913363.113, "dur": 40.755, + "args": { + "External id": 31684,"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": 4183437, "tid": 4183437, + "ts": 658971913408.782, "dur": 3.460, + "args": { + "External id": 31685,"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": 4183437, "tid": 4183437, + "ts": 658971913410.460, "dur": 0.688, + "args": { + "External id": 31686,"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": 4183437, "tid": 4183437, + "ts": 658971913419.655, "dur": 1.818, + "args": { + "External id": 31687,"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": 4183437, "tid": 4183437, + "ts": 658971913429.949, "dur": 6.101, + "args": { + "External id": 31688,"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": 4183437, "tid": 4183437, + "ts": 658971913431.850, "dur": 3.934, + "args": { + "External id": 31689,"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": 4183437, "tid": 4183437, + "ts": 658971913521.701, "dur": 228.777, + "args": { + "External id": 31690,"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": 4183437, "tid": 4183437, + "ts": 658971913525.831, "dur": 2.338, + "args": { + "External id": 31691,"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": 4183437, "tid": 4183437, + "ts": 658971913529.580, "dur": 220.193, + "args": { + "External id": 31692,"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": 4183437, "tid": 4183437, + "ts": 658971913531.114, "dur": 0.512, + "args": { + "External id": 31693,"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": 4183437, "tid": 4183437, + "ts": 658971913532.902, "dur": 21.489, + "args": { + "External id": 31694,"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": 4183437, "tid": 4183437, + "ts": 658971913555.831, "dur": 5.275, + "args": { + "External id": 31695,"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": 4183437, "tid": 4183437, + "ts": 658971913559.874, "dur": 0.931, + "args": { + "External id": 31696,"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": 4183437, "tid": 4183437, + "ts": 658971913561.947, "dur": 20.534, + "args": { + "External id": 31697,"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": 4183437, "tid": 4183437, + "ts": 658971913562.868, "dur": 1.616, + "args": { + "External id": 31698,"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": 4183437, "tid": 4183437, + "ts": 658971913565.540, "dur": 16.574, + "args": { + "External id": 31699,"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": 4183437, "tid": 4183437, + "ts": 658971913568.013, "dur": 2.360, + "args": { + "External id": 31700,"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": 4183437, "tid": 4183437, + "ts": 658971913583.843, "dur": 19.978, + "args": { + "External id": 31701,"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": 4183437, "tid": 4183437, + "ts": 658971913605.340, "dur": 16.321, + "args": { + "External id": 31702,"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": 4183437, "tid": 4183437, + "ts": 658971913624.457, "dur": 15.434, + "args": { + "External id": 31703,"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": 4183437, "tid": 4183437, + "ts": 658971913641.326, "dur": 52.260, + "args": { + "External id": 31704,"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": 4183437, "tid": 4183437, + "ts": 658971913696.976, "dur": 23.760, + "args": { + "External id": 31705,"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": 4183437, "tid": 4183437, + "ts": 658971913699.110, "dur": 1.884, + "args": { + "External id": 31706,"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": 4183437, "tid": 4183437, + "ts": 658971913703.508, "dur": 0.886, + "args": { + "External id": 31707,"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": 4183437, "tid": 4183437, + "ts": 658971913722.341, "dur": 13.295, + "args": { + "External id": 31708,"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": 4183437, "tid": 4183437, + "ts": 658971913736.705, "dur": 11.689, + "args": { + "External id": 31709,"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": 4183437, "tid": 4183437, + "ts": 658971913757.788, "dur": 2.213, + "args": { + "External id": 31710,"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": 4183437, "tid": 4183437, + "ts": 658971913779.080, "dur": 4.011, + "args": { + "External id": 31711,"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": 4183437, "tid": 4183437, + "ts": 658971913781.517, "dur": 0.598, + "args": { + "External id": 31712,"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": 4183437, "tid": 4183437, + "ts": 658971913852.355, "dur": 46.399, + "args": { + "External id": 31713,"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": 4183437, "tid": 4183437, + "ts": 658971913903.293, "dur": 4.395, + "args": { + "External id": 31714,"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": 4183437, "tid": 4183437, + "ts": 658971913905.940, "dur": 0.669, + "args": { + "External id": 31715,"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": 4183437, "tid": 4183437, + "ts": 658971913909.257, "dur": 23.416, + "args": { + "External id": 31716,"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": 4183437, "tid": 4183437, + "ts": 658971913937.156, "dur": 8.013, + "args": { + "External id": 31717,"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": 4183437, "tid": 4183437, + "ts": 658971913938.973, "dur": 5.572, + "args": { + "External id": 31718,"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": 4183437, "tid": 4183437, + "ts": 658971913940.962, "dur": 3.376, + "args": { + "External id": 31719,"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": 4183437, "tid": 4183437, + "ts": 658971913948.054, "dur": 43.360, + "args": { + "External id": 31720,"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": 4183437, "tid": 4183437, + "ts": 658971913949.255, "dur": 41.698, + "args": { + "External id": 31721,"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": 4183437, "tid": 4183437, + "ts": 658971913995.217, "dur": 13.350, + "args": { + "External id": 31722,"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": 4183437, "tid": 4183437, + "ts": 658971914013.788, "dur": 3.642, + "args": { + "External id": 31723,"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": 4183437, "tid": 4183437, + "ts": 658971914015.712, "dur": 0.988, + "args": { + "External id": 31724,"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": 4183437, "tid": 4183437, + "ts": 658971914021.417, "dur": 47.089, + "args": { + "External id": 31725,"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": 4183437, "tid": 4183437, + "ts": 658971914022.511, "dur": 3.742, + "args": { + "External id": 31726,"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": 4183437, "tid": 4183437, + "ts": 658971914023.353, "dur": 2.269, + "args": { + "External id": 31727,"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": 4183437, "tid": 4183437, + "ts": 658971914024.647, "dur": 0.754, + "args": { + "External id": 31728,"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": 4183437, "tid": 4183437, + "ts": 658971914026.812, "dur": 41.243, + "args": { + "External id": 31729,"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": 4183437, "tid": 4183437, + "ts": 658971914027.498, "dur": 40.033, + "args": { + "External id": 31730,"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": 4183437, "tid": 4183437, + "ts": 658971914072.112, "dur": 3.916, + "args": { + "External id": 31731,"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": 4183437, "tid": 4183437, + "ts": 658971914073.952, "dur": 1.071, + "args": { + "External id": 31732,"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": 4183437, "tid": 4183437, + "ts": 658971914081.266, "dur": 1.481, + "args": { + "External id": 31733,"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": 4183437, "tid": 4183437, + "ts": 658971914090.426, "dur": 5.927, + "args": { + "External id": 31734,"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": 4183437, "tid": 4183437, + "ts": 658971914092.412, "dur": 3.649, + "args": { + "External id": 31735,"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": 4183437, "tid": 4183437, + "ts": 658971914177.726, "dur": 295.917, + "args": { + "External id": 31736,"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": 4183437, "tid": 4183437, + "ts": 658971914179.858, "dur": 2.246, + "args": { + "External id": 31737,"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": 4183437, "tid": 4183437, + "ts": 658971914185.940, "dur": 287.171, + "args": { + "External id": 31738,"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": 4183437, "tid": 4183437, + "ts": 658971914187.375, "dur": 0.393, + "args": { + "External id": 31739,"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": 4183437, "tid": 4183437, + "ts": 658971914189.184, "dur": 18.866, + "args": { + "External id": 31740,"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": 4183437, "tid": 4183437, + "ts": 658971914209.381, "dur": 4.419, + "args": { + "External id": 31741,"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": 4183437, "tid": 4183437, + "ts": 658971914211.112, "dur": 2.387, + "args": { + "External id": 31742,"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": 4183437, "tid": 4183437, + "ts": 658971914214.606, "dur": 40.203, + "args": { + "External id": 31743,"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": 4183437, "tid": 4183437, + "ts": 658971914215.465, "dur": 1.259, + "args": { + "External id": 31744,"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": 4183437, "tid": 4183437, + "ts": 658971914236.566, "dur": 17.947, + "args": { + "External id": 31745,"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": 4183437, "tid": 4183437, + "ts": 658971914239.608, "dur": 2.352, + "args": { + "External id": 31746,"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": 4183437, "tid": 4183437, + "ts": 658971914256.264, "dur": 41.877, + "args": { + "External id": 31747,"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": 4183437, "tid": 4183437, + "ts": 658971914300.211, "dur": 38.822, + "args": { + "External id": 31748,"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": 4183437, "tid": 4183437, + "ts": 658971914342.160, "dur": 40.603, + "args": { + "External id": 31749,"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": 4183437, "tid": 4183437, + "ts": 658971914384.144, "dur": 29.697, + "args": { + "External id": 31750,"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": 4183437, "tid": 4183437, + "ts": 658971914416.207, "dur": 26.133, + "args": { + "External id": 31751,"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": 4183437, "tid": 4183437, + "ts": 658971914418.071, "dur": 1.529, + "args": { + "External id": 31752,"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": 4183437, "tid": 4183437, + "ts": 658971914421.446, "dur": 0.723, + "args": { + "External id": 31753,"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": 4183437, "tid": 4183437, + "ts": 658971914444.191, "dur": 14.724, + "args": { + "External id": 31754,"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": 4183437, "tid": 4183437, + "ts": 658971914459.947, "dur": 12.168, + "args": { + "External id": 31755,"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": 4183437, "tid": 4183437, + "ts": 658971914481.214, "dur": 2.226, + "args": { + "External id": 31756,"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": 4183437, "tid": 4183437, + "ts": 658971914492.393, "dur": 3.420, + "args": { + "External id": 31757,"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": 4183437, "tid": 4183437, + "ts": 658971914494.666, "dur": 0.365, + "args": { + "External id": 31758,"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": 4183437, "tid": 4183437, + "ts": 658971914566.246, "dur": 46.583, + "args": { + "External id": 31759,"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": 4183437, "tid": 4183437, + "ts": 658971914617.331, "dur": 4.597, + "args": { + "External id": 31760,"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": 4183437, "tid": 4183437, + "ts": 658971914619.797, "dur": 1.018, + "args": { + "External id": 31761,"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": 4183437, "tid": 4183437, + "ts": 658971914623.548, "dur": 23.926, + "args": { + "External id": 31762,"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": 4183437, "tid": 4183437, + "ts": 658971914686.733, "dur": 7.329, + "args": { + "External id": 31763,"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": 4183437, "tid": 4183437, + "ts": 658971914688.617, "dur": 4.475, + "args": { + "External id": 31764,"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": 4183437, "tid": 4183437, + "ts": 658971914690.963, "dur": 1.719, + "args": { + "External id": 31765,"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": 4183437, "tid": 4183437, + "ts": 658971914697.642, "dur": 50.132, + "args": { + "External id": 31766,"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": 4183437, "tid": 4183437, + "ts": 658971914698.709, "dur": 48.293, + "args": { + "External id": 31767,"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": 4183437, "tid": 4183437, + "ts": 658971914751.611, "dur": 17.452, + "args": { + "External id": 31768,"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": 4183437, "tid": 4183437, + "ts": 658971914775.300, "dur": 4.292, + "args": { + "External id": 31769,"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": 4183437, "tid": 4183437, + "ts": 658971914777.793, "dur": 0.982, + "args": { + "External id": 31770,"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": 4183437, "tid": 4183437, + "ts": 658971914783.544, "dur": 46.304, + "args": { + "External id": 31771,"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": 4183437, "tid": 4183437, + "ts": 658971914784.632, "dur": 3.943, + "args": { + "External id": 31772,"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": 4183437, "tid": 4183437, + "ts": 658971914785.394, "dur": 2.596, + "args": { + "External id": 31773,"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": 4183437, "tid": 4183437, + "ts": 658971914787.047, "dur": 0.810, + "args": { + "External id": 31774,"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": 4183437, "tid": 4183437, + "ts": 658971914789.194, "dur": 40.241, + "args": { + "External id": 31775,"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": 4183437, "tid": 4183437, + "ts": 658971914789.787, "dur": 39.183, + "args": { + "External id": 31776,"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": 4183437, "tid": 4183437, + "ts": 658971914833.915, "dur": 3.896, + "args": { + "External id": 31777,"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": 4183437, "tid": 4183437, + "ts": 658971914835.604, "dur": 1.208, + "args": { + "External id": 31778,"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": 4183437, "tid": 4183437, + "ts": 658971914843.647, "dur": 1.766, + "args": { + "External id": 31779,"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": 4183437, "tid": 4183437, + "ts": 658971914853.236, "dur": 8.357, + "args": { + "External id": 31780,"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": 4183437, "tid": 4183437, + "ts": 658971914855.512, "dur": 5.772, + "args": { + "External id": 31781,"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": 4183437, "tid": 4183437, + "ts": 658971914945.887, "dur": 188.450, + "args": { + "External id": 31782,"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": 4183437, "tid": 4183437, + "ts": 658971914947.962, "dur": 1.879, + "args": { + "External id": 31783,"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": 4183437, "tid": 4183437, + "ts": 658971914951.171, "dur": 182.639, + "args": { + "External id": 31784,"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": 4183437, "tid": 4183437, + "ts": 658971914953.022, "dur": 0.385, + "args": { + "External id": 31785,"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": 4183437, "tid": 4183437, + "ts": 658971914954.827, "dur": 24.352, + "args": { + "External id": 31786,"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": 4183437, "tid": 4183437, + "ts": 658971914980.557, "dur": 3.191, + "args": { + "External id": 31787,"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": 4183437, "tid": 4183437, + "ts": 658971914982.659, "dur": 0.784, + "args": { + "External id": 31788,"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": 4183437, "tid": 4183437, + "ts": 658971914984.617, "dur": 23.753, + "args": { + "External id": 31789,"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": 4183437, "tid": 4183437, + "ts": 658971914985.680, "dur": 1.625, + "args": { + "External id": 31790,"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": 4183437, "tid": 4183437, + "ts": 658971914988.571, "dur": 19.413, + "args": { + "External id": 31791,"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": 4183437, "tid": 4183437, + "ts": 658971914993.041, "dur": 2.029, + "args": { + "External id": 31792,"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": 4183437, "tid": 4183437, + "ts": 658971915010.013, "dur": 20.313, + "args": { + "External id": 31793,"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": 4183437, "tid": 4183437, + "ts": 658971915031.803, "dur": 12.793, + "args": { + "External id": 31794,"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": 4183437, "tid": 4183437, + "ts": 658971915052.438, "dur": 14.246, + "args": { + "External id": 31795,"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": 4183437, "tid": 4183437, + "ts": 658971915068.316, "dur": 13.809, + "args": { + "External id": 31796,"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": 4183437, "tid": 4183437, + "ts": 658971915083.876, "dur": 19.002, + "args": { + "External id": 31797,"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": 4183437, "tid": 4183437, + "ts": 658971915085.495, "dur": 1.051, + "args": { + "External id": 31798,"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": 4183437, "tid": 4183437, + "ts": 658971915088.282, "dur": 0.661, + "args": { + "External id": 31799,"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": 4183437, "tid": 4183437, + "ts": 658971915104.331, "dur": 12.803, + "args": { + "External id": 31800,"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": 4183437, "tid": 4183437, + "ts": 658971915118.194, "dur": 14.488, + "args": { + "External id": 31801,"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": 4183437, "tid": 4183437, + "ts": 658971915139.982, "dur": 1.850, + "args": { + "External id": 31802,"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": 4183437, "tid": 4183437, + "ts": 658971915150.047, "dur": 3.141, + "args": { + "External id": 31803,"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": 4183437, "tid": 4183437, + "ts": 658971915151.919, "dur": 0.575, + "args": { + "External id": 31804,"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": 4183437, "tid": 4183437, + "ts": 658971915216.335, "dur": 41.691, + "args": { + "External id": 31805,"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": 4183437, "tid": 4183437, + "ts": 658971915280.673, "dur": 7.608, + "args": { + "External id": 31806,"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": 4183437, "tid": 4183437, + "ts": 658971915283.782, "dur": 2.693, + "args": { + "External id": 31807,"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": 4183437, "tid": 4183437, + "ts": 658971915289.931, "dur": 26.774, + "args": { + "External id": 31808,"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": 4183437, "tid": 4183437, + "ts": 658971915321.996, "dur": 5.725, + "args": { + "External id": 31809,"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": 4183437, "tid": 4183437, + "ts": 658971915323.845, "dur": 3.246, + "args": { + "External id": 31810,"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": 4183437, "tid": 4183437, + "ts": 658971915325.740, "dur": 1.017, + "args": { + "External id": 31811,"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": 4183437, "tid": 4183437, + "ts": 658971915330.904, "dur": 44.769, + "args": { + "External id": 31812,"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": 4183437, "tid": 4183437, + "ts": 658971915331.948, "dur": 43.021, + "args": { + "External id": 31813,"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": 4183437, "tid": 4183437, + "ts": 658971915379.519, "dur": 15.194, + "args": { + "External id": 31814,"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": 4183437, "tid": 4183437, + "ts": 658971915400.676, "dur": 3.230, + "args": { + "External id": 31815,"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": 4183437, "tid": 4183437, + "ts": 658971915402.309, "dur": 0.760, + "args": { + "External id": 31816,"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": 4183437, "tid": 4183437, + "ts": 658971915408.367, "dur": 47.566, + "args": { + "External id": 31817,"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": 4183437, "tid": 4183437, + "ts": 658971915409.052, "dur": 4.154, + "args": { + "External id": 31818,"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": 4183437, "tid": 4183437, + "ts": 658971915409.986, "dur": 2.640, + "args": { + "External id": 31819,"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": 4183437, "tid": 4183437, + "ts": 658971915411.434, "dur": 0.850, + "args": { + "External id": 31820,"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": 4183437, "tid": 4183437, + "ts": 658971915413.890, "dur": 41.575, + "args": { + "External id": 31821,"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": 4183437, "tid": 4183437, + "ts": 658971915414.872, "dur": 40.124, + "args": { + "External id": 31822,"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": 4183437, "tid": 4183437, + "ts": 658971915459.390, "dur": 4.138, + "args": { + "External id": 31823,"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": 4183437, "tid": 4183437, + "ts": 658971915461.494, "dur": 0.781, + "args": { + "External id": 31824,"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": 4183437, "tid": 4183437, + "ts": 658971915469.036, "dur": 1.594, + "args": { + "External id": 31825,"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": 4183437, "tid": 4183437, + "ts": 658971915477.890, "dur": 6.627, + "args": { + "External id": 31826,"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": 4183437, "tid": 4183437, + "ts": 658971915479.935, "dur": 4.299, + "args": { + "External id": 31827,"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": 4183437, "tid": 4183437, + "ts": 658971915567.693, "dur": 211.033, + "args": { + "External id": 31828,"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": 4183437, "tid": 4183437, + "ts": 658971915569.695, "dur": 3.759, + "args": { + "External id": 31829,"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": 4183437, "tid": 4183437, + "ts": 658971915574.770, "dur": 203.357, + "args": { + "External id": 31830,"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": 4183437, "tid": 4183437, + "ts": 658971915576.052, "dur": 0.479, + "args": { + "External id": 31831,"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": 4183437, "tid": 4183437, + "ts": 658971915577.837, "dur": 19.256, + "args": { + "External id": 31832,"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": 4183437, "tid": 4183437, + "ts": 658971915598.421, "dur": 5.762, + "args": { + "External id": 31833,"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": 4183437, "tid": 4183437, + "ts": 658971915602.360, "dur": 1.554, + "args": { + "External id": 31834,"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": 4183437, "tid": 4183437, + "ts": 658971915605.027, "dur": 20.110, + "args": { + "External id": 31835,"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": 4183437, "tid": 4183437, + "ts": 658971915605.935, "dur": 2.235, + "args": { + "External id": 31836,"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": 4183437, "tid": 4183437, + "ts": 658971915609.345, "dur": 15.473, + "args": { + "External id": 31837,"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": 4183437, "tid": 4183437, + "ts": 658971915611.600, "dur": 2.259, + "args": { + "External id": 31838,"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": 4183437, "tid": 4183437, + "ts": 658971915626.666, "dur": 18.051, + "args": { + "External id": 31839,"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": 4183437, "tid": 4183437, + "ts": 658971915645.933, "dur": 50.025, + "args": { + "External id": 31840,"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": 4183437, "tid": 4183437, + "ts": 658971915700.262, "dur": 14.519, + "args": { + "External id": 31841,"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": 4183437, "tid": 4183437, + "ts": 658971915716.307, "dur": 11.960, + "args": { + "External id": 31842,"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": 4183437, "tid": 4183437, + "ts": 658971915730.192, "dur": 21.949, + "args": { + "External id": 31843,"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": 4183437, "tid": 4183437, + "ts": 658971915734.625, "dur": 1.538, + "args": { + "External id": 31844,"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": 4183437, "tid": 4183437, + "ts": 658971915738.083, "dur": 0.864, + "args": { + "External id": 31845,"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": 4183437, "tid": 4183437, + "ts": 658971915753.992, "dur": 11.019, + "args": { + "External id": 31846,"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": 4183437, "tid": 4183437, + "ts": 658971915766.057, "dur": 10.970, + "args": { + "External id": 31847,"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": 4183437, "tid": 4183437, + "ts": 658971915786.033, "dur": 2.227, + "args": { + "External id": 31848,"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": 4183437, "tid": 4183437, + "ts": 658971915797.132, "dur": 3.589, + "args": { + "External id": 31849,"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": 4183437, "tid": 4183437, + "ts": 658971915799.279, "dur": 0.604, + "args": { + "External id": 31850,"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": 4183437, "tid": 4183437, + "ts": 658971915867.436, "dur": 46.038, + "args": { + "External id": 31851,"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": 4183437, "tid": 4183437, + "ts": 658971915917.952, "dur": 4.559, + "args": { + "External id": 31852,"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": 4183437, "tid": 4183437, + "ts": 658971915920.561, "dur": 0.955, + "args": { + "External id": 31853,"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": 4183437, "tid": 4183437, + "ts": 658971915923.812, "dur": 21.410, + "args": { + "External id": 31854,"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": 4183437, "tid": 4183437, + "ts": 658971915949.705, "dur": 5.362, + "args": { + "External id": 31855,"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": 4183437, "tid": 4183437, + "ts": 658971915951.554, "dur": 2.807, + "args": { + "External id": 31856,"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": 4183437, "tid": 4183437, + "ts": 658971915953.069, "dur": 1.117, + "args": { + "External id": 31857,"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": 4183437, "tid": 4183437, + "ts": 658971915957.919, "dur": 41.501, + "args": { + "External id": 31858,"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": 4183437, "tid": 4183437, + "ts": 658971915958.957, "dur": 39.879, + "args": { + "External id": 31859,"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": 4183437, "tid": 4183437, + "ts": 658971916002.896, "dur": 15.083, + "args": { + "External id": 31860,"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": 4183437, "tid": 4183437, + "ts": 658971916022.661, "dur": 22.671, + "args": { + "External id": 31861,"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": 4183437, "tid": 4183437, + "ts": 658971916025.275, "dur": 19.668, + "args": { + "External id": 31862,"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": 4183437, "tid": 4183437, + "ts": 658971916029.964, "dur": 0.778, + "args": { + "External id": 31863,"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": 4183437, "tid": 4183437, + "ts": 658971916050.592, "dur": 30.390, + "args": { + "External id": 31864,"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": 4183437, "tid": 4183437, + "ts": 658971916052.606, "dur": 28.120, + "args": { + "External id": 31865,"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": 4183437, "tid": 4183437, + "ts": 658971916057.441, "dur": 3.844, + "args": { + "External id": 31866,"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": 4183437, "tid": 4183437, + "ts": 658971916062.723, "dur": 17.355, + "args": { + "External id": 31867,"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": 4183437, "tid": 4183437, + "ts": 658971916096.138, "dur": 4.773, + "args": { + "External id": 31868,"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": 4183437, "tid": 4183437, + "ts": 658971916098.118, "dur": 2.631, + "args": { + "External id": 31869,"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": 4183437, "tid": 4183437, + "ts": 658971916102.285, "dur": 1.278, + "args": { + "External id": 31870,"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": 4183437, "tid": 4183437, + "ts": 658971916103.005, "dur": 0.482, + "args": { + "External id": 31871,"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": 4183437, "tid": 4183437, + "ts": 658971916141.136, "dur": 22.015, + "args": { + "External id": 31872,"Sequence number": 460077, "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": 4183437, "tid": 4183437, "ts": 658971916141.136, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183437, "tid": 4183437, + "ts": 658971916169.114, "dur": 5.480, + "args": { + "External id": 31873,"Sequence number": 460078, "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": 4183437, "tid": 4183437, + "ts": 658971916172.292, "dur": 1.092, + "args": { + "External id": 31874,"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": 4183437, "tid": 4183437, + "ts": 658971916177.258, "dur": 6.418, + "args": { + "External id": 31875,"Sequence number": 460078, "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": 4183437, "tid": 4183437, + "ts": 658971916181.343, "dur": 1.085, + "args": { + "External id": 31876,"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": 4183437, "tid": 4183437, + "ts": 658971916184.922, "dur": 2.756, + "args": { + "External id": 31877,"Sequence number": 460078, "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": 4183437, "tid": 4183437, + "ts": 658971916186.210, "dur": 0.885, + "args": { + "External id": 31878,"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": 4183437, "tid": 4183437, + "ts": 658971916191.367, "dur": 6.363, + "args": { + "External id": 31879,"Sequence number": 460078, "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": 4183437, "tid": 4183437, "ts": 658971916191.367, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971916194.932, "dur": 1.580, + "args": { + "External id": 31880,"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": 4183437, "tid": 4183437, + "ts": 658971916198.743, "dur": 4.677, + "args": { + "External id": 31881,"Sequence number": 460079, "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": 4183437, "tid": 4183437, "ts": 658971916198.743, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971916201.764, "dur": 0.905, + "args": { + "External id": 31882,"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": 4183437, "tid": 4183437, + "ts": 658971916204.387, "dur": 5.539, + "args": { + "External id": 31883,"Sequence number": 460080, "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": 4183437, "tid": 4183437, "ts": 658971916204.387, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971916207.810, "dur": 1.177, + "args": { + "External id": 31884,"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": 4183437, "tid": 4183437, + "ts": 658971916211.154, "dur": 4.553, + "args": { + "External id": 31885,"Sequence number": 460081, "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": 4183437, "tid": 4183437, "ts": 658971916211.154, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971916213.864, "dur": 1.101, + "args": { + "External id": 31886,"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": 4183437, "tid": 4183437, + "ts": 658971916219.583, "dur": 30.356, + "args": { + "External id": 31887,"Sequence number": 460082, "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": 4183437, "tid": 4183437, + "ts": 658971916221.280, "dur": 28.442, + "args": { + "External id": 31888,"Sequence number": 460082, "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": 4183437, "tid": 4183437, + "ts": 658971916223.881, "dur": 7.935, + "args": { + "External id": 31889,"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": 4183437, "tid": 4183437, + "ts": 658971916226.123, "dur": 5.087, + "args": { + "External id": 31890,"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": 4183437, "tid": 4183437, + "ts": 658971916232.920, "dur": 16.324, + "args": { + "External id": 31891,"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": 4183437, "tid": 4183437, + "ts": 658971916293.295, "dur": 5.654, + "args": { + "External id": 31892,"Sequence number": 460082, "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": 4183437, "tid": 4183437, "ts": 658971916293.295, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971916301.656, "dur": 1.248, + "args": { + "External id": 31893,"Sequence number": 460083, "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": 4183437, "tid": 4183437, + "ts": 658971916333.842, "dur": 22237.730, + "args": { + "External id": 31894,"Sequence number": 460083, "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": 4183437, "tid": 4183437, "ts": 658971916333.842, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183437, "tid": 4183437, + "ts": 658971916349.882, "dur": 29.093, + "args": { + "External id": 31895,"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": 4183437, "tid": 4183437, + "ts": 658971916350.642, "dur": 28.150, + "args": { + "External id": 31896,"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": 4183437, "tid": 4183437, + "ts": 658971916352.447, "dur": 6.325, + "args": { + "External id": 31897,"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": 4183437, "tid": 4183437, + "ts": 658971916354.321, "dur": 4.092, + "args": { + "External id": 31898,"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": 4183437, "tid": 4183437, + "ts": 658971916359.618, "dur": 18.798, + "args": { + "External id": 31899,"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": 4183437, "tid": 4183437, + "ts": 658971916394.246, "dur": 23.788, + "args": { + "External id": 31900,"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": 4183437, "tid": 4183437, + "ts": 658971916395.406, "dur": 5.885, + "args": { + "External id": 31901,"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": 4183437, "tid": 4183437, + "ts": 658971916397.328, "dur": 3.662, + "args": { + "External id": 31902,"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": 4183437, "tid": 4183437, + "ts": 658971916402.790, "dur": 15.009, + "args": { + "External id": 31903,"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": 4183437, "tid": 4183437, + "ts": 658971916404.599, "dur": 12.772, + "args": { + "External id": 31904,"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": 4183437, "tid": 4183437, + "ts": 658971916421.694, "dur": 20.532, + "args": { + "External id": 31905,"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": 4183437, "tid": 4183437, + "ts": 658971916422.655, "dur": 4.118, + "args": { + "External id": 31906,"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": 4183437, "tid": 4183437, + "ts": 658971916423.880, "dur": 2.620, + "args": { + "External id": 31907,"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": 4183437, "tid": 4183437, + "ts": 658971916427.337, "dur": 14.661, + "args": { + "External id": 31908,"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": 4183437, "tid": 4183437, + "ts": 658971916428.197, "dur": 13.382, + "args": { + "External id": 31909,"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": 4183437, "tid": 4183437, + "ts": 658971916447.949, "dur": 16.423, + "args": { + "External id": 31910,"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": 4183437, "tid": 4183437, + "ts": 658971916449.618, "dur": 2.633, + "args": { + "External id": 31911,"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": 4183437, "tid": 4183437, + "ts": 658971916452.941, "dur": 11.175, + "args": { + "External id": 31912,"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": 4183437, "tid": 4183437, + "ts": 658971916453.582, "dur": 10.223, + "args": { + "External id": 31913,"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": 4183437, "tid": 4183437, + "ts": 658971916469.600, "dur": 22.261, + "args": { + "External id": 31914,"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": 4183437, "tid": 4183437, + "ts": 658971916494.644, "dur": 47.362, + "args": { + "External id": 31915,"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": 4183437, "tid": 4183437, + "ts": 658971916496.769, "dur": 44.804, + "args": { + "External id": 31916,"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": 4183437, "tid": 4183437, + "ts": 658971916501.127, "dur": 1.158, + "args": { + "External id": 31917,"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": 4183437, "tid": 4183437, + "ts": 658971916503.906, "dur": 21.722, + "args": { + "External id": 31918,"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": 4183437, "tid": 4183437, + "ts": 658971916507.625, "dur": 17.803, + "args": { + "External id": 31919,"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": 4183437, "tid": 4183437, + "ts": 658971916509.738, "dur": 2.556, + "args": { + "External id": 31920,"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": 4183437, "tid": 4183437, + "ts": 658971916513.251, "dur": 11.733, + "args": { + "External id": 31921,"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": 4183437, "tid": 4183437, + "ts": 658971916545.947, "dur": 16626.212, + "args": { + "External id": 31922,"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": 4183437, "tid": 4183437, + "ts": 658971916547.583, "dur": 16622.664, + "args": { + "External id": 31923,"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": 4183437, "tid": 4183437, + "ts": 658971933183.456, "dur": 6.975, + "args": { + "External id": 31924,"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": 4183437, "tid": 4183437, + "ts": 658971933187.520, "dur": 1.338, + "args": { + "External id": 31925,"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": 4183437, "tid": 4183437, + "ts": 658971933195.540, "dur": 110.382, + "args": { + "External id": 31926,"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": 4183437, "tid": 4183437, + "ts": 658971933197.378, "dur": 6.378, + "args": { + "External id": 31927,"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": 4183437, "tid": 4183437, + "ts": 658971933199.582, "dur": 3.331, + "args": { + "External id": 31928,"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": 4183437, "tid": 4183437, + "ts": 658971933201.531, "dur": 1.134, + "args": { + "External id": 31929,"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": 4183437, "tid": 4183437, + "ts": 658971933205.040, "dur": 100.034, + "args": { + "External id": 31930,"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": 4183437, "tid": 4183437, + "ts": 658971933206.639, "dur": 97.199, + "args": { + "External id": 31931,"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": 4183437, "tid": 4183437, + "ts": 658971933310.465, "dur": 5.144, + "args": { + "External id": 31932,"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": 4183437, "tid": 4183437, + "ts": 658971933312.829, "dur": 1.465, + "args": { + "External id": 31933,"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": 4183437, "tid": 4183437, + "ts": 658971933323.171, "dur": 2.511, + "args": { + "External id": 31934,"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": 4183437, "tid": 4183437, + "ts": 658971933334.530, "dur": 6.946, + "args": { + "External id": 31935,"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": 4183437, "tid": 4183437, + "ts": 658971933336.635, "dur": 4.574, + "args": { + "External id": 31936,"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": 4183437, "tid": 4183437, + "ts": 658971933459.877, "dur": 232.715, + "args": { + "External id": 31937,"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": 4183437, "tid": 4183437, + "ts": 658971933462.517, "dur": 4.388, + "args": { + "External id": 31938,"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": 4183437, "tid": 4183437, + "ts": 658971933468.774, "dur": 223.036, + "args": { + "External id": 31939,"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": 4183437, "tid": 4183437, + "ts": 658971933470.687, "dur": 0.615, + "args": { + "External id": 31940,"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": 4183437, "tid": 4183437, + "ts": 658971933473.022, "dur": 24.865, + "args": { + "External id": 31941,"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": 4183437, "tid": 4183437, + "ts": 658971933499.858, "dur": 5.883, + "args": { + "External id": 31942,"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": 4183437, "tid": 4183437, + "ts": 658971933504.414, "dur": 1.064, + "args": { + "External id": 31943,"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": 4183437, "tid": 4183437, + "ts": 658971933506.712, "dur": 33.907, + "args": { + "External id": 31944,"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": 4183437, "tid": 4183437, + "ts": 658971933520.054, "dur": 1.273, + "args": { + "External id": 31945,"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": 4183437, "tid": 4183437, + "ts": 658971933522.906, "dur": 17.389, + "args": { + "External id": 31946,"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": 4183437, "tid": 4183437, + "ts": 658971933525.945, "dur": 3.075, + "args": { + "External id": 31947,"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": 4183437, "tid": 4183437, + "ts": 658971933542.430, "dur": 21.724, + "args": { + "External id": 31948,"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": 4183437, "tid": 4183437, + "ts": 658971933565.735, "dur": 16.165, + "args": { + "External id": 31949,"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": 4183437, "tid": 4183437, + "ts": 658971933584.910, "dur": 14.169, + "args": { + "External id": 31950,"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": 4183437, "tid": 4183437, + "ts": 658971933600.369, "dur": 12.372, + "args": { + "External id": 31951,"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": 4183437, "tid": 4183437, + "ts": 658971933614.772, "dur": 19.110, + "args": { + "External id": 31952,"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": 4183437, "tid": 4183437, + "ts": 658971933616.634, "dur": 1.334, + "args": { + "External id": 31953,"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": 4183437, "tid": 4183437, + "ts": 658971933620.158, "dur": 1.341, + "args": { + "External id": 31954,"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": 4183437, "tid": 4183437, + "ts": 658971933635.618, "dur": 11.292, + "args": { + "External id": 31955,"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": 4183437, "tid": 4183437, + "ts": 658971933648.410, "dur": 41.321, + "args": { + "External id": 31956,"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": 4183437, "tid": 4183437, + "ts": 658971933701.337, "dur": 2.579, + "args": { + "External id": 31957,"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": 4183437, "tid": 4183437, + "ts": 658971933711.278, "dur": 4.957, + "args": { + "External id": 31958,"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": 4183437, "tid": 4183437, + "ts": 658971933713.885, "dur": 1.323, + "args": { + "External id": 31959,"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": 4183437, "tid": 4183437, + "ts": 658971933788.836, "dur": 53.959, + "args": { + "External id": 31960,"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": 4183437, "tid": 4183437, + "ts": 658971933848.243, "dur": 5.695, + "args": { + "External id": 31961,"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": 4183437, "tid": 4183437, + "ts": 658971933850.715, "dur": 0.991, + "args": { + "External id": 31962,"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": 4183437, "tid": 4183437, + "ts": 658971933855.648, "dur": 26.151, + "args": { + "External id": 31963,"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": 4183437, "tid": 4183437, + "ts": 658971933886.678, "dur": 6.430, + "args": { + "External id": 31964,"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": 4183437, "tid": 4183437, + "ts": 658971933888.671, "dur": 3.719, + "args": { + "External id": 31965,"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": 4183437, "tid": 4183437, + "ts": 658971933890.762, "dur": 1.443, + "args": { + "External id": 31966,"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": 4183437, "tid": 4183437, + "ts": 658971933896.335, "dur": 43.955, + "args": { + "External id": 31967,"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": 4183437, "tid": 4183437, + "ts": 658971933897.928, "dur": 41.744, + "args": { + "External id": 31968,"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": 4183437, "tid": 4183437, + "ts": 658971933944.380, "dur": 15.296, + "args": { + "External id": 31969,"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": 4183437, "tid": 4183437, + "ts": 658971933965.166, "dur": 3.787, + "args": { + "External id": 31970,"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": 4183437, "tid": 4183437, + "ts": 658971933967.192, "dur": 0.940, + "args": { + "External id": 31971,"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": 4183437, "tid": 4183437, + "ts": 658971933973.500, "dur": 47.219, + "args": { + "External id": 31972,"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": 4183437, "tid": 4183437, + "ts": 658971933974.729, "dur": 3.629, + "args": { + "External id": 31973,"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": 4183437, "tid": 4183437, + "ts": 658971933975.578, "dur": 2.195, + "args": { + "External id": 31974,"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": 4183437, "tid": 4183437, + "ts": 658971933976.740, "dur": 0.900, + "args": { + "External id": 31975,"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": 4183437, "tid": 4183437, + "ts": 658971933979.348, "dur": 40.906, + "args": { + "External id": 31976,"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": 4183437, "tid": 4183437, + "ts": 658971933979.826, "dur": 39.901, + "args": { + "External id": 31977,"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": 4183437, "tid": 4183437, + "ts": 658971934024.532, "dur": 3.844, + "args": { + "External id": 31978,"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": 4183437, "tid": 4183437, + "ts": 658971934026.143, "dur": 1.102, + "args": { + "External id": 31979,"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": 4183437, "tid": 4183437, + "ts": 658971934033.397, "dur": 1.642, + "args": { + "External id": 31980,"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": 4183437, "tid": 4183437, + "ts": 658971934042.359, "dur": 7.955, + "args": { + "External id": 31981,"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": 4183437, "tid": 4183437, + "ts": 658971934044.305, "dur": 5.693, + "args": { + "External id": 31982,"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": 4183437, "tid": 4183437, + "ts": 658971934134.983, "dur": 194.845, + "args": { + "External id": 31983,"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": 4183437, "tid": 4183437, + "ts": 658971934136.909, "dur": 2.114, + "args": { + "External id": 31984,"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": 4183437, "tid": 4183437, + "ts": 658971934140.274, "dur": 189.048, + "args": { + "External id": 31985,"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": 4183437, "tid": 4183437, + "ts": 658971934141.848, "dur": 0.347, + "args": { + "External id": 31986,"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": 4183437, "tid": 4183437, + "ts": 658971934143.320, "dur": 21.308, + "args": { + "External id": 31987,"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": 4183437, "tid": 4183437, + "ts": 658971934166.199, "dur": 3.060, + "args": { + "External id": 31988,"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": 4183437, "tid": 4183437, + "ts": 658971934167.991, "dur": 0.980, + "args": { + "External id": 31989,"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": 4183437, "tid": 4183437, + "ts": 658971934170.099, "dur": 21.968, + "args": { + "External id": 31990,"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": 4183437, "tid": 4183437, + "ts": 658971934171.147, "dur": 1.306, + "args": { + "External id": 31991,"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": 4183437, "tid": 4183437, + "ts": 658971934173.664, "dur": 18.093, + "args": { + "External id": 31992,"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": 4183437, "tid": 4183437, + "ts": 658971934178.427, "dur": 2.718, + "args": { + "External id": 31993,"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": 4183437, "tid": 4183437, + "ts": 658971934193.748, "dur": 18.846, + "args": { + "External id": 31994,"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": 4183437, "tid": 4183437, + "ts": 658971934214.292, "dur": 12.493, + "args": { + "External id": 31995,"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": 4183437, "tid": 4183437, + "ts": 658971934229.114, "dur": 11.718, + "args": { + "External id": 31996,"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": 4183437, "tid": 4183437, + "ts": 658971934242.222, "dur": 11.558, + "args": { + "External id": 31997,"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": 4183437, "tid": 4183437, + "ts": 658971934255.369, "dur": 36.291, + "args": { + "External id": 31998,"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": 4183437, "tid": 4183437, + "ts": 658971934257.115, "dur": 1.304, + "args": { + "External id": 31999,"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": 4183437, "tid": 4183437, + "ts": 658971934260.262, "dur": 0.747, + "args": { + "External id": 32000,"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": 4183437, "tid": 4183437, + "ts": 658971934294.258, "dur": 13.783, + "args": { + "External id": 32001,"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": 4183437, "tid": 4183437, + "ts": 658971934309.424, "dur": 18.918, + "args": { + "External id": 32002,"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": 4183437, "tid": 4183437, + "ts": 658971934336.800, "dur": 2.677, + "args": { + "External id": 32003,"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": 4183437, "tid": 4183437, + "ts": 658971934348.240, "dur": 3.595, + "args": { + "External id": 32004,"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": 4183437, "tid": 4183437, + "ts": 658971934350.422, "dur": 0.645, + "args": { + "External id": 32005,"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": 4183437, "tid": 4183437, + "ts": 658971934424.212, "dur": 46.505, + "args": { + "External id": 32006,"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": 4183437, "tid": 4183437, + "ts": 658971934475.458, "dur": 4.848, + "args": { + "External id": 32007,"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": 4183437, "tid": 4183437, + "ts": 658971934477.818, "dur": 1.270, + "args": { + "External id": 32008,"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": 4183437, "tid": 4183437, + "ts": 658971934481.644, "dur": 29.180, + "args": { + "External id": 32009,"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": 4183437, "tid": 4183437, + "ts": 658971934515.284, "dur": 5.188, + "args": { + "External id": 32010,"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": 4183437, "tid": 4183437, + "ts": 658971934516.637, "dur": 3.231, + "args": { + "External id": 32011,"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": 4183437, "tid": 4183437, + "ts": 658971934518.608, "dur": 1.058, + "args": { + "External id": 32012,"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": 4183437, "tid": 4183437, + "ts": 658971934523.013, "dur": 47.741, + "args": { + "External id": 32013,"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": 4183437, "tid": 4183437, + "ts": 658971934524.202, "dur": 45.992, + "args": { + "External id": 32014,"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": 4183437, "tid": 4183437, + "ts": 658971934574.440, "dur": 16.059, + "args": { + "External id": 32015,"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": 4183437, "tid": 4183437, + "ts": 658971934595.925, "dur": 3.325, + "args": { + "External id": 32016,"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": 4183437, "tid": 4183437, + "ts": 658971934597.702, "dur": 0.724, + "args": { + "External id": 32017,"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": 4183437, "tid": 4183437, + "ts": 658971934603.432, "dur": 101.643, + "args": { + "External id": 32018,"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": 4183437, "tid": 4183437, + "ts": 658971934604.450, "dur": 6.116, + "args": { + "External id": 32019,"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": 4183437, "tid": 4183437, + "ts": 658971934605.350, "dur": 4.545, + "args": { + "External id": 32020,"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": 4183437, "tid": 4183437, + "ts": 658971934606.986, "dur": 2.704, + "args": { + "External id": 32021,"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": 4183437, "tid": 4183437, + "ts": 658971934620.892, "dur": 83.560, + "args": { + "External id": 32022,"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": 4183437, "tid": 4183437, + "ts": 658971934623.106, "dur": 80.283, + "args": { + "External id": 32023,"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": 4183437, "tid": 4183437, + "ts": 658971934711.474, "dur": 4.672, + "args": { + "External id": 32024,"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": 4183437, "tid": 4183437, + "ts": 658971934714.205, "dur": 0.684, + "args": { + "External id": 32025,"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": 4183437, "tid": 4183437, + "ts": 658971934722.919, "dur": 1.898, + "args": { + "External id": 32026,"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": 4183437, "tid": 4183437, + "ts": 658971934733.306, "dur": 6.586, + "args": { + "External id": 32027,"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": 4183437, "tid": 4183437, + "ts": 658971934735.379, "dur": 4.222, + "args": { + "External id": 32028,"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": 4183437, "tid": 4183437, + "ts": 658971934833.312, "dur": 187.443, + "args": { + "External id": 32029,"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": 4183437, "tid": 4183437, + "ts": 658971934837.837, "dur": 2.042, + "args": { + "External id": 32030,"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": 4183437, "tid": 4183437, + "ts": 658971934841.140, "dur": 179.196, + "args": { + "External id": 32031,"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": 4183437, "tid": 4183437, + "ts": 658971934842.582, "dur": 0.403, + "args": { + "External id": 32032,"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": 4183437, "tid": 4183437, + "ts": 658971934844.290, "dur": 24.097, + "args": { + "External id": 32033,"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": 4183437, "tid": 4183437, + "ts": 658971934870.206, "dur": 5.396, + "args": { + "External id": 32034,"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": 4183437, "tid": 4183437, + "ts": 658971934874.171, "dur": 1.000, + "args": { + "External id": 32035,"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": 4183437, "tid": 4183437, + "ts": 658971934876.292, "dur": 21.934, + "args": { + "External id": 32036,"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": 4183437, "tid": 4183437, + "ts": 658971934877.411, "dur": 1.780, + "args": { + "External id": 32037,"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": 4183437, "tid": 4183437, + "ts": 658971934880.464, "dur": 17.373, + "args": { + "External id": 32038,"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": 4183437, "tid": 4183437, + "ts": 658971934883.277, "dur": 2.437, + "args": { + "External id": 32039,"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": 4183437, "tid": 4183437, + "ts": 658971934899.860, "dur": 20.477, + "args": { + "External id": 32040,"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": 4183437, "tid": 4183437, + "ts": 658971934921.812, "dur": 14.571, + "args": { + "External id": 32041,"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": 4183437, "tid": 4183437, + "ts": 658971934939.144, "dur": 14.752, + "args": { + "External id": 32042,"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": 4183437, "tid": 4183437, + "ts": 658971934955.323, "dur": 13.151, + "args": { + "External id": 32043,"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": 4183437, "tid": 4183437, + "ts": 658971934970.427, "dur": 20.511, + "args": { + "External id": 32044,"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": 4183437, "tid": 4183437, + "ts": 658971934972.376, "dur": 1.107, + "args": { + "External id": 32045,"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": 4183437, "tid": 4183437, + "ts": 658971934975.318, "dur": 0.711, + "args": { + "External id": 32046,"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": 4183437, "tid": 4183437, + "ts": 658971934992.476, "dur": 13.122, + "args": { + "External id": 32047,"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": 4183437, "tid": 4183437, + "ts": 658971935006.777, "dur": 12.381, + "args": { + "External id": 32048,"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": 4183437, "tid": 4183437, + "ts": 658971935029.584, "dur": 1.603, + "args": { + "External id": 32049,"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": 4183437, "tid": 4183437, + "ts": 658971935040.430, "dur": 3.375, + "args": { + "External id": 32050,"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": 4183437, "tid": 4183437, + "ts": 658971935042.448, "dur": 0.570, + "args": { + "External id": 32051,"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": 4183437, "tid": 4183437, + "ts": 658971935108.214, "dur": 46.395, + "args": { + "External id": 32052,"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": 4183437, "tid": 4183437, + "ts": 658971935159.249, "dur": 4.233, + "args": { + "External id": 32053,"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": 4183437, "tid": 4183437, + "ts": 658971935161.601, "dur": 0.685, + "args": { + "External id": 32054,"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": 4183437, "tid": 4183437, + "ts": 658971935164.650, "dur": 25.300, + "args": { + "External id": 32055,"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": 4183437, "tid": 4183437, + "ts": 658971935194.119, "dur": 6.974, + "args": { + "External id": 32056,"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": 4183437, "tid": 4183437, + "ts": 658971935195.990, "dur": 4.476, + "args": { + "External id": 32057,"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": 4183437, "tid": 4183437, + "ts": 658971935197.384, "dur": 2.868, + "args": { + "External id": 32058,"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": 4183437, "tid": 4183437, + "ts": 658971935203.520, "dur": 42.805, + "args": { + "External id": 32059,"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": 4183437, "tid": 4183437, + "ts": 658971935204.710, "dur": 41.012, + "args": { + "External id": 32060,"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": 4183437, "tid": 4183437, + "ts": 658971935249.830, "dur": 36.237, + "args": { + "External id": 32061,"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": 4183437, "tid": 4183437, + "ts": 658971935293.947, "dur": 4.726, + "args": { + "External id": 32062,"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": 4183437, "tid": 4183437, + "ts": 658971935296.568, "dur": 0.949, + "args": { + "External id": 32063,"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": 4183437, "tid": 4183437, + "ts": 658971935303.182, "dur": 52.389, + "args": { + "External id": 32064,"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": 4183437, "tid": 4183437, + "ts": 658971935303.979, "dur": 3.834, + "args": { + "External id": 32065,"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": 4183437, "tid": 4183437, + "ts": 658971935305.024, "dur": 2.183, + "args": { + "External id": 32066,"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": 4183437, "tid": 4183437, + "ts": 658971935306.274, "dur": 0.773, + "args": { + "External id": 32067,"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": 4183437, "tid": 4183437, + "ts": 658971935308.576, "dur": 46.630, + "args": { + "External id": 32068,"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": 4183437, "tid": 4183437, + "ts": 658971935309.377, "dur": 45.303, + "args": { + "External id": 32069,"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": 4183437, "tid": 4183437, + "ts": 658971935359.463, "dur": 3.963, + "args": { + "External id": 32070,"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": 4183437, "tid": 4183437, + "ts": 658971935361.384, "dur": 0.832, + "args": { + "External id": 32071,"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": 4183437, "tid": 4183437, + "ts": 658971935369.474, "dur": 1.789, + "args": { + "External id": 32072,"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": 4183437, "tid": 4183437, + "ts": 658971935378.623, "dur": 6.203, + "args": { + "External id": 32073,"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": 4183437, "tid": 4183437, + "ts": 658971935380.345, "dur": 4.215, + "args": { + "External id": 32074,"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": 4183437, "tid": 4183437, + "ts": 658971935467.274, "dur": 173.291, + "args": { + "External id": 32075,"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": 4183437, "tid": 4183437, + "ts": 658971935469.561, "dur": 2.513, + "args": { + "External id": 32076,"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": 4183437, "tid": 4183437, + "ts": 658971935475.781, "dur": 164.244, + "args": { + "External id": 32077,"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": 4183437, "tid": 4183437, + "ts": 658971935477.081, "dur": 0.350, + "args": { + "External id": 32078,"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": 4183437, "tid": 4183437, + "ts": 658971935478.814, "dur": 20.306, + "args": { + "External id": 32079,"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": 4183437, "tid": 4183437, + "ts": 658971935500.500, "dur": 5.706, + "args": { + "External id": 32080,"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": 4183437, "tid": 4183437, + "ts": 658971935502.872, "dur": 3.025, + "args": { + "External id": 32081,"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": 4183437, "tid": 4183437, + "ts": 658971935507.071, "dur": 18.784, + "args": { + "External id": 32082,"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": 4183437, "tid": 4183437, + "ts": 658971935507.895, "dur": 1.497, + "args": { + "External id": 32083,"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": 4183437, "tid": 4183437, + "ts": 658971935510.494, "dur": 15.057, + "args": { + "External id": 32084,"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": 4183437, "tid": 4183437, + "ts": 658971935512.743, "dur": 2.596, + "args": { + "External id": 32085,"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": 4183437, "tid": 4183437, + "ts": 658971935527.467, "dur": 19.068, + "args": { + "External id": 32086,"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": 4183437, "tid": 4183437, + "ts": 658971935548.033, "dur": 12.106, + "args": { + "External id": 32087,"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": 4183437, "tid": 4183437, + "ts": 658971935562.766, "dur": 11.595, + "args": { + "External id": 32088,"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": 4183437, "tid": 4183437, + "ts": 658971935575.816, "dur": 12.169, + "args": { + "External id": 32089,"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": 4183437, "tid": 4183437, + "ts": 658971935589.532, "dur": 20.891, + "args": { + "External id": 32090,"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": 4183437, "tid": 4183437, + "ts": 658971935591.439, "dur": 1.005, + "args": { + "External id": 32091,"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": 4183437, "tid": 4183437, + "ts": 658971935595.195, "dur": 3.376, + "args": { + "External id": 32092,"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": 4183437, "tid": 4183437, + "ts": 658971935611.832, "dur": 11.343, + "args": { + "External id": 32093,"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": 4183437, "tid": 4183437, + "ts": 658971935624.150, "dur": 14.605, + "args": { + "External id": 32094,"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": 4183437, "tid": 4183437, + "ts": 658971935647.070, "dur": 1.612, + "args": { + "External id": 32095,"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": 4183437, "tid": 4183437, + "ts": 658971935696.443, "dur": 4.887, + "args": { + "External id": 32096,"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": 4183437, "tid": 4183437, + "ts": 658971935698.777, "dur": 1.235, + "args": { + "External id": 32097,"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": 4183437, "tid": 4183437, + "ts": 658971935770.230, "dur": 46.033, + "args": { + "External id": 32098,"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": 4183437, "tid": 4183437, + "ts": 658971935820.728, "dur": 4.652, + "args": { + "External id": 32099,"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": 4183437, "tid": 4183437, + "ts": 658971935823.444, "dur": 0.839, + "args": { + "External id": 32100,"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": 4183437, "tid": 4183437, + "ts": 658971935826.919, "dur": 23.867, + "args": { + "External id": 32101,"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": 4183437, "tid": 4183437, + "ts": 658971935855.127, "dur": 6.202, + "args": { + "External id": 32102,"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": 4183437, "tid": 4183437, + "ts": 658971935856.734, "dur": 3.997, + "args": { + "External id": 32103,"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": 4183437, "tid": 4183437, + "ts": 658971935858.852, "dur": 1.638, + "args": { + "External id": 32104,"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": 4183437, "tid": 4183437, + "ts": 658971935864.088, "dur": 40.853, + "args": { + "External id": 32105,"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": 4183437, "tid": 4183437, + "ts": 658971935865.579, "dur": 38.681, + "args": { + "External id": 32106,"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": 4183437, "tid": 4183437, + "ts": 658971935908.319, "dur": 15.127, + "args": { + "External id": 32107,"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": 4183437, "tid": 4183437, + "ts": 658971935928.464, "dur": 4.136, + "args": { + "External id": 32108,"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": 4183437, "tid": 4183437, + "ts": 658971935931.075, "dur": 0.739, + "args": { + "External id": 32109,"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": 4183437, "tid": 4183437, + "ts": 658971935936.353, "dur": 46.867, + "args": { + "External id": 32110,"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": 4183437, "tid": 4183437, + "ts": 658971935937.385, "dur": 4.042, + "args": { + "External id": 32111,"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": 4183437, "tid": 4183437, + "ts": 658971935938.296, "dur": 2.538, + "args": { + "External id": 32112,"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": 4183437, "tid": 4183437, + "ts": 658971935940.113, "dur": 0.592, + "args": { + "External id": 32113,"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": 4183437, "tid": 4183437, + "ts": 658971935942.047, "dur": 40.794, + "args": { + "External id": 32114,"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": 4183437, "tid": 4183437, + "ts": 658971935942.805, "dur": 39.360, + "args": { + "External id": 32115,"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": 4183437, "tid": 4183437, + "ts": 658971935987.232, "dur": 3.472, + "args": { + "External id": 32116,"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": 4183437, "tid": 4183437, + "ts": 658971935989.183, "dur": 0.453, + "args": { + "External id": 32117,"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": 4183437, "tid": 4183437, + "ts": 658971935996.665, "dur": 1.439, + "args": { + "External id": 32118,"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": 4183437, "tid": 4183437, + "ts": 658971936004.949, "dur": 5.678, + "args": { + "External id": 32119,"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": 4183437, "tid": 4183437, + "ts": 658971936006.876, "dur": 3.466, + "args": { + "External id": 32120,"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": 4183437, "tid": 4183437, + "ts": 658971936086.550, "dur": 172.716, + "args": { + "External id": 32121,"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": 4183437, "tid": 4183437, + "ts": 658971936090.931, "dur": 1.947, + "args": { + "External id": 32122,"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": 4183437, "tid": 4183437, + "ts": 658971936094.317, "dur": 164.412, + "args": { + "External id": 32123,"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": 4183437, "tid": 4183437, + "ts": 658971936095.683, "dur": 0.577, + "args": { + "External id": 32124,"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": 4183437, "tid": 4183437, + "ts": 658971936097.355, "dur": 19.261, + "args": { + "External id": 32125,"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": 4183437, "tid": 4183437, + "ts": 658971936118.167, "dur": 4.934, + "args": { + "External id": 32126,"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": 4183437, "tid": 4183437, + "ts": 658971936122.120, "dur": 0.702, + "args": { + "External id": 32127,"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": 4183437, "tid": 4183437, + "ts": 658971936123.832, "dur": 19.071, + "args": { + "External id": 32128,"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": 4183437, "tid": 4183437, + "ts": 658971936124.605, "dur": 1.051, + "args": { + "External id": 32129,"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": 4183437, "tid": 4183437, + "ts": 658971936126.751, "dur": 15.733, + "args": { + "External id": 32130,"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": 4183437, "tid": 4183437, + "ts": 658971936128.994, "dur": 2.244, + "args": { + "External id": 32131,"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": 4183437, "tid": 4183437, + "ts": 658971936144.287, "dur": 19.982, + "args": { + "External id": 32132,"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": 4183437, "tid": 4183437, + "ts": 658971936165.609, "dur": 12.961, + "args": { + "External id": 32133,"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": 4183437, "tid": 4183437, + "ts": 658971936181.029, "dur": 12.765, + "args": { + "External id": 32134,"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": 4183437, "tid": 4183437, + "ts": 658971936195.180, "dur": 11.557, + "args": { + "External id": 32135,"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": 4183437, "tid": 4183437, + "ts": 658971936208.564, "dur": 22.787, + "args": { + "External id": 32136,"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": 4183437, "tid": 4183437, + "ts": 658971936212.962, "dur": 0.953, + "args": { + "External id": 32137,"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": 4183437, "tid": 4183437, + "ts": 658971936216.403, "dur": 0.961, + "args": { + "External id": 32138,"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": 4183437, "tid": 4183437, + "ts": 658971936232.687, "dur": 12.732, + "args": { + "External id": 32139,"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": 4183437, "tid": 4183437, + "ts": 658971936246.515, "dur": 11.005, + "args": { + "External id": 32140,"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": 4183437, "tid": 4183437, + "ts": 658971936283.020, "dur": 2.521, + "args": { + "External id": 32141,"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": 4183437, "tid": 4183437, + "ts": 658971936294.909, "dur": 3.629, + "args": { + "External id": 32142,"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": 4183437, "tid": 4183437, + "ts": 658971936297.264, "dur": 0.503, + "args": { + "External id": 32143,"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": 4183437, "tid": 4183437, + "ts": 658971936361.679, "dur": 41.563, + "args": { + "External id": 32144,"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": 4183437, "tid": 4183437, + "ts": 658971936407.834, "dur": 4.723, + "args": { + "External id": 32145,"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": 4183437, "tid": 4183437, + "ts": 658971936410.342, "dur": 1.140, + "args": { + "External id": 32146,"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": 4183437, "tid": 4183437, + "ts": 658971936413.980, "dur": 22.891, + "args": { + "External id": 32147,"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": 4183437, "tid": 4183437, + "ts": 658971936441.440, "dur": 6.356, + "args": { + "External id": 32148,"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": 4183437, "tid": 4183437, + "ts": 658971936442.918, "dur": 4.161, + "args": { + "External id": 32149,"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": 4183437, "tid": 4183437, + "ts": 658971936445.602, "dur": 1.262, + "args": { + "External id": 32150,"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": 4183437, "tid": 4183437, + "ts": 658971936449.971, "dur": 40.754, + "args": { + "External id": 32151,"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": 4183437, "tid": 4183437, + "ts": 658971936451.195, "dur": 38.898, + "args": { + "External id": 32152,"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": 4183437, "tid": 4183437, + "ts": 658971936493.977, "dur": 13.848, + "args": { + "External id": 32153,"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": 4183437, "tid": 4183437, + "ts": 658971936512.980, "dur": 4.196, + "args": { + "External id": 32154,"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": 4183437, "tid": 4183437, + "ts": 658971936515.510, "dur": 0.840, + "args": { + "External id": 32155,"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": 4183437, "tid": 4183437, + "ts": 658971936521.332, "dur": 45.550, + "args": { + "External id": 32156,"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": 4183437, "tid": 4183437, + "ts": 658971936522.262, "dur": 3.958, + "args": { + "External id": 32157,"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": 4183437, "tid": 4183437, + "ts": 658971936523.025, "dur": 2.627, + "args": { + "External id": 32158,"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": 4183437, "tid": 4183437, + "ts": 658971936524.739, "dur": 0.763, + "args": { + "External id": 32159,"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": 4183437, "tid": 4183437, + "ts": 658971936526.909, "dur": 39.468, + "args": { + "External id": 32160,"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": 4183437, "tid": 4183437, + "ts": 658971936527.457, "dur": 38.475, + "args": { + "External id": 32161,"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": 4183437, "tid": 4183437, + "ts": 658971936570.364, "dur": 3.805, + "args": { + "External id": 32162,"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": 4183437, "tid": 4183437, + "ts": 658971936572.236, "dur": 0.899, + "args": { + "External id": 32163,"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": 4183437, "tid": 4183437, + "ts": 658971936579.028, "dur": 1.582, + "args": { + "External id": 32164,"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": 4183437, "tid": 4183437, + "ts": 658971936587.620, "dur": 5.567, + "args": { + "External id": 32165,"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": 4183437, "tid": 4183437, + "ts": 658971936589.409, "dur": 3.493, + "args": { + "External id": 32166,"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": 4183437, "tid": 4183437, + "ts": 658971936704.619, "dur": 174.719, + "args": { + "External id": 32167,"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": 4183437, "tid": 4183437, + "ts": 658971936709.014, "dur": 3.045, + "args": { + "External id": 32168,"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": 4183437, "tid": 4183437, + "ts": 658971936713.929, "dur": 164.972, + "args": { + "External id": 32169,"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": 4183437, "tid": 4183437, + "ts": 658971936715.799, "dur": 0.486, + "args": { + "External id": 32170,"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": 4183437, "tid": 4183437, + "ts": 658971936717.702, "dur": 21.639, + "args": { + "External id": 32171,"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": 4183437, "tid": 4183437, + "ts": 658971936740.886, "dur": 5.231, + "args": { + "External id": 32172,"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": 4183437, "tid": 4183437, + "ts": 658971936744.889, "dur": 0.890, + "args": { + "External id": 32173,"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": 4183437, "tid": 4183437, + "ts": 658971936747.070, "dur": 19.462, + "args": { + "External id": 32174,"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": 4183437, "tid": 4183437, + "ts": 658971936748.446, "dur": 1.067, + "args": { + "External id": 32175,"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": 4183437, "tid": 4183437, + "ts": 658971936750.698, "dur": 15.532, + "args": { + "External id": 32176,"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": 4183437, "tid": 4183437, + "ts": 658971936752.870, "dur": 2.847, + "args": { + "External id": 32177,"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": 4183437, "tid": 4183437, + "ts": 658971936767.926, "dur": 19.953, + "args": { + "External id": 32178,"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": 4183437, "tid": 4183437, + "ts": 658971936789.263, "dur": 15.320, + "args": { + "External id": 32179,"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": 4183437, "tid": 4183437, + "ts": 658971936807.485, "dur": 12.652, + "args": { + "External id": 32180,"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": 4183437, "tid": 4183437, + "ts": 658971936821.603, "dur": 11.871, + "args": { + "External id": 32181,"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": 4183437, "tid": 4183437, + "ts": 658971936835.071, "dur": 18.001, + "args": { + "External id": 32182,"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": 4183437, "tid": 4183437, + "ts": 658971936837.148, "dur": 1.142, + "args": { + "External id": 32183,"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": 4183437, "tid": 4183437, + "ts": 658971936840.409, "dur": 0.630, + "args": { + "External id": 32184,"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": 4183437, "tid": 4183437, + "ts": 658971936854.599, "dur": 11.211, + "args": { + "External id": 32185,"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": 4183437, "tid": 4183437, + "ts": 658971936866.812, "dur": 11.116, + "args": { + "External id": 32186,"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": 4183437, "tid": 4183437, + "ts": 658971936885.790, "dur": 1.995, + "args": { + "External id": 32187,"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": 4183437, "tid": 4183437, + "ts": 658971936896.403, "dur": 3.858, + "args": { + "External id": 32188,"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": 4183437, "tid": 4183437, + "ts": 658971936898.698, "dur": 0.712, + "args": { + "External id": 32189,"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": 4183437, "tid": 4183437, + "ts": 658971936976.551, "dur": 45.048, + "args": { + "External id": 32190,"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": 4183437, "tid": 4183437, + "ts": 658971937026.169, "dur": 3.970, + "args": { + "External id": 32191,"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": 4183437, "tid": 4183437, + "ts": 658971937028.448, "dur": 0.522, + "args": { + "External id": 32192,"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": 4183437, "tid": 4183437, + "ts": 658971937031.712, "dur": 21.334, + "args": { + "External id": 32193,"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": 4183437, "tid": 4183437, + "ts": 658971937057.591, "dur": 7.627, + "args": { + "External id": 32194,"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": 4183437, "tid": 4183437, + "ts": 658971937059.573, "dur": 5.033, + "args": { + "External id": 32195,"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": 4183437, "tid": 4183437, + "ts": 658971937061.469, "dur": 2.943, + "args": { + "External id": 32196,"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": 4183437, "tid": 4183437, + "ts": 658971937067.602, "dur": 39.863, + "args": { + "External id": 32197,"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": 4183437, "tid": 4183437, + "ts": 658971937068.802, "dur": 38.122, + "args": { + "External id": 32198,"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": 4183437, "tid": 4183437, + "ts": 658971937111.139, "dur": 15.546, + "args": { + "External id": 32199,"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": 4183437, "tid": 4183437, + "ts": 658971937131.658, "dur": 3.754, + "args": { + "External id": 32200,"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": 4183437, "tid": 4183437, + "ts": 658971937133.825, "dur": 0.795, + "args": { + "External id": 32201,"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": 4183437, "tid": 4183437, + "ts": 658971937139.406, "dur": 45.845, + "args": { + "External id": 32202,"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": 4183437, "tid": 4183437, + "ts": 658971937140.346, "dur": 3.744, + "args": { + "External id": 32203,"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": 4183437, "tid": 4183437, + "ts": 658971937141.265, "dur": 2.222, + "args": { + "External id": 32204,"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": 4183437, "tid": 4183437, + "ts": 658971937142.616, "dur": 0.756, + "args": { + "External id": 32205,"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": 4183437, "tid": 4183437, + "ts": 658971937144.778, "dur": 40.079, + "args": { + "External id": 32206,"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": 4183437, "tid": 4183437, + "ts": 658971937145.529, "dur": 38.831, + "args": { + "External id": 32207,"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": 4183437, "tid": 4183437, + "ts": 658971937188.914, "dur": 3.651, + "args": { + "External id": 32208,"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": 4183437, "tid": 4183437, + "ts": 658971937190.717, "dur": 0.821, + "args": { + "External id": 32209,"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": 4183437, "tid": 4183437, + "ts": 658971937197.707, "dur": 1.638, + "args": { + "External id": 32210,"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": 4183437, "tid": 4183437, + "ts": 658971937206.238, "dur": 11.253, + "args": { + "External id": 32211,"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": 4183437, "tid": 4183437, + "ts": 658971937211.791, "dur": 5.373, + "args": { + "External id": 32212,"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": 4183437, "tid": 4183437, + "ts": 658971937323.759, "dur": 235.195, + "args": { + "External id": 32213,"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": 4183437, "tid": 4183437, + "ts": 658971937325.826, "dur": 3.068, + "args": { + "External id": 32214,"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": 4183437, "tid": 4183437, + "ts": 658971937330.647, "dur": 227.636, + "args": { + "External id": 32215,"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": 4183437, "tid": 4183437, + "ts": 658971937332.331, "dur": 0.440, + "args": { + "External id": 32216,"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": 4183437, "tid": 4183437, + "ts": 658971937333.787, "dur": 33.141, + "args": { + "External id": 32217,"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": 4183437, "tid": 4183437, + "ts": 658971937368.402, "dur": 3.349, + "args": { + "External id": 32218,"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": 4183437, "tid": 4183437, + "ts": 658971937370.622, "dur": 0.800, + "args": { + "External id": 32219,"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": 4183437, "tid": 4183437, + "ts": 658971937372.802, "dur": 33.899, + "args": { + "External id": 32220,"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": 4183437, "tid": 4183437, + "ts": 658971937373.808, "dur": 1.187, + "args": { + "External id": 32221,"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": 4183437, "tid": 4183437, + "ts": 658971937376.095, "dur": 30.296, + "args": { + "External id": 32222,"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": 4183437, "tid": 4183437, + "ts": 658971937380.815, "dur": 2.122, + "args": { + "External id": 32223,"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": 4183437, "tid": 4183437, + "ts": 658971937408.230, "dur": 33.410, + "args": { + "External id": 32224,"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": 4183437, "tid": 4183437, + "ts": 658971937443.144, "dur": 28.157, + "args": { + "External id": 32225,"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": 4183437, "tid": 4183437, + "ts": 658971937474.040, "dur": 18.137, + "args": { + "External id": 32226,"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": 4183437, "tid": 4183437, + "ts": 658971937493.471, "dur": 13.962, + "args": { + "External id": 32227,"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": 4183437, "tid": 4183437, + "ts": 658971937509.192, "dur": 20.524, + "args": { + "External id": 32228,"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": 4183437, "tid": 4183437, + "ts": 658971937511.247, "dur": 0.861, + "args": { + "External id": 32229,"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": 4183437, "tid": 4183437, + "ts": 658971937513.779, "dur": 0.747, + "args": { + "External id": 32230,"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": 4183437, "tid": 4183437, + "ts": 658971937531.242, "dur": 12.614, + "args": { + "External id": 32231,"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": 4183437, "tid": 4183437, + "ts": 658971937545.026, "dur": 12.143, + "args": { + "External id": 32232,"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": 4183437, "tid": 4183437, + "ts": 658971937565.361, "dur": 2.206, + "args": { + "External id": 32233,"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": 4183437, "tid": 4183437, + "ts": 658971937576.716, "dur": 3.544, + "args": { + "External id": 32234,"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": 4183437, "tid": 4183437, + "ts": 658971937579.093, "dur": 0.390, + "args": { + "External id": 32235,"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": 4183437, "tid": 4183437, + "ts": 658971937643.279, "dur": 84.768, + "args": { + "External id": 32236,"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": 4183437, "tid": 4183437, + "ts": 658971937735.376, "dur": 6.395, + "args": { + "External id": 32237,"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": 4183437, "tid": 4183437, + "ts": 658971937739.222, "dur": 1.068, + "args": { + "External id": 32238,"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": 4183437, "tid": 4183437, + "ts": 658971937743.104, "dur": 26.446, + "args": { + "External id": 32239,"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": 4183437, "tid": 4183437, + "ts": 658971937774.455, "dur": 6.083, + "args": { + "External id": 32240,"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": 4183437, "tid": 4183437, + "ts": 658971937776.307, "dur": 3.616, + "args": { + "External id": 32241,"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": 4183437, "tid": 4183437, + "ts": 658971937778.503, "dur": 1.223, + "args": { + "External id": 32242,"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": 4183437, "tid": 4183437, + "ts": 658971937783.407, "dur": 42.675, + "args": { + "External id": 32243,"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": 4183437, "tid": 4183437, + "ts": 658971937784.655, "dur": 40.831, + "args": { + "External id": 32244,"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": 4183437, "tid": 4183437, + "ts": 658971937829.614, "dur": 15.296, + "args": { + "External id": 32245,"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": 4183437, "tid": 4183437, + "ts": 658971937850.350, "dur": 3.983, + "args": { + "External id": 32246,"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": 4183437, "tid": 4183437, + "ts": 658971937852.880, "dur": 0.556, + "args": { + "External id": 32247,"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": 4183437, "tid": 4183437, + "ts": 658971937858.188, "dur": 46.731, + "args": { + "External id": 32248,"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": 4183437, "tid": 4183437, + "ts": 658971937859.213, "dur": 3.849, + "args": { + "External id": 32249,"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": 4183437, "tid": 4183437, + "ts": 658971937859.941, "dur": 2.537, + "args": { + "External id": 32250,"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": 4183437, "tid": 4183437, + "ts": 658971937861.660, "dur": 0.692, + "args": { + "External id": 32251,"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": 4183437, "tid": 4183437, + "ts": 658971937863.629, "dur": 40.812, + "args": { + "External id": 32252,"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": 4183437, "tid": 4183437, + "ts": 658971937864.259, "dur": 39.607, + "args": { + "External id": 32253,"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": 4183437, "tid": 4183437, + "ts": 658971937908.779, "dur": 6.195, + "args": { + "External id": 32254,"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": 4183437, "tid": 4183437, + "ts": 658971937911.177, "dur": 2.638, + "args": { + "External id": 32255,"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": 4183437, "tid": 4183437, + "ts": 658971937921.003, "dur": 1.543, + "args": { + "External id": 32256,"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": 4183437, "tid": 4183437, + "ts": 658971937950.690, "dur": 5.719, + "args": { + "External id": 32257,"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": 4183437, "tid": 4183437, + "ts": 658971937952.664, "dur": 3.493, + "args": { + "External id": 32258,"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": 4183437, "tid": 4183437, + "ts": 658971938042.287, "dur": 174.494, + "args": { + "External id": 32259,"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": 4183437, "tid": 4183437, + "ts": 658971938044.175, "dur": 1.595, + "args": { + "External id": 32260,"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": 4183437, "tid": 4183437, + "ts": 658971938049.042, "dur": 167.210, + "args": { + "External id": 32261,"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": 4183437, "tid": 4183437, + "ts": 658971938050.307, "dur": 0.309, + "args": { + "External id": 32262,"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": 4183437, "tid": 4183437, + "ts": 658971938051.690, "dur": 20.602, + "args": { + "External id": 32263,"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": 4183437, "tid": 4183437, + "ts": 658971938073.752, "dur": 5.438, + "args": { + "External id": 32264,"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": 4183437, "tid": 4183437, + "ts": 658971938075.990, "dur": 2.880, + "args": { + "External id": 32265,"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": 4183437, "tid": 4183437, + "ts": 658971938079.864, "dur": 21.243, + "args": { + "External id": 32266,"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": 4183437, "tid": 4183437, + "ts": 658971938080.676, "dur": 1.215, + "args": { + "External id": 32267,"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": 4183437, "tid": 4183437, + "ts": 658971938083.045, "dur": 17.714, + "args": { + "External id": 32268,"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": 4183437, "tid": 4183437, + "ts": 658971938085.338, "dur": 2.766, + "args": { + "External id": 32269,"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": 4183437, "tid": 4183437, + "ts": 658971938102.549, "dur": 19.649, + "args": { + "External id": 32270,"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": 4183437, "tid": 4183437, + "ts": 658971938123.525, "dur": 13.850, + "args": { + "External id": 32271,"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": 4183437, "tid": 4183437, + "ts": 658971938140.263, "dur": 13.776, + "args": { + "External id": 32272,"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": 4183437, "tid": 4183437, + "ts": 658971938155.366, "dur": 13.065, + "args": { + "External id": 32273,"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": 4183437, "tid": 4183437, + "ts": 658971938169.905, "dur": 20.493, + "args": { + "External id": 32274,"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": 4183437, "tid": 4183437, + "ts": 658971938171.830, "dur": 1.007, + "args": { + "External id": 32275,"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": 4183437, "tid": 4183437, + "ts": 658971938174.889, "dur": 2.719, + "args": { + "External id": 32276,"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": 4183437, "tid": 4183437, + "ts": 658971938191.987, "dur": 10.707, + "args": { + "External id": 32277,"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": 4183437, "tid": 4183437, + "ts": 658971938203.805, "dur": 11.362, + "args": { + "External id": 32278,"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": 4183437, "tid": 4183437, + "ts": 658971938222.414, "dur": 1.484, + "args": { + "External id": 32279,"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": 4183437, "tid": 4183437, + "ts": 658971938231.900, "dur": 3.109, + "args": { + "External id": 32280,"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": 4183437, "tid": 4183437, + "ts": 658971938233.761, "dur": 0.453, + "args": { + "External id": 32281,"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": 4183437, "tid": 4183437, + "ts": 658971938319.855, "dur": 43.290, + "args": { + "External id": 32282,"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": 4183437, "tid": 4183437, + "ts": 658971938368.338, "dur": 5.344, + "args": { + "External id": 32283,"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": 4183437, "tid": 4183437, + "ts": 658971938371.605, "dur": 0.744, + "args": { + "External id": 32284,"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": 4183437, "tid": 4183437, + "ts": 658971938375.048, "dur": 21.556, + "args": { + "External id": 32285,"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": 4183437, "tid": 4183437, + "ts": 658971938400.808, "dur": 5.488, + "args": { + "External id": 32286,"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": 4183437, "tid": 4183437, + "ts": 658971938402.351, "dur": 3.400, + "args": { + "External id": 32287,"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": 4183437, "tid": 4183437, + "ts": 658971938404.571, "dur": 1.006, + "args": { + "External id": 32288,"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": 4183437, "tid": 4183437, + "ts": 658971938408.610, "dur": 39.777, + "args": { + "External id": 32289,"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": 4183437, "tid": 4183437, + "ts": 658971938409.918, "dur": 37.787, + "args": { + "External id": 32290,"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": 4183437, "tid": 4183437, + "ts": 658971938451.826, "dur": 14.263, + "args": { + "External id": 32291,"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": 4183437, "tid": 4183437, + "ts": 658971938470.422, "dur": 22.192, + "args": { + "External id": 32292,"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": 4183437, "tid": 4183437, + "ts": 658971938473.122, "dur": 19.054, + "args": { + "External id": 32293,"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": 4183437, "tid": 4183437, + "ts": 658971938477.801, "dur": 0.975, + "args": { + "External id": 32294,"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": 4183437, "tid": 4183437, + "ts": 658971938497.806, "dur": 27.383, + "args": { + "External id": 32295,"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": 4183437, "tid": 4183437, + "ts": 658971938502.095, "dur": 22.894, + "args": { + "External id": 32296,"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": 4183437, "tid": 4183437, + "ts": 658971938506.795, "dur": 3.799, + "args": { + "External id": 32297,"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": 4183437, "tid": 4183437, + "ts": 658971938511.809, "dur": 12.602, + "args": { + "External id": 32298,"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": 4183437, "tid": 4183437, + "ts": 658971938539.496, "dur": 5.354, + "args": { + "External id": 32299,"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": 4183437, "tid": 4183437, + "ts": 658971938541.730, "dur": 2.839, + "args": { + "External id": 32300,"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": 4183437, "tid": 4183437, + "ts": 658971938546.003, "dur": 1.707, + "args": { + "External id": 32301,"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": 4183437, "tid": 4183437, + "ts": 658971938547.002, "dur": 0.633, + "args": { + "External id": 32302,"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": 4183437, "tid": 4183437, + "ts": 658971938587.514, "dur": 21.267, + "args": { + "External id": 32303,"Sequence number": 460084, "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": 4183437, "tid": 4183437, + "ts": 658971938610.587, "dur": 14.587, + "args": { + "External id": 32304,"Sequence number": 460085, "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": 4183437, "tid": 4183437, "ts": 658971938610.587, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183437, "tid": 4183437, + "ts": 658971938630.853, "dur": 6.071, + "args": { + "External id": 32305,"Sequence number": 460086, "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": 4183437, "tid": 4183437, + "ts": 658971938634.513, "dur": 1.020, + "args": { + "External id": 32306,"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": 4183437, "tid": 4183437, + "ts": 658971938639.208, "dur": 6.742, + "args": { + "External id": 32307,"Sequence number": 460086, "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": 4183437, "tid": 4183437, + "ts": 658971938643.911, "dur": 0.822, + "args": { + "External id": 32308,"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": 4183437, "tid": 4183437, + "ts": 658971938647.393, "dur": 37.808, + "args": { + "External id": 32309,"Sequence number": 460086, "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": 4183437, "tid": 4183437, + "ts": 658971938649.416, "dur": 0.455, + "args": { + "External id": 32310,"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": 4183437, "tid": 4183437, + "ts": 658971938692.826, "dur": 7.048, + "args": { + "External id": 32311,"Sequence number": 460086, "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": 4183437, "tid": 4183437, "ts": 658971938692.826, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971938696.848, "dur": 1.200, + "args": { + "External id": 32312,"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": 4183437, "tid": 4183437, + "ts": 658971938701.052, "dur": 7.066, + "args": { + "External id": 32313,"Sequence number": 460087, "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": 4183437, "tid": 4183437, "ts": 658971938701.052, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971938706.852, "dur": 0.443, + "args": { + "External id": 32314,"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": 4183437, "tid": 4183437, + "ts": 658971938709.179, "dur": 5.642, + "args": { + "External id": 32315,"Sequence number": 460088, "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": 4183437, "tid": 4183437, "ts": 658971938709.179, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971938713.218, "dur": 0.637, + "args": { + "External id": 32316,"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": 4183437, "tid": 4183437, + "ts": 658971938715.965, "dur": 3.811, + "args": { + "External id": 32317,"Sequence number": 460089, "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": 4183437, "tid": 4183437, "ts": 658971938715.965, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971938718.525, "dur": 0.498, + "args": { + "External id": 32318,"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": 4183437, "tid": 4183437, + "ts": 658971938723.470, "dur": 34.641, + "args": { + "External id": 32319,"Sequence number": 460090, "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": 4183437, "tid": 4183437, + "ts": 658971938725.232, "dur": 32.680, + "args": { + "External id": 32320,"Sequence number": 460090, "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": 4183437, "tid": 4183437, + "ts": 658971938727.809, "dur": 7.082, + "args": { + "External id": 32321,"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": 4183437, "tid": 4183437, + "ts": 658971938730.470, "dur": 3.793, + "args": { + "External id": 32322,"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": 4183437, "tid": 4183437, + "ts": 658971938735.667, "dur": 21.792, + "args": { + "External id": 32323,"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": 4183437, "tid": 4183437, + "ts": 658971938784.935, "dur": 5.929, + "args": { + "External id": 32324,"Sequence number": 460090, "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": 4183437, "tid": 4183437, "ts": 658971938784.935, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971938793.737, "dur": 0.849, + "args": { + "External id": 32325,"Sequence number": 460091, "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": 4183437, "tid": 4183437, + "ts": 658971938824.954, "dur": 24310.635, + "args": { + "External id": 32326,"Sequence number": 460091, "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": 4183437, "tid": 4183437, "ts": 658971938824.954, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183437, "tid": 4183437, + "ts": 658971938841.067, "dur": 26.937, + "args": { + "External id": 32327,"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": 4183437, "tid": 4183437, + "ts": 658971938841.735, "dur": 26.059, + "args": { + "External id": 32328,"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": 4183437, "tid": 4183437, + "ts": 658971938843.397, "dur": 5.508, + "args": { + "External id": 32329,"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": 4183437, "tid": 4183437, + "ts": 658971938844.930, "dur": 3.485, + "args": { + "External id": 32330,"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": 4183437, "tid": 4183437, + "ts": 658971938849.815, "dur": 17.594, + "args": { + "External id": 32331,"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": 4183437, "tid": 4183437, + "ts": 658971938882.424, "dur": 27.297, + "args": { + "External id": 32332,"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": 4183437, "tid": 4183437, + "ts": 658971938883.570, "dur": 6.837, + "args": { + "External id": 32333,"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": 4183437, "tid": 4183437, + "ts": 658971938886.461, "dur": 3.627, + "args": { + "External id": 32334,"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": 4183437, "tid": 4183437, + "ts": 658971938891.812, "dur": 17.695, + "args": { + "External id": 32335,"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": 4183437, "tid": 4183437, + "ts": 658971938893.576, "dur": 15.466, + "args": { + "External id": 32336,"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": 4183437, "tid": 4183437, + "ts": 658971938913.435, "dur": 20.386, + "args": { + "External id": 32337,"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": 4183437, "tid": 4183437, + "ts": 658971938914.487, "dur": 4.242, + "args": { + "External id": 32338,"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": 4183437, "tid": 4183437, + "ts": 658971938916.119, "dur": 2.379, + "args": { + "External id": 32339,"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": 4183437, "tid": 4183437, + "ts": 658971938919.399, "dur": 14.225, + "args": { + "External id": 32340,"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": 4183437, "tid": 4183437, + "ts": 658971938920.079, "dur": 13.233, + "args": { + "External id": 32341,"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": 4183437, "tid": 4183437, + "ts": 658971938939.593, "dur": 20.181, + "args": { + "External id": 32342,"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": 4183437, "tid": 4183437, + "ts": 658971938943.623, "dur": 2.075, + "args": { + "External id": 32343,"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": 4183437, "tid": 4183437, + "ts": 658971938946.321, "dur": 13.211, + "args": { + "External id": 32344,"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": 4183437, "tid": 4183437, + "ts": 658971938947.105, "dur": 12.071, + "args": { + "External id": 32345,"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": 4183437, "tid": 4183437, + "ts": 658971938965.130, "dur": 22.237, + "args": { + "External id": 32346,"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": 4183437, "tid": 4183437, + "ts": 658971938990.073, "dur": 50.963, + "args": { + "External id": 32347,"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": 4183437, "tid": 4183437, + "ts": 658971938991.978, "dur": 48.559, + "args": { + "External id": 32348,"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": 4183437, "tid": 4183437, + "ts": 658971938997.060, "dur": 1.310, + "args": { + "External id": 32349,"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": 4183437, "tid": 4183437, + "ts": 658971939000.018, "dur": 24.152, + "args": { + "External id": 32350,"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": 4183437, "tid": 4183437, + "ts": 658971939001.572, "dur": 22.415, + "args": { + "External id": 32351,"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": 4183437, "tid": 4183437, + "ts": 658971939005.460, "dur": 2.407, + "args": { + "External id": 32352,"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": 4183437, "tid": 4183437, + "ts": 658971939008.569, "dur": 14.963, + "args": { + "External id": 32353,"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": 4183437, "tid": 4183437, + "ts": 658971939044.806, "dur": 18766.835, + "args": { + "External id": 32354,"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": 4183437, "tid": 4183437, + "ts": 658971939046.795, "dur": 18763.531, + "args": { + "External id": 32355,"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": 4183437, "tid": 4183437, + "ts": 658971957822.020, "dur": 8.913, + "args": { + "External id": 32356,"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": 4183437, "tid": 4183437, + "ts": 658971957828.423, "dur": 0.920, + "args": { + "External id": 32357,"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": 4183437, "tid": 4183437, + "ts": 658971957835.956, "dur": 100.010, + "args": { + "External id": 32358,"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": 4183437, "tid": 4183437, + "ts": 658971957837.458, "dur": 6.252, + "args": { + "External id": 32359,"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": 4183437, "tid": 4183437, + "ts": 658971957839.619, "dur": 3.250, + "args": { + "External id": 32360,"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": 4183437, "tid": 4183437, + "ts": 658971957841.702, "dur": 0.897, + "args": { + "External id": 32361,"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": 4183437, "tid": 4183437, + "ts": 658971957844.804, "dur": 90.383, + "args": { + "External id": 32362,"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": 4183437, "tid": 4183437, + "ts": 658971957846.406, "dur": 87.822, + "args": { + "External id": 32363,"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": 4183437, "tid": 4183437, + "ts": 658971957939.441, "dur": 4.565, + "args": { + "External id": 32364,"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": 4183437, "tid": 4183437, + "ts": 658971957942.029, "dur": 0.735, + "args": { + "External id": 32365,"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": 4183437, "tid": 4183437, + "ts": 658971957950.839, "dur": 2.367, + "args": { + "External id": 32366,"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": 4183437, "tid": 4183437, + "ts": 658971957962.115, "dur": 6.068, + "args": { + "External id": 32367,"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": 4183437, "tid": 4183437, + "ts": 658971957964.414, "dur": 3.488, + "args": { + "External id": 32368,"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": 4183437, "tid": 4183437, + "ts": 658971958095.211, "dur": 218.404, + "args": { + "External id": 32369,"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": 4183437, "tid": 4183437, + "ts": 658971958097.923, "dur": 2.003, + "args": { + "External id": 32370,"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": 4183437, "tid": 4183437, + "ts": 658971958103.775, "dur": 209.249, + "args": { + "External id": 32371,"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": 4183437, "tid": 4183437, + "ts": 658971958105.733, "dur": 0.540, + "args": { + "External id": 32372,"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": 4183437, "tid": 4183437, + "ts": 658971958107.989, "dur": 26.067, + "args": { + "External id": 32373,"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": 4183437, "tid": 4183437, + "ts": 658971958135.987, "dur": 5.204, + "args": { + "External id": 32374,"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": 4183437, "tid": 4183437, + "ts": 658971958138.165, "dur": 2.690, + "args": { + "External id": 32375,"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": 4183437, "tid": 4183437, + "ts": 658971958142.314, "dur": 23.715, + "args": { + "External id": 32376,"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": 4183437, "tid": 4183437, + "ts": 658971958143.434, "dur": 1.017, + "args": { + "External id": 32377,"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": 4183437, "tid": 4183437, + "ts": 658971958145.830, "dur": 19.865, + "args": { + "External id": 32378,"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": 4183437, "tid": 4183437, + "ts": 658971958149.018, "dur": 3.052, + "args": { + "External id": 32379,"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": 4183437, "tid": 4183437, + "ts": 658971958167.905, "dur": 22.848, + "args": { + "External id": 32380,"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": 4183437, "tid": 4183437, + "ts": 658971958192.876, "dur": 15.291, + "args": { + "External id": 32381,"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": 4183437, "tid": 4183437, + "ts": 658971958211.021, "dur": 15.018, + "args": { + "External id": 32382,"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": 4183437, "tid": 4183437, + "ts": 658971958227.734, "dur": 14.461, + "args": { + "External id": 32383,"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": 4183437, "tid": 4183437, + "ts": 658971958244.129, "dur": 36.676, + "args": { + "External id": 32384,"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": 4183437, "tid": 4183437, + "ts": 658971958246.460, "dur": 1.404, + "args": { + "External id": 32385,"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": 4183437, "tid": 4183437, + "ts": 658971958250.396, "dur": 0.622, + "args": { + "External id": 32386,"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": 4183437, "tid": 4183437, + "ts": 658971958283.665, "dur": 14.536, + "args": { + "External id": 32387,"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": 4183437, "tid": 4183437, + "ts": 658971958299.742, "dur": 12.396, + "args": { + "External id": 32388,"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": 4183437, "tid": 4183437, + "ts": 658971958321.535, "dur": 2.452, + "args": { + "External id": 32389,"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": 4183437, "tid": 4183437, + "ts": 658971958331.338, "dur": 3.735, + "args": { + "External id": 32390,"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": 4183437, "tid": 4183437, + "ts": 658971958333.597, "dur": 0.508, + "args": { + "External id": 32391,"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": 4183437, "tid": 4183437, + "ts": 658971958413.866, "dur": 57.385, + "args": { + "External id": 32392,"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": 4183437, "tid": 4183437, + "ts": 658971958476.210, "dur": 8.503, + "args": { + "External id": 32393,"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": 4183437, "tid": 4183437, + "ts": 658971958479.155, "dur": 2.747, + "args": { + "External id": 32394,"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": 4183437, "tid": 4183437, + "ts": 658971958486.548, "dur": 24.817, + "args": { + "External id": 32395,"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": 4183437, "tid": 4183437, + "ts": 658971958516.520, "dur": 5.861, + "args": { + "External id": 32396,"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": 4183437, "tid": 4183437, + "ts": 658971958518.322, "dur": 3.363, + "args": { + "External id": 32397,"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": 4183437, "tid": 4183437, + "ts": 658971958520.511, "dur": 0.919, + "args": { + "External id": 32398,"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": 4183437, "tid": 4183437, + "ts": 658971958525.969, "dur": 44.573, + "args": { + "External id": 32399,"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": 4183437, "tid": 4183437, + "ts": 658971958527.078, "dur": 42.948, + "args": { + "External id": 32400,"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": 4183437, "tid": 4183437, + "ts": 658971958574.645, "dur": 14.893, + "args": { + "External id": 32401,"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": 4183437, "tid": 4183437, + "ts": 658971958595.942, "dur": 4.085, + "args": { + "External id": 32402,"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": 4183437, "tid": 4183437, + "ts": 658971958598.290, "dur": 0.758, + "args": { + "External id": 32403,"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": 4183437, "tid": 4183437, + "ts": 658971958604.979, "dur": 81.236, + "args": { + "External id": 32404,"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": 4183437, "tid": 4183437, + "ts": 658971958606.217, "dur": 4.020, + "args": { + "External id": 32405,"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": 4183437, "tid": 4183437, + "ts": 658971958607.174, "dur": 2.257, + "args": { + "External id": 32406,"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": 4183437, "tid": 4183437, + "ts": 658971958608.756, "dur": 0.530, + "args": { + "External id": 32407,"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": 4183437, "tid": 4183437, + "ts": 658971958610.834, "dur": 40.533, + "args": { + "External id": 32408,"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": 4183437, "tid": 4183437, + "ts": 658971958611.472, "dur": 39.255, + "args": { + "External id": 32409,"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": 4183437, "tid": 4183437, + "ts": 658971958693.726, "dur": 4.877, + "args": { + "External id": 32410,"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": 4183437, "tid": 4183437, + "ts": 658971958696.398, "dur": 0.893, + "args": { + "External id": 32411,"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": 4183437, "tid": 4183437, + "ts": 658971958705.764, "dur": 1.807, + "args": { + "External id": 32412,"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": 4183437, "tid": 4183437, + "ts": 658971958715.719, "dur": 6.796, + "args": { + "External id": 32413,"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": 4183437, "tid": 4183437, + "ts": 658971958718.177, "dur": 4.092, + "args": { + "External id": 32414,"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": 4183437, "tid": 4183437, + "ts": 658971958820.958, "dur": 180.788, + "args": { + "External id": 32415,"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": 4183437, "tid": 4183437, + "ts": 658971958822.874, "dur": 4.125, + "args": { + "External id": 32416,"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": 4183437, "tid": 4183437, + "ts": 658971958828.600, "dur": 172.717, + "args": { + "External id": 32417,"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": 4183437, "tid": 4183437, + "ts": 658971958830.446, "dur": 0.461, + "args": { + "External id": 32418,"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": 4183437, "tid": 4183437, + "ts": 658971958832.402, "dur": 21.777, + "args": { + "External id": 32419,"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": 4183437, "tid": 4183437, + "ts": 658971958856.205, "dur": 5.653, + "args": { + "External id": 32420,"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": 4183437, "tid": 4183437, + "ts": 658971958860.768, "dur": 0.815, + "args": { + "External id": 32421,"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": 4183437, "tid": 4183437, + "ts": 658971958863.085, "dur": 23.964, + "args": { + "External id": 32422,"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": 4183437, "tid": 4183437, + "ts": 658971958864.421, "dur": 1.020, + "args": { + "External id": 32423,"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": 4183437, "tid": 4183437, + "ts": 658971958870.253, "dur": 16.509, + "args": { + "External id": 32424,"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": 4183437, "tid": 4183437, + "ts": 658971958872.861, "dur": 2.475, + "args": { + "External id": 32425,"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": 4183437, "tid": 4183437, + "ts": 658971958888.769, "dur": 20.290, + "args": { + "External id": 32426,"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": 4183437, "tid": 4183437, + "ts": 658971958910.732, "dur": 12.744, + "args": { + "External id": 32427,"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": 4183437, "tid": 4183437, + "ts": 658971958926.119, "dur": 12.968, + "args": { + "External id": 32428,"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": 4183437, "tid": 4183437, + "ts": 658971958940.967, "dur": 11.889, + "args": { + "External id": 32429,"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": 4183437, "tid": 4183437, + "ts": 658971958954.676, "dur": 20.391, + "args": { + "External id": 32430,"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": 4183437, "tid": 4183437, + "ts": 658971958958.778, "dur": 1.275, + "args": { + "External id": 32431,"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": 4183437, "tid": 4183437, + "ts": 658971958961.854, "dur": 0.858, + "args": { + "External id": 32432,"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": 4183437, "tid": 4183437, + "ts": 658971958976.940, "dur": 11.325, + "args": { + "External id": 32433,"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": 4183437, "tid": 4183437, + "ts": 658971958989.345, "dur": 11.102, + "args": { + "External id": 32434,"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": 4183437, "tid": 4183437, + "ts": 658971959008.058, "dur": 1.941, + "args": { + "External id": 32435,"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": 4183437, "tid": 4183437, + "ts": 658971959019.040, "dur": 3.589, + "args": { + "External id": 32436,"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": 4183437, "tid": 4183437, + "ts": 658971959021.237, "dur": 0.370, + "args": { + "External id": 32437,"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": 4183437, "tid": 4183437, + "ts": 658971959089.583, "dur": 52.061, + "args": { + "External id": 32438,"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": 4183437, "tid": 4183437, + "ts": 658971959146.478, "dur": 5.299, + "args": { + "External id": 32439,"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": 4183437, "tid": 4183437, + "ts": 658971959149.943, "dur": 0.801, + "args": { + "External id": 32440,"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": 4183437, "tid": 4183437, + "ts": 658971959153.484, "dur": 28.659, + "args": { + "External id": 32441,"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": 4183437, "tid": 4183437, + "ts": 658971959186.729, "dur": 6.153, + "args": { + "External id": 32442,"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": 4183437, "tid": 4183437, + "ts": 658971959188.784, "dur": 3.433, + "args": { + "External id": 32443,"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": 4183437, "tid": 4183437, + "ts": 658971959190.900, "dur": 1.115, + "args": { + "External id": 32444,"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": 4183437, "tid": 4183437, + "ts": 658971959195.751, "dur": 62.471, + "args": { + "External id": 32445,"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": 4183437, "tid": 4183437, + "ts": 658971959196.899, "dur": 60.747, + "args": { + "External id": 32446,"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": 4183437, "tid": 4183437, + "ts": 658971959277.638, "dur": 18.033, + "args": { + "External id": 32447,"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": 4183437, "tid": 4183437, + "ts": 658971959303.022, "dur": 5.092, + "args": { + "External id": 32448,"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": 4183437, "tid": 4183437, + "ts": 658971959305.934, "dur": 1.027, + "args": { + "External id": 32449,"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": 4183437, "tid": 4183437, + "ts": 658971959312.924, "dur": 52.169, + "args": { + "External id": 32450,"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": 4183437, "tid": 4183437, + "ts": 658971959313.713, "dur": 4.443, + "args": { + "External id": 32451,"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": 4183437, "tid": 4183437, + "ts": 658971959315.256, "dur": 2.283, + "args": { + "External id": 32452,"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": 4183437, "tid": 4183437, + "ts": 658971959316.707, "dur": 0.678, + "args": { + "External id": 32453,"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": 4183437, "tid": 4183437, + "ts": 658971959318.788, "dur": 45.820, + "args": { + "External id": 32454,"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": 4183437, "tid": 4183437, + "ts": 658971959319.823, "dur": 44.190, + "args": { + "External id": 32455,"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": 4183437, "tid": 4183437, + "ts": 658971959369.436, "dur": 3.532, + "args": { + "External id": 32456,"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": 4183437, "tid": 4183437, + "ts": 658971959371.307, "dur": 0.586, + "args": { + "External id": 32457,"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": 4183437, "tid": 4183437, + "ts": 658971959378.866, "dur": 1.833, + "args": { + "External id": 32458,"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": 4183437, "tid": 4183437, + "ts": 658971959388.475, "dur": 5.606, + "args": { + "External id": 32459,"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": 4183437, "tid": 4183437, + "ts": 658971959390.551, "dur": 3.307, + "args": { + "External id": 32460,"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": 4183437, "tid": 4183437, + "ts": 658971959478.894, "dur": 166.456, + "args": { + "External id": 32461,"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": 4183437, "tid": 4183437, + "ts": 658971959482.872, "dur": 2.143, + "args": { + "External id": 32462,"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": 4183437, "tid": 4183437, + "ts": 658971959486.292, "dur": 158.465, + "args": { + "External id": 32463,"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": 4183437, "tid": 4183437, + "ts": 658971959487.799, "dur": 0.443, + "args": { + "External id": 32464,"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": 4183437, "tid": 4183437, + "ts": 658971959489.844, "dur": 18.895, + "args": { + "External id": 32465,"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": 4183437, "tid": 4183437, + "ts": 658971959510.374, "dur": 5.020, + "args": { + "External id": 32466,"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": 4183437, "tid": 4183437, + "ts": 658971959514.392, "dur": 0.777, + "args": { + "External id": 32467,"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": 4183437, "tid": 4183437, + "ts": 658971959516.230, "dur": 18.813, + "args": { + "External id": 32468,"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": 4183437, "tid": 4183437, + "ts": 658971959517.357, "dur": 1.169, + "args": { + "External id": 32469,"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": 4183437, "tid": 4183437, + "ts": 658971959519.490, "dur": 15.236, + "args": { + "External id": 32470,"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": 4183437, "tid": 4183437, + "ts": 658971959521.788, "dur": 2.080, + "args": { + "External id": 32471,"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": 4183437, "tid": 4183437, + "ts": 658971959536.404, "dur": 17.679, + "args": { + "External id": 32472,"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": 4183437, "tid": 4183437, + "ts": 658971959555.583, "dur": 15.498, + "args": { + "External id": 32473,"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": 4183437, "tid": 4183437, + "ts": 658971959573.679, "dur": 11.915, + "args": { + "External id": 32474,"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": 4183437, "tid": 4183437, + "ts": 658971959586.907, "dur": 11.812, + "args": { + "External id": 32475,"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": 4183437, "tid": 4183437, + "ts": 658971959600.722, "dur": 17.934, + "args": { + "External id": 32476,"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": 4183437, "tid": 4183437, + "ts": 658971959602.406, "dur": 0.936, + "args": { + "External id": 32477,"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": 4183437, "tid": 4183437, + "ts": 658971959605.841, "dur": 0.455, + "args": { + "External id": 32478,"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": 4183437, "tid": 4183437, + "ts": 658971959619.961, "dur": 11.554, + "args": { + "External id": 32479,"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": 4183437, "tid": 4183437, + "ts": 658971959632.929, "dur": 10.711, + "args": { + "External id": 32480,"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": 4183437, "tid": 4183437, + "ts": 658971959686.302, "dur": 2.685, + "args": { + "External id": 32481,"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": 4183437, "tid": 4183437, + "ts": 658971959700.632, "dur": 4.148, + "args": { + "External id": 32482,"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": 4183437, "tid": 4183437, + "ts": 658971959703.149, "dur": 0.664, + "args": { + "External id": 32483,"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": 4183437, "tid": 4183437, + "ts": 658971959774.761, "dur": 45.624, + "args": { + "External id": 32484,"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": 4183437, "tid": 4183437, + "ts": 658971959825.315, "dur": 4.211, + "args": { + "External id": 32485,"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": 4183437, "tid": 4183437, + "ts": 658971959827.837, "dur": 0.681, + "args": { + "External id": 32486,"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": 4183437, "tid": 4183437, + "ts": 658971959831.118, "dur": 22.816, + "args": { + "External id": 32487,"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": 4183437, "tid": 4183437, + "ts": 658971959858.154, "dur": 5.411, + "args": { + "External id": 32488,"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": 4183437, "tid": 4183437, + "ts": 658971959859.710, "dur": 3.285, + "args": { + "External id": 32489,"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": 4183437, "tid": 4183437, + "ts": 658971959861.729, "dur": 1.062, + "args": { + "External id": 32490,"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": 4183437, "tid": 4183437, + "ts": 658971959866.411, "dur": 40.563, + "args": { + "External id": 32491,"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": 4183437, "tid": 4183437, + "ts": 658971959867.571, "dur": 38.906, + "args": { + "External id": 32492,"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": 4183437, "tid": 4183437, + "ts": 658971959910.631, "dur": 14.513, + "args": { + "External id": 32493,"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": 4183437, "tid": 4183437, + "ts": 658971959930.285, "dur": 3.623, + "args": { + "External id": 32494,"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": 4183437, "tid": 4183437, + "ts": 658971959932.657, "dur": 0.448, + "args": { + "External id": 32495,"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": 4183437, "tid": 4183437, + "ts": 658971959937.870, "dur": 45.745, + "args": { + "External id": 32496,"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": 4183437, "tid": 4183437, + "ts": 658971959938.698, "dur": 3.517, + "args": { + "External id": 32497,"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": 4183437, "tid": 4183437, + "ts": 658971959939.388, "dur": 2.236, + "args": { + "External id": 32498,"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": 4183437, "tid": 4183437, + "ts": 658971959940.978, "dur": 0.527, + "args": { + "External id": 32499,"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": 4183437, "tid": 4183437, + "ts": 658971959942.769, "dur": 40.405, + "args": { + "External id": 32500,"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": 4183437, "tid": 4183437, + "ts": 658971959943.416, "dur": 39.149, + "args": { + "External id": 32501,"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": 4183437, "tid": 4183437, + "ts": 658971959987.301, "dur": 3.383, + "args": { + "External id": 32502,"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": 4183437, "tid": 4183437, + "ts": 658971959989.138, "dur": 0.498, + "args": { + "External id": 32503,"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": 4183437, "tid": 4183437, + "ts": 658971959996.246, "dur": 1.285, + "args": { + "External id": 32504,"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": 4183437, "tid": 4183437, + "ts": 658971960004.682, "dur": 7.491, + "args": { + "External id": 32505,"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": 4183437, "tid": 4183437, + "ts": 658971960006.636, "dur": 5.261, + "args": { + "External id": 32506,"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": 4183437, "tid": 4183437, + "ts": 658971960090.610, "dur": 164.104, + "args": { + "External id": 32507,"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": 4183437, "tid": 4183437, + "ts": 658971960092.327, "dur": 1.984, + "args": { + "External id": 32508,"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": 4183437, "tid": 4183437, + "ts": 658971960095.637, "dur": 158.383, + "args": { + "External id": 32509,"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": 4183437, "tid": 4183437, + "ts": 658971960097.413, "dur": 0.317, + "args": { + "External id": 32510,"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": 4183437, "tid": 4183437, + "ts": 658971960099.016, "dur": 20.597, + "args": { + "External id": 32511,"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": 4183437, "tid": 4183437, + "ts": 658971960121.080, "dur": 3.183, + "args": { + "External id": 32512,"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": 4183437, "tid": 4183437, + "ts": 658971960123.541, "dur": 0.513, + "args": { + "External id": 32513,"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": 4183437, "tid": 4183437, + "ts": 658971960125.233, "dur": 21.192, + "args": { + "External id": 32514,"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": 4183437, "tid": 4183437, + "ts": 658971960125.973, "dur": 1.296, + "args": { + "External id": 32515,"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": 4183437, "tid": 4183437, + "ts": 658971960128.433, "dur": 17.696, + "args": { + "External id": 32516,"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": 4183437, "tid": 4183437, + "ts": 658971960132.836, "dur": 2.475, + "args": { + "External id": 32517,"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": 4183437, "tid": 4183437, + "ts": 658971960147.917, "dur": 19.322, + "args": { + "External id": 32518,"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": 4183437, "tid": 4183437, + "ts": 658971960168.686, "dur": 12.057, + "args": { + "External id": 32519,"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": 4183437, "tid": 4183437, + "ts": 658971960183.320, "dur": 12.491, + "args": { + "External id": 32520,"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": 4183437, "tid": 4183437, + "ts": 658971960197.287, "dur": 11.771, + "args": { + "External id": 32521,"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": 4183437, "tid": 4183437, + "ts": 658971960210.903, "dur": 17.498, + "args": { + "External id": 32522,"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": 4183437, "tid": 4183437, + "ts": 658971960212.746, "dur": 1.086, + "args": { + "External id": 32523,"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": 4183437, "tid": 4183437, + "ts": 658971960215.745, "dur": 0.697, + "args": { + "External id": 32524,"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": 4183437, "tid": 4183437, + "ts": 658971960230.101, "dur": 10.935, + "args": { + "External id": 32525,"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": 4183437, "tid": 4183437, + "ts": 658971960242.044, "dur": 11.112, + "args": { + "External id": 32526,"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": 4183437, "tid": 4183437, + "ts": 658971960260.606, "dur": 16.797, + "args": { + "External id": 32527,"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": 4183437, "tid": 4183437, + "ts": 658971960288.368, "dur": 4.117, + "args": { + "External id": 32528,"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": 4183437, "tid": 4183437, + "ts": 658971960290.998, "dur": 0.643, + "args": { + "External id": 32529,"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": 4183437, "tid": 4183437, + "ts": 658971960356.145, "dur": 43.050, + "args": { + "External id": 32530,"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": 4183437, "tid": 4183437, + "ts": 658971960403.689, "dur": 4.173, + "args": { + "External id": 32531,"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": 4183437, "tid": 4183437, + "ts": 658971960406.276, "dur": 0.735, + "args": { + "External id": 32532,"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": 4183437, "tid": 4183437, + "ts": 658971960409.234, "dur": 22.436, + "args": { + "External id": 32533,"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": 4183437, "tid": 4183437, + "ts": 658971960435.823, "dur": 4.881, + "args": { + "External id": 32534,"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": 4183437, "tid": 4183437, + "ts": 658971960437.175, "dur": 2.958, + "args": { + "External id": 32535,"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": 4183437, "tid": 4183437, + "ts": 658971960439.079, "dur": 0.861, + "args": { + "External id": 32536,"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": 4183437, "tid": 4183437, + "ts": 658971960443.322, "dur": 39.758, + "args": { + "External id": 32537,"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": 4183437, "tid": 4183437, + "ts": 658971960444.444, "dur": 38.077, + "args": { + "External id": 32538,"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": 4183437, "tid": 4183437, + "ts": 658971960486.494, "dur": 13.745, + "args": { + "External id": 32539,"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": 4183437, "tid": 4183437, + "ts": 658971960505.092, "dur": 3.656, + "args": { + "External id": 32540,"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": 4183437, "tid": 4183437, + "ts": 658971960507.417, "dur": 0.444, + "args": { + "External id": 32541,"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": 4183437, "tid": 4183437, + "ts": 658971960512.472, "dur": 48.004, + "args": { + "External id": 32542,"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": 4183437, "tid": 4183437, + "ts": 658971960513.257, "dur": 4.140, + "args": { + "External id": 32543,"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": 4183437, "tid": 4183437, + "ts": 658971960513.851, "dur": 2.984, + "args": { + "External id": 32544,"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": 4183437, "tid": 4183437, + "ts": 658971960516.146, "dur": 0.533, + "args": { + "External id": 32545,"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": 4183437, "tid": 4183437, + "ts": 658971960520.673, "dur": 39.383, + "args": { + "External id": 32546,"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": 4183437, "tid": 4183437, + "ts": 658971960521.347, "dur": 38.186, + "args": { + "External id": 32547,"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": 4183437, "tid": 4183437, + "ts": 658971960564.015, "dur": 5.404, + "args": { + "External id": 32548,"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": 4183437, "tid": 4183437, + "ts": 658971960565.781, "dur": 2.551, + "args": { + "External id": 32549,"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": 4183437, "tid": 4183437, + "ts": 658971960574.357, "dur": 1.401, + "args": { + "External id": 32550,"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": 4183437, "tid": 4183437, + "ts": 658971960582.618, "dur": 4.972, + "args": { + "External id": 32551,"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": 4183437, "tid": 4183437, + "ts": 658971960584.297, "dur": 3.058, + "args": { + "External id": 32552,"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": 4183437, "tid": 4183437, + "ts": 658971960699.088, "dur": 171.726, + "args": { + "External id": 32553,"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": 4183437, "tid": 4183437, + "ts": 658971960701.388, "dur": 3.101, + "args": { + "External id": 32554,"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": 4183437, "tid": 4183437, + "ts": 658971960706.243, "dur": 164.165, + "args": { + "External id": 32555,"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": 4183437, "tid": 4183437, + "ts": 658971960707.670, "dur": 0.503, + "args": { + "External id": 32556,"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": 4183437, "tid": 4183437, + "ts": 658971960709.690, "dur": 23.740, + "args": { + "External id": 32557,"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": 4183437, "tid": 4183437, + "ts": 658971960734.707, "dur": 3.956, + "args": { + "External id": 32558,"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": 4183437, "tid": 4183437, + "ts": 658971960737.469, "dur": 0.888, + "args": { + "External id": 32559,"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": 4183437, "tid": 4183437, + "ts": 658971960739.503, "dur": 21.375, + "args": { + "External id": 32560,"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": 4183437, "tid": 4183437, + "ts": 658971960740.563, "dur": 1.169, + "args": { + "External id": 32561,"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": 4183437, "tid": 4183437, + "ts": 658971960742.656, "dur": 17.837, + "args": { + "External id": 32562,"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": 4183437, "tid": 4183437, + "ts": 658971960746.988, "dur": 2.157, + "args": { + "External id": 32563,"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": 4183437, "tid": 4183437, + "ts": 658971960762.285, "dur": 18.778, + "args": { + "External id": 32564,"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": 4183437, "tid": 4183437, + "ts": 658971960782.633, "dur": 12.646, + "args": { + "External id": 32565,"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": 4183437, "tid": 4183437, + "ts": 658971960797.405, "dur": 12.005, + "args": { + "External id": 32566,"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": 4183437, "tid": 4183437, + "ts": 658971960810.890, "dur": 11.871, + "args": { + "External id": 32567,"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": 4183437, "tid": 4183437, + "ts": 658971960824.459, "dur": 18.060, + "args": { + "External id": 32568,"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": 4183437, "tid": 4183437, + "ts": 658971960826.376, "dur": 0.979, + "args": { + "External id": 32569,"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": 4183437, "tid": 4183437, + "ts": 658971960829.576, "dur": 0.736, + "args": { + "External id": 32570,"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": 4183437, "tid": 4183437, + "ts": 658971960844.339, "dur": 11.617, + "args": { + "External id": 32571,"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": 4183437, "tid": 4183437, + "ts": 658971960857.077, "dur": 12.435, + "args": { + "External id": 32572,"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": 4183437, "tid": 4183437, + "ts": 658971960876.809, "dur": 1.954, + "args": { + "External id": 32573,"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": 4183437, "tid": 4183437, + "ts": 658971960887.959, "dur": 3.178, + "args": { + "External id": 32574,"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": 4183437, "tid": 4183437, + "ts": 658971960890.086, "dur": 0.348, + "args": { + "External id": 32575,"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": 4183437, "tid": 4183437, + "ts": 658971960959.896, "dur": 45.084, + "args": { + "External id": 32576,"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": 4183437, "tid": 4183437, + "ts": 658971961010.060, "dur": 5.265, + "args": { + "External id": 32577,"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": 4183437, "tid": 4183437, + "ts": 658971961013.284, "dur": 1.012, + "args": { + "External id": 32578,"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": 4183437, "tid": 4183437, + "ts": 658971961016.576, "dur": 23.458, + "args": { + "External id": 32579,"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": 4183437, "tid": 4183437, + "ts": 658971961044.389, "dur": 5.548, + "args": { + "External id": 32580,"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": 4183437, "tid": 4183437, + "ts": 658971961045.914, "dur": 3.191, + "args": { + "External id": 32581,"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": 4183437, "tid": 4183437, + "ts": 658971961048.039, "dur": 0.861, + "args": { + "External id": 32582,"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": 4183437, "tid": 4183437, + "ts": 658971961052.424, "dur": 39.710, + "args": { + "External id": 32583,"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": 4183437, "tid": 4183437, + "ts": 658971961053.323, "dur": 38.268, + "args": { + "External id": 32584,"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": 4183437, "tid": 4183437, + "ts": 658971961096.056, "dur": 13.955, + "args": { + "External id": 32585,"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": 4183437, "tid": 4183437, + "ts": 658971961115.071, "dur": 4.029, + "args": { + "External id": 32586,"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": 4183437, "tid": 4183437, + "ts": 658971961117.630, "dur": 0.606, + "args": { + "External id": 32587,"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": 4183437, "tid": 4183437, + "ts": 658971961122.983, "dur": 48.025, + "args": { + "External id": 32588,"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": 4183437, "tid": 4183437, + "ts": 658971961123.778, "dur": 6.232, + "args": { + "External id": 32589,"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": 4183437, "tid": 4183437, + "ts": 658971961124.616, "dur": 4.722, + "args": { + "External id": 32590,"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": 4183437, "tid": 4183437, + "ts": 658971961128.698, "dur": 0.521, + "args": { + "External id": 32591,"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": 4183437, "tid": 4183437, + "ts": 658971961130.738, "dur": 39.782, + "args": { + "External id": 32592,"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": 4183437, "tid": 4183437, + "ts": 658971961131.240, "dur": 38.511, + "args": { + "External id": 32593,"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": 4183437, "tid": 4183437, + "ts": 658971961175.115, "dur": 3.820, + "args": { + "External id": 32594,"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": 4183437, "tid": 4183437, + "ts": 658971961177.309, "dur": 0.545, + "args": { + "External id": 32595,"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": 4183437, "tid": 4183437, + "ts": 658971961184.325, "dur": 1.406, + "args": { + "External id": 32596,"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": 4183437, "tid": 4183437, + "ts": 658971961192.954, "dur": 5.103, + "args": { + "External id": 32597,"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": 4183437, "tid": 4183437, + "ts": 658971961194.734, "dur": 3.048, + "args": { + "External id": 32598,"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": 4183437, "tid": 4183437, + "ts": 658971961295.442, "dur": 176.788, + "args": { + "External id": 32599,"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": 4183437, "tid": 4183437, + "ts": 658971961297.503, "dur": 2.837, + "args": { + "External id": 32600,"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": 4183437, "tid": 4183437, + "ts": 658971961301.863, "dur": 169.957, + "args": { + "External id": 32601,"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": 4183437, "tid": 4183437, + "ts": 658971961306.397, "dur": 0.249, + "args": { + "External id": 32602,"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": 4183437, "tid": 4183437, + "ts": 658971961307.688, "dur": 21.257, + "args": { + "External id": 32603,"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": 4183437, "tid": 4183437, + "ts": 658971961330.487, "dur": 3.745, + "args": { + "External id": 32604,"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": 4183437, "tid": 4183437, + "ts": 658971961333.373, "dur": 0.613, + "args": { + "External id": 32605,"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": 4183437, "tid": 4183437, + "ts": 658971961335.086, "dur": 21.720, + "args": { + "External id": 32606,"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": 4183437, "tid": 4183437, + "ts": 658971961338.282, "dur": 0.871, + "args": { + "External id": 32607,"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": 4183437, "tid": 4183437, + "ts": 658971961340.258, "dur": 16.243, + "args": { + "External id": 32608,"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": 4183437, "tid": 4183437, + "ts": 658971961343.114, "dur": 2.405, + "args": { + "External id": 32609,"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": 4183437, "tid": 4183437, + "ts": 658971961358.461, "dur": 20.021, + "args": { + "External id": 32610,"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": 4183437, "tid": 4183437, + "ts": 658971961379.893, "dur": 12.103, + "args": { + "External id": 32611,"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": 4183437, "tid": 4183437, + "ts": 658971961394.788, "dur": 12.847, + "args": { + "External id": 32612,"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": 4183437, "tid": 4183437, + "ts": 658971961409.305, "dur": 12.060, + "args": { + "External id": 32613,"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": 4183437, "tid": 4183437, + "ts": 658971961423.074, "dur": 19.827, + "args": { + "External id": 32614,"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": 4183437, "tid": 4183437, + "ts": 658971961425.219, "dur": 1.003, + "args": { + "External id": 32615,"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": 4183437, "tid": 4183437, + "ts": 658971961428.732, "dur": 0.559, + "args": { + "External id": 32616,"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": 4183437, "tid": 4183437, + "ts": 658971961444.535, "dur": 12.688, + "args": { + "External id": 32617,"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": 4183437, "tid": 4183437, + "ts": 658971961458.335, "dur": 12.349, + "args": { + "External id": 32618,"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": 4183437, "tid": 4183437, + "ts": 658971961478.290, "dur": 1.995, + "args": { + "External id": 32619,"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": 4183437, "tid": 4183437, + "ts": 658971961489.308, "dur": 3.692, + "args": { + "External id": 32620,"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": 4183437, "tid": 4183437, + "ts": 658971961491.768, "dur": 0.429, + "args": { + "External id": 32621,"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": 4183437, "tid": 4183437, + "ts": 658971961556.455, "dur": 43.400, + "args": { + "External id": 32622,"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": 4183437, "tid": 4183437, + "ts": 658971961604.357, "dur": 6.584, + "args": { + "External id": 32623,"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": 4183437, "tid": 4183437, + "ts": 658971961606.838, "dur": 2.992, + "args": { + "External id": 32624,"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": 4183437, "tid": 4183437, + "ts": 658971961612.260, "dur": 23.946, + "args": { + "External id": 32625,"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": 4183437, "tid": 4183437, + "ts": 658971961640.493, "dur": 5.752, + "args": { + "External id": 32626,"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": 4183437, "tid": 4183437, + "ts": 658971961642.141, "dur": 3.469, + "args": { + "External id": 32627,"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": 4183437, "tid": 4183437, + "ts": 658971961644.467, "dur": 0.900, + "args": { + "External id": 32628,"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": 4183437, "tid": 4183437, + "ts": 658971961648.557, "dur": 98.323, + "args": { + "External id": 32629,"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": 4183437, "tid": 4183437, + "ts": 658971961649.387, "dur": 96.513, + "args": { + "External id": 32630,"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": 4183437, "tid": 4183437, + "ts": 658971961752.697, "dur": 16.062, + "args": { + "External id": 32631,"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": 4183437, "tid": 4183437, + "ts": 658971961774.909, "dur": 4.436, + "args": { + "External id": 32632,"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": 4183437, "tid": 4183437, + "ts": 658971961777.675, "dur": 0.564, + "args": { + "External id": 32633,"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": 4183437, "tid": 4183437, + "ts": 658971961783.454, "dur": 51.279, + "args": { + "External id": 32634,"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": 4183437, "tid": 4183437, + "ts": 658971961784.417, "dur": 4.801, + "args": { + "External id": 32635,"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": 4183437, "tid": 4183437, + "ts": 658971961785.734, "dur": 2.885, + "args": { + "External id": 32636,"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": 4183437, "tid": 4183437, + "ts": 658971961787.621, "dur": 0.848, + "args": { + "External id": 32637,"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": 4183437, "tid": 4183437, + "ts": 658971961789.939, "dur": 44.388, + "args": { + "External id": 32638,"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": 4183437, "tid": 4183437, + "ts": 658971961790.767, "dur": 43.002, + "args": { + "External id": 32639,"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": 4183437, "tid": 4183437, + "ts": 658971961838.717, "dur": 3.364, + "args": { + "External id": 32640,"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": 4183437, "tid": 4183437, + "ts": 658971961840.417, "dur": 0.508, + "args": { + "External id": 32641,"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": 4183437, "tid": 4183437, + "ts": 658971961848.234, "dur": 1.963, + "args": { + "External id": 32642,"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": 4183437, "tid": 4183437, + "ts": 658971961857.883, "dur": 6.141, + "args": { + "External id": 32643,"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": 4183437, "tid": 4183437, + "ts": 658971961859.890, "dur": 3.862, + "args": { + "External id": 32644,"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": 4183437, "tid": 4183437, + "ts": 658971961947.035, "dur": 227.816, + "args": { + "External id": 32645,"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": 4183437, "tid": 4183437, + "ts": 658971961949.261, "dur": 4.443, + "args": { + "External id": 32646,"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": 4183437, "tid": 4183437, + "ts": 658971961955.230, "dur": 219.162, + "args": { + "External id": 32647,"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": 4183437, "tid": 4183437, + "ts": 658971961956.665, "dur": 0.360, + "args": { + "External id": 32648,"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": 4183437, "tid": 4183437, + "ts": 658971961958.342, "dur": 18.812, + "args": { + "External id": 32649,"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": 4183437, "tid": 4183437, + "ts": 658971961978.722, "dur": 5.744, + "args": { + "External id": 32650,"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": 4183437, "tid": 4183437, + "ts": 658971961983.369, "dur": 0.859, + "args": { + "External id": 32651,"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": 4183437, "tid": 4183437, + "ts": 658971961985.313, "dur": 18.644, + "args": { + "External id": 32652,"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": 4183437, "tid": 4183437, + "ts": 658971961986.688, "dur": 1.018, + "args": { + "External id": 32653,"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": 4183437, "tid": 4183437, + "ts": 658971961988.943, "dur": 14.719, + "args": { + "External id": 32654,"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": 4183437, "tid": 4183437, + "ts": 658971961991.341, "dur": 2.085, + "args": { + "External id": 32655,"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": 4183437, "tid": 4183437, + "ts": 658971962005.438, "dur": 18.404, + "args": { + "External id": 32656,"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": 4183437, "tid": 4183437, + "ts": 658971962025.676, "dur": 12.761, + "args": { + "External id": 32657,"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": 4183437, "tid": 4183437, + "ts": 658971962040.772, "dur": 12.098, + "args": { + "External id": 32658,"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": 4183437, "tid": 4183437, + "ts": 658971962054.755, "dur": 15.401, + "args": { + "External id": 32659,"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": 4183437, "tid": 4183437, + "ts": 658971962071.702, "dur": 21.584, + "args": { + "External id": 32660,"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": 4183437, "tid": 4183437, + "ts": 658971962073.652, "dur": 1.041, + "args": { + "External id": 32661,"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": 4183437, "tid": 4183437, + "ts": 658971962077.096, "dur": 2.879, + "args": { + "External id": 32662,"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": 4183437, "tid": 4183437, + "ts": 658971962094.975, "dur": 35.705, + "args": { + "External id": 32663,"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": 4183437, "tid": 4183437, + "ts": 658971962131.859, "dur": 41.647, + "args": { + "External id": 32664,"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": 4183437, "tid": 4183437, + "ts": 658971962181.416, "dur": 1.642, + "args": { + "External id": 32665,"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": 4183437, "tid": 4183437, + "ts": 658971962191.238, "dur": 3.338, + "args": { + "External id": 32666,"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": 4183437, "tid": 4183437, + "ts": 658971962193.245, "dur": 0.457, + "args": { + "External id": 32667,"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": 4183437, "tid": 4183437, + "ts": 658971962255.267, "dur": 59.095, + "args": { + "External id": 32668,"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": 4183437, "tid": 4183437, + "ts": 658971962323.661, "dur": 4.897, + "args": { + "External id": 32669,"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": 4183437, "tid": 4183437, + "ts": 658971962326.359, "dur": 0.890, + "args": { + "External id": 32670,"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": 4183437, "tid": 4183437, + "ts": 658971962330.191, "dur": 22.880, + "args": { + "External id": 32671,"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": 4183437, "tid": 4183437, + "ts": 658971962358.053, "dur": 7.387, + "args": { + "External id": 32672,"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": 4183437, "tid": 4183437, + "ts": 658971962359.673, "dur": 5.097, + "args": { + "External id": 32673,"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": 4183437, "tid": 4183437, + "ts": 658971962361.622, "dur": 2.912, + "args": { + "External id": 32674,"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": 4183437, "tid": 4183437, + "ts": 658971962368.411, "dur": 43.364, + "args": { + "External id": 32675,"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": 4183437, "tid": 4183437, + "ts": 658971962369.620, "dur": 41.637, + "args": { + "External id": 32676,"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": 4183437, "tid": 4183437, + "ts": 658971962415.608, "dur": 13.901, + "args": { + "External id": 32677,"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": 4183437, "tid": 4183437, + "ts": 658971962434.875, "dur": 3.812, + "args": { + "External id": 32678,"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": 4183437, "tid": 4183437, + "ts": 658971962437.384, "dur": 0.531, + "args": { + "External id": 32679,"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": 4183437, "tid": 4183437, + "ts": 658971962442.728, "dur": 47.200, + "args": { + "External id": 32680,"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": 4183437, "tid": 4183437, + "ts": 658971962443.804, "dur": 4.170, + "args": { + "External id": 32681,"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": 4183437, "tid": 4183437, + "ts": 658971962444.780, "dur": 2.552, + "args": { + "External id": 32682,"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": 4183437, "tid": 4183437, + "ts": 658971962446.577, "dur": 0.608, + "args": { + "External id": 32683,"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": 4183437, "tid": 4183437, + "ts": 658971962448.820, "dur": 40.750, + "args": { + "External id": 32684,"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": 4183437, "tid": 4183437, + "ts": 658971962449.726, "dur": 39.299, + "args": { + "External id": 32685,"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": 4183437, "tid": 4183437, + "ts": 658971962493.656, "dur": 3.963, + "args": { + "External id": 32686,"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": 4183437, "tid": 4183437, + "ts": 658971962495.411, "dur": 1.204, + "args": { + "External id": 32687,"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": 4183437, "tid": 4183437, + "ts": 658971962503.397, "dur": 1.679, + "args": { + "External id": 32688,"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": 4183437, "tid": 4183437, + "ts": 658971962512.499, "dur": 6.092, + "args": { + "External id": 32689,"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": 4183437, "tid": 4183437, + "ts": 658971962514.501, "dur": 3.805, + "args": { + "External id": 32690,"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": 4183437, "tid": 4183437, + "ts": 658971962594.345, "dur": 209.938, + "args": { + "External id": 32691,"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": 4183437, "tid": 4183437, + "ts": 658971962596.130, "dur": 2.023, + "args": { + "External id": 32692,"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": 4183437, "tid": 4183437, + "ts": 658971962602.231, "dur": 201.542, + "args": { + "External id": 32693,"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": 4183437, "tid": 4183437, + "ts": 658971962603.564, "dur": 0.488, + "args": { + "External id": 32694,"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": 4183437, "tid": 4183437, + "ts": 658971962605.169, "dur": 17.696, + "args": { + "External id": 32695,"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": 4183437, "tid": 4183437, + "ts": 658971962624.187, "dur": 4.813, + "args": { + "External id": 32696,"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": 4183437, "tid": 4183437, + "ts": 658971962626.012, "dur": 2.633, + "args": { + "External id": 32697,"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": 4183437, "tid": 4183437, + "ts": 658971962630.049, "dur": 18.961, + "args": { + "External id": 32698,"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": 4183437, "tid": 4183437, + "ts": 658971962631.066, "dur": 1.351, + "args": { + "External id": 32699,"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": 4183437, "tid": 4183437, + "ts": 658971962633.476, "dur": 15.253, + "args": { + "External id": 32700,"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": 4183437, "tid": 4183437, + "ts": 658971962635.733, "dur": 2.277, + "args": { + "External id": 32701,"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": 4183437, "tid": 4183437, + "ts": 658971962688.826, "dur": 23.638, + "args": { + "External id": 32702,"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": 4183437, "tid": 4183437, + "ts": 658971962714.600, "dur": 12.740, + "args": { + "External id": 32703,"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": 4183437, "tid": 4183437, + "ts": 658971962729.876, "dur": 13.229, + "args": { + "External id": 32704,"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": 4183437, "tid": 4183437, + "ts": 658971962744.601, "dur": 11.423, + "args": { + "External id": 32705,"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": 4183437, "tid": 4183437, + "ts": 658971962757.964, "dur": 19.993, + "args": { + "External id": 32706,"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": 4183437, "tid": 4183437, + "ts": 658971962760.076, "dur": 1.320, + "args": { + "External id": 32707,"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": 4183437, "tid": 4183437, + "ts": 658971962763.586, "dur": 0.737, + "args": { + "External id": 32708,"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": 4183437, "tid": 4183437, + "ts": 658971962779.656, "dur": 10.849, + "args": { + "External id": 32709,"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": 4183437, "tid": 4183437, + "ts": 658971962791.470, "dur": 10.997, + "args": { + "External id": 32710,"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": 4183437, "tid": 4183437, + "ts": 658971962811.592, "dur": 2.389, + "args": { + "External id": 32711,"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": 4183437, "tid": 4183437, + "ts": 658971962822.516, "dur": 3.746, + "args": { + "External id": 32712,"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": 4183437, "tid": 4183437, + "ts": 658971962824.994, "dur": 0.507, + "args": { + "External id": 32713,"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": 4183437, "tid": 4183437, + "ts": 658971962891.171, "dur": 42.626, + "args": { + "External id": 32714,"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": 4183437, "tid": 4183437, + "ts": 658971962938.088, "dur": 6.602, + "args": { + "External id": 32715,"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": 4183437, "tid": 4183437, + "ts": 658971962940.539, "dur": 3.027, + "args": { + "External id": 32716,"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": 4183437, "tid": 4183437, + "ts": 658971962946.296, "dur": 20.865, + "args": { + "External id": 32717,"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": 4183437, "tid": 4183437, + "ts": 658971962971.182, "dur": 5.948, + "args": { + "External id": 32718,"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": 4183437, "tid": 4183437, + "ts": 658971962972.810, "dur": 3.529, + "args": { + "External id": 32719,"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": 4183437, "tid": 4183437, + "ts": 658971962975.128, "dur": 1.010, + "args": { + "External id": 32720,"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": 4183437, "tid": 4183437, + "ts": 658971962979.598, "dur": 39.454, + "args": { + "External id": 32721,"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": 4183437, "tid": 4183437, + "ts": 658971962980.515, "dur": 37.952, + "args": { + "External id": 32722,"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": 4183437, "tid": 4183437, + "ts": 658971963022.591, "dur": 13.500, + "args": { + "External id": 32723,"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": 4183437, "tid": 4183437, + "ts": 658971963040.463, "dur": 21.847, + "args": { + "External id": 32724,"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": 4183437, "tid": 4183437, + "ts": 658971963042.876, "dur": 19.047, + "args": { + "External id": 32725,"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": 4183437, "tid": 4183437, + "ts": 658971963046.811, "dur": 1.137, + "args": { + "External id": 32726,"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": 4183437, "tid": 4183437, + "ts": 658971963066.972, "dur": 24.362, + "args": { + "External id": 32727,"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": 4183437, "tid": 4183437, + "ts": 658971963068.524, "dur": 22.602, + "args": { + "External id": 32728,"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": 4183437, "tid": 4183437, + "ts": 658971963073.333, "dur": 3.553, + "args": { + "External id": 32729,"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": 4183437, "tid": 4183437, + "ts": 658971963077.942, "dur": 12.709, + "args": { + "External id": 32730,"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": 4183437, "tid": 4183437, + "ts": 658971963103.102, "dur": 5.478, + "args": { + "External id": 32731,"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": 4183437, "tid": 4183437, + "ts": 658971963105.583, "dur": 2.742, + "args": { + "External id": 32732,"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": 4183437, "tid": 4183437, + "ts": 658971963109.901, "dur": 1.750, + "args": { + "External id": 32733,"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": 4183437, "tid": 4183437, + "ts": 658971963111.009, "dur": 0.564, + "args": { + "External id": 32734,"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": 4183437, "tid": 4183437, + "ts": 658971963152.707, "dur": 23.713, + "args": { + "External id": 32735,"Sequence number": 460092, "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": 4183437, "tid": 4183437, + "ts": 658971963178.347, "dur": 12.789, + "args": { + "External id": 32736,"Sequence number": 460093, "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": 4183437, "tid": 4183437, "ts": 658971963178.347, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183437, "tid": 4183437, + "ts": 658971963196.981, "dur": 5.781, + "args": { + "External id": 32737,"Sequence number": 460094, "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": 4183437, "tid": 4183437, + "ts": 658971963200.487, "dur": 1.037, + "args": { + "External id": 32738,"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": 4183437, "tid": 4183437, + "ts": 658971963205.288, "dur": 6.133, + "args": { + "External id": 32739,"Sequence number": 460094, "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": 4183437, "tid": 4183437, + "ts": 658971963209.728, "dur": 0.560, + "args": { + "External id": 32740,"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": 4183437, "tid": 4183437, + "ts": 658971963212.715, "dur": 2.499, + "args": { + "External id": 32741,"Sequence number": 460094, "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": 4183437, "tid": 4183437, + "ts": 658971963214.168, "dur": 0.469, + "args": { + "External id": 32742,"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": 4183437, "tid": 4183437, + "ts": 658971963219.126, "dur": 5.483, + "args": { + "External id": 32743,"Sequence number": 460094, "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": 4183437, "tid": 4183437, "ts": 658971963219.126, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971963222.617, "dur": 0.737, + "args": { + "External id": 32744,"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": 4183437, "tid": 4183437, + "ts": 658971963225.885, "dur": 5.032, + "args": { + "External id": 32745,"Sequence number": 460095, "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": 4183437, "tid": 4183437, "ts": 658971963225.885, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971963229.665, "dur": 0.460, + "args": { + "External id": 32746,"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": 4183437, "tid": 4183437, + "ts": 658971963231.888, "dur": 5.000, + "args": { + "External id": 32747,"Sequence number": 460096, "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": 4183437, "tid": 4183437, "ts": 658971963231.888, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971963235.514, "dur": 0.423, + "args": { + "External id": 32748,"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": 4183437, "tid": 4183437, + "ts": 658971963237.860, "dur": 4.273, + "args": { + "External id": 32749,"Sequence number": 460097, "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": 4183437, "tid": 4183437, "ts": 658971963237.860, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183437, "tid": 4183437, + "ts": 658971963240.797, "dur": 0.559, + "args": { + "External id": 32750,"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": 4183437, "tid": 4183437, + "ts": 658971963245.449, "dur": 48.197, + "args": { + "External id": 32751,"Sequence number": 460098, "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": 4183437, "tid": 4183437, + "ts": 658971963246.978, "dur": 46.477, + "args": { + "External id": 32752,"Sequence number": 460098, "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": 4183437, "tid": 4183437, + "ts": 658971963249.716, "dur": 6.350, + "args": { + "External id": 32753,"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": 4183437, "tid": 4183437, + "ts": 658971963251.947, "dur": 3.513, + "args": { + "External id": 32754,"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": 4183437, "tid": 4183437, + "ts": 658971963257.081, "dur": 35.624, + "args": { + "External id": 32755,"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": 4183437, "tid": 4183437, + "ts": 658971963320.702, "dur": 4.880, + "args": { + "External id": 32756,"Sequence number": 460098, "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": 4183437, "tid": 4183437, "ts": 658971963320.702, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183437, "tid": 4183437, + "ts": 658971963328.222, "dur": 3.434, + "args": { + "External id": 32757,"Sequence number": 460099, "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": 4183437, "tid": 4183437, + "ts": 658971963362.667, "dur": 24750.562, + "args": { + "External id": 32758,"Sequence number": 460099, "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": 4183437, "tid": 4183437, "ts": 658971963362.667, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183437, "tid": 4183437, + "ts": 658971963377.597, "dur": 26.868, + "args": { + "External id": 32759,"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": 4183437, "tid": 4183437, + "ts": 658971963378.561, "dur": 25.703, + "args": { + "External id": 32760,"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": 4183437, "tid": 4183437, + "ts": 658971963379.944, "dur": 6.520, + "args": { + "External id": 32761,"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": 4183437, "tid": 4183437, + "ts": 658971963381.934, "dur": 4.105, + "args": { + "External id": 32762,"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": 4183437, "tid": 4183437, + "ts": 658971963387.298, "dur": 16.559, + "args": { + "External id": 32763,"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": 4183437, "tid": 4183437, + "ts": 658971963419.886, "dur": 24.817, + "args": { + "External id": 32764,"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": 4183437, "tid": 4183437, + "ts": 658971963420.877, "dur": 6.163, + "args": { + "External id": 32765,"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": 4183437, "tid": 4183437, + "ts": 658971963423.208, "dur": 3.557, + "args": { + "External id": 32766,"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": 4183437, "tid": 4183437, + "ts": 658971963428.451, "dur": 16.039, + "args": { + "External id": 32767,"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": 4183437, "tid": 4183437, + "ts": 658971963430.153, "dur": 13.917, + "args": { + "External id": 32768,"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": 4183437, "tid": 4183437, + "ts": 658971963470.238, "dur": 17.851, + "args": { + "External id": 32769,"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": 4183437, "tid": 4183437, + "ts": 658971963471.247, "dur": 3.592, + "args": { + "External id": 32770,"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": 4183437, "tid": 4183437, + "ts": 658971963472.245, "dur": 2.323, + "args": { + "External id": 32771,"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": 4183437, "tid": 4183437, + "ts": 658971963475.427, "dur": 12.403, + "args": { + "External id": 32772,"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": 4183437, "tid": 4183437, + "ts": 658971963475.795, "dur": 11.586, + "args": { + "External id": 32773,"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": 4183437, "tid": 4183437, + "ts": 658971963493.902, "dur": 16.883, + "args": { + "External id": 32774,"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": 4183437, "tid": 4183437, + "ts": 658971963495.533, "dur": 4.384, + "args": { + "External id": 32775,"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": 4183437, "tid": 4183437, + "ts": 658971963500.528, "dur": 10.001, + "args": { + "External id": 32776,"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": 4183437, "tid": 4183437, + "ts": 658971963501.072, "dur": 9.030, + "args": { + "External id": 32777,"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": 4183437, "tid": 4183437, + "ts": 658971963515.783, "dur": 21.548, + "args": { + "External id": 32778,"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": 4183437, "tid": 4183437, + "ts": 658971963540.123, "dur": 47.293, + "args": { + "External id": 32779,"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": 4183437, "tid": 4183437, + "ts": 658971963541.804, "dur": 45.129, + "args": { + "External id": 32780,"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": 4183437, "tid": 4183437, + "ts": 658971963545.646, "dur": 1.031, + "args": { + "External id": 32781,"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": 4183437, "tid": 4183437, + "ts": 658971963548.417, "dur": 22.481, + "args": { + "External id": 32782,"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": 4183437, "tid": 4183437, + "ts": 658971963549.919, "dur": 20.778, + "args": { + "External id": 32783,"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": 4183437, "tid": 4183437, + "ts": 658971963554.317, "dur": 2.919, + "args": { + "External id": 32784,"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": 4183437, "tid": 4183437, + "ts": 658971963557.905, "dur": 12.408, + "args": { + "External id": 32785,"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": 4183437, "tid": 4183437, + "ts": 658971963591.561, "dur": 18968.357, + "args": { + "External id": 32786,"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": 4183437, "tid": 4183437, + "ts": 658971963592.879, "dur": 18965.811, + "args": { + "External id": 32787,"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": 4183437, "tid": 4183437, + "ts": 658971982569.904, "dur": 7.275, + "args": { + "External id": 32788,"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": 4183437, "tid": 4183437, + "ts": 658971982574.226, "dur": 0.940, + "args": { + "External id": 32789,"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": 4183437, "tid": 4183437, + "ts": 658971982582.481, "dur": 128.518, + "args": { + "External id": 32790,"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": 4183437, "tid": 4183437, + "ts": 658971982584.397, "dur": 6.126, + "args": { + "External id": 32791,"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": 4183437, "tid": 4183437, + "ts": 658971982586.510, "dur": 3.172, + "args": { + "External id": 32792,"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": 4183437, "tid": 4183437, + "ts": 658971982588.415, "dur": 1.006, + "args": { + "External id": 32793,"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": 4183437, "tid": 4183437, + "ts": 658971982591.761, "dur": 118.522, + "args": { + "External id": 32794,"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": 4183437, "tid": 4183437, + "ts": 658971982593.238, "dur": 115.779, + "args": { + "External id": 32795,"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": 4183437, "tid": 4183437, + "ts": 658971982715.890, "dur": 5.818, + "args": { + "External id": 32796,"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": 4183437, "tid": 4183437, + "ts": 658971982718.986, "dur": 0.948, + "args": { + "External id": 32797,"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": 4183437, "tid": 4183437, + "ts": 658971982729.075, "dur": 2.519, + "args": { + "External id": 32798,"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": 4183437, "tid": 4183437, + "ts": 658971982743.830, "dur": 6.754, + "args": { + "External id": 32799,"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": 4183437, "tid": 4183437, + "ts": 658971982746.231, "dur": 4.096, + "args": { + "External id": 32800,"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": 4183437, "tid": 4183437, + "ts": 658971982879.905, "dur": 201.623, + "args": { + "External id": 32801,"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": 4183437, "tid": 4183437, + "ts": 658971982884.771, "dur": 2.237, + "args": { + "External id": 32802,"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": 4183437, "tid": 4183437, + "ts": 658971982888.500, "dur": 192.373, + "args": { + "External id": 32803,"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": 4183437, "tid": 4183437, + "ts": 658971982890.438, "dur": 0.613, + "args": { + "External id": 32804,"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": 4183437, "tid": 4183437, + "ts": 658971982892.711, "dur": 24.816, + "args": { + "External id": 32805,"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": 4183437, "tid": 4183437, + "ts": 658971982919.262, "dur": 5.649, + "args": { + "External id": 32806,"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": 4183437, "tid": 4183437, + "ts": 658971982923.463, "dur": 1.131, + "args": { + "External id": 32807,"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": 4183437, "tid": 4183437, + "ts": 658971982926.103, "dur": 23.654, + "args": { + "External id": 32808,"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": 4183437, "tid": 4183437, + "ts": 658971982927.572, "dur": 1.359, + "args": { + "External id": 32809,"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": 4183437, "tid": 4183437, + "ts": 658971982930.365, "dur": 19.122, + "args": { + "External id": 32810,"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": 4183437, "tid": 4183437, + "ts": 658971982934.028, "dur": 3.605, + "args": { + "External id": 32811,"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": 4183437, "tid": 4183437, + "ts": 658971982951.554, "dur": 22.466, + "args": { + "External id": 32812,"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": 4183437, "tid": 4183437, + "ts": 658971982975.887, "dur": 17.036, + "args": { + "External id": 32813,"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": 4183437, "tid": 4183437, + "ts": 658971982996.122, "dur": 16.000, + "args": { + "External id": 32814,"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": 4183437, "tid": 4183437, + "ts": 658971983013.588, "dur": 14.308, + "args": { + "External id": 32815,"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": 4183437, "tid": 4183437, + "ts": 658971983029.769, "dur": 22.821, + "args": { + "External id": 32816,"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": 4183437, "tid": 4183437, + "ts": 658971983032.262, "dur": 1.469, + "args": { + "External id": 32817,"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": 4183437, "tid": 4183437, + "ts": 658971983036.601, "dur": 0.986, + "args": { + "External id": 32818,"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": 4183437, "tid": 4183437, + "ts": 658971983054.040, "dur": 13.079, + "args": { + "External id": 32819,"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": 4183437, "tid": 4183437, + "ts": 658971983068.726, "dur": 11.297, + "args": { + "External id": 32820,"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": 4183437, "tid": 4183437, + "ts": 658971983088.096, "dur": 1.879, + "args": { + "External id": 32821,"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": 4183437, "tid": 4183437, + "ts": 658971983096.348, "dur": 4.643, + "args": { + "External id": 32822,"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": 4183437, "tid": 4183437, + "ts": 658971983099.068, "dur": 0.881, + "args": { + "External id": 32823,"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": 4183437, "tid": 4183437, + "ts": 658971983173.098, "dur": 57.313, + "args": { + "External id": 32824,"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": 4183437, "tid": 4183437, + "ts": 658971983235.523, "dur": 10.708, + "args": { + "External id": 32825,"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": 4183437, "tid": 4183437, + "ts": 658971983242.598, "dur": 2.017, + "args": { + "External id": 32826,"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": 4183437, "tid": 4183437, + "ts": 658971983247.780, "dur": 44.411, + "args": { + "External id": 32827,"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": 4183437, "tid": 4183437, + "ts": 658971983299.720, "dur": 8.740, + "args": { + "External id": 32828,"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": 4183437, "tid": 4183437, + "ts": 658971983301.681, "dur": 5.335, + "args": { + "External id": 32829,"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": 4183437, "tid": 4183437, + "ts": 658971983303.904, "dur": 2.818, + "args": { + "External id": 32830,"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": 4183437, "tid": 4183437, + "ts": 658971983312.214, "dur": 50.603, + "args": { + "External id": 32831,"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": 4183437, "tid": 4183437, + "ts": 658971983313.627, "dur": 48.471, + "args": { + "External id": 32832,"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": 4183437, "tid": 4183437, + "ts": 658971983366.849, "dur": 17.798, + "args": { + "External id": 32833,"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": 4183437, "tid": 4183437, + "ts": 658971983391.510, "dur": 5.199, + "args": { + "External id": 32834,"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": 4183437, "tid": 4183437, + "ts": 658971983394.162, "dur": 1.023, + "args": { + "External id": 32835,"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": 4183437, "tid": 4183437, + "ts": 658971983401.235, "dur": 51.111, + "args": { + "External id": 32836,"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": 4183437, "tid": 4183437, + "ts": 658971983402.363, "dur": 4.515, + "args": { + "External id": 32837,"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": 4183437, "tid": 4183437, + "ts": 658971983403.271, "dur": 2.973, + "args": { + "External id": 32838,"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": 4183437, "tid": 4183437, + "ts": 658971983405.099, "dur": 0.865, + "args": { + "External id": 32839,"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": 4183437, "tid": 4183437, + "ts": 658971983407.464, "dur": 44.374, + "args": { + "External id": 32840,"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": 4183437, "tid": 4183437, + "ts": 658971983408.586, "dur": 42.689, + "args": { + "External id": 32841,"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": 4183437, "tid": 4183437, + "ts": 658971983456.915, "dur": 4.673, + "args": { + "External id": 32842,"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": 4183437, "tid": 4183437, + "ts": 658971983459.252, "dur": 1.043, + "args": { + "External id": 32843,"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": 4183437, "tid": 4183437, + "ts": 658971983468.033, "dur": 2.103, + "args": { + "External id": 32844,"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": 4183437, "tid": 4183437, + "ts": 658971983478.557, "dur": 6.353, + "args": { + "External id": 32845,"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": 4183437, "tid": 4183437, + "ts": 658971983480.731, "dur": 3.922, + "args": { + "External id": 32846,"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": 4183437, "tid": 4183437, + "ts": 658971983582.172, "dur": 264.106, + "args": { + "External id": 32847,"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": 4183437, "tid": 4183437, + "ts": 658971983584.620, "dur": 2.308, + "args": { + "External id": 32848,"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": 4183437, "tid": 4183437, + "ts": 658971983590.886, "dur": 254.900, + "args": { + "External id": 32849,"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": 4183437, "tid": 4183437, + "ts": 658971983592.494, "dur": 0.504, + "args": { + "External id": 32850,"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": 4183437, "tid": 4183437, + "ts": 658971983594.802, "dur": 21.477, + "args": { + "External id": 32851,"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": 4183437, "tid": 4183437, + "ts": 658971983617.968, "dur": 5.628, + "args": { + "External id": 32852,"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": 4183437, "tid": 4183437, + "ts": 658971983620.352, "dur": 2.801, + "args": { + "External id": 32853,"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": 4183437, "tid": 4183437, + "ts": 658971983624.752, "dur": 22.741, + "args": { + "External id": 32854,"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": 4183437, "tid": 4183437, + "ts": 658971983626.096, "dur": 1.452, + "args": { + "External id": 32855,"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": 4183437, "tid": 4183437, + "ts": 658971983629.022, "dur": 18.216, + "args": { + "External id": 32856,"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": 4183437, "tid": 4183437, + "ts": 658971983631.691, "dur": 3.121, + "args": { + "External id": 32857,"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": 4183437, "tid": 4183437, + "ts": 658971983648.994, "dur": 59.283, + "args": { + "External id": 32858,"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": 4183437, "tid": 4183437, + "ts": 658971983710.690, "dur": 16.011, + "args": { + "External id": 32859,"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": 4183437, "tid": 4183437, + "ts": 658971983729.482, "dur": 14.292, + "args": { + "External id": 32860,"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": 4183437, "tid": 4183437, + "ts": 658971983745.442, "dur": 14.443, + "args": { + "External id": 32861,"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": 4183437, "tid": 4183437, + "ts": 658971983762.410, "dur": 30.836, + "args": { + "External id": 32862,"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": 4183437, "tid": 4183437, + "ts": 658971983764.818, "dur": 1.810, + "args": { + "External id": 32863,"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": 4183437, "tid": 4183437, + "ts": 658971983770.083, "dur": 2.803, + "args": { + "External id": 32864,"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": 4183437, "tid": 4183437, + "ts": 658971983795.208, "dur": 16.617, + "args": { + "External id": 32865,"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": 4183437, "tid": 4183437, + "ts": 658971983812.954, "dur": 31.807, + "args": { + "External id": 32866,"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": 4183437, "tid": 4183437, + "ts": 658971983854.116, "dur": 2.718, + "args": { + "External id": 32867,"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": 4183437, "tid": 4183437, + "ts": 658971983866.501, "dur": 3.921, + "args": { + "External id": 32868,"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": 4183437, "tid": 4183437, + "ts": 658971983869.034, "dur": 0.420, + "args": { + "External id": 32869,"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": 4183437, "tid": 4183437, + "ts": 658971983949.345, "dur": 48.454, + "args": { + "External id": 32870,"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": 4183437, "tid": 4183437, + "ts": 658971984002.966, "dur": 4.719, + "args": { + "External id": 32871,"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": 4183437, "tid": 4183437, + "ts": 658971984005.803, "dur": 0.946, + "args": { + "External id": 32872,"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": 4183437, "tid": 4183437, + "ts": 658971984009.340, "dur": 24.519, + "args": { + "External id": 32873,"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": 4183437, "tid": 4183437, + "ts": 658971984047.333, "dur": 8.730, + "args": { + "External id": 32874,"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": 4183437, "tid": 4183437, + "ts": 658971984050.216, "dur": 5.125, + "args": { + "External id": 32875,"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": 4183437, "tid": 4183437, + "ts": 658971984051.813, "dur": 3.278, + "args": { + "External id": 32876,"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": 4183437, "tid": 4183437, + "ts": 658971984058.805, "dur": 45.699, + "args": { + "External id": 32877,"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": 4183437, "tid": 4183437, + "ts": 658971984059.996, "dur": 43.611, + "args": { + "External id": 32878,"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": 4183437, "tid": 4183437, + "ts": 658971984108.847, "dur": 16.082, + "args": { + "External id": 32879,"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": 4183437, "tid": 4183437, + "ts": 658971984130.670, "dur": 4.552, + "args": { + "External id": 32880,"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": 4183437, "tid": 4183437, + "ts": 658971984133.393, "dur": 0.944, + "args": { + "External id": 32881,"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": 4183437, "tid": 4183437, + "ts": 658971984140.142, "dur": 47.541, + "args": { + "External id": 32882,"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": 4183437, "tid": 4183437, + "ts": 658971984141.107, "dur": 4.665, + "args": { + "External id": 32883,"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": 4183437, "tid": 4183437, + "ts": 658971984142.243, "dur": 2.924, + "args": { + "External id": 32884,"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": 4183437, "tid": 4183437, + "ts": 658971984144.178, "dur": 0.836, + "args": { + "External id": 32885,"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": 4183437, "tid": 4183437, + "ts": 658971984146.574, "dur": 40.802, + "args": { + "External id": 32886,"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": 4183437, "tid": 4183437, + "ts": 658971984147.357, "dur": 39.390, + "args": { + "External id": 32887,"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": 4183437, "tid": 4183437, + "ts": 658971984191.582, "dur": 4.051, + "args": { + "External id": 32888,"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": 4183437, "tid": 4183437, + "ts": 658971984193.355, "dur": 1.142, + "args": { + "External id": 32889,"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": 4183437, "tid": 4183437, + "ts": 658971984201.612, "dur": 1.896, + "args": { + "External id": 32890,"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": 4183437, "tid": 4183437, + "ts": 658971984211.496, "dur": 6.626, + "args": { + "External id": 32891,"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": 4183437, "tid": 4183437, + "ts": 658971984213.815, "dur": 4.042, + "args": { + "External id": 32892,"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": 4183437, "tid": 4183437, + "ts": 658971984322.379, "dur": 192.103, + "args": { + "External id": 32893,"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": 4183437, "tid": 4183437, + "ts": 658971984324.944, "dur": 2.659, + "args": { + "External id": 32894,"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": 4183437, "tid": 4183437, + "ts": 658971984331.717, "dur": 182.386, + "args": { + "External id": 32895,"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": 4183437, "tid": 4183437, + "ts": 658971984333.481, "dur": 0.532, + "args": { + "External id": 32896,"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": 4183437, "tid": 4183437, + "ts": 658971984335.155, "dur": 23.187, + "args": { + "External id": 32897,"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": 4183437, "tid": 4183437, + "ts": 658971984359.745, "dur": 5.661, + "args": { + "External id": 32898,"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": 4183437, "tid": 4183437, + "ts": 658971984362.459, "dur": 2.569, + "args": { + "External id": 32899,"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": 4183437, "tid": 4183437, + "ts": 658971984366.451, "dur": 20.757, + "args": { + "External id": 32900,"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": 4183437, "tid": 4183437, + "ts": 658971984367.626, "dur": 1.182, + "args": { + "External id": 32901,"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": 4183437, "tid": 4183437, + "ts": 658971984370.196, "dur": 16.736, + "args": { + "External id": 32902,"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": 4183437, "tid": 4183437, + "ts": 658971984372.722, "dur": 2.365, + "args": { + "External id": 32903,"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": 4183437, "tid": 4183437, + "ts": 658971984390.927, "dur": 20.890, + "args": { + "External id": 32904,"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": 4183437, "tid": 4183437, + "ts": 658971984413.230, "dur": 17.062, + "args": { + "External id": 32905,"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": 4183437, "tid": 4183437, + "ts": 658971984432.872, "dur": 14.754, + "args": { + "External id": 32906,"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": 4183437, "tid": 4183437, + "ts": 658971984449.068, "dur": 13.881, + "args": { + "External id": 32907,"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": 4183437, "tid": 4183437, + "ts": 658971984464.924, "dur": 19.929, + "args": { + "External id": 32908,"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": 4183437, "tid": 4183437, + "ts": 658971984466.646, "dur": 1.016, + "args": { + "External id": 32909,"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": 4183437, "tid": 4183437, + "ts": 658971984470.015, "dur": 0.904, + "args": { + "External id": 32910,"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": 4183437, "tid": 4183437, + "ts": 658971984486.457, "dur": 13.187, + "args": { + "External id": 32911,"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": 4183437, "tid": 4183437, + "ts": 658971984501.119, "dur": 12.038, + "args": { + "External id": 32912,"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": 4183437, "tid": 4183437, + "ts": 658971984520.577, "dur": 2.074, + "args": { + "External id": 32913,"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": 4183437, "tid": 4183437, + "ts": 658971984532.003, "dur": 3.724, + "args": { + "External id": 32914,"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": 4183437, "tid": 4183437, + "ts": 658971984534.422, "dur": 0.473, + "args": { + "External id": 32915,"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": 4183437, "tid": 4183437, + "ts": 658971984600.495, "dur": 44.919, + "args": { + "External id": 32916,"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": 4183437, "tid": 4183437, + "ts": 658971984650.461, "dur": 40.547, + "args": { + "External id": 32917,"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": 4183437, "tid": 4183437, + "ts": 658971984688.085, "dur": 1.194, + "args": { + "External id": 32918,"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": 4183437, "tid": 4183437, + "ts": 658971984692.646, "dur": 28.169, + "args": { + "External id": 32919,"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": 4183437, "tid": 4183437, + "ts": 658971984726.400, "dur": 6.873, + "args": { + "External id": 32920,"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": 4183437, "tid": 4183437, + "ts": 658971984728.294, "dur": 4.378, + "args": { + "External id": 32921,"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": 4183437, "tid": 4183437, + "ts": 658971984730.797, "dur": 1.645, + "args": { + "External id": 32922,"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": 4183437, "tid": 4183437, + "ts": 658971984736.431, "dur": 46.800, + "args": { + "External id": 32923,"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": 4183437, "tid": 4183437, + "ts": 658971984738.014, "dur": 44.375, + "args": { + "External id": 32924,"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": 4183437, "tid": 4183437, + "ts": 658971984787.147, "dur": 20.800, + "args": { + "External id": 32925,"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": 4183437, "tid": 4183437, + "ts": 658971984813.816, "dur": 4.394, + "args": { + "External id": 32926,"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": 4183437, "tid": 4183437, + "ts": 658971984816.365, "dur": 1.010, + "args": { + "External id": 32927,"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": 4183437, "tid": 4183437, + "ts": 658971984822.667, "dur": 49.064, + "args": { + "External id": 32928,"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": 4183437, "tid": 4183437, + "ts": 658971984823.694, "dur": 4.267, + "args": { + "External id": 32929,"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": 4183437, "tid": 4183437, + "ts": 658971984824.502, "dur": 2.884, + "args": { + "External id": 32930,"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": 4183437, "tid": 4183437, + "ts": 658971984826.519, "dur": 0.728, + "args": { + "External id": 32931,"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": 4183437, "tid": 4183437, + "ts": 658971984828.652, "dur": 42.673, + "args": { + "External id": 32932,"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": 4183437, "tid": 4183437, + "ts": 658971984829.581, "dur": 41.044, + "args": { + "External id": 32933,"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": 4183437, "tid": 4183437, + "ts": 658971984875.730, "dur": 3.587, + "args": { + "External id": 32934,"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": 4183437, "tid": 4183437, + "ts": 658971984877.514, "dur": 0.715, + "args": { + "External id": 32935,"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": 4183437, "tid": 4183437, + "ts": 658971984885.568, "dur": 1.649, + "args": { + "External id": 32936,"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": 4183437, "tid": 4183437, + "ts": 658971984894.865, "dur": 7.851, + "args": { + "External id": 32937,"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": 4183437, "tid": 4183437, + "ts": 658971984896.724, "dur": 5.661, + "args": { + "External id": 32938,"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": 4183437, "tid": 4183437, + "ts": 658971984986.778, "dur": 169.482, + "args": { + "External id": 32939,"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": 4183437, "tid": 4183437, + "ts": 658971984988.998, "dur": 1.824, + "args": { + "External id": 32940,"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": 4183437, "tid": 4183437, + "ts": 658971984992.297, "dur": 163.549, + "args": { + "External id": 32941,"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": 4183437, "tid": 4183437, + "ts": 658971984993.929, "dur": 0.313, + "args": { + "External id": 32942,"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": 4183437, "tid": 4183437, + "ts": 658971984995.689, "dur": 21.404, + "args": { + "External id": 32943,"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": 4183437, "tid": 4183437, + "ts": 658971985018.682, "dur": 3.553, + "args": { + "External id": 32944,"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": 4183437, "tid": 4183437, + "ts": 658971985021.002, "dur": 0.937, + "args": { + "External id": 32945,"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": 4183437, "tid": 4183437, + "ts": 658971985023.212, "dur": 22.053, + "args": { + "External id": 32946,"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": 4183437, "tid": 4183437, + "ts": 658971985024.101, "dur": 1.508, + "args": { + "External id": 32947,"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": 4183437, "tid": 4183437, + "ts": 658971985026.593, "dur": 18.264, + "args": { + "External id": 32948,"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": 4183437, "tid": 4183437, + "ts": 658971985031.035, "dur": 2.370, + "args": { + "External id": 32949,"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": 4183437, "tid": 4183437, + "ts": 658971985047.031, "dur": 18.678, + "args": { + "External id": 32950,"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": 4183437, "tid": 4183437, + "ts": 658971985066.923, "dur": 12.238, + "args": { + "External id": 32951,"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": 4183437, "tid": 4183437, + "ts": 658971985082.119, "dur": 12.650, + "args": { + "External id": 32952,"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": 4183437, "tid": 4183437, + "ts": 658971985096.465, "dur": 12.162, + "args": { + "External id": 32953,"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": 4183437, "tid": 4183437, + "ts": 658971985110.376, "dur": 19.822, + "args": { + "External id": 32954,"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": 4183437, "tid": 4183437, + "ts": 658971985112.538, "dur": 1.504, + "args": { + "External id": 32955,"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": 4183437, "tid": 4183437, + "ts": 658971985116.913, "dur": 1.244, + "args": { + "External id": 32956,"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": 4183437, "tid": 4183437, + "ts": 658971985131.860, "dur": 10.970, + "args": { + "External id": 32957,"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": 4183437, "tid": 4183437, + "ts": 658971985143.961, "dur": 10.778, + "args": { + "External id": 32958,"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": 4183437, "tid": 4183437, + "ts": 658971985161.900, "dur": 2.329, + "args": { + "External id": 32959,"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": 4183437, "tid": 4183437, + "ts": 658971985172.753, "dur": 3.689, + "args": { + "External id": 32960,"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": 4183437, "tid": 4183437, + "ts": 658971985175.339, "dur": 0.370, + "args": { + "External id": 32961,"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": 4183437, "tid": 4183437, + "ts": 658971985237.186, "dur": 52.543, + "args": { + "External id": 32962,"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": 4183437, "tid": 4183437, + "ts": 658971985295.856, "dur": 6.662, + "args": { + "External id": 32963,"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": 4183437, "tid": 4183437, + "ts": 658971985299.798, "dur": 1.466, + "args": { + "External id": 32964,"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": 4183437, "tid": 4183437, + "ts": 658971985303.980, "dur": 21.423, + "args": { + "External id": 32965,"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": 4183437, "tid": 4183437, + "ts": 658971985330.530, "dur": 5.745, + "args": { + "External id": 32966,"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": 4183437, "tid": 4183437, + "ts": 658971985332.498, "dur": 3.152, + "args": { + "External id": 32967,"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": 4183437, "tid": 4183437, + "ts": 658971985334.429, "dur": 1.010, + "args": { + "External id": 32968,"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": 4183437, "tid": 4183437, + "ts": 658971985339.760, "dur": 43.969, + "args": { + "External id": 32969,"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": 4183437, "tid": 4183437, + "ts": 658971985341.228, "dur": 41.794, + "args": { + "External id": 32970,"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": 4183437, "tid": 4183437, + "ts": 658971985386.995, "dur": 14.818, + "args": { + "External id": 32971,"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": 4183437, "tid": 4183437, + "ts": 658971985406.911, "dur": 4.384, + "args": { + "External id": 32972,"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": 4183437, "tid": 4183437, + "ts": 658971985409.617, "dur": 0.811, + "args": { + "External id": 32973,"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": 4183437, "tid": 4183437, + "ts": 658971985415.246, "dur": 49.257, + "args": { + "External id": 32974,"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": 4183437, "tid": 4183437, + "ts": 658971985416.313, "dur": 6.253, + "args": { + "External id": 32975,"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": 4183437, "tid": 4183437, + "ts": 658971985417.517, "dur": 4.428, + "args": { + "External id": 32976,"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": 4183437, "tid": 4183437, + "ts": 658971985419.041, "dur": 2.723, + "args": { + "External id": 32977,"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": 4183437, "tid": 4183437, + "ts": 658971985423.352, "dur": 40.775, + "args": { + "External id": 32978,"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": 4183437, "tid": 4183437, + "ts": 658971985423.989, "dur": 39.418, + "args": { + "External id": 32979,"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": 4183437, "tid": 4183437, + "ts": 658971985468.805, "dur": 3.558, + "args": { + "External id": 32980,"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": 4183437, "tid": 4183437, + "ts": 658971985470.647, "dur": 0.586, + "args": { + "External id": 32981,"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": 4183437, "tid": 4183437, + "ts": 658971985477.874, "dur": 1.768, + "args": { + "External id": 32982,"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": 4183437, "tid": 4183437, + "ts": 658971985486.621, "dur": 4.925, + "args": { + "External id": 32983,"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": 4183437, "tid": 4183437, + "ts": 658971985488.318, "dur": 2.968, + "args": { + "External id": 32984,"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": 4183437, "tid": 4183437, + "ts": 658971985569.663, "dur": 216.235, + "args": { + "External id": 32985,"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": 4183437, "tid": 4183437, + "ts": 658971985572.000, "dur": 2.046, + "args": { + "External id": 32986,"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": 4183437, "tid": 4183437, + "ts": 658971985575.453, "dur": 210.006, + "args": { + "External id": 32987,"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": 4183437, "tid": 4183437, + "ts": 658971985577.076, "dur": 0.502, + "args": { + "External id": 32988,"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": 4183437, "tid": 4183437, + "ts": 658971985581.181, "dur": 19.175, + "args": { + "External id": 32989,"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": 4183437, "tid": 4183437, + "ts": 658971985601.986, "dur": 3.939, + "args": { + "External id": 32990,"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": 4183437, "tid": 4183437, + "ts": 658971985604.825, "dur": 0.743, + "args": { + "External id": 32991,"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": 4183437, "tid": 4183437, + "ts": 658971985606.751, "dur": 23.570, + "args": { + "External id": 32992,"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": 4183437, "tid": 4183437, + "ts": 658971985607.765, "dur": 3.340, + "args": { + "External id": 32993,"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": 4183437, "tid": 4183437, + "ts": 658971985612.400, "dur": 17.486, + "args": { + "External id": 32994,"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": 4183437, "tid": 4183437, + "ts": 658971985614.961, "dur": 2.134, + "args": { + "External id": 32995,"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": 4183437, "tid": 4183437, + "ts": 658971985632.015, "dur": 53.338, + "args": { + "External id": 32996,"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": 4183437, "tid": 4183437, + "ts": 658971985688.059, "dur": 15.023, + "args": { + "External id": 32997,"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": 4183437, "tid": 4183437, + "ts": 658971985706.352, "dur": 13.510, + "args": { + "External id": 32998,"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": 4183437, "tid": 4183437, + "ts": 658971985721.565, "dur": 12.103, + "args": { + "External id": 32999,"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": 4183437, "tid": 4183437, + "ts": 658971985735.916, "dur": 22.414, + "args": { + "External id": 33000,"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": 4183437, "tid": 4183437, + "ts": 658971985737.989, "dur": 1.369, + "args": { + "External id": 33001,"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": 4183437, "tid": 4183437, + "ts": 658971985741.698, "dur": 1.411, + "args": { + "External id": 33002,"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": 4183437, "tid": 4183437, + "ts": 658971985759.898, "dur": 12.322, + "args": { + "External id": 33003,"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": 4183437, "tid": 4183437, + "ts": 658971985773.403, "dur": 10.891, + "args": { + "External id": 33004,"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": 4183437, "tid": 4183437, + "ts": 658971985793.608, "dur": 2.614, + "args": { + "External id": 33005,"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": 4183437, "tid": 4183437, + "ts": 658971985806.286, "dur": 3.856, + "args": { + "External id": 33006,"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": 4183437, "tid": 4183437, + "ts": 658971985808.668, "dur": 0.657, + "args": { + "External id": 33007,"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": 4183437, "tid": 4183437, + "ts": 658971985877.274, "dur": 49.044, + "args": { + "External id": 33008,"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": 4183437, "tid": 4183437, + "ts": 658971985930.980, "dur": 4.816, + "args": { + "External id": 33009,"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": 4183437, "tid": 4183437, + "ts": 658971985934.168, "dur": 0.686, + "args": { + "External id": 33010,"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": 4183437, "tid": 4183437, + "ts": 658971985937.240, "dur": 23.845, + "args": { + "External id": 33011,"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": 4183437, "tid": 4183437, + "ts": 658971985965.982, "dur": 6.617, + "args": { + "External id": 33012,"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": 4183437, "tid": 4183437, + "ts": 658971985967.714, "dur": 4.031, + "args": { + "External id": 33013,"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": 4183437, "tid": 4183437, + "ts": 658971985970.133, "dur": 1.376, + "args": { + "External id": 33014,"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": 4183437, "tid": 4183437, + "ts": 658971985974.765, "dur": 43.013, + "args": { + "External id": 33015,"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": 4183437, "tid": 4183437, + "ts": 658971985976.119, "dur": 41.110, + "args": { + "External id": 33016,"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": 4183437, "tid": 4183437, + "ts": 658971986021.525, "dur": 13.602, + "args": { + "External id": 33017,"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": 4183437, "tid": 4183437, + "ts": 658971986041.229, "dur": 4.397, + "args": { + "External id": 33018,"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": 4183437, "tid": 4183437, + "ts": 658971986043.616, "dur": 1.225, + "args": { + "External id": 33019,"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": 4183437, "tid": 4183437, + "ts": 658971986050.004, "dur": 51.105, + "args": { + "External id": 33020,"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": 4183437, "tid": 4183437, + "ts": 658971986051.191, "dur": 6.366, + "args": { + "External id": 33021,"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": 4183437, "tid": 4183437, + "ts": 658971986052.073, "dur": 4.786, + "args": { + "External id": 33022,"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": 4183437, "tid": 4183437, + "ts": 658971986056.078, "dur": 0.628, + "args": { + "External id": 33023,"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": 4183437, "tid": 4183437, + "ts": 658971986058.182, "dur": 42.316, + "args": { + "External id": 33024,"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": 4183437, "tid": 4183437, + "ts": 658971986059.114, "dur": 40.517, + "args": { + "External id": 33025,"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": 4183437, "tid": 4183437, + "ts": 658971986104.808, "dur": 4.004, + "args": { + "External id": 33026,"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": 4183437, "tid": 4183437, + "ts": 658971986106.716, "dur": 0.915, + "args": { + "External id": 33027,"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": 4183437, "tid": 4183437, + "ts": 658971986114.680, "dur": 1.823, + "args": { + "External id": 33028,"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": 4183437, "tid": 4183437, + "ts": 658971986123.876, "dur": 5.449, + "args": { + "External id": 33029,"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": 4183437, "tid": 4183437, + "ts": 658971986125.779, "dur": 3.291, + "args": { + "External id": 33030,"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": 4183437, "tid": 4183437, + "ts": 658971986206.233, "dur": 188.125, + "args": { + "External id": 33031,"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": 4183437, "tid": 4183437, + "ts": 658971986208.528, "dur": 2.527, + "args": { + "External id": 33032,"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": 4183437, "tid": 4183437, + "ts": 658971986212.653, "dur": 181.248, + "args": { + "External id": 33033,"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": 4183437, "tid": 4183437, + "ts": 658971986216.298, "dur": 0.502, + "args": { + "External id": 33034,"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": 4183437, "tid": 4183437, + "ts": 658971986218.254, "dur": 18.276, + "args": { + "External id": 33035,"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": 4183437, "tid": 4183437, + "ts": 658971986238.264, "dur": 4.024, + "args": { + "External id": 33036,"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": 4183437, "tid": 4183437, + "ts": 658971986240.742, "dur": 1.253, + "args": { + "External id": 33037,"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": 4183437, "tid": 4183437, + "ts": 658971986243.195, "dur": 38.714, + "args": { + "External id": 33038,"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": 4183437, "tid": 4183437, + "ts": 658971986246.333, "dur": 1.267, + "args": { + "External id": 33039,"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": 4183437, "tid": 4183437, + "ts": 658971986248.859, "dur": 32.464, + "args": { + "External id": 33040,"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": 4183437, "tid": 4183437, + "ts": 658971986251.298, "dur": 2.446, + "args": { + "External id": 33041,"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": 4183437, "tid": 4183437, + "ts": 658971986284.031, "dur": 20.053, + "args": { + "External id": 33042,"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": 4183437, "tid": 4183437, + "ts": 658971986305.487, "dur": 12.933, + "args": { + "External id": 33043,"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": 4183437, "tid": 4183437, + "ts": 658971986321.106, "dur": 12.024, + "args": { + "External id": 33044,"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": 4183437, "tid": 4183437, + "ts": 658971986334.493, "dur": 11.138, + "args": { + "External id": 33045,"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": 4183437, "tid": 4183437, + "ts": 658971986347.706, "dur": 20.185, + "args": { + "External id": 33046,"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": 4183437, "tid": 4183437, + "ts": 658971986349.835, "dur": 1.569, + "args": { + "External id": 33047,"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": 4183437, "tid": 4183437, + "ts": 658971986353.568, "dur": 1.084, + "args": { + "External id": 33048,"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": 4183437, "tid": 4183437, + "ts": 658971986369.372, "dur": 10.847, + "args": { + "External id": 33049,"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": 4183437, "tid": 4183437, + "ts": 658971986381.432, "dur": 11.404, + "args": { + "External id": 33050,"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": 4183437, "tid": 4183437, + "ts": 658971986401.419, "dur": 2.520, + "args": { + "External id": 33051,"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": 4183437, "tid": 4183437, + "ts": 658971986416.010, "dur": 3.746, + "args": { + "External id": 33052,"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": 4183437, "tid": 4183437, + "ts": 658971986418.434, "dur": 0.493, + "args": { + "External id": 33053,"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": 4183437, "tid": 4183437, + "ts": 658971986484.010, "dur": 42.481, + "args": { + "External id": 33054,"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": 4183437, "tid": 4183437, + "ts": 658971986530.795, "dur": 7.310, + "args": { + "External id": 33055,"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": 4183437, "tid": 4183437, + "ts": 658971986533.366, "dur": 3.656, + "args": { + "External id": 33056,"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": 4183437, "tid": 4183437, + "ts": 658971986539.340, "dur": 25.638, + "args": { + "External id": 33057,"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": 4183437, "tid": 4183437, + "ts": 658971986569.224, "dur": 5.864, + "args": { + "External id": 33058,"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": 4183437, "tid": 4183437, + "ts": 658971986570.542, "dur": 3.755, + "args": { + "External id": 33059,"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": 4183437, "tid": 4183437, + "ts": 658971986573.043, "dur": 1.043, + "args": { + "External id": 33060,"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": 4183437, "tid": 4183437, + "ts": 658971986577.513, "dur": 40.497, + "args": { + "External id": 33061,"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": 4183437, "tid": 4183437, + "ts": 658971986578.360, "dur": 39.038, + "args": { + "External id": 33062,"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": 4183437, "tid": 4183437, + "ts": 658971986621.514, "dur": 13.747, + "args": { + "External id": 33063,"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": 4183437, "tid": 4183437, + "ts": 658971986640.541, "dur": 3.681, + "args": { + "External id": 33064,"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": 4183437, "tid": 4183437, + "ts": 658971986642.765, "dur": 0.682, + "args": { + "External id": 33065,"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": 4183437, "tid": 4183437, + "ts": 658971986647.869, "dur": 91.201, + "args": { + "External id": 33066,"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": 4183437, "tid": 4183437, + "ts": 658971986648.890, "dur": 40.953, + "args": { + "External id": 33067,"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": 4183437, "tid": 4183437, + "ts": 658971986649.615, "dur": 39.248, + "args": { + "External id": 33068,"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": 4183437, "tid": 4183437, + "ts": 658971986687.512, "dur": 0.895, + "args": { + "External id": 33069,"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": 4183437, "tid": 4183437, + "ts": 658971986690.566, "dur": 47.944, + "args": { + "External id": 33070,"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": 4183437, "tid": 4183437, + "ts": 658971986691.454, "dur": 46.391, + "args": { + "External id": 33071,"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": 4183437, "tid": 4183437, + "ts": 658971986744.114, "dur": 4.446, + "args": { + "External id": 33072,"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": 4183437, "tid": 4183437, + "ts": 658971986746.419, "dur": 0.791, + "args": { + "External id": 33073,"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": 4183437, "tid": 4183437, + "ts": 658971986755.047, "dur": 1.874, + "args": { + "External id": 33074,"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": 4183437, "tid": 4183437, + "ts": 658971986764.892, "dur": 6.305, + "args": { + "External id": 33075,"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": 4183437, "tid": 4183437, + "ts": 658971986767.086, "dur": 3.867, + "args": { + "External id": 33076,"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": 4183437, "tid": 4183437, + "ts": 658971986851.503, "dur": 279.082, + "args": { + "External id": 33077,"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": 4183437, "tid": 4183437, + "ts": 658971986853.744, "dur": 4.113, + "args": { + "External id": 33078,"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": 4183437, "tid": 4183437, + "ts": 658971986859.330, "dur": 270.821, + "args": { + "External id": 33079,"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": 4183437, "tid": 4183437, + "ts": 658971986861.381, "dur": 0.527, + "args": { + "External id": 33080,"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": 4183437, "tid": 4183437, + "ts": 658971986863.114, "dur": 21.389, + "args": { + "External id": 33081,"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": 4183437, "tid": 4183437, + "ts": 658971986886.342, "dur": 5.679, + "args": { + "External id": 33082,"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": 4183437, "tid": 4183437, + "ts": 658971986891.070, "dur": 0.739, + "args": { + "External id": 33083,"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": 4183437, "tid": 4183437, + "ts": 658971986893.068, "dur": 31.621, + "args": { + "External id": 33084,"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": 4183437, "tid": 4183437, + "ts": 658971986893.972, "dur": 1.117, + "args": { + "External id": 33085,"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": 4183437, "tid": 4183437, + "ts": 658971986896.343, "dur": 28.079, + "args": { + "External id": 33086,"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": 4183437, "tid": 4183437, + "ts": 658971986898.740, "dur": 2.264, + "args": { + "External id": 33087,"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": 4183437, "tid": 4183437, + "ts": 658971986926.427, "dur": 41.748, + "args": { + "External id": 33088,"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": 4183437, "tid": 4183437, + "ts": 658971986969.491, "dur": 40.246, + "args": { + "External id": 33089,"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": 4183437, "tid": 4183437, + "ts": 658971987011.916, "dur": 35.056, + "args": { + "External id": 33090,"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": 4183437, "tid": 4183437, + "ts": 658971987048.558, "dur": 26.284, + "args": { + "External id": 33091,"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": 4183437, "tid": 4183437, + "ts": 658971987076.320, "dur": 23.260, + "args": { + "External id": 33092,"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": 4183437, "tid": 4183437, + "ts": 658971987080.580, "dur": 0.836, + "args": { + "External id": 33093,"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": 4183437, "tid": 4183437, + "ts": 658971987084.126, "dur": 0.964, + "args": { + "External id": 33094,"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": 4183437, "tid": 4183437, + "ts": 658971987101.229, "dur": 14.293, + "args": { + "External id": 33095,"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": 4183437, "tid": 4183437, + "ts": 658971987116.655, "dur": 12.516, + "args": { + "External id": 33096,"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": 4183437, "tid": 4183437, + "ts": 658971987136.365, "dur": 1.593, + "args": { + "External id": 33097,"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": 4183437, "tid": 4183437, + "ts": 658971987146.605, "dur": 3.815, + "args": { + "External id": 33098,"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": 4183437, "tid": 4183437, + "ts": 658971987149.245, "dur": 0.424, + "args": { + "External id": 33099,"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": 4183437, "tid": 4183437, + "ts": 658971987210.484, "dur": 39.563, + "args": { + "External id": 33100,"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": 4183437, "tid": 4183437, + "ts": 658971987254.290, "dur": 4.740, + "args": { + "External id": 33101,"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": 4183437, "tid": 4183437, + "ts": 658971987257.122, "dur": 0.975, + "args": { + "External id": 33102,"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": 4183437, "tid": 4183437, + "ts": 658971987260.311, "dur": 41.372, + "args": { + "External id": 33103,"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": 4183437, "tid": 4183437, + "ts": 658971987308.346, "dur": 6.655, + "args": { + "External id": 33104,"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": 4183437, "tid": 4183437, + "ts": 658971987309.933, "dur": 4.113, + "args": { + "External id": 33105,"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": 4183437, "tid": 4183437, + "ts": 658971987312.002, "dur": 1.854, + "args": { + "External id": 33106,"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": 4183437, "tid": 4183437, + "ts": 658971987317.970, "dur": 41.765, + "args": { + "External id": 33107,"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": 4183437, "tid": 4183437, + "ts": 658971987319.189, "dur": 39.899, + "args": { + "External id": 33108,"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": 4183437, "tid": 4183437, + "ts": 658971987363.524, "dur": 15.932, + "args": { + "External id": 33109,"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": 4183437, "tid": 4183437, + "ts": 658971987385.510, "dur": 4.223, + "args": { + "External id": 33110,"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": 4183437, "tid": 4183437, + "ts": 658971987388.119, "dur": 0.700, + "args": { + "External id": 33111,"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": 4183437, "tid": 4183437, + "ts": 658971987393.888, "dur": 45.978, + "args": { + "External id": 33112,"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": 4183437, "tid": 4183437, + "ts": 658971987394.829, "dur": 4.058, + "args": { + "External id": 33113,"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": 4183437, "tid": 4183437, + "ts": 658971987395.639, "dur": 2.627, + "args": { + "External id": 33114,"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": 4183437, "tid": 4183437, + "ts": 658971987397.477, "dur": 0.642, + "args": { + "External id": 33115,"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": 4183437, "tid": 4183437, + "ts": 658971987399.451, "dur": 40.017, + "args": { + "External id": 33116,"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": 4183437, "tid": 4183437, + "ts": 658971987400.419, "dur": 38.518, + "args": { + "External id": 33117,"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": 4183437, "tid": 4183437, + "ts": 658971987444.112, "dur": 3.636, + "args": { + "External id": 33118,"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": 4183437, "tid": 4183437, + "ts": 658971987445.853, "dur": 0.639, + "args": { + "External id": 33119,"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": 4183437, "tid": 4183437, + "ts": 658971987453.948, "dur": 1.636, + "args": { + "External id": 33120,"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": 4183437, "tid": 4183437, + "ts": 658971987462.473, "dur": 5.547, + "args": { + "External id": 33121,"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": 4183437, "tid": 4183437, + "ts": 658971987464.316, "dur": 3.464, + "args": { + "External id": 33122,"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": 4183437, "tid": 4183437, + "ts": 658971987546.732, "dur": 220.728, + "args": { + "External id": 33123,"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": 4183437, "tid": 4183437, + "ts": 658971987551.355, "dur": 2.004, + "args": { + "External id": 33124,"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": 4183437, "tid": 4183437, + "ts": 658971987554.745, "dur": 212.230, + "args": { + "External id": 33125,"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": 4183437, "tid": 4183437, + "ts": 658971987556.321, "dur": 0.366, + "args": { + "External id": 33126,"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": 4183437, "tid": 4183437, + "ts": 658971987558.068, "dur": 20.213, + "args": { + "External id": 33127,"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": 4183437, "tid": 4183437, + "ts": 658971987579.646, "dur": 5.160, + "args": { + "External id": 33128,"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": 4183437, "tid": 4183437, + "ts": 658971987583.632, "dur": 0.901, + "args": { + "External id": 33129,"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": 4183437, "tid": 4183437, + "ts": 658971987585.631, "dur": 21.439, + "args": { + "External id": 33130,"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": 4183437, "tid": 4183437, + "ts": 658971987586.761, "dur": 1.353, + "args": { + "External id": 33131,"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": 4183437, "tid": 4183437, + "ts": 658971987589.213, "dur": 17.610, + "args": { + "External id": 33132,"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": 4183437, "tid": 4183437, + "ts": 658971987591.610, "dur": 2.234, + "args": { + "External id": 33133,"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": 4183437, "tid": 4183437, + "ts": 658971987608.608, "dur": 20.981, + "args": { + "External id": 33134,"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": 4183437, "tid": 4183437, + "ts": 658971987630.849, "dur": 14.248, + "args": { + "External id": 33135,"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": 4183437, "tid": 4183437, + "ts": 658971987647.577, "dur": 48.885, + "args": { + "External id": 33136,"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": 4183437, "tid": 4183437, + "ts": 658971987698.928, "dur": 14.357, + "args": { + "External id": 33137,"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": 4183437, "tid": 4183437, + "ts": 658971987715.196, "dur": 23.459, + "args": { + "External id": 33138,"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": 4183437, "tid": 4183437, + "ts": 658971987717.506, "dur": 2.281, + "args": { + "External id": 33139,"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": 4183437, "tid": 4183437, + "ts": 658971987722.636, "dur": 0.779, + "args": { + "External id": 33140,"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": 4183437, "tid": 4183437, + "ts": 658971987740.175, "dur": 12.862, + "args": { + "External id": 33141,"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": 4183437, "tid": 4183437, + "ts": 658971987754.298, "dur": 11.507, + "args": { + "External id": 33142,"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": 4183437, "tid": 4183437, + "ts": 658971987774.559, "dur": 2.159, + "args": { + "External id": 33143,"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": 4183437, "tid": 4183437, + "ts": 658971987785.761, "dur": 3.702, + "args": { + "External id": 33144,"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": 4183437, "tid": 4183437, + "ts": 658971987788.190, "dur": 0.538, + "args": { + "External id": 33145,"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": 4183437, "tid": 4183437, + "ts": 658971987857.231, "dur": 44.816, + "args": { + "External id": 33146,"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": 4183437, "tid": 4183437, + "ts": 658971987906.557, "dur": 7.366, + "args": { + "External id": 33147,"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": 4183437, "tid": 4183437, + "ts": 658971987912.305, "dur": 0.648, + "args": { + "External id": 33148,"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": 4183437, "tid": 4183437, + "ts": 658971987915.554, "dur": 22.510, + "args": { + "External id": 33149,"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": 4183437, "tid": 4183437, + "ts": 658971987942.443, "dur": 7.727, + "args": { + "External id": 33150,"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": 4183437, "tid": 4183437, + "ts": 658971987944.102, "dur": 5.476, + "args": { + "External id": 33151,"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": 4183437, "tid": 4183437, + "ts": 658971987945.907, "dur": 3.428, + "args": { + "External id": 33152,"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": 4183437, "tid": 4183437, + "ts": 658971987952.713, "dur": 39.201, + "args": { + "External id": 33153,"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": 4183437, "tid": 4183437, + "ts": 658971987953.807, "dur": 37.289, + "args": { + "External id": 33154,"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": 4183437, "tid": 4183437, + "ts": 658971987995.729, "dur": 14.915, + "args": { + "External id": 33155,"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": 4183437, "tid": 4183437, + "ts": 658971988015.067, "dur": 24.460, + "args": { + "External id": 33156,"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": 4183437, "tid": 4183437, + "ts": 658971988017.874, "dur": 21.308, + "args": { + "External id": 33157,"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": 4183437, "tid": 4183437, + "ts": 658971988022.911, "dur": 1.032, + "args": { + "External id": 33158,"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": 4183437, "tid": 4183437, + "ts": 658971988044.228, "dur": 25.770, + "args": { + "External id": 33159,"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": 4183437, "tid": 4183437, + "ts": 658971988046.096, "dur": 23.691, + "args": { + "External id": 33160,"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": 4183437, "tid": 4183437, + "ts": 658971988050.883, "dur": 3.308, + "args": { + "External id": 33161,"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": 4183437, "tid": 4183437, + "ts": 658971988055.716, "dur": 13.618, + "args": { + "External id": 33162,"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": 4183437, "tid": 4183437, + "ts": 658971988082.015, "dur": 5.373, + "args": { + "External id": 33163,"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": 4183437, "tid": 4183437, + "ts": 658971988084.207, "dur": 2.868, + "args": { + "External id": 33164,"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": 4183437, "tid": 4183437, + "ts": 658971988088.571, "dur": 1.689, + "args": { + "External id": 33165,"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": 4183437, "tid": 4183437, + "ts": 658971988089.480, "dur": 0.705, + "args": { + "External id": 33166,"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": 4183437, "tid": 4183437, + "ts": 658971988129.357, "dur": 23.504, + "args": { + "External id": 33167,"Sequence number": 460100, "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": 4183437, "tid": 4183437, + "ts": 658971988154.810, "dur": 15.465, + "args": { + "External id": 33168,"Sequence number": 460101, "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": 4183437, "tid": 4183437, "ts": 658971988154.810, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 4183437, "tid": 4183437, + "ts": 658971988298.119, "dur": 42.564, + "args": { + "External id": 33169,"Record function id": 0, "Ev Idx": 8576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 4183437, "tid": 4183437, + "ts": 658971988443.382, "dur": 39.381, + "args": { + "External id": 33170,"Sequence number": 460102, "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": 4183437, "tid": 4183437, "ts": 658971988443.382, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 4183437, "tid": 4183437, + "ts": 658971988543.780, "dur": 26.832, + "args": { + "External id": 33171,"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": 4183437, "tid": 4183437, + "ts": 658971988545.335, "dur": 8.398, + "args": { + "External id": 33172,"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": 4183437, "tid": 4183437, + "ts": 658971988549.328, "dur": 3.765, + "args": { + "External id": 33173,"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": 4183437, "tid": 4183437, + "ts": 658971988555.219, "dur": 15.029, + "args": { + "External id": 33174,"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": 4183437, "tid": 4183437, + "ts": 658972439747.969, "dur": 45.319, + "args": { + "External id": 33175,"Sequence number": 460103, "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": 4183437, "tid": 4183437, + "ts": 658972439852.541, "dur": 19.918, + "args": { + "External id": 33176,"Sequence number": 460104, "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": 4183437, "tid": 4183437, + "ts": 658972439879.674, "dur": 22.561, + "args": { + "External id": 33177,"Sequence number": 460105, "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": 4183437, "tid": 4183437, + "ts": 658972440320.461, "dur": 25.700, + "args": { + "External id": 33178,"Sequence number": 460106, "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": 4183437, "tid": 4183437, + "ts": 658972440352.705, "dur": 13.523, + "args": { + "External id": 33179,"Sequence number": 460107, "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": 4183437, "tid": 4183437, + "ts": 658972441733.345, "dur": 2091.837, + "args": { + "External id": 33180,"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": 4183437, "tid": 4183437, + "ts": 658972442173.213, "dur": 576.429, + "args": { + "External id": 33181,"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": 4183437, "tid": 4183437, + "ts": 658972442191.206, "dur": 62.933, + "args": { + "External id": 33182,"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": 4183437, "tid": 4183437, + "ts": 658972442194.400, "dur": 11.965, + "args": { + "External id": 33183,"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": 4183437, "tid": 4183437, + "ts": 658972442209.336, "dur": 44.509, + "args": { + "External id": 33184,"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": 4183437, "tid": 4183437, + "ts": 658972442211.493, "dur": 41.786, + "args": { + "External id": 33185,"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": 4183437, "tid": 4183437, + "ts": 658972443853.981, "dur": 3.416, + "args": { + "External id": 33186,"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": 4183437, "tid": 4183437, + "ts": 658972443859.701, "dur": 0.551, + "args": { + "External id": 33187,"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": 4183437, "tid": 4183437, + "ts": 658972443861.441, "dur": 0.564, + "args": { + "External id": 33188,"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": 4183437, "tid": 4183437, + "ts": 658972443863.296, "dur": 0.344, + "args": { + "External id": 33189,"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": 4183437, "tid": 4183437, + "ts": 658972443864.734, "dur": 0.525, + "args": { + "External id": 33190,"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": 4183437, "tid": 4183437, + "ts": 658972443866.338, "dur": 0.450, + "args": { + "External id": 33191,"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": 4183437, "tid": 4183437, + "ts": 658972443867.843, "dur": 0.399, + "args": { + "External id": 33192,"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": 4183437, "tid": 4183437, + "ts": 658972443870.412, "dur": 0.460, + "args": { + "External id": 33193,"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": 4183437, "tid": 4183437, + "ts": 658972443871.877, "dur": 0.284, + "args": { + "External id": 33194,"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": 4183437, "tid": 4183437, + "ts": 658972443873.179, "dur": 0.313, + "args": { + "External id": 33195,"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": 4183437, "tid": 4183437, + "ts": 658972443874.473, "dur": 0.516, + "args": { + "External id": 33196,"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": 4183437, "tid": 4183437, + "ts": 658972443875.822, "dur": 0.300, + "args": { + "External id": 33197,"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": 4183437, "tid": 4183437, + "ts": 658972443877.125, "dur": 0.309, + "args": { + "External id": 33198,"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": 4183437, "tid": 4183437, + "ts": 658972443878.199, "dur": 0.420, + "args": { + "External id": 33199,"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": 4183437, "tid": 4183437, + "ts": 658972443879.395, "dur": 0.404, + "args": { + "External id": 33200,"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": 4183437, "tid": 4183437, + "ts": 658972443881.829, "dur": 0.420, + "args": { + "External id": 33201,"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": 4183437, "tid": 4183437, + "ts": 658972443883.242, "dur": 0.204, + "args": { + "External id": 33202,"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": 4183437, "tid": 4183437, + "ts": 658972443884.669, "dur": 0.207, + "args": { + "External id": 33203,"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": 4183437, "tid": 4183437, + "ts": 658972443885.849, "dur": 0.206, + "args": { + "External id": 33204,"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": 4183437, "tid": 4183437, + "ts": 658972443886.943, "dur": 0.206, + "args": { + "External id": 33205,"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": 4183437, "tid": 4183437, + "ts": 658972443887.941, "dur": 0.205, + "args": { + "External id": 33206,"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": 4183437, "tid": 4183437, + "ts": 658972443888.943, "dur": 0.206, + "args": { + "External id": 33207,"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": 4183437, "tid": 4183437, + "ts": 658972443889.910, "dur": 0.220, + "args": { + "External id": 33208,"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": 4183437, "tid": 4183437, + "ts": 658972443892.254, "dur": 0.211, + "args": { + "External id": 33209,"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": 4183437, "tid": 4183437, + "ts": 658972443896.796, "dur": 0.216, + "args": { + "External id": 33210,"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": 4183437, "tid": 4183437, + "ts": 658972443897.927, "dur": 0.224, + "args": { + "External id": 33211,"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": 4183437, "tid": 4183437, + "ts": 658972443899.126, "dur": 0.216, + "args": { + "External id": 33212,"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": 4183437, "tid": 4183437, + "ts": 658972443900.121, "dur": 0.206, + "args": { + "External id": 33213,"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": 4183437, "tid": 4183437, + "ts": 658972443901.097, "dur": 0.232, + "args": { + "External id": 33214,"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": 4183437, "tid": 4183437, + "ts": 658972443902.176, "dur": 0.239, + "args": { + "External id": 33215,"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": 4183437, "tid": 4183437, + "ts": 658972443903.203, "dur": 0.321, + "args": { + "External id": 33216,"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": 4183437, "tid": 4183437, + "ts": 658972443906.188, "dur": 0.220, + "args": { + "External id": 33217,"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": 4183437, "tid": 4183437, + "ts": 658972443907.186, "dur": 0.208, + "args": { + "External id": 33218,"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": 4183437, "tid": 4183437, + "ts": 658972443908.421, "dur": 0.322, + "args": { + "External id": 33219,"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": 4183437, "tid": 4183437, + "ts": 658972443909.561, "dur": 0.268, + "args": { + "External id": 33220,"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": 4183437, "tid": 4183437, + "ts": 658972443910.631, "dur": 0.307, + "args": { + "External id": 33221,"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": 4183437, "tid": 4183437, + "ts": 658972443911.738, "dur": 0.321, + "args": { + "External id": 33222,"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": 4183437, "tid": 4183437, + "ts": 658972443912.905, "dur": 0.389, + "args": { + "External id": 33223,"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": 4183437, "tid": 4183437, + "ts": 658972443914.088, "dur": 0.278, + "args": { + "External id": 33224,"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": 4183437, "tid": 4183437, + "ts": 658972443916.952, "dur": 0.437, + "args": { + "External id": 33225,"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": 4183437, "tid": 4183437, + "ts": 658972443918.190, "dur": 0.291, + "args": { + "External id": 33226,"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": 4183437, "tid": 4183437, + "ts": 658972443919.465, "dur": 0.228, + "args": { + "External id": 33227,"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": 4183437, "tid": 4183437, + "ts": 658972443920.695, "dur": 0.426, + "args": { + "External id": 33228,"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": 4183437, "tid": 4183437, + "ts": 658972443921.886, "dur": 0.321, + "args": { + "External id": 33229,"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": 4183437, "tid": 4183437, + "ts": 658972443923.021, "dur": 0.206, + "args": { + "External id": 33230,"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": 4183437, "tid": 4183437, + "ts": 658972443923.993, "dur": 0.419, + "args": { + "External id": 33231,"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": 4183437, "tid": 4183437, + "ts": 658972443925.193, "dur": 0.426, + "args": { + "External id": 33232,"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": 4183437, "tid": 4183437, + "ts": 658972443928.902, "dur": 0.452, + "args": { + "External id": 33233,"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": 4183437, "tid": 4183437, + "ts": 658972443930.308, "dur": 0.438, + "args": { + "External id": 33234,"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": 4183437, "tid": 4183437, + "ts": 658972443931.685, "dur": 0.471, + "args": { + "External id": 33235,"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": 4183437, "tid": 4183437, + "ts": 658972443933.108, "dur": 0.445, + "args": { + "External id": 33236,"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": 4183437, "tid": 4183437, + "ts": 658972443934.400, "dur": 0.212, + "args": { + "External id": 33237,"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": 4183437, "tid": 4183437, + "ts": 658972443935.443, "dur": 0.420, + "args": { + "External id": 33238,"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": 4183437, "tid": 4183437, + "ts": 658972443937.041, "dur": 0.451, + "args": { + "External id": 33239,"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": 4183437, "tid": 4183437, + "ts": 658972443938.628, "dur": 0.232, + "args": { + "External id": 33240,"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": 4183437, "tid": 4183437, + "ts": 658972443941.403, "dur": 0.473, + "args": { + "External id": 33241,"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": 4183437, "tid": 4183437, + "ts": 658972443942.715, "dur": 0.413, + "args": { + "External id": 33242,"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": 4183437, "tid": 4183437, + "ts": 658972443943.894, "dur": 0.411, + "args": { + "External id": 33243,"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": 4183437, "tid": 4183437, + "ts": 658972443945.087, "dur": 0.488, + "args": { + "External id": 33244,"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": 4183437, "tid": 4183437, + "ts": 658972443946.354, "dur": 0.206, + "args": { + "External id": 33245,"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": 4183437, "tid": 4183437, + "ts": 658972443947.349, "dur": 0.392, + "args": { + "External id": 33246,"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": 4183437, "tid": 4183437, + "ts": 658972443948.543, "dur": 0.407, + "args": { + "External id": 33247,"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": 4183437, "tid": 4183437, + "ts": 658972443949.742, "dur": 0.229, + "args": { + "External id": 33248,"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": 4183437, "tid": 4183437, + "ts": 658972443955.238, "dur": 0.394, + "args": { + "External id": 33249,"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": 4183437, "tid": 4183437, + "ts": 658972443956.400, "dur": 0.420, + "args": { + "External id": 33250,"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": 4183437, "tid": 4183437, + "ts": 658972443957.803, "dur": 0.398, + "args": { + "External id": 33251,"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": 4183437, "tid": 4183437, + "ts": 658972443958.981, "dur": 0.393, + "args": { + "External id": 33252,"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": 4183437, "tid": 4183437, + "ts": 658972443960.163, "dur": 0.202, + "args": { + "External id": 33253,"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": 4183437, "tid": 4183437, + "ts": 658972443961.132, "dur": 0.332, + "args": { + "External id": 33254,"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": 4183437, "tid": 4183437, + "ts": 658972443962.232, "dur": 0.207, + "args": { + "External id": 33255,"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": 4183437, "tid": 4183437, + "ts": 658972443963.209, "dur": 0.306, + "args": { + "External id": 33256,"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": 4183437, "tid": 4183437, + "ts": 658972443966.167, "dur": 0.204, + "args": { + "External id": 33257,"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": 4183437, "tid": 4183437, + "ts": 658972443967.185, "dur": 0.203, + "args": { + "External id": 33258,"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": 4183437, "tid": 4183437, + "ts": 658972443968.162, "dur": 0.308, + "args": { + "External id": 33259,"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": 4183437, "tid": 4183437, + "ts": 658972443969.287, "dur": 0.232, + "args": { + "External id": 33260,"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": 4183437, "tid": 4183437, + "ts": 658972443970.327, "dur": 0.205, + "args": { + "External id": 33261,"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": 4183437, "tid": 4183437, + "ts": 658972443971.334, "dur": 0.273, + "args": { + "External id": 33262,"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": 4183437, "tid": 4183437, + "ts": 658972443973.235, "dur": 0.212, + "args": { + "External id": 33263,"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": 4183437, "tid": 4183437, + "ts": 658972443974.259, "dur": 0.208, + "args": { + "External id": 33264,"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": 4183437, "tid": 4183437, + "ts": 658972443976.565, "dur": 0.254, + "args": { + "External id": 33265,"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": 4183437, "tid": 4183437, + "ts": 658972443977.599, "dur": 0.223, + "args": { + "External id": 33266,"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": 4183437, "tid": 4183437, + "ts": 658972443978.646, "dur": 0.207, + "args": { + "External id": 33267,"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": 4183437, "tid": 4183437, + "ts": 658972443979.643, "dur": 0.213, + "args": { + "External id": 33268,"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": 4183437, "tid": 4183437, + "ts": 658972443980.627, "dur": 0.211, + "args": { + "External id": 33269,"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": 4183437, "tid": 4183437, + "ts": 658972443981.648, "dur": 0.209, + "args": { + "External id": 33270,"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": 4183437, "tid": 4183437, + "ts": 658972443982.643, "dur": 0.211, + "args": { + "External id": 33271,"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": 4183437, "tid": 4183437, + "ts": 658972443983.647, "dur": 0.207, + "args": { + "External id": 33272,"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": 4183437, "tid": 4183437, + "ts": 658972443985.707, "dur": 0.209, + "args": { + "External id": 33273,"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": 4183437, "tid": 4183437, + "ts": 658972443986.875, "dur": 0.205, + "args": { + "External id": 33274,"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": 4183437, "tid": 4183437, + "ts": 658972443987.882, "dur": 0.225, + "args": { + "External id": 33275,"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": 4183437, "tid": 4183437, + "ts": 658972443989.059, "dur": 0.211, + "args": { + "External id": 33276,"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": 4183437, "tid": 4183437, + "ts": 658972443990.047, "dur": 0.207, + "args": { + "External id": 33277,"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": 4183437, "tid": 4183437, + "ts": 658972443991.063, "dur": 0.211, + "args": { + "External id": 33278,"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": 4183437, "tid": 4183437, + "ts": 658972443992.745, "dur": 0.240, + "args": { + "External id": 33279,"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": 4183437, "tid": 4183437, + "ts": 658972443993.761, "dur": 0.210, + "args": { + "External id": 33280,"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": 4183437, "tid": 4183437, + "ts": 658972444019.014, "dur": 0.232, + "args": { + "External id": 37889,"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": 4183437, "tid": 4183437, + "ts": 658972444020.249, "dur": 0.223, + "args": { + "External id": 37890,"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": 4183437, "tid": 4183437, + "ts": 658972444021.296, "dur": 0.244, + "args": { + "External id": 37891,"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": 4183437, "tid": 4183437, + "ts": 658972444022.357, "dur": 0.229, + "args": { + "External id": 37892,"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": 4183437, "tid": 4183437, + "ts": 658972444023.387, "dur": 0.213, + "args": { + "External id": 37893,"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": 4183437, "tid": 4183437, + "ts": 658972444024.406, "dur": 0.207, + "args": { + "External id": 37894,"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": 4183437, "tid": 4183437, + "ts": 658972444025.406, "dur": 0.207, + "args": { + "External id": 37895,"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": 4183437, "tid": 4183437, + "ts": 658972444026.392, "dur": 0.208, + "args": { + "External id": 37896,"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": 4183437, "tid": 4183437, + "ts": 658972444028.732, "dur": 0.236, + "args": { + "External id": 37897,"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": 4183437, "tid": 4183437, + "ts": 658972444029.755, "dur": 0.209, + "args": { + "External id": 37898,"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": 4183437, "tid": 4183437, + "ts": 658972444030.740, "dur": 0.212, + "args": { + "External id": 37899,"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": 4183437, "tid": 4183437, + "ts": 658972444031.751, "dur": 0.207, + "args": { + "External id": 37900,"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": 4183437, "tid": 4183437, + "ts": 658972444032.743, "dur": 0.208, + "args": { + "External id": 37901,"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": 4183437, "tid": 4183437, + "ts": 658972444033.723, "dur": 0.239, + "args": { + "External id": 37902,"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": 4183437, "tid": 4183437, + "ts": 658972444035.216, "dur": 0.211, + "args": { + "External id": 37903,"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": 4183437, "tid": 4183437, + "ts": 658972444036.196, "dur": 0.207, + "args": { + "External id": 37904,"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": 4183437, "tid": 4183437, + "ts": 658972444038.345, "dur": 0.208, + "args": { + "External id": 37905,"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": 4183437, "tid": 4183437, + "ts": 658972444039.365, "dur": 0.205, + "args": { + "External id": 37906,"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": 4183437, "tid": 4183437, + "ts": 658972444040.343, "dur": 0.210, + "args": { + "External id": 37907,"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": 4183437, "tid": 4183437, + "ts": 658972444041.367, "dur": 0.207, + "args": { + "External id": 37908,"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": 4183437, "tid": 4183437, + "ts": 658972444042.340, "dur": 0.211, + "args": { + "External id": 37909,"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": 4183437, "tid": 4183437, + "ts": 658972444043.315, "dur": 0.210, + "args": { + "External id": 37910,"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": 4183437, "tid": 4183437, + "ts": 658972444044.325, "dur": 0.208, + "args": { + "External id": 37911,"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": 4183437, "tid": 4183437, + "ts": 658972444048.966, "dur": 0.213, + "args": { + "External id": 37912,"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": 4183437, "tid": 4183437, + "ts": 658972444051.332, "dur": 0.210, + "args": { + "External id": 37913,"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": 4183437, "tid": 4183437, + "ts": 658972444052.301, "dur": 0.224, + "args": { + "External id": 37914,"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": 4183437, "tid": 4183437, + "ts": 658972444053.272, "dur": 0.208, + "args": { + "External id": 37915,"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": 4183437, "tid": 4183437, + "ts": 658972444054.225, "dur": 0.208, + "args": { + "External id": 37916,"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": 4183437, "tid": 4183437, + "ts": 658972444055.172, "dur": 0.207, + "args": { + "External id": 37917,"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": 4183437, "tid": 4183437, + "ts": 658972444056.092, "dur": 0.205, + "args": { + "External id": 37918,"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": 4183437, "tid": 4183437, + "ts": 658972444057.056, "dur": 0.215, + "args": { + "External id": 37919,"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": 4183437, "tid": 4183437, + "ts": 658972444058.012, "dur": 0.203, + "args": { + "External id": 37920,"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": 4183437, "tid": 4183437, + "ts": 658972444060.074, "dur": 0.213, + "args": { + "External id": 37921,"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": 4183437, "tid": 4183437, + "ts": 658972444061.049, "dur": 0.258, + "args": { + "External id": 37922,"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": 4183437, "tid": 4183437, + "ts": 658972444063.436, "dur": 0.216, + "args": { + "External id": 37923,"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": 4183437, "tid": 4183437, + "ts": 658972444064.443, "dur": 0.210, + "args": { + "External id": 37924,"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": 4183437, "tid": 4183437, + "ts": 658972444065.411, "dur": 0.212, + "args": { + "External id": 37925,"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": 4183437, "tid": 4183437, + "ts": 658972444066.379, "dur": 0.207, + "args": { + "External id": 37926,"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": 4183437, "tid": 4183437, + "ts": 658972444067.327, "dur": 0.207, + "args": { + "External id": 37927,"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": 4183437, "tid": 4183437, + "ts": 658972444068.319, "dur": 0.206, + "args": { + "External id": 37928,"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": 4183437, "tid": 4183437, + "ts": 658972444073.793, "dur": 0.213, + "args": { + "External id": 37929,"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": 4183437, "tid": 4183437, + "ts": 658972444074.789, "dur": 0.207, + "args": { + "External id": 37930,"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": 4183437, "tid": 4183437, + "ts": 658972444075.759, "dur": 0.206, + "args": { + "External id": 37931,"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": 4183437, "tid": 4183437, + "ts": 658972444076.849, "dur": 0.207, + "args": { + "External id": 37932,"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": 4183437, "tid": 4183437, + "ts": 658972444077.805, "dur": 0.207, + "args": { + "External id": 37933,"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": 4183437, "tid": 4183437, + "ts": 658972444078.764, "dur": 0.208, + "args": { + "External id": 37934,"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": 4183437, "tid": 4183437, + "ts": 658972444079.705, "dur": 0.207, + "args": { + "External id": 37935,"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": 4183437, "tid": 4183437, + "ts": 658972444080.675, "dur": 0.208, + "args": { + "External id": 37936,"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": 4183437, "tid": 4183437, + "ts": 658972444082.833, "dur": 0.214, + "args": { + "External id": 37937,"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": 4183437, "tid": 4183437, + "ts": 658972444083.828, "dur": 0.206, + "args": { + "External id": 37938,"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": 4183437, "tid": 4183437, + "ts": 658972444084.773, "dur": 0.207, + "args": { + "External id": 37939,"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": 4183437, "tid": 4183437, + "ts": 658972444085.746, "dur": 0.208, + "args": { + "External id": 37940,"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": 4183437, "tid": 4183437, + "ts": 658972444086.699, "dur": 0.206, + "args": { + "External id": 37941,"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": 4183437, "tid": 4183437, + "ts": 658972444087.670, "dur": 0.207, + "args": { + "External id": 37942,"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": 4183437, "tid": 4183437, + "ts": 658972444089.285, "dur": 0.209, + "args": { + "External id": 37943,"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": 4183437, "tid": 4183437, + "ts": 658972444090.251, "dur": 0.210, + "args": { + "External id": 37944,"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": 4183437, "tid": 4183437, + "ts": 658972444092.378, "dur": 0.211, + "args": { + "External id": 37945,"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": 4183437, "tid": 4183437, + "ts": 658972444093.418, "dur": 0.207, + "args": { + "External id": 37946,"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": 4183437, "tid": 4183437, + "ts": 658972444094.364, "dur": 0.208, + "args": { + "External id": 37947,"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": 4183437, "tid": 4183437, + "ts": 658972444095.358, "dur": 0.209, + "args": { + "External id": 37948,"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": 4183437, "tid": 4183437, + "ts": 658972444096.354, "dur": 0.213, + "args": { + "External id": 37949,"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": 4183437, "tid": 4183437, + "ts": 658972444097.309, "dur": 0.209, + "args": { + "External id": 37950,"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": 4183437, "tid": 4183437, + "ts": 658972444098.478, "dur": 0.207, + "args": { + "External id": 37951,"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": 4183437, "tid": 4183437, + "ts": 658972444099.425, "dur": 0.207, + "args": { + "External id": 37952,"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": 4183437, "tid": 4183437, + "ts": 658972444101.721, "dur": 0.210, + "args": { + "External id": 37953,"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": 4183437, "tid": 4183437, + "ts": 658972444102.678, "dur": 0.208, + "args": { + "External id": 37954,"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": 4183437, "tid": 4183437, + "ts": 658972444104.276, "dur": 0.231, + "args": { + "External id": 37955,"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": 4183437, "tid": 4183437, + "ts": 658972444105.296, "dur": 0.211, + "args": { + "External id": 37956,"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": 4183437, "tid": 4183437, + "ts": 658972444106.255, "dur": 0.208, + "args": { + "External id": 37957,"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": 4183437, "tid": 4183437, + "ts": 658972444107.211, "dur": 0.209, + "args": { + "External id": 37958,"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": 4183437, "tid": 4183437, + "ts": 658972444108.194, "dur": 0.209, + "args": { + "External id": 37959,"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": 4183437, "tid": 4183437, + "ts": 658972444109.161, "dur": 0.208, + "args": { + "External id": 37960,"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": 4183437, "tid": 4183437, + "ts": 658972444111.164, "dur": 0.234, + "args": { + "External id": 37961,"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": 4183437, "tid": 4183437, + "ts": 658972444112.183, "dur": 0.231, + "args": { + "External id": 37962,"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": 4183437, "tid": 4183437, + "ts": 658972444113.154, "dur": 0.207, + "args": { + "External id": 37963,"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": 4183437, "tid": 4183437, + "ts": 658972444114.144, "dur": 0.207, + "args": { + "External id": 37964,"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": 4183437, "tid": 4183437, + "ts": 658972444115.103, "dur": 0.206, + "args": { + "External id": 37965,"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": 4183437, "tid": 4183437, + "ts": 658972444116.067, "dur": 0.207, + "args": { + "External id": 37966,"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": 4183437, "tid": 4183437, + "ts": 658972444117.411, "dur": 0.208, + "args": { + "External id": 37967,"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": 4183437, "tid": 4183437, + "ts": 658972444118.398, "dur": 0.207, + "args": { + "External id": 37968,"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": 4183437, "tid": 4183437, + "ts": 658972444120.820, "dur": 0.211, + "args": { + "External id": 37969,"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": 4183437, "tid": 4183437, + "ts": 658972444121.796, "dur": 0.233, + "args": { + "External id": 37970,"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": 4183437, "tid": 4183437, + "ts": 658972444122.771, "dur": 0.210, + "args": { + "External id": 37971,"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": 4183437, "tid": 4183437, + "ts": 658972444123.718, "dur": 0.211, + "args": { + "External id": 37972,"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": 4183437, "tid": 4183437, + "ts": 658972444124.685, "dur": 0.206, + "args": { + "External id": 37973,"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": 4183437, "tid": 4183437, + "ts": 658972444125.709, "dur": 0.228, + "args": { + "External id": 37974,"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": 4183437, "tid": 4183437, + "ts": 658972444126.733, "dur": 0.216, + "args": { + "External id": 37975,"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": 4183437, "tid": 4183437, + "ts": 658972444130.958, "dur": 0.209, + "args": { + "External id": 37976,"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": 4183437, "tid": 4183437, + "ts": 658972444133.071, "dur": 0.210, + "args": { + "External id": 37977,"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": 4183437, "tid": 4183437, + "ts": 658972444134.091, "dur": 0.209, + "args": { + "External id": 37978,"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": 4183437, "tid": 4183437, + "ts": 658972444135.047, "dur": 0.210, + "args": { + "External id": 37979,"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": 4183437, "tid": 4183437, + "ts": 658972444136.004, "dur": 0.207, + "args": { + "External id": 37980,"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": 4183437, "tid": 4183437, + "ts": 658972444136.958, "dur": 0.208, + "args": { + "External id": 37981,"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": 4183437, "tid": 4183437, + "ts": 658972444137.939, "dur": 0.209, + "args": { + "External id": 37982,"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": 4183437, "tid": 4183437, + "ts": 658972444138.914, "dur": 0.206, + "args": { + "External id": 37983,"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": 4183437, "tid": 4183437, + "ts": 658972444139.879, "dur": 0.207, + "args": { + "External id": 37984,"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": 4183437, "tid": 4183437, + "ts": 658972444142.484, "dur": 0.207, + "args": { + "External id": 37985,"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": 4183437, "tid": 4183437, + "ts": 658972444143.440, "dur": 0.207, + "args": { + "External id": 37986,"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": 4183437, "tid": 4183437, + "ts": 658972444144.388, "dur": 0.210, + "args": { + "External id": 37987,"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": 4183437, "tid": 4183437, + "ts": 658972444145.367, "dur": 0.206, + "args": { + "External id": 37988,"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": 4183437, "tid": 4183437, + "ts": 658972444146.375, "dur": 0.229, + "args": { + "External id": 37989,"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": 4183437, "tid": 4183437, + "ts": 658972444147.351, "dur": 0.207, + "args": { + "External id": 37990,"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": 4183437, "tid": 4183437, + "ts": 658972444148.319, "dur": 0.208, + "args": { + "External id": 37991,"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": 4183437, "tid": 4183437, + "ts": 658972444149.272, "dur": 0.209, + "args": { + "External id": 37992,"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": 4183437, "tid": 4183437, + "ts": 658972444151.748, "dur": 0.208, + "args": { + "External id": 37993,"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": 4183437, "tid": 4183437, + "ts": 658972444152.749, "dur": 0.208, + "args": { + "External id": 37994,"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": 4183437, "tid": 4183437, + "ts": 658972444154.006, "dur": 0.211, + "args": { + "External id": 37995,"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": 4183437, "tid": 4183437, + "ts": 658972444154.949, "dur": 0.209, + "args": { + "External id": 37996,"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": 4183437, "tid": 4183437, + "ts": 658972444163.231, "dur": 0.254, + "args": { + "External id": 37997,"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": 4183437, "tid": 4183437, + "ts": 658972444164.371, "dur": 0.209, + "args": { + "External id": 37998,"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": 4183437, "tid": 4183437, + "ts": 658972444165.380, "dur": 0.213, + "args": { + "External id": 37999,"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": 4183437, "tid": 4183437, + "ts": 658972444166.394, "dur": 0.209, + "args": { + "External id": 38000,"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": 4183437, "tid": 4183437, + "ts": 658972444168.567, "dur": 0.206, + "args": { + "External id": 38001,"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": 4183437, "tid": 4183437, + "ts": 658972444169.511, "dur": 0.206, + "args": { + "External id": 38002,"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": 4183437, "tid": 4183437, + "ts": 658972444170.500, "dur": 0.205, + "args": { + "External id": 38003,"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": 4183437, "tid": 4183437, + "ts": 658972444171.476, "dur": 0.253, + "args": { + "External id": 38004,"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": 4183437, "tid": 4183437, + "ts": 658972444172.449, "dur": 0.202, + "args": { + "External id": 38005,"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": 4183437, "tid": 4183437, + "ts": 658972444173.372, "dur": 0.204, + "args": { + "External id": 38006,"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": 4183437, "tid": 4183437, + "ts": 658972444174.323, "dur": 0.204, + "args": { + "External id": 38007,"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": 4183437, "tid": 4183437, + "ts": 658972444175.283, "dur": 0.205, + "args": { + "External id": 38008,"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": 4183437, "tid": 4183437, + "ts": 658972444177.260, "dur": 0.210, + "args": { + "External id": 38009,"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": 4183437, "tid": 4183437, + "ts": 658972444178.248, "dur": 0.242, + "args": { + "External id": 38010,"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": 4183437, "tid": 4183437, + "ts": 658972444179.243, "dur": 0.207, + "args": { + "External id": 38011,"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": 4183437, "tid": 4183437, + "ts": 658972444180.190, "dur": 0.202, + "args": { + "External id": 38012,"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": 4183437, "tid": 4183437, + "ts": 658972444223.030, "dur": 1152.726, + "args": { + "External id": 38013,"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": 4183437, "tid": 4183437, + "ts": 658972444580.352, "dur": 728.903, + "args": { + "External id": 38014,"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": 4183437, "tid": 4183437, + "ts": 658972444586.812, "dur": 7.141, + "args": { + "External id": 38015,"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": 4183437, "tid": 4183437, + "ts": 658972444590.670, "dur": 2.693, + "args": { + "External id": 38016,"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": 4183437, "tid": 4183437, + "ts": 658972444594.543, "dur": 3.094, + "args": { + "External id": 38017,"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": 4183437, "tid": 4183437, + "ts": 658972444595.318, "dur": 2.093, + "args": { + "External id": 38018,"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": 4183437, "tid": 4183437, + "ts": 658972444598.034, "dur": 2.773, + "args": { + "External id": 38019,"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": 4183437, "tid": 4183437, + "ts": 658972444600.364, "dur": 0.331, + "args": { + "External id": 38020,"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": 4183437, "tid": 4183437, + "ts": 658972444601.067, "dur": 1.785, + "args": { + "External id": 38021,"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": 4183437, "tid": 4183437, + "ts": 658972444601.490, "dur": 1.292, + "args": { + "External id": 38022,"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": 4183437, "tid": 4183437, + "ts": 658972444604.166, "dur": 4.516, + "args": { + "External id": 38023,"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": 4183437, "tid": 4183437, + "ts": 658972444608.144, "dur": 0.438, + "args": { + "External id": 38024,"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": 4183437, "tid": 4183437, + "ts": 658972444609.001, "dur": 0.916, + "args": { + "External id": 38025,"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": 4183437, "tid": 4183437, + "ts": 658972444609.427, "dur": 0.392, + "args": { + "External id": 38026,"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": 4183437, "tid": 4183437, + "ts": 658972444610.164, "dur": 0.792, + "args": { + "External id": 38027,"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": 4183437, "tid": 4183437, + "ts": 658972444610.513, "dur": 0.353, + "args": { + "External id": 38028,"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": 4183437, "tid": 4183437, + "ts": 658972444611.310, "dur": 4.248, + "args": { + "External id": 38029,"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": 4183437, "tid": 4183437, + "ts": 658972444615.237, "dur": 0.249, + "args": { + "External id": 38030,"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": 4183437, "tid": 4183437, + "ts": 658972444615.802, "dur": 0.896, + "args": { + "External id": 38031,"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": 4183437, "tid": 4183437, + "ts": 658972444616.188, "dur": 0.415, + "args": { + "External id": 38032,"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": 4183437, "tid": 4183437, + "ts": 658972444616.928, "dur": 2.812, + "args": { + "External id": 38033,"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": 4183437, "tid": 4183437, + "ts": 658972444617.278, "dur": 2.359, + "args": { + "External id": 38034,"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": 4183437, "tid": 4183437, + "ts": 658972444619.976, "dur": 2.381, + "args": { + "External id": 38035,"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": 4183437, "tid": 4183437, + "ts": 658972444621.878, "dur": 0.417, + "args": { + "External id": 38036,"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": 4183437, "tid": 4183437, + "ts": 658972444622.589, "dur": 0.741, + "args": { + "External id": 38037,"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": 4183437, "tid": 4183437, + "ts": 658972444622.959, "dur": 0.300, + "args": { + "External id": 38038,"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": 4183437, "tid": 4183437, + "ts": 658972444624.681, "dur": 4.699, + "args": { + "External id": 38039,"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": 4183437, "tid": 4183437, + "ts": 658972444628.621, "dur": 0.684, + "args": { + "External id": 38040,"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": 4183437, "tid": 4183437, + "ts": 658972444629.634, "dur": 0.814, + "args": { + "External id": 38041,"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": 4183437, "tid": 4183437, + "ts": 658972444630.004, "dur": 0.381, + "args": { + "External id": 38042,"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": 4183437, "tid": 4183437, + "ts": 658972444630.696, "dur": 1.042, + "args": { + "External id": 38043,"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": 4183437, "tid": 4183437, + "ts": 658972444631.051, "dur": 0.590, + "args": { + "External id": 38044,"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": 4183437, "tid": 4183437, + "ts": 658972444631.989, "dur": 3.013, + "args": { + "External id": 38045,"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": 4183437, "tid": 4183437, + "ts": 658972444634.623, "dur": 0.284, + "args": { + "External id": 38046,"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": 4183437, "tid": 4183437, + "ts": 658972444635.229, "dur": 1.008, + "args": { + "External id": 38047,"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": 4183437, "tid": 4183437, + "ts": 658972444635.585, "dur": 0.582, + "args": { + "External id": 38048,"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": 4183437, "tid": 4183437, + "ts": 658972444636.469, "dur": 2.666, + "args": { + "External id": 38049,"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": 4183437, "tid": 4183437, + "ts": 658972444636.827, "dur": 2.058, + "args": { + "External id": 38050,"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": 4183437, "tid": 4183437, + "ts": 658972444639.367, "dur": 2.414, + "args": { + "External id": 38051,"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": 4183437, "tid": 4183437, + "ts": 658972444641.118, "dur": 0.569, + "args": { + "External id": 38052,"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": 4183437, "tid": 4183437, + "ts": 658972444642.009, "dur": 0.817, + "args": { + "External id": 38053,"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": 4183437, "tid": 4183437, + "ts": 658972444642.412, "dur": 0.339, + "args": { + "External id": 38054,"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": 4183437, "tid": 4183437, + "ts": 658972444644.249, "dur": 4.603, + "args": { + "External id": 38055,"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": 4183437, "tid": 4183437, + "ts": 658972444648.456, "dur": 0.326, + "args": { + "External id": 38056,"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": 4183437, "tid": 4183437, + "ts": 658972444649.097, "dur": 0.677, + "args": { + "External id": 38057,"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": 4183437, "tid": 4183437, + "ts": 658972444649.449, "dur": 0.263, + "args": { + "External id": 38058,"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": 4183437, "tid": 4183437, + "ts": 658972444650.002, "dur": 1.661, + "args": { + "External id": 38059,"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": 4183437, "tid": 4183437, + "ts": 658972444650.372, "dur": 1.222, + "args": { + "External id": 38060,"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": 4183437, "tid": 4183437, + "ts": 658972444651.917, "dur": 30.118, + "args": { + "External id": 38061,"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": 4183437, "tid": 4183437, + "ts": 658972444681.016, "dur": 0.627, + "args": { + "External id": 38062,"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": 4183437, "tid": 4183437, + "ts": 658972444682.538, "dur": 1.537, + "args": { + "External id": 38063,"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": 4183437, "tid": 4183437, + "ts": 658972444683.072, "dur": 0.943, + "args": { + "External id": 38064,"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": 4183437, "tid": 4183437, + "ts": 658972444684.340, "dur": 3.076, + "args": { + "External id": 38065,"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": 4183437, "tid": 4183437, + "ts": 658972444684.708, "dur": 2.538, + "args": { + "External id": 38066,"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": 4183437, "tid": 4183437, + "ts": 658972444687.665, "dur": 2.945, + "args": { + "External id": 38067,"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": 4183437, "tid": 4183437, + "ts": 658972444689.869, "dur": 0.645, + "args": { + "External id": 38068,"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": 4183437, "tid": 4183437, + "ts": 658972444690.866, "dur": 1.042, + "args": { + "External id": 38069,"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": 4183437, "tid": 4183437, + "ts": 658972444691.228, "dur": 0.582, + "args": { + "External id": 38070,"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": 4183437, "tid": 4183437, + "ts": 658972444692.963, "dur": 4.305, + "args": { + "External id": 38071,"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": 4183437, "tid": 4183437, + "ts": 658972444696.661, "dur": 0.507, + "args": { + "External id": 38072,"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": 4183437, "tid": 4183437, + "ts": 658972444697.521, "dur": 0.925, + "args": { + "External id": 38073,"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": 4183437, "tid": 4183437, + "ts": 658972444697.895, "dur": 0.482, + "args": { + "External id": 38074,"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": 4183437, "tid": 4183437, + "ts": 658972444698.681, "dur": 1.148, + "args": { + "External id": 38075,"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": 4183437, "tid": 4183437, + "ts": 658972444699.035, "dur": 0.690, + "args": { + "External id": 38076,"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": 4183437, "tid": 4183437, + "ts": 658972444700.057, "dur": 2.893, + "args": { + "External id": 38077,"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": 4183437, "tid": 4183437, + "ts": 658972444702.559, "dur": 0.328, + "args": { + "External id": 38078,"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": 4183437, "tid": 4183437, + "ts": 658972444703.181, "dur": 1.091, + "args": { + "External id": 38079,"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": 4183437, "tid": 4183437, + "ts": 658972444703.572, "dur": 0.607, + "args": { + "External id": 38080,"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": 4183437, "tid": 4183437, + "ts": 658972444704.500, "dur": 2.289, + "args": { + "External id": 38081,"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": 4183437, "tid": 4183437, + "ts": 658972444704.855, "dur": 1.856, + "args": { + "External id": 38082,"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": 4183437, "tid": 4183437, + "ts": 658972444707.042, "dur": 2.533, + "args": { + "External id": 38083,"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": 4183437, "tid": 4183437, + "ts": 658972444708.876, "dur": 0.605, + "args": { + "External id": 38084,"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": 4183437, "tid": 4183437, + "ts": 658972444709.938, "dur": 0.828, + "args": { + "External id": 38085,"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": 4183437, "tid": 4183437, + "ts": 658972444710.290, "dur": 0.402, + "args": { + "External id": 38086,"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": 4183437, "tid": 4183437, + "ts": 658972444711.257, "dur": 4.129, + "args": { + "External id": 38087,"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": 4183437, "tid": 4183437, + "ts": 658972444714.900, "dur": 0.417, + "args": { + "External id": 38088,"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": 4183437, "tid": 4183437, + "ts": 658972444715.634, "dur": 0.698, + "args": { + "External id": 38089,"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": 4183437, "tid": 4183437, + "ts": 658972444715.984, "dur": 0.283, + "args": { + "External id": 38090,"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": 4183437, "tid": 4183437, + "ts": 658972444716.556, "dur": 1.105, + "args": { + "External id": 38091,"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": 4183437, "tid": 4183437, + "ts": 658972444716.921, "dur": 0.668, + "args": { + "External id": 38092,"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": 4183437, "tid": 4183437, + "ts": 658972444717.886, "dur": 2.667, + "args": { + "External id": 38093,"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": 4183437, "tid": 4183437, + "ts": 658972444720.200, "dur": 0.288, + "args": { + "External id": 38094,"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": 4183437, "tid": 4183437, + "ts": 658972444720.776, "dur": 1.312, + "args": { + "External id": 38095,"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": 4183437, "tid": 4183437, + "ts": 658972444721.146, "dur": 0.848, + "args": { + "External id": 38096,"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": 4183437, "tid": 4183437, + "ts": 658972444722.341, "dur": 2.943, + "args": { + "External id": 38097,"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": 4183437, "tid": 4183437, + "ts": 658972444722.726, "dur": 2.448, + "args": { + "External id": 38098,"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": 4183437, "tid": 4183437, + "ts": 658972444725.514, "dur": 1.320, + "args": { + "External id": 38099,"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": 4183437, "tid": 4183437, + "ts": 658972444726.138, "dur": 0.604, + "args": { + "External id": 38100,"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": 4183437, "tid": 4183437, + "ts": 658972444727.089, "dur": 0.881, + "args": { + "External id": 38101,"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": 4183437, "tid": 4183437, + "ts": 658972444727.445, "dur": 0.423, + "args": { + "External id": 38102,"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": 4183437, "tid": 4183437, + "ts": 658972444729.088, "dur": 3.285, + "args": { + "External id": 38103,"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": 4183437, "tid": 4183437, + "ts": 658972444731.708, "dur": 0.602, + "args": { + "External id": 38104,"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": 4183437, "tid": 4183437, + "ts": 658972444732.634, "dur": 0.696, + "args": { + "External id": 38105,"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": 4183437, "tid": 4183437, + "ts": 658972444732.987, "dur": 0.270, + "args": { + "External id": 38106,"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": 4183437, "tid": 4183437, + "ts": 658972444733.554, "dur": 1.040, + "args": { + "External id": 38107,"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": 4183437, "tid": 4183437, + "ts": 658972444733.926, "dur": 0.595, + "args": { + "External id": 38108,"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": 4183437, "tid": 4183437, + "ts": 658972444735.012, "dur": 2.578, + "args": { + "External id": 38109,"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": 4183437, "tid": 4183437, + "ts": 658972444737.268, "dur": 0.248, + "args": { + "External id": 38110,"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": 4183437, "tid": 4183437, + "ts": 658972444737.943, "dur": 1.320, + "args": { + "External id": 38111,"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": 4183437, "tid": 4183437, + "ts": 658972444738.294, "dur": 0.900, + "args": { + "External id": 38112,"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": 4183437, "tid": 4183437, + "ts": 658972444739.492, "dur": 3.520, + "args": { + "External id": 38113,"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": 4183437, "tid": 4183437, + "ts": 658972444739.842, "dur": 3.087, + "args": { + "External id": 38114,"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": 4183437, "tid": 4183437, + "ts": 658972444743.285, "dur": 1.376, + "args": { + "External id": 38115,"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": 4183437, "tid": 4183437, + "ts": 658972444744.087, "dur": 0.510, + "args": { + "External id": 38116,"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": 4183437, "tid": 4183437, + "ts": 658972444745.141, "dur": 0.797, + "args": { + "External id": 38117,"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": 4183437, "tid": 4183437, + "ts": 658972444745.494, "dur": 0.373, + "args": { + "External id": 38118,"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": 4183437, "tid": 4183437, + "ts": 658972444746.552, "dur": 2.995, + "args": { + "External id": 38119,"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": 4183437, "tid": 4183437, + "ts": 658972444749.082, "dur": 0.368, + "args": { + "External id": 38120,"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": 4183437, "tid": 4183437, + "ts": 658972444749.814, "dur": 0.749, + "args": { + "External id": 38121,"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": 4183437, "tid": 4183437, + "ts": 658972444750.162, "dur": 0.305, + "args": { + "External id": 38122,"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": 4183437, "tid": 4183437, + "ts": 658972444750.787, "dur": 0.956, + "args": { + "External id": 38123,"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": 4183437, "tid": 4183437, + "ts": 658972444751.161, "dur": 0.512, + "args": { + "External id": 38124,"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": 4183437, "tid": 4183437, + "ts": 658972444751.986, "dur": 2.544, + "args": { + "External id": 38125,"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": 4183437, "tid": 4183437, + "ts": 658972444754.207, "dur": 0.264, + "args": { + "External id": 38126,"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": 4183437, "tid": 4183437, + "ts": 658972444754.838, "dur": 1.052, + "args": { + "External id": 38127,"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": 4183437, "tid": 4183437, + "ts": 658972444755.192, "dur": 0.602, + "args": { + "External id": 38128,"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": 4183437, "tid": 4183437, + "ts": 658972444756.342, "dur": 2.675, + "args": { + "External id": 38129,"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": 4183437, "tid": 4183437, + "ts": 658972444756.695, "dur": 2.248, + "args": { + "External id": 38130,"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": 4183437, "tid": 4183437, + "ts": 658972444759.245, "dur": 1.238, + "args": { + "External id": 38131,"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": 4183437, "tid": 4183437, + "ts": 658972444759.912, "dur": 0.479, + "args": { + "External id": 38132,"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": 4183437, "tid": 4183437, + "ts": 658972444760.707, "dur": 0.858, + "args": { + "External id": 38133,"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": 4183437, "tid": 4183437, + "ts": 658972444761.131, "dur": 0.363, + "args": { + "External id": 38134,"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": 4183437, "tid": 4183437, + "ts": 658972444762.493, "dur": 3.385, + "args": { + "External id": 38135,"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": 4183437, "tid": 4183437, + "ts": 658972444765.300, "dur": 0.514, + "args": { + "External id": 38136,"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": 4183437, "tid": 4183437, + "ts": 658972444766.127, "dur": 0.777, + "args": { + "External id": 38137,"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": 4183437, "tid": 4183437, + "ts": 658972444766.498, "dur": 0.305, + "args": { + "External id": 38138,"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": 4183437, "tid": 4183437, + "ts": 658972444767.160, "dur": 1.157, + "args": { + "External id": 38139,"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": 4183437, "tid": 4183437, + "ts": 658972444767.567, "dur": 0.680, + "args": { + "External id": 38140,"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": 4183437, "tid": 4183437, + "ts": 658972444768.540, "dur": 2.459, + "args": { + "External id": 38141,"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": 4183437, "tid": 4183437, + "ts": 658972444770.678, "dur": 0.258, + "args": { + "External id": 38142,"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": 4183437, "tid": 4183437, + "ts": 658972444771.271, "dur": 1.115, + "args": { + "External id": 38143,"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": 4183437, "tid": 4183437, + "ts": 658972444771.640, "dur": 0.680, + "args": { + "External id": 38144,"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": 4183437, "tid": 4183437, + "ts": 658972444772.735, "dur": 2.684, + "args": { + "External id": 38145,"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": 4183437, "tid": 4183437, + "ts": 658972444773.094, "dur": 2.045, + "args": { + "External id": 38146,"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": 4183437, "tid": 4183437, + "ts": 658972444775.664, "dur": 1.359, + "args": { + "External id": 38147,"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": 4183437, "tid": 4183437, + "ts": 658972444776.304, "dur": 0.627, + "args": { + "External id": 38148,"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": 4183437, "tid": 4183437, + "ts": 658972444777.343, "dur": 0.816, + "args": { + "External id": 38149,"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": 4183437, "tid": 4183437, + "ts": 658972444777.707, "dur": 0.381, + "args": { + "External id": 38150,"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": 4183437, "tid": 4183437, + "ts": 658972444779.004, "dur": 3.423, + "args": { + "External id": 38151,"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": 4183437, "tid": 4183437, + "ts": 658972444781.662, "dur": 0.666, + "args": { + "External id": 38152,"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": 4183437, "tid": 4183437, + "ts": 658972444782.677, "dur": 0.950, + "args": { + "External id": 38153,"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": 4183437, "tid": 4183437, + "ts": 658972444783.059, "dur": 0.464, + "args": { + "External id": 38154,"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": 4183437, "tid": 4183437, + "ts": 658972444783.853, "dur": 0.978, + "args": { + "External id": 38155,"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": 4183437, "tid": 4183437, + "ts": 658972444784.206, "dur": 0.555, + "args": { + "External id": 38156,"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": 4183437, "tid": 4183437, + "ts": 658972444785.059, "dur": 2.634, + "args": { + "External id": 38157,"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": 4183437, "tid": 4183437, + "ts": 658972444787.380, "dur": 0.247, + "args": { + "External id": 38158,"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": 4183437, "tid": 4183437, + "ts": 658972444788.139, "dur": 1.200, + "args": { + "External id": 38159,"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": 4183437, "tid": 4183437, + "ts": 658972444788.508, "dur": 0.767, + "args": { + "External id": 38160,"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": 4183437, "tid": 4183437, + "ts": 658972444789.594, "dur": 2.698, + "args": { + "External id": 38161,"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": 4183437, "tid": 4183437, + "ts": 658972444789.944, "dur": 2.047, + "args": { + "External id": 38162,"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": 4183437, "tid": 4183437, + "ts": 658972444792.529, "dur": 1.343, + "args": { + "External id": 38163,"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": 4183437, "tid": 4183437, + "ts": 658972444793.267, "dur": 0.543, + "args": { + "External id": 38164,"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": 4183437, "tid": 4183437, + "ts": 658972444794.105, "dur": 0.852, + "args": { + "External id": 38165,"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": 4183437, "tid": 4183437, + "ts": 658972444794.486, "dur": 0.400, + "args": { + "External id": 38166,"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": 4183437, "tid": 4183437, + "ts": 658972444795.705, "dur": 3.133, + "args": { + "External id": 38167,"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": 4183437, "tid": 4183437, + "ts": 658972444798.178, "dur": 0.595, + "args": { + "External id": 38168,"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": 4183437, "tid": 4183437, + "ts": 658972444799.130, "dur": 1.494, + "args": { + "External id": 38169,"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": 4183437, "tid": 4183437, + "ts": 658972444799.902, "dur": 0.655, + "args": { + "External id": 38170,"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": 4183437, "tid": 4183437, + "ts": 658972444800.871, "dur": 1.625, + "args": { + "External id": 38171,"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": 4183437, "tid": 4183437, + "ts": 658972444801.548, "dur": 0.876, + "args": { + "External id": 38172,"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": 4183437, "tid": 4183437, + "ts": 658972444802.747, "dur": 3.206, + "args": { + "External id": 38173,"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": 4183437, "tid": 4183437, + "ts": 658972444805.297, "dur": 0.562, + "args": { + "External id": 38174,"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": 4183437, "tid": 4183437, + "ts": 658972444806.194, "dur": 1.326, + "args": { + "External id": 38175,"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": 4183437, "tid": 4183437, + "ts": 658972444807.017, "dur": 0.410, + "args": { + "External id": 38176,"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": 4183437, "tid": 4183437, + "ts": 658972444807.792, "dur": 2.794, + "args": { + "External id": 38177,"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": 4183437, "tid": 4183437, + "ts": 658972444808.508, "dur": 1.999, + "args": { + "External id": 38178,"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": 4183437, "tid": 4183437, + "ts": 658972444810.832, "dur": 1.165, + "args": { + "External id": 38179,"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": 4183437, "tid": 4183437, + "ts": 658972444811.389, "dur": 0.537, + "args": { + "External id": 38180,"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": 4183437, "tid": 4183437, + "ts": 658972444812.348, "dur": 1.335, + "args": { + "External id": 38181,"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": 4183437, "tid": 4183437, + "ts": 658972444812.878, "dur": 0.730, + "args": { + "External id": 38182,"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": 4183437, "tid": 4183437, + "ts": 658972444814.497, "dur": 2.994, + "args": { + "External id": 38183,"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": 4183437, "tid": 4183437, + "ts": 658972444817.107, "dur": 0.283, + "args": { + "External id": 38184,"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": 4183437, "tid": 4183437, + "ts": 658972444817.758, "dur": 1.301, + "args": { + "External id": 38185,"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": 4183437, "tid": 4183437, + "ts": 658972444818.496, "dur": 0.501, + "args": { + "External id": 38186,"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": 4183437, "tid": 4183437, + "ts": 658972444819.476, "dur": 1.152, + "args": { + "External id": 38187,"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": 4183437, "tid": 4183437, + "ts": 658972444820.026, "dur": 0.530, + "args": { + "External id": 38188,"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": 4183437, "tid": 4183437, + "ts": 658972444821.079, "dur": 3.075, + "args": { + "External id": 38189,"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": 4183437, "tid": 4183437, + "ts": 658972444823.495, "dur": 0.594, + "args": { + "External id": 38190,"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": 4183437, "tid": 4183437, + "ts": 658972444824.486, "dur": 1.295, + "args": { + "External id": 38191,"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": 4183437, "tid": 4183437, + "ts": 658972444825.267, "dur": 0.451, + "args": { + "External id": 38192,"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": 4183437, "tid": 4183437, + "ts": 658972444826.024, "dur": 2.782, + "args": { + "External id": 38193,"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": 4183437, "tid": 4183437, + "ts": 658972444826.606, "dur": 2.125, + "args": { + "External id": 38194,"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": 4183437, "tid": 4183437, + "ts": 658972444829.051, "dur": 1.486, + "args": { + "External id": 38195,"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": 4183437, "tid": 4183437, + "ts": 658972444829.681, "dur": 0.789, + "args": { + "External id": 38196,"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": 4183437, "tid": 4183437, + "ts": 658972444830.779, "dur": 1.607, + "args": { + "External id": 38197,"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": 4183437, "tid": 4183437, + "ts": 658972444831.442, "dur": 0.870, + "args": { + "External id": 38198,"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": 4183437, "tid": 4183437, + "ts": 658972444833.336, "dur": 3.751, + "args": { + "External id": 38199,"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": 4183437, "tid": 4183437, + "ts": 658972444836.350, "dur": 0.671, + "args": { + "External id": 38200,"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": 4183437, "tid": 4183437, + "ts": 658972444837.350, "dur": 1.393, + "args": { + "External id": 38201,"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": 4183437, "tid": 4183437, + "ts": 658972444837.960, "dur": 0.707, + "args": { + "External id": 38202,"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": 4183437, "tid": 4183437, + "ts": 658972444838.986, "dur": 1.855, + "args": { + "External id": 38203,"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": 4183437, "tid": 4183437, + "ts": 658972444839.897, "dur": 0.871, + "args": { + "External id": 38204,"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": 4183437, "tid": 4183437, + "ts": 658972444841.086, "dur": 2.960, + "args": { + "External id": 38205,"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": 4183437, "tid": 4183437, + "ts": 658972444843.414, "dur": 0.535, + "args": { + "External id": 38206,"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": 4183437, "tid": 4183437, + "ts": 658972444844.289, "dur": 1.392, + "args": { + "External id": 38207,"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": 4183437, "tid": 4183437, + "ts": 658972444844.939, "dur": 0.680, + "args": { + "External id": 38208,"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": 4183437, "tid": 4183437, + "ts": 658972444846.102, "dur": 2.757, + "args": { + "External id": 38209,"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": 4183437, "tid": 4183437, + "ts": 658972444846.734, "dur": 2.047, + "args": { + "External id": 38210,"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": 4183437, "tid": 4183437, + "ts": 658972444849.103, "dur": 1.407, + "args": { + "External id": 38211,"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": 4183437, "tid": 4183437, + "ts": 658972444849.683, "dur": 0.767, + "args": { + "External id": 38212,"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": 4183437, "tid": 4183437, + "ts": 658972444850.894, "dur": 1.635, + "args": { + "External id": 38213,"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": 4183437, "tid": 4183437, + "ts": 658972444851.822, "dur": 0.636, + "args": { + "External id": 38214,"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": 4183437, "tid": 4183437, + "ts": 658972444853.245, "dur": 3.996, + "args": { + "External id": 38215,"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": 4183437, "tid": 4183437, + "ts": 658972444856.716, "dur": 0.451, + "args": { + "External id": 38216,"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": 4183437, "tid": 4183437, + "ts": 658972444857.506, "dur": 1.382, + "args": { + "External id": 38217,"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": 4183437, "tid": 4183437, + "ts": 658972444858.199, "dur": 0.621, + "args": { + "External id": 38218,"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": 4183437, "tid": 4183437, + "ts": 658972444859.131, "dur": 1.408, + "args": { + "External id": 38219,"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": 4183437, "tid": 4183437, + "ts": 658972444859.869, "dur": 0.598, + "args": { + "External id": 38220,"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": 4183437, "tid": 4183437, + "ts": 658972444860.878, "dur": 2.465, + "args": { + "External id": 38221,"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": 4183437, "tid": 4183437, + "ts": 658972444862.817, "dur": 0.463, + "args": { + "External id": 38222,"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": 4183437, "tid": 4183437, + "ts": 658972444863.605, "dur": 1.244, + "args": { + "External id": 38223,"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": 4183437, "tid": 4183437, + "ts": 658972444864.221, "dur": 0.565, + "args": { + "External id": 38224,"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": 4183437, "tid": 4183437, + "ts": 658972444865.118, "dur": 3.131, + "args": { + "External id": 38225,"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": 4183437, "tid": 4183437, + "ts": 658972444865.785, "dur": 2.387, + "args": { + "External id": 38226,"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": 4183437, "tid": 4183437, + "ts": 658972444868.494, "dur": 1.273, + "args": { + "External id": 38227,"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": 4183437, "tid": 4183437, + "ts": 658972444869.185, "dur": 0.520, + "args": { + "External id": 38228,"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": 4183437, "tid": 4183437, + "ts": 658972444870.012, "dur": 1.759, + "args": { + "External id": 38229,"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": 4183437, "tid": 4183437, + "ts": 658972444870.827, "dur": 0.873, + "args": { + "External id": 38230,"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": 4183437, "tid": 4183437, + "ts": 658972444872.570, "dur": 4.342, + "args": { + "External id": 38231,"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": 4183437, "tid": 4183437, + "ts": 658972444875.541, "dur": 1.310, + "args": { + "External id": 38232,"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": 4183437, "tid": 4183437, + "ts": 658972444877.175, "dur": 1.557, + "args": { + "External id": 38233,"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": 4183437, "tid": 4183437, + "ts": 658972444878.066, "dur": 0.604, + "args": { + "External id": 38234,"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": 4183437, "tid": 4183437, + "ts": 658972444878.972, "dur": 1.102, + "args": { + "External id": 38235,"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": 4183437, "tid": 4183437, + "ts": 658972444879.556, "dur": 0.446, + "args": { + "External id": 38236,"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": 4183437, "tid": 4183437, + "ts": 658972444880.318, "dur": 2.634, + "args": { + "External id": 38237,"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": 4183437, "tid": 4183437, + "ts": 658972444882.292, "dur": 0.591, + "args": { + "External id": 38238,"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": 4183437, "tid": 4183437, + "ts": 658972444883.193, "dur": 1.624, + "args": { + "External id": 38239,"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": 4183437, "tid": 4183437, + "ts": 658972444884.061, "dur": 0.696, + "args": { + "External id": 38240,"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": 4183437, "tid": 4183437, + "ts": 658972444885.058, "dur": 2.741, + "args": { + "External id": 38241,"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": 4183437, "tid": 4183437, + "ts": 658972444885.698, "dur": 2.022, + "args": { + "External id": 38242,"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": 4183437, "tid": 4183437, + "ts": 658972444888.045, "dur": 1.531, + "args": { + "External id": 38243,"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": 4183437, "tid": 4183437, + "ts": 658972444888.888, "dur": 0.624, + "args": { + "External id": 38244,"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": 4183437, "tid": 4183437, + "ts": 658972444889.818, "dur": 1.851, + "args": { + "External id": 38245,"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": 4183437, "tid": 4183437, + "ts": 658972444890.471, "dur": 1.123, + "args": { + "External id": 38246,"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": 4183437, "tid": 4183437, + "ts": 658972444892.457, "dur": 3.089, + "args": { + "External id": 38247,"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": 4183437, "tid": 4183437, + "ts": 658972444895.019, "dur": 0.430, + "args": { + "External id": 38248,"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": 4183437, "tid": 4183437, + "ts": 658972444895.822, "dur": 1.241, + "args": { + "External id": 38249,"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": 4183437, "tid": 4183437, + "ts": 658972444896.419, "dur": 0.575, + "args": { + "External id": 38250,"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": 4183437, "tid": 4183437, + "ts": 658972444897.389, "dur": 1.455, + "args": { + "External id": 38251,"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": 4183437, "tid": 4183437, + "ts": 658972444898.101, "dur": 0.670, + "args": { + "External id": 38252,"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": 4183437, "tid": 4183437, + "ts": 658972444899.117, "dur": 3.369, + "args": { + "External id": 38253,"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": 4183437, "tid": 4183437, + "ts": 658972444901.607, "dur": 0.807, + "args": { + "External id": 38254,"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": 4183437, "tid": 4183437, + "ts": 658972444902.897, "dur": 1.379, + "args": { + "External id": 38255,"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": 4183437, "tid": 4183437, + "ts": 658972444903.683, "dur": 0.530, + "args": { + "External id": 38256,"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": 4183437, "tid": 4183437, + "ts": 658972444904.705, "dur": 3.297, + "args": { + "External id": 38257,"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": 4183437, "tid": 4183437, + "ts": 658972444905.402, "dur": 2.346, + "args": { + "External id": 38258,"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": 4183437, "tid": 4183437, + "ts": 658972444908.246, "dur": 1.308, + "args": { + "External id": 38259,"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": 4183437, "tid": 4183437, + "ts": 658972444909.021, "dur": 0.470, + "args": { + "External id": 38260,"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": 4183437, "tid": 4183437, + "ts": 658972444909.972, "dur": 1.568, + "args": { + "External id": 38261,"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": 4183437, "tid": 4183437, + "ts": 658972444910.677, "dur": 0.791, + "args": { + "External id": 38262,"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": 4183437, "tid": 4183437, + "ts": 658972444912.285, "dur": 3.237, + "args": { + "External id": 38263,"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": 4183437, "tid": 4183437, + "ts": 658972444914.852, "dur": 0.598, + "args": { + "External id": 38264,"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": 4183437, "tid": 4183437, + "ts": 658972444915.784, "dur": 1.153, + "args": { + "External id": 38265,"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": 4183437, "tid": 4183437, + "ts": 658972444916.466, "dur": 0.400, + "args": { + "External id": 38266,"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": 4183437, "tid": 4183437, + "ts": 658972444917.178, "dur": 1.023, + "args": { + "External id": 38267,"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": 4183437, "tid": 4183437, + "ts": 658972444917.744, "dur": 0.385, + "args": { + "External id": 38268,"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": 4183437, "tid": 4183437, + "ts": 658972444918.443, "dur": 2.869, + "args": { + "External id": 38269,"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": 4183437, "tid": 4183437, + "ts": 658972444920.651, "dur": 0.570, + "args": { + "External id": 38270,"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": 4183437, "tid": 4183437, + "ts": 658972444921.551, "dur": 1.052, + "args": { + "External id": 38271,"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": 4183437, "tid": 4183437, + "ts": 658972444922.143, "dur": 0.389, + "args": { + "External id": 38272,"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": 4183437, "tid": 4183437, + "ts": 658972444922.846, "dur": 2.409, + "args": { + "External id": 38273,"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": 4183437, "tid": 4183437, + "ts": 658972444923.340, "dur": 1.838, + "args": { + "External id": 38274,"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": 4183437, "tid": 4183437, + "ts": 658972444925.542, "dur": 1.203, + "args": { + "External id": 38275,"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": 4183437, "tid": 4183437, + "ts": 658972444926.158, "dur": 0.522, + "args": { + "External id": 38276,"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": 4183437, "tid": 4183437, + "ts": 658972444927.215, "dur": 1.352, + "args": { + "External id": 38277,"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": 4183437, "tid": 4183437, + "ts": 658972444927.984, "dur": 0.487, + "args": { + "External id": 38278,"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": 4183437, "tid": 4183437, + "ts": 658972444928.876, "dur": 3.099, + "args": { + "External id": 38279,"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": 4183437, "tid": 4183437, + "ts": 658972444931.511, "dur": 0.390, + "args": { + "External id": 38280,"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": 4183437, "tid": 4183437, + "ts": 658972444932.459, "dur": 0.906, + "args": { + "External id": 38281,"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": 4183437, "tid": 4183437, + "ts": 658972444932.951, "dur": 0.343, + "args": { + "External id": 38282,"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": 4183437, "tid": 4183437, + "ts": 658972444933.645, "dur": 1.188, + "args": { + "External id": 38283,"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": 4183437, "tid": 4183437, + "ts": 658972444934.130, "dur": 0.630, + "args": { + "External id": 38284,"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": 4183437, "tid": 4183437, + "ts": 658972444935.114, "dur": 3.203, + "args": { + "External id": 38285,"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": 4183437, "tid": 4183437, + "ts": 658972444938.006, "dur": 0.236, + "args": { + "External id": 38286,"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": 4183437, "tid": 4183437, + "ts": 658972444938.657, "dur": 0.995, + "args": { + "External id": 38287,"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": 4183437, "tid": 4183437, + "ts": 658972444939.157, "dur": 0.424, + "args": { + "External id": 38288,"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": 4183437, "tid": 4183437, + "ts": 658972444939.991, "dur": 2.705, + "args": { + "External id": 38289,"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": 4183437, "tid": 4183437, + "ts": 658972444940.644, "dur": 1.977, + "args": { + "External id": 38290,"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": 4183437, "tid": 4183437, + "ts": 658972444942.995, "dur": 0.857, + "args": { + "External id": 38291,"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": 4183437, "tid": 4183437, + "ts": 658972444943.541, "dur": 0.240, + "args": { + "External id": 38292,"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": 4183437, "tid": 4183437, + "ts": 658972444944.339, "dur": 1.080, + "args": { + "External id": 38293,"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": 4183437, "tid": 4183437, + "ts": 658972444944.957, "dur": 0.390, + "args": { + "External id": 38294,"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": 4183437, "tid": 4183437, + "ts": 658972444945.672, "dur": 2.513, + "args": { + "External id": 38295,"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": 4183437, "tid": 4183437, + "ts": 658972444947.858, "dur": 0.254, + "args": { + "External id": 38296,"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": 4183437, "tid": 4183437, + "ts": 658972444948.625, "dur": 1.426, + "args": { + "External id": 38297,"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": 4183437, "tid": 4183437, + "ts": 658972444949.267, "dur": 0.717, + "args": { + "External id": 38298,"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": 4183437, "tid": 4183437, + "ts": 658972444950.369, "dur": 1.292, + "args": { + "External id": 38299,"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": 4183437, "tid": 4183437, + "ts": 658972444951.128, "dur": 0.431, + "args": { + "External id": 38300,"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": 4183437, "tid": 4183437, + "ts": 658972444951.974, "dur": 2.575, + "args": { + "External id": 38301,"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": 4183437, "tid": 4183437, + "ts": 658972444953.967, "dur": 0.517, + "args": { + "External id": 38302,"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": 4183437, "tid": 4183437, + "ts": 658972444954.900, "dur": 1.230, + "args": { + "External id": 38303,"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": 4183437, "tid": 4183437, + "ts": 658972444955.465, "dur": 0.569, + "args": { + "External id": 38304,"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": 4183437, "tid": 4183437, + "ts": 658972444956.403, "dur": 3.674, + "args": { + "External id": 38305,"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": 4183437, "tid": 4183437, + "ts": 658972444957.121, "dur": 2.879, + "args": { + "External id": 38306,"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": 4183437, "tid": 4183437, + "ts": 658972444960.433, "dur": 1.084, + "args": { + "External id": 38307,"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": 4183437, "tid": 4183437, + "ts": 658972444961.011, "dur": 0.446, + "args": { + "External id": 38308,"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": 4183437, "tid": 4183437, + "ts": 658972444961.985, "dur": 1.389, + "args": { + "External id": 38309,"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": 4183437, "tid": 4183437, + "ts": 658972444962.629, "dur": 0.675, + "args": { + "External id": 38310,"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": 4183437, "tid": 4183437, + "ts": 658972444963.737, "dur": 3.580, + "args": { + "External id": 38311,"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": 4183437, "tid": 4183437, + "ts": 658972444966.483, "dur": 0.735, + "args": { + "External id": 38312,"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": 4183437, "tid": 4183437, + "ts": 658972444967.615, "dur": 1.670, + "args": { + "External id": 38313,"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": 4183437, "tid": 4183437, + "ts": 658972444968.527, "dur": 0.696, + "args": { + "External id": 38314,"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": 4183437, "tid": 4183437, + "ts": 658972444969.843, "dur": 1.251, + "args": { + "External id": 38315,"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": 4183437, "tid": 4183437, + "ts": 658972444970.440, "dur": 0.579, + "args": { + "External id": 38316,"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": 4183437, "tid": 4183437, + "ts": 658972444971.372, "dur": 2.753, + "args": { + "External id": 38317,"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": 4183437, "tid": 4183437, + "ts": 658972444973.563, "dur": 0.501, + "args": { + "External id": 38318,"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": 4183437, "tid": 4183437, + "ts": 658972444974.381, "dur": 1.402, + "args": { + "External id": 38319,"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": 4183437, "tid": 4183437, + "ts": 658972444974.938, "dur": 0.780, + "args": { + "External id": 38320,"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": 4183437, "tid": 4183437, + "ts": 658972444976.050, "dur": 3.089, + "args": { + "External id": 38321,"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": 4183437, "tid": 4183437, + "ts": 658972444977.049, "dur": 1.978, + "args": { + "External id": 38322,"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": 4183437, "tid": 4183437, + "ts": 658972444979.510, "dur": 1.337, + "args": { + "External id": 38323,"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": 4183437, "tid": 4183437, + "ts": 658972444980.243, "dur": 0.531, + "args": { + "External id": 38324,"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": 4183437, "tid": 4183437, + "ts": 658972444981.526, "dur": 1.561, + "args": { + "External id": 38325,"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": 4183437, "tid": 4183437, + "ts": 658972444982.268, "dur": 0.746, + "args": { + "External id": 38326,"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": 4183437, "tid": 4183437, + "ts": 658972444983.660, "dur": 3.281, + "args": { + "External id": 38327,"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": 4183437, "tid": 4183437, + "ts": 658972444986.242, "dur": 0.601, + "args": { + "External id": 38328,"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": 4183437, "tid": 4183437, + "ts": 658972444987.210, "dur": 1.165, + "args": { + "External id": 38329,"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": 4183437, "tid": 4183437, + "ts": 658972444987.713, "dur": 0.597, + "args": { + "External id": 38330,"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": 4183437, "tid": 4183437, + "ts": 658972444988.867, "dur": 1.511, + "args": { + "External id": 38331,"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": 4183437, "tid": 4183437, + "ts": 658972444989.642, "dur": 0.638, + "args": { + "External id": 38332,"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": 4183437, "tid": 4183437, + "ts": 658972444990.643, "dur": 3.588, + "args": { + "External id": 38333,"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": 4183437, "tid": 4183437, + "ts": 658972444993.611, "dur": 0.552, + "args": { + "External id": 38334,"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": 4183437, "tid": 4183437, + "ts": 658972444994.485, "dur": 1.349, + "args": { + "External id": 38335,"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": 4183437, "tid": 4183437, + "ts": 658972444994.987, "dur": 0.757, + "args": { + "External id": 38336,"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": 4183437, "tid": 4183437, + "ts": 658972444996.096, "dur": 3.291, + "args": { + "External id": 38337,"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": 4183437, "tid": 4183437, + "ts": 658972444996.965, "dur": 2.133, + "args": { + "External id": 38338,"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": 4183437, "tid": 4183437, + "ts": 658972444999.849, "dur": 1.397, + "args": { + "External id": 38339,"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": 4183437, "tid": 4183437, + "ts": 658972445000.754, "dur": 0.432, + "args": { + "External id": 38340,"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": 4183437, "tid": 4183437, + "ts": 658972445001.516, "dur": 1.346, + "args": { + "External id": 38341,"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": 4183437, "tid": 4183437, + "ts": 658972445002.103, "dur": 0.687, + "args": { + "External id": 38342,"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": 4183437, "tid": 4183437, + "ts": 658972445003.501, "dur": 3.495, + "args": { + "External id": 38343,"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": 4183437, "tid": 4183437, + "ts": 658972445006.466, "dur": 0.460, + "args": { + "External id": 38344,"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": 4183437, "tid": 4183437, + "ts": 658972445007.265, "dur": 1.284, + "args": { + "External id": 38345,"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": 4183437, "tid": 4183437, + "ts": 658972445007.809, "dur": 0.674, + "args": { + "External id": 38346,"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": 4183437, "tid": 4183437, + "ts": 658972445008.948, "dur": 1.404, + "args": { + "External id": 38347,"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": 4183437, "tid": 4183437, + "ts": 658972445009.541, "dur": 0.740, + "args": { + "External id": 38348,"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": 4183437, "tid": 4183437, + "ts": 658972445010.624, "dur": 3.182, + "args": { + "External id": 38349,"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": 4183437, "tid": 4183437, + "ts": 658972445013.183, "dur": 0.558, + "args": { + "External id": 38350,"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": 4183437, "tid": 4183437, + "ts": 658972445014.097, "dur": 1.672, + "args": { + "External id": 38351,"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": 4183437, "tid": 4183437, + "ts": 658972445014.875, "dur": 0.794, + "args": { + "External id": 38352,"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": 4183437, "tid": 4183437, + "ts": 658972445016.036, "dur": 2.499, + "args": { + "External id": 38353,"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": 4183437, "tid": 4183437, + "ts": 658972445016.634, "dur": 1.798, + "args": { + "External id": 38354,"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": 4183437, "tid": 4183437, + "ts": 658972445018.938, "dur": 1.148, + "args": { + "External id": 38355,"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": 4183437, "tid": 4183437, + "ts": 658972445019.456, "dur": 0.568, + "args": { + "External id": 38356,"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": 4183437, "tid": 4183437, + "ts": 658972445020.353, "dur": 1.444, + "args": { + "External id": 38357,"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": 4183437, "tid": 4183437, + "ts": 658972445021.022, "dur": 0.703, + "args": { + "External id": 38358,"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": 4183437, "tid": 4183437, + "ts": 658972445022.046, "dur": 3.152, + "args": { + "External id": 38359,"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": 4183437, "tid": 4183437, + "ts": 658972445024.618, "dur": 0.481, + "args": { + "External id": 38360,"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": 4183437, "tid": 4183437, + "ts": 658972445025.473, "dur": 1.643, + "args": { + "External id": 38361,"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": 4183437, "tid": 4183437, + "ts": 658972445026.529, "dur": 0.527, + "args": { + "External id": 38362,"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": 4183437, "tid": 4183437, + "ts": 658972445027.374, "dur": 1.331, + "args": { + "External id": 38363,"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": 4183437, "tid": 4183437, + "ts": 658972445027.934, "dur": 0.700, + "args": { + "External id": 38364,"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": 4183437, "tid": 4183437, + "ts": 658972445029.036, "dur": 3.078, + "args": { + "External id": 38365,"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": 4183437, "tid": 4183437, + "ts": 658972445031.481, "dur": 0.566, + "args": { + "External id": 38366,"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": 4183437, "tid": 4183437, + "ts": 658972445032.369, "dur": 1.368, + "args": { + "External id": 38367,"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": 4183437, "tid": 4183437, + "ts": 658972445032.948, "dur": 0.721, + "args": { + "External id": 38368,"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": 4183437, "tid": 4183437, + "ts": 658972445033.999, "dur": 2.769, + "args": { + "External id": 38369,"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": 4183437, "tid": 4183437, + "ts": 658972445034.754, "dur": 1.940, + "args": { + "External id": 38370,"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": 4183437, "tid": 4183437, + "ts": 658972445037.242, "dur": 1.320, + "args": { + "External id": 38371,"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": 4183437, "tid": 4183437, + "ts": 658972445037.930, "dur": 0.572, + "args": { + "External id": 38372,"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": 4183437, "tid": 4183437, + "ts": 658972445038.942, "dur": 1.280, + "args": { + "External id": 38373,"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": 4183437, "tid": 4183437, + "ts": 658972445039.627, "dur": 0.498, + "args": { + "External id": 38374,"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": 4183437, "tid": 4183437, + "ts": 658972445040.608, "dur": 3.227, + "args": { + "External id": 38375,"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": 4183437, "tid": 4183437, + "ts": 658972445043.269, "dur": 0.498, + "args": { + "External id": 38376,"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": 4183437, "tid": 4183437, + "ts": 658972445044.120, "dur": 1.383, + "args": { + "External id": 38377,"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": 4183437, "tid": 4183437, + "ts": 658972445044.664, "dur": 0.774, + "args": { + "External id": 38378,"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": 4183437, "tid": 4183437, + "ts": 658972445045.755, "dur": 1.245, + "args": { + "External id": 38379,"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": 4183437, "tid": 4183437, + "ts": 658972445046.391, "dur": 0.537, + "args": { + "External id": 38380,"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": 4183437, "tid": 4183437, + "ts": 658972445047.266, "dur": 3.011, + "args": { + "External id": 38381,"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": 4183437, "tid": 4183437, + "ts": 658972445049.588, "dur": 0.622, + "args": { + "External id": 38382,"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": 4183437, "tid": 4183437, + "ts": 658972445050.730, "dur": 1.520, + "args": { + "External id": 38383,"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": 4183437, "tid": 4183437, + "ts": 658972445051.500, "dur": 0.649, + "args": { + "External id": 38384,"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": 4183437, "tid": 4183437, + "ts": 658972445052.892, "dur": 3.109, + "args": { + "External id": 38385,"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": 4183437, "tid": 4183437, + "ts": 658972445053.625, "dur": 2.204, + "args": { + "External id": 38386,"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": 4183437, "tid": 4183437, + "ts": 658972445056.428, "dur": 1.147, + "args": { + "External id": 38387,"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": 4183437, "tid": 4183437, + "ts": 658972445056.992, "dur": 0.484, + "args": { + "External id": 38388,"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": 4183437, "tid": 4183437, + "ts": 658972445058.062, "dur": 1.485, + "args": { + "External id": 38389,"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": 4183437, "tid": 4183437, + "ts": 658972445058.782, "dur": 0.692, + "args": { + "External id": 38390,"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": 4183437, "tid": 4183437, + "ts": 658972445060.007, "dur": 3.342, + "args": { + "External id": 38391,"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": 4183437, "tid": 4183437, + "ts": 658972445062.831, "dur": 0.419, + "args": { + "External id": 38392,"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": 4183437, "tid": 4183437, + "ts": 658972445063.622, "dur": 1.280, + "args": { + "External id": 38393,"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": 4183437, "tid": 4183437, + "ts": 658972445064.341, "dur": 0.501, + "args": { + "External id": 38394,"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": 4183437, "tid": 4183437, + "ts": 658972445065.153, "dur": 1.208, + "args": { + "External id": 38395,"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": 4183437, "tid": 4183437, + "ts": 658972445065.691, "dur": 0.599, + "args": { + "External id": 38396,"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": 4183437, "tid": 4183437, + "ts": 658972445066.711, "dur": 2.722, + "args": { + "External id": 38397,"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": 4183437, "tid": 4183437, + "ts": 658972445068.928, "dur": 0.445, + "args": { + "External id": 38398,"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": 4183437, "tid": 4183437, + "ts": 658972445069.874, "dur": 1.262, + "args": { + "External id": 38399,"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": 4183437, "tid": 4183437, + "ts": 658972445070.436, "dur": 0.638, + "args": { + "External id": 38400,"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": 4183437, "tid": 4183437, + "ts": 658972445091.109, "dur": 2.551, + "args": { + "External id": 38401,"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": 4183437, "tid": 4183437, + "ts": 658972445091.748, "dur": 1.786, + "args": { + "External id": 38402,"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": 4183437, "tid": 4183437, + "ts": 658972445094.055, "dur": 0.957, + "args": { + "External id": 38403,"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": 4183437, "tid": 4183437, + "ts": 658972445094.493, "dur": 0.428, + "args": { + "External id": 38404,"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": 4183437, "tid": 4183437, + "ts": 658972445095.640, "dur": 1.316, + "args": { + "External id": 38405,"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": 4183437, "tid": 4183437, + "ts": 658972445096.256, "dur": 0.627, + "args": { + "External id": 38406,"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": 4183437, "tid": 4183437, + "ts": 658972445097.236, "dur": 2.805, + "args": { + "External id": 38407,"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": 4183437, "tid": 4183437, + "ts": 658972445099.558, "dur": 0.384, + "args": { + "External id": 38408,"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": 4183437, "tid": 4183437, + "ts": 658972445100.335, "dur": 0.872, + "args": { + "External id": 38409,"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": 4183437, "tid": 4183437, + "ts": 658972445100.731, "dur": 0.404, + "args": { + "External id": 38410,"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": 4183437, "tid": 4183437, + "ts": 658972445101.473, "dur": 1.443, + "args": { + "External id": 38411,"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": 4183437, "tid": 4183437, + "ts": 658972445102.232, "dur": 0.613, + "args": { + "External id": 38412,"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": 4183437, "tid": 4183437, + "ts": 658972445103.336, "dur": 2.858, + "args": { + "External id": 38413,"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": 4183437, "tid": 4183437, + "ts": 658972445105.601, "dur": 0.523, + "args": { + "External id": 38414,"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": 4183437, "tid": 4183437, + "ts": 658972445106.467, "dur": 0.829, + "args": { + "External id": 38415,"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": 4183437, "tid": 4183437, + "ts": 658972445106.874, "dur": 0.351, + "args": { + "External id": 38416,"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": 4183437, "tid": 4183437, + "ts": 658972445107.702, "dur": 3.007, + "args": { + "External id": 38417,"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": 4183437, "tid": 4183437, + "ts": 658972445108.129, "dur": 2.505, + "args": { + "External id": 38418,"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": 4183437, "tid": 4183437, + "ts": 658972445110.996, "dur": 1.042, + "args": { + "External id": 38419,"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": 4183437, "tid": 4183437, + "ts": 658972445111.534, "dur": 0.435, + "args": { + "External id": 38420,"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": 4183437, "tid": 4183437, + "ts": 658972445112.749, "dur": 1.313, + "args": { + "External id": 38421,"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": 4183437, "tid": 4183437, + "ts": 658972445113.298, "dur": 0.693, + "args": { + "External id": 38422,"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": 4183437, "tid": 4183437, + "ts": 658972445114.522, "dur": 3.448, + "args": { + "External id": 38423,"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": 4183437, "tid": 4183437, + "ts": 658972445117.205, "dur": 0.671, + "args": { + "External id": 38424,"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": 4183437, "tid": 4183437, + "ts": 658972445118.258, "dur": 1.490, + "args": { + "External id": 38425,"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": 4183437, "tid": 4183437, + "ts": 658972445118.919, "dur": 0.763, + "args": { + "External id": 38426,"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": 4183437, "tid": 4183437, + "ts": 658972445120.017, "dur": 7.739, + "args": { + "External id": 38427,"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": 4183437, "tid": 4183437, + "ts": 658972445125.314, "dur": 2.371, + "args": { + "External id": 38428,"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": 4183437, "tid": 4183437, + "ts": 658972445128.171, "dur": 1.275, + "args": { + "External id": 38429,"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": 4183437, "tid": 4183437, + "ts": 658972445128.736, "dur": 0.643, + "args": { + "External id": 38430,"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": 4183437, "tid": 4183437, + "ts": 658972445129.714, "dur": 1.477, + "args": { + "External id": 38431,"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": 4183437, "tid": 4183437, + "ts": 658972445130.294, "dur": 0.827, + "args": { + "External id": 38432,"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": 4183437, "tid": 4183437, + "ts": 658972445131.659, "dur": 3.141, + "args": { + "External id": 38433,"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": 4183437, "tid": 4183437, + "ts": 658972445134.074, "dur": 0.635, + "args": { + "External id": 38434,"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": 4183437, "tid": 4183437, + "ts": 658972445135.106, "dur": 1.288, + "args": { + "External id": 38435,"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": 4183437, "tid": 4183437, + "ts": 658972445135.710, "dur": 0.622, + "args": { + "External id": 38436,"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": 4183437, "tid": 4183437, + "ts": 658972445136.648, "dur": 1.526, + "args": { + "External id": 38437,"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": 4183437, "tid": 4183437, + "ts": 658972445137.225, "dur": 0.878, + "args": { + "External id": 38438,"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": 4183437, "tid": 4183437, + "ts": 658972445138.438, "dur": 3.156, + "args": { + "External id": 38439,"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": 4183437, "tid": 4183437, + "ts": 658972445140.734, "dur": 0.791, + "args": { + "External id": 38440,"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": 4183437, "tid": 4183437, + "ts": 658972445141.989, "dur": 1.365, + "args": { + "External id": 38441,"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": 4183437, "tid": 4183437, + "ts": 658972445142.605, "dur": 0.650, + "args": { + "External id": 38442,"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": 4183437, "tid": 4183437, + "ts": 658972445143.802, "dur": 2.856, + "args": { + "External id": 38443,"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": 4183437, "tid": 4183437, + "ts": 658972445144.390, "dur": 2.104, + "args": { + "External id": 38444,"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": 4183437, "tid": 4183437, + "ts": 658972445146.916, "dur": 1.113, + "args": { + "External id": 38445,"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": 4183437, "tid": 4183437, + "ts": 658972445147.459, "dur": 0.509, + "args": { + "External id": 38446,"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": 4183437, "tid": 4183437, + "ts": 658972445148.294, "dur": 1.397, + "args": { + "External id": 38447,"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": 4183437, "tid": 4183437, + "ts": 658972445148.830, "dur": 0.790, + "args": { + "External id": 38448,"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": 4183437, "tid": 4183437, + "ts": 658972445150.030, "dur": 2.884, + "args": { + "External id": 38449,"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": 4183437, "tid": 4183437, + "ts": 658972445152.366, "dur": 0.487, + "args": { + "External id": 38450,"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": 4183437, "tid": 4183437, + "ts": 658972445153.185, "dur": 1.331, + "args": { + "External id": 38451,"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": 4183437, "tid": 4183437, + "ts": 658972445153.827, "dur": 0.618, + "args": { + "External id": 38452,"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": 4183437, "tid": 4183437, + "ts": 658972445174.396, "dur": 125.765, + "args": { + "External id": 38453,"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": 4183437, "tid": 4183437, + "ts": 658972445389.318, "dur": 127.151, + "args": { + "External id": 38454,"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": 4183437, "tid": 4183437, + "ts": 658972445449.714, "dur": 47.053, + "args": { + "External id": 38455,"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": 4183437, "tid": 4183437, + "ts": 658972445465.662, "dur": 1.164, + "args": { + "External id": 38456,"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": 4183437, "tid": 4183437, + "ts": 658972445794.867, "dur": 909.339, + "args": { + "External id": 38457,"Sequence number": 460108, "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": 4183437, "tid": 4183437, + "ts": 658972445854.312, "dur": 53.255, + "args": { + "External id": 38458,"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": 4183437, "tid": 4183437, + "ts": 658972445860.713, "dur": 1.564, + "args": { + "External id": 38459,"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": 4183437, "tid": 4183437, + "ts": 658972445864.512, "dur": 0.676, + "args": { + "External id": 38460,"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": 4183437, "tid": 4183437, + "ts": 658972445932.563, "dur": 444.236, + "args": { + "External id": 38461,"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": 4183437, "tid": 4183437, + "ts": 658972445937.630, "dur": 43.995, + "args": { + "External id": 38462,"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": 4183437, "tid": 4183437, + "ts": 658972445941.036, "dur": 8.906, + "args": { + "External id": 38463,"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": 4183437, "tid": 4183437, + "ts": 658972445945.224, "dur": 3.950, + "args": { + "External id": 38464,"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": 4183437, "tid": 4183437, + "ts": 658972445951.371, "dur": 29.689, + "args": { + "External id": 38465,"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": 4183437, "tid": 4183437, + "ts": 658972445991.846, "dur": 381.061, + "args": { + "External id": 38466,"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": 4183437, "tid": 4183437, + "ts": 658972446019.732, "dur": 345.950, + "args": { + "External id": 38467,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[[]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 4183437, "tid": 4183437, + "ts": 658972446036.618, "dur": 323.100, + "args": { + "External id": 38468,"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": 4183437, "tid": 4183437, + "ts": 658972446440.126, "dur": 193.964, + "args": { + "External id": 38469,"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": 4183437, "tid": 4183437, + "ts": 658972446533.197, "dur": 26.612, + "args": { + "External id": 38470,"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": 4183437, "tid": 4183437, + "ts": 658972446547.935, "dur": 3.761, + "args": { + "External id": 38471,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 4183437, "tid": 4183437, + "ts": 658972446587.614, "dur": 40.811, + "args": { + "External id": 38472,"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": 4183437, "tid": 4183437, + "ts": 658972446590.725, "dur": 1.197, + "args": { + "External id": 38473,"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": 4183437, "tid": 4183437, + "ts": 658972446593.389, "dur": 0.940, + "args": { + "External id": 38474,"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": 4183437, "tid": 4183437, + "ts": 658972446723.474, "dur": 22.116, + "args": { + "External id": 38475,"Sequence number": 460109, "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": 4183437, "tid": 4183437, + "ts": 658972446734.000, "dur": 8.180, + "args": { + "External id": 38476,"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": 4183437, "tid": 4183437, + "ts": 658972446736.577, "dur": 5.438, + "args": { + "External id": 38477,"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": 4183437, "tid": 4183437, + "ts": 658972447089.983, "dur": 38.519, + "args": { + "External id": 38478,"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": 4183437, "tid": 4183437, + "ts": 658972447138.067, "dur": 23.236, + "args": { + "External id": 38479,"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": 4183437, "tid": 4183437, + "ts": 658972447168.714, "dur": 23.758, + "args": { + "External id": 38480,"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": 4183437, "tid": 4183437, + "ts": 658972447205.311, "dur": 29.169, + "args": { + "External id": 38481,"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": 4183437, "tid": 4183437, + "ts": 658972447209.951, "dur": 0.874, + "args": { + "External id": 38482,"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": 4183437, "tid": 4183437, + "ts": 658972447250.013, "dur": 4.322, + "args": { + "External id": 38483,"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": 4183437, "tid": 4183437, + "ts": 658972447361.083, "dur": 514.458, + "args": { + "External id": 38484,"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": 4183437, "tid": 4183437, + "ts": 658972447780.135, "dur": 68.490, + "args": { + "External id": 38485,"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": 4183437, "tid": 4183437, + "ts": 658972447915.707, "dur": 26.852, + "args": { + "External id": 38486,"Sequence number": 460110, "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": 4183437, "tid": 4183437, + "ts": 658972447919.361, "dur": 22.672, + "args": { + "External id": 38487,"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": 4183437, "tid": 4183437, + "ts": 658972447945.898, "dur": 868.352, + "args": { + "External id": 38488,"Sequence number": 460110, "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": 4183437, "tid": 4183437, + "ts": 658972447947.706, "dur": 866.243, + "args": { + "External id": 38489,"Sequence number": 460110, "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": 4183437, "tid": 4183437, + "ts": 658972447949.826, "dur": 863.099, + "args": { + "External id": 38490,"Sequence number": 460110, "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": 4183437, "tid": 4183437, + "ts": 658972448820.272, "dur": 60.927, + "args": { + "External id": 38491,"Sequence number": 460110, "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": 4183437, "tid": 4183437, + "ts": 658972448823.791, "dur": 33.432, + "args": { + "External id": 38492,"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": 4183437, "tid": 4183437, + "ts": 658972448829.898, "dur": 3.132, + "args": { + "External id": 38493,"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": 4183437, "tid": 4183437, + "ts": 658972448834.839, "dur": 22.103, + "args": { + "External id": 38494,"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": 4183437, "tid": 4183437, + "ts": 658972448839.993, "dur": 2.628, + "args": { + "External id": 38495,"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": 4183437, "tid": 4183437, + "ts": 658972448859.178, "dur": 21.176, + "args": { + "External id": 38496,"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": 4183437, "tid": 4183437, + "ts": 658972448883.537, "dur": 37.499, + "args": { + "External id": 38497,"Sequence number": 460110, "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": 4183437, "tid": 4183437, + "ts": 658972448884.554, "dur": 36.329, + "args": { + "External id": 38498,"Sequence number": 460110, "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": 4183437, "tid": 4183437, + "ts": 658972448885.657, "dur": 35.018, + "args": { + "External id": 38499,"Sequence number": 460110, "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": 4183437, "tid": 4183437, + "ts": 658972448955.374, "dur": 4271.009, + "args": { + "External id": 38500,"Record function id": 0, "Ev Idx": 9299 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 4183437, "tid": 4183437, + "ts": 658972448987.876, "dur": 4218.547, + "args": { + "External id": 38501,"Record function id": 0, "Ev Idx": 9300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 4183437, "tid": 4183437, + "ts": 658972449970.053, "dur": 197.405, + "args": { + "External id": 38502,"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": 4183437, "tid": 4183437, + "ts": 658972449986.766, "dur": 1.087, + "args": { + "External id": 38503,"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": 4183437, "tid": 4183437, + "ts": 658972449988.971, "dur": 0.214, + "args": { + "External id": 38504,"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": 4183437, "tid": 4183437, + "ts": 658972449989.803, "dur": 0.404, + "args": { + "External id": 38505,"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": 4183437, "tid": 4183437, + "ts": 658972449990.816, "dur": 0.338, + "args": { + "External id": 38506,"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": 4183437, "tid": 4183437, + "ts": 658972449991.801, "dur": 0.050, + "args": { + "External id": 38507,"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": 4183437, "tid": 4183437, + "ts": 658972449992.284, "dur": 0.275, + "args": { + "External id": 38508,"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": 4183437, "tid": 4183437, + "ts": 658972449993.011, "dur": 0.064, + "args": { + "External id": 38509,"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": 4183437, "tid": 4183437, + "ts": 658972449993.339, "dur": 0.065, + "args": { + "External id": 38510,"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": 4183437, "tid": 4183437, + "ts": 658972449994.081, "dur": 0.066, + "args": { + "External id": 38511,"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": 4183437, "tid": 4183437, + "ts": 658972449994.577, "dur": 0.055, + "args": { + "External id": 38512,"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": 4183437, "tid": 4183437, + "ts": 658972449995.311, "dur": 0.059, + "args": { + "External id": 38513,"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": 4183437, "tid": 4183437, + "ts": 658972449995.821, "dur": 0.062, + "args": { + "External id": 38514,"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": 4183437, "tid": 4183437, + "ts": 658972449996.258, "dur": 0.062, + "args": { + "External id": 38515,"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": 4183437, "tid": 4183437, + "ts": 658972449996.724, "dur": 0.067, + "args": { + "External id": 38516,"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": 4183437, "tid": 4183437, + "ts": 658972449997.089, "dur": 0.065, + "args": { + "External id": 38517,"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": 4183437, "tid": 4183437, + "ts": 658972449997.567, "dur": 0.067, + "args": { + "External id": 38518,"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": 4183437, "tid": 4183437, + "ts": 658972449997.940, "dur": 0.065, + "args": { + "External id": 38519,"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": 4183437, "tid": 4183437, + "ts": 658972449998.324, "dur": 0.050, + "args": { + "External id": 38520,"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": 4183437, "tid": 4183437, + "ts": 658972449998.769, "dur": 0.056, + "args": { + "External id": 38521,"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": 4183437, "tid": 4183437, + "ts": 658972449999.080, "dur": 0.056, + "args": { + "External id": 38522,"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": 4183437, "tid": 4183437, + "ts": 658972449999.460, "dur": 0.089, + "args": { + "External id": 38523,"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": 4183437, "tid": 4183437, + "ts": 658972449999.851, "dur": 0.080, + "args": { + "External id": 38524,"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": 4183437, "tid": 4183437, + "ts": 658972450000.303, "dur": 0.063, + "args": { + "External id": 38525,"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": 4183437, "tid": 4183437, + "ts": 658972450000.658, "dur": 0.061, + "args": { + "External id": 38526,"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": 4183437, "tid": 4183437, + "ts": 658972450001.028, "dur": 0.178, + "args": { + "External id": 38527,"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": 4183437, "tid": 4183437, + "ts": 658972450001.624, "dur": 0.211, + "args": { + "External id": 38528,"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": 4183437, "tid": 4183437, + "ts": 658972450002.155, "dur": 0.190, + "args": { + "External id": 38529,"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": 4183437, "tid": 4183437, + "ts": 658972450002.631, "dur": 0.098, + "args": { + "External id": 38530,"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": 4183437, "tid": 4183437, + "ts": 658972450003.076, "dur": 0.288, + "args": { + "External id": 38531,"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": 4183437, "tid": 4183437, + "ts": 658972450003.728, "dur": 0.076, + "args": { + "External id": 38532,"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": 4183437, "tid": 4183437, + "ts": 658972450004.227, "dur": 0.064, + "args": { + "External id": 38533,"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": 4183437, "tid": 4183437, + "ts": 658972450004.894, "dur": 0.064, + "args": { + "External id": 38534,"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": 4183437, "tid": 4183437, + "ts": 658972450005.307, "dur": 0.064, + "args": { + "External id": 38535,"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": 4183437, "tid": 4183437, + "ts": 658972450005.764, "dur": 0.272, + "args": { + "External id": 38536,"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": 4183437, "tid": 4183437, + "ts": 658972450006.401, "dur": 0.068, + "args": { + "External id": 38537,"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": 4183437, "tid": 4183437, + "ts": 658972450006.830, "dur": 0.065, + "args": { + "External id": 38538,"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": 4183437, "tid": 4183437, + "ts": 658972450007.264, "dur": 0.067, + "args": { + "External id": 38539,"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": 4183437, "tid": 4183437, + "ts": 658972450007.660, "dur": 0.065, + "args": { + "External id": 38540,"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": 4183437, "tid": 4183437, + "ts": 658972450008.191, "dur": 0.068, + "args": { + "External id": 38541,"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": 4183437, "tid": 4183437, + "ts": 658972450008.551, "dur": 0.066, + "args": { + "External id": 38542,"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": 4183437, "tid": 4183437, + "ts": 658972450009.045, "dur": 0.065, + "args": { + "External id": 38543,"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": 4183437, "tid": 4183437, + "ts": 658972450009.451, "dur": 0.063, + "args": { + "External id": 38544,"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": 4183437, "tid": 4183437, + "ts": 658972450009.934, "dur": 0.068, + "args": { + "External id": 38545,"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": 4183437, "tid": 4183437, + "ts": 658972450010.425, "dur": 0.064, + "args": { + "External id": 38546,"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": 4183437, "tid": 4183437, + "ts": 658972450010.954, "dur": 0.061, + "args": { + "External id": 38547,"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": 4183437, "tid": 4183437, + "ts": 658972450011.446, "dur": 0.059, + "args": { + "External id": 38548,"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": 4183437, "tid": 4183437, + "ts": 658972450011.914, "dur": 0.065, + "args": { + "External id": 38549,"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": 4183437, "tid": 4183437, + "ts": 658972450012.528, "dur": 0.063, + "args": { + "External id": 38550,"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": 4183437, "tid": 4183437, + "ts": 658972450012.850, "dur": 0.062, + "args": { + "External id": 38551,"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": 4183437, "tid": 4183437, + "ts": 658972450013.413, "dur": 0.058, + "args": { + "External id": 38552,"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": 4183437, "tid": 4183437, + "ts": 658972450013.904, "dur": 0.063, + "args": { + "External id": 38553,"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": 4183437, "tid": 4183437, + "ts": 658972450014.436, "dur": 0.060, + "args": { + "External id": 38554,"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": 4183437, "tid": 4183437, + "ts": 658972450014.945, "dur": 0.068, + "args": { + "External id": 38555,"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": 4183437, "tid": 4183437, + "ts": 658972450015.483, "dur": 0.057, + "args": { + "External id": 38556,"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": 4183437, "tid": 4183437, + "ts": 658972450015.943, "dur": 0.066, + "args": { + "External id": 38557,"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": 4183437, "tid": 4183437, + "ts": 658972450016.374, "dur": 0.060, + "args": { + "External id": 38558,"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": 4183437, "tid": 4183437, + "ts": 658972450016.763, "dur": 0.064, + "args": { + "External id": 38559,"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": 4183437, "tid": 4183437, + "ts": 658972450017.178, "dur": 0.064, + "args": { + "External id": 38560,"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": 4183437, "tid": 4183437, + "ts": 658972450017.617, "dur": 0.049, + "args": { + "External id": 38561,"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": 4183437, "tid": 4183437, + "ts": 658972450017.963, "dur": 0.059, + "args": { + "External id": 38562,"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": 4183437, "tid": 4183437, + "ts": 658972450018.356, "dur": 0.055, + "args": { + "External id": 38563,"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": 4183437, "tid": 4183437, + "ts": 658972450018.788, "dur": 0.050, + "args": { + "External id": 38564,"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": 4183437, "tid": 4183437, + "ts": 658972450019.220, "dur": 0.053, + "args": { + "External id": 38565,"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": 4183437, "tid": 4183437, + "ts": 658972450019.636, "dur": 0.052, + "args": { + "External id": 38566,"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": 4183437, "tid": 4183437, + "ts": 658972450020.037, "dur": 0.056, + "args": { + "External id": 38567,"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": 4183437, "tid": 4183437, + "ts": 658972450020.492, "dur": 0.064, + "args": { + "External id": 38568,"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": 4183437, "tid": 4183437, + "ts": 658972450020.920, "dur": 0.063, + "args": { + "External id": 38569,"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": 4183437, "tid": 4183437, + "ts": 658972450021.343, "dur": 0.064, + "args": { + "External id": 38570,"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": 4183437, "tid": 4183437, + "ts": 658972450021.797, "dur": 0.067, + "args": { + "External id": 38571,"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": 4183437, "tid": 4183437, + "ts": 658972450022.322, "dur": 0.175, + "args": { + "External id": 38572,"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": 4183437, "tid": 4183437, + "ts": 658972450022.954, "dur": 0.061, + "args": { + "External id": 38573,"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": 4183437, "tid": 4183437, + "ts": 658972450023.710, "dur": 0.065, + "args": { + "External id": 38574,"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": 4183437, "tid": 4183437, + "ts": 658972450024.128, "dur": 0.062, + "args": { + "External id": 38575,"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": 4183437, "tid": 4183437, + "ts": 658972450024.638, "dur": 0.065, + "args": { + "External id": 38576,"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": 4183437, "tid": 4183437, + "ts": 658972450025.156, "dur": 0.062, + "args": { + "External id": 38577,"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": 4183437, "tid": 4183437, + "ts": 658972450025.481, "dur": 0.068, + "args": { + "External id": 38578,"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": 4183437, "tid": 4183437, + "ts": 658972450026.025, "dur": 0.065, + "args": { + "External id": 38579,"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": 4183437, "tid": 4183437, + "ts": 658972450026.459, "dur": 0.061, + "args": { + "External id": 38580,"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": 4183437, "tid": 4183437, + "ts": 658972450026.844, "dur": 0.063, + "args": { + "External id": 38581,"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": 4183437, "tid": 4183437, + "ts": 658972450027.369, "dur": 0.065, + "args": { + "External id": 38582,"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": 4183437, "tid": 4183437, + "ts": 658972450027.788, "dur": 0.063, + "args": { + "External id": 38583,"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": 4183437, "tid": 4183437, + "ts": 658972450028.207, "dur": 0.064, + "args": { + "External id": 38584,"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": 4183437, "tid": 4183437, + "ts": 658972450028.662, "dur": 0.064, + "args": { + "External id": 38585,"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": 4183437, "tid": 4183437, + "ts": 658972450029.002, "dur": 0.057, + "args": { + "External id": 38586,"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": 4183437, "tid": 4183437, + "ts": 658972450029.423, "dur": 0.065, + "args": { + "External id": 38587,"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": 4183437, "tid": 4183437, + "ts": 658972450029.852, "dur": 0.062, + "args": { + "External id": 38588,"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": 4183437, "tid": 4183437, + "ts": 658972450030.363, "dur": 0.076, + "args": { + "External id": 38589,"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": 4183437, "tid": 4183437, + "ts": 658972450030.795, "dur": 0.055, + "args": { + "External id": 38590,"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": 4183437, "tid": 4183437, + "ts": 658972450031.234, "dur": 0.049, + "args": { + "External id": 38591,"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": 4183437, "tid": 4183437, + "ts": 658972450031.640, "dur": 0.059, + "args": { + "External id": 38592,"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": 4183437, "tid": 4183437, + "ts": 658972450032.006, "dur": 0.054, + "args": { + "External id": 38593,"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": 4183437, "tid": 4183437, + "ts": 658972450032.529, "dur": 0.057, + "args": { + "External id": 38594,"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": 4183437, "tid": 4183437, + "ts": 658972450032.950, "dur": 0.055, + "args": { + "External id": 38595,"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": 4183437, "tid": 4183437, + "ts": 658972450033.364, "dur": 0.050, + "args": { + "External id": 38596,"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": 4183437, "tid": 4183437, + "ts": 658972450033.796, "dur": 0.064, + "args": { + "External id": 38597,"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": 4183437, "tid": 4183437, + "ts": 658972450034.140, "dur": 0.063, + "args": { + "External id": 38598,"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": 4183437, "tid": 4183437, + "ts": 658972450034.595, "dur": 0.064, + "args": { + "External id": 38599,"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": 4183437, "tid": 4183437, + "ts": 658972450035.070, "dur": 0.064, + "args": { + "External id": 38600,"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": 4183437, "tid": 4183437, + "ts": 658972450035.477, "dur": 0.053, + "args": { + "External id": 38601,"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": 4183437, "tid": 4183437, + "ts": 658972450035.918, "dur": 0.055, + "args": { + "External id": 38602,"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": 4183437, "tid": 4183437, + "ts": 658972450036.346, "dur": 0.064, + "args": { + "External id": 38603,"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": 4183437, "tid": 4183437, + "ts": 658972450037.065, "dur": 0.066, + "args": { + "External id": 38604,"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": 4183437, "tid": 4183437, + "ts": 658972450037.485, "dur": 0.060, + "args": { + "External id": 38605,"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": 4183437, "tid": 4183437, + "ts": 658972450038.063, "dur": 0.069, + "args": { + "External id": 38606,"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": 4183437, "tid": 4183437, + "ts": 658972450038.624, "dur": 0.064, + "args": { + "External id": 38607,"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": 4183437, "tid": 4183437, + "ts": 658972450039.004, "dur": 0.063, + "args": { + "External id": 38608,"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": 4183437, "tid": 4183437, + "ts": 658972450039.416, "dur": 0.060, + "args": { + "External id": 38609,"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": 4183437, "tid": 4183437, + "ts": 658972450039.885, "dur": 0.065, + "args": { + "External id": 38610,"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": 4183437, "tid": 4183437, + "ts": 658972450040.334, "dur": 0.058, + "args": { + "External id": 38611,"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": 4183437, "tid": 4183437, + "ts": 658972450040.790, "dur": 0.065, + "args": { + "External id": 38612,"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": 4183437, "tid": 4183437, + "ts": 658972450041.232, "dur": 0.062, + "args": { + "External id": 38613,"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": 4183437, "tid": 4183437, + "ts": 658972450041.664, "dur": 0.063, + "args": { + "External id": 38614,"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": 4183437, "tid": 4183437, + "ts": 658972450042.322, "dur": 0.059, + "args": { + "External id": 38615,"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": 4183437, "tid": 4183437, + "ts": 658972450042.743, "dur": 0.061, + "args": { + "External id": 38616,"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": 4183437, "tid": 4183437, + "ts": 658972450043.299, "dur": 0.058, + "args": { + "External id": 38617,"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": 4183437, "tid": 4183437, + "ts": 658972450043.676, "dur": 0.060, + "args": { + "External id": 38618,"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": 4183437, "tid": 4183437, + "ts": 658972450044.071, "dur": 0.063, + "args": { + "External id": 38619,"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": 4183437, "tid": 4183437, + "ts": 658972450044.424, "dur": 0.064, + "args": { + "External id": 38620,"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": 4183437, "tid": 4183437, + "ts": 658972450044.790, "dur": 0.065, + "args": { + "External id": 38621,"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": 4183437, "tid": 4183437, + "ts": 658972450045.200, "dur": 0.066, + "args": { + "External id": 38622,"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": 4183437, "tid": 4183437, + "ts": 658972450045.622, "dur": 0.065, + "args": { + "External id": 38623,"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": 4183437, "tid": 4183437, + "ts": 658972450046.016, "dur": 0.064, + "args": { + "External id": 38624,"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": 4183437, "tid": 4183437, + "ts": 658972450046.372, "dur": 0.065, + "args": { + "External id": 38625,"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": 4183437, "tid": 4183437, + "ts": 658972450046.858, "dur": 0.067, + "args": { + "External id": 38626,"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": 4183437, "tid": 4183437, + "ts": 658972450047.295, "dur": 0.065, + "args": { + "External id": 38627,"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": 4183437, "tid": 4183437, + "ts": 658972450047.725, "dur": 0.062, + "args": { + "External id": 38628,"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": 4183437, "tid": 4183437, + "ts": 658972450048.203, "dur": 0.051, + "args": { + "External id": 38629,"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": 4183437, "tid": 4183437, + "ts": 658972450048.576, "dur": 0.206, + "args": { + "External id": 38630,"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": 4183437, "tid": 4183437, + "ts": 658972450049.171, "dur": 0.066, + "args": { + "External id": 38631,"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": 4183437, "tid": 4183437, + "ts": 658972450049.554, "dur": 0.073, + "args": { + "External id": 38632,"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": 4183437, "tid": 4183437, + "ts": 658972450049.987, "dur": 0.198, + "args": { + "External id": 38633,"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": 4183437, "tid": 4183437, + "ts": 658972450050.480, "dur": 0.225, + "args": { + "External id": 38634,"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": 4183437, "tid": 4183437, + "ts": 658972450051.061, "dur": 0.189, + "args": { + "External id": 38635,"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": 4183437, "tid": 4183437, + "ts": 658972450051.501, "dur": 0.196, + "args": { + "External id": 38636,"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": 4183437, "tid": 4183437, + "ts": 658972450052.073, "dur": 0.061, + "args": { + "External id": 38637,"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": 4183437, "tid": 4183437, + "ts": 658972450052.532, "dur": 0.065, + "args": { + "External id": 38638,"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": 4183437, "tid": 4183437, + "ts": 658972450052.954, "dur": 0.060, + "args": { + "External id": 38639,"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": 4183437, "tid": 4183437, + "ts": 658972450053.394, "dur": 0.066, + "args": { + "External id": 38640,"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": 4183437, "tid": 4183437, + "ts": 658972450053.810, "dur": 0.048, + "args": { + "External id": 38641,"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": 4183437, "tid": 4183437, + "ts": 658972450054.212, "dur": 0.065, + "args": { + "External id": 38642,"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": 4183437, "tid": 4183437, + "ts": 658972450054.666, "dur": 0.053, + "args": { + "External id": 38643,"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": 4183437, "tid": 4183437, + "ts": 658972450055.074, "dur": 0.063, + "args": { + "External id": 38644,"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": 4183437, "tid": 4183437, + "ts": 658972450055.480, "dur": 0.063, + "args": { + "External id": 38645,"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": 4183437, "tid": 4183437, + "ts": 658972450055.939, "dur": 0.059, + "args": { + "External id": 38646,"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": 4183437, "tid": 4183437, + "ts": 658972450056.314, "dur": 0.063, + "args": { + "External id": 38647,"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": 4183437, "tid": 4183437, + "ts": 658972450056.727, "dur": 0.063, + "args": { + "External id": 38648,"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": 4183437, "tid": 4183437, + "ts": 658972450057.170, "dur": 0.065, + "args": { + "External id": 38649,"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": 4183437, "tid": 4183437, + "ts": 658972450057.581, "dur": 0.059, + "args": { + "External id": 38650,"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": 4183437, "tid": 4183437, + "ts": 658972450058.040, "dur": 0.062, + "args": { + "External id": 38651,"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": 4183437, "tid": 4183437, + "ts": 658972450058.491, "dur": 0.065, + "args": { + "External id": 38652,"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": 4183437, "tid": 4183437, + "ts": 658972450059.034, "dur": 0.066, + "args": { + "External id": 38653,"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": 4183437, "tid": 4183437, + "ts": 658972450059.436, "dur": 0.066, + "args": { + "External id": 38654,"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": 4183437, "tid": 4183437, + "ts": 658972450059.874, "dur": 0.060, + "args": { + "External id": 38655,"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": 4183437, "tid": 4183437, + "ts": 658972450060.243, "dur": 0.066, + "args": { + "External id": 38656,"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": 4183437, "tid": 4183437, + "ts": 658972450060.663, "dur": 0.060, + "args": { + "External id": 38657,"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": 4183437, "tid": 4183437, + "ts": 658972450061.157, "dur": 0.054, + "args": { + "External id": 38658,"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": 4183437, "tid": 4183437, + "ts": 658972450061.623, "dur": 0.062, + "args": { + "External id": 38659,"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": 4183437, "tid": 4183437, + "ts": 658972450062.071, "dur": 0.059, + "args": { + "External id": 38660,"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": 4183437, "tid": 4183437, + "ts": 658972450062.470, "dur": 0.060, + "args": { + "External id": 38661,"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": 4183437, "tid": 4183437, + "ts": 658972450062.815, "dur": 0.064, + "args": { + "External id": 38662,"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": 4183437, "tid": 4183437, + "ts": 658972450063.248, "dur": 0.066, + "args": { + "External id": 38663,"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": 4183437, "tid": 4183437, + "ts": 658972450063.688, "dur": 0.063, + "args": { + "External id": 38664,"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": 4183437, "tid": 4183437, + "ts": 658972450064.067, "dur": 0.063, + "args": { + "External id": 38665,"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": 4183437, "tid": 4183437, + "ts": 658972450064.416, "dur": 0.063, + "args": { + "External id": 38666,"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": 4183437, "tid": 4183437, + "ts": 658972450064.742, "dur": 0.067, + "args": { + "External id": 38667,"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": 4183437, "tid": 4183437, + "ts": 658972450065.104, "dur": 0.090, + "args": { + "External id": 38668,"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": 4183437, "tid": 4183437, + "ts": 658972450065.566, "dur": 0.065, + "args": { + "External id": 38669,"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": 4183437, "tid": 4183437, + "ts": 658972450065.980, "dur": 0.331, + "args": { + "External id": 38670,"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": 4183437, "tid": 4183437, + "ts": 658972450066.803, "dur": 0.067, + "args": { + "External id": 38671,"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": 4183437, "tid": 4183437, + "ts": 658972450067.305, "dur": 0.217, + "args": { + "External id": 38672,"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": 4183437, "tid": 4183437, + "ts": 658972450067.824, "dur": 0.192, + "args": { + "External id": 38673,"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": 4183437, "tid": 4183437, + "ts": 658972450068.496, "dur": 0.180, + "args": { + "External id": 38674,"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": 4183437, "tid": 4183437, + "ts": 658972450069.058, "dur": 0.227, + "args": { + "External id": 38675,"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": 4183437, "tid": 4183437, + "ts": 658972450069.919, "dur": 0.094, + "args": { + "External id": 38676,"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": 4183437, "tid": 4183437, + "ts": 658972450070.394, "dur": 0.078, + "args": { + "External id": 38677,"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": 4183437, "tid": 4183437, + "ts": 658972450070.960, "dur": 0.065, + "args": { + "External id": 38678,"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": 4183437, "tid": 4183437, + "ts": 658972450071.335, "dur": 0.066, + "args": { + "External id": 38679,"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": 4183437, "tid": 4183437, + "ts": 658972450071.752, "dur": 0.061, + "args": { + "External id": 38680,"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": 4183437, "tid": 4183437, + "ts": 658972450072.320, "dur": 0.067, + "args": { + "External id": 38681,"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": 4183437, "tid": 4183437, + "ts": 658972450072.745, "dur": 0.056, + "args": { + "External id": 38682,"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": 4183437, "tid": 4183437, + "ts": 658972450073.084, "dur": 0.070, + "args": { + "External id": 38683,"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": 4183437, "tid": 4183437, + "ts": 658972450073.529, "dur": 0.065, + "args": { + "External id": 38684,"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": 4183437, "tid": 4183437, + "ts": 658972450073.949, "dur": 0.058, + "args": { + "External id": 38685,"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": 4183437, "tid": 4183437, + "ts": 658972450074.372, "dur": 0.065, + "args": { + "External id": 38686,"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": 4183437, "tid": 4183437, + "ts": 658972450074.802, "dur": 0.063, + "args": { + "External id": 38687,"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": 4183437, "tid": 4183437, + "ts": 658972450075.254, "dur": 0.056, + "args": { + "External id": 38688,"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": 4183437, "tid": 4183437, + "ts": 658972450075.652, "dur": 0.065, + "args": { + "External id": 38689,"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": 4183437, "tid": 4183437, + "ts": 658972450076.070, "dur": 0.065, + "args": { + "External id": 38690,"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": 4183437, "tid": 4183437, + "ts": 658972450076.438, "dur": 0.306, + "args": { + "External id": 38691,"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": 4183437, "tid": 4183437, + "ts": 658972450077.255, "dur": 0.068, + "args": { + "External id": 38692,"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": 4183437, "tid": 4183437, + "ts": 658972450077.678, "dur": 0.066, + "args": { + "External id": 38693,"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": 4183437, "tid": 4183437, + "ts": 658972450078.082, "dur": 0.067, + "args": { + "External id": 38694,"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": 4183437, "tid": 4183437, + "ts": 658972450078.485, "dur": 0.057, + "args": { + "External id": 38695,"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": 4183437, "tid": 4183437, + "ts": 658972450078.837, "dur": 0.064, + "args": { + "External id": 38696,"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": 4183437, "tid": 4183437, + "ts": 658972450079.267, "dur": 0.083, + "args": { + "External id": 38697,"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": 4183437, "tid": 4183437, + "ts": 658972450079.695, "dur": 0.195, + "args": { + "External id": 38698,"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": 4183437, "tid": 4183437, + "ts": 658972450080.270, "dur": 0.224, + "args": { + "External id": 38699,"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": 4183437, "tid": 4183437, + "ts": 658972450080.865, "dur": 0.084, + "args": { + "External id": 38700,"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": 4183437, "tid": 4183437, + "ts": 658972450081.331, "dur": 0.055, + "args": { + "External id": 38701,"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": 4183437, "tid": 4183437, + "ts": 658972450081.756, "dur": 0.069, + "args": { + "External id": 38702,"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": 4183437, "tid": 4183437, + "ts": 658972450082.216, "dur": 0.067, + "args": { + "External id": 38703,"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": 4183437, "tid": 4183437, + "ts": 658972450082.634, "dur": 0.065, + "args": { + "External id": 38704,"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": 4183437, "tid": 4183437, + "ts": 658972450083.191, "dur": 0.237, + "args": { + "External id": 38705,"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": 4183437, "tid": 4183437, + "ts": 658972450083.743, "dur": 0.187, + "args": { + "External id": 38706,"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": 4183437, "tid": 4183437, + "ts": 658972450084.323, "dur": 0.233, + "args": { + "External id": 38707,"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": 4183437, "tid": 4183437, + "ts": 658972450084.960, "dur": 0.200, + "args": { + "External id": 38708,"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": 4183437, "tid": 4183437, + "ts": 658972450085.547, "dur": 0.064, + "args": { + "External id": 38709,"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": 4183437, "tid": 4183437, + "ts": 658972450086.118, "dur": 0.186, + "args": { + "External id": 38710,"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": 4183437, "tid": 4183437, + "ts": 658972450086.719, "dur": 0.365, + "args": { + "External id": 38711,"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": 4183437, "tid": 4183437, + "ts": 658972450087.417, "dur": 0.318, + "args": { + "External id": 38712,"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": 4183437, "tid": 4183437, + "ts": 658972450088.138, "dur": 0.231, + "args": { + "External id": 38713,"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": 4183437, "tid": 4183437, + "ts": 658972450088.740, "dur": 0.197, + "args": { + "External id": 38714,"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": 4183437, "tid": 4183437, + "ts": 658972450089.262, "dur": 0.253, + "args": { + "External id": 38715,"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": 4183437, "tid": 4183437, + "ts": 658972450089.831, "dur": 0.094, + "args": { + "External id": 38716,"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": 4183437, "tid": 4183437, + "ts": 658972450090.267, "dur": 0.067, + "args": { + "External id": 38717,"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": 4183437, "tid": 4183437, + "ts": 658972450090.671, "dur": 0.072, + "args": { + "External id": 38718,"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": 4183437, "tid": 4183437, + "ts": 658972450091.039, "dur": 0.184, + "args": { + "External id": 38719,"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": 4183437, "tid": 4183437, + "ts": 658972450091.576, "dur": 0.197, + "args": { + "External id": 38720,"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": 4183437, "tid": 4183437, + "ts": 658972450092.164, "dur": 0.087, + "args": { + "External id": 38721,"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": 4183437, "tid": 4183437, + "ts": 658972450555.593, "dur": 2571.496, + "args": { + "External id": 38722,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "0.00029992535393923549", "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": 4183437, "tid": 4183437, + "ts": 658972452790.908, "dur": 219.108, + "args": { + "External id": 38723,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "0.00029992535393923549", "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": 658971661257.325, "pid": 4183437, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 658971661257.325, "pid": 4183437, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 658971661257.325, "pid": 4183437, "tid": 0, + "args": { + "sort_index": 4183437 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 658971661257.325, "pid": 4183437, "tid": 31318, + "args": { + "name": "thread 31318 (pt_autograd_1)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 658971661257.325, "pid": 4183437, "tid": 31318, + "args": { + "sort_index": 31318 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 658971661257.325, "pid": 4183437, "tid": 4183437, + "args": { + "name": "thread 4183437 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 658971661257.325, "pid": 4183437, "tid": 4183437, + "args": { + "sort_index": 4183437 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 658971661257.325, "pid": 4183437, "tid": 31318, + "args": { + "name": "thread 31318 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 658971661257.325, "pid": 4183437, "tid": 31318, + "args": { + "sort_index": 31318 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 658971661191.053, "dur": 792265.457, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 658971661191.053, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 658971661191.053 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 658972487873.786 + } + ], + "traceName": "exp/mtp.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine/profile_trace/iteration_2048/rank1_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file