From c509a7864591a0bf517602a728c77e0266203102 Mon Sep 17 00:00:00 2001 From: PyTorch UpdateBot Date: Mon, 13 Oct 2025 11:47:32 +0000 Subject: [PATCH] Update slow tests (#165301) This PR is auto-generated weekly by [this action](https://github.com/pytorch/pytorch/blob/main/.github/workflows/weekly.yml). Update the list of slow tests. Pull Request resolved: https://github.com/pytorch/pytorch/pull/165301 Approved by: https://github.com/pytorchbot --- test/slow_tests.json | 476 +++++++++++++++++++++---------------------- 1 file changed, 235 insertions(+), 241 deletions(-) diff --git a/test/slow_tests.json b/test/slow_tests.json index 21e30a99f31f..dc75ed8380ce 100644 --- a/test/slow_tests.json +++ b/test/slow_tests.json @@ -1,243 +1,237 @@ { - "EndToEndLSTM (__main__.RNNTest)": 191.33366902669272, - "MultiheadAttention (__main__.ModulesTest)": 134.8723347981771, - "test_AllenaiLongformerBase_repro_cpu_halide (__main__.HalideCpuTests)": 213.43866475423178, - "test__adaptive_avg_pool2d (__main__.CPUReproTests)": 110.66888766818576, - "test_adaptive_max_pool2d1_cpu_halide (__main__.HalideCpuTests)": 116.15466562906902, - "test_after_aot_cpu_runtime_error (__main__.MinifierIsolateTests)": 68.31822289360895, - "test_after_aot_gpu_runtime_error (__main__.MinifierIsolateTests)": 65.6883316040039, - "test_alexnet_prefix_cpu_halide (__main__.HalideCpuTests)": 177.9036661783854, - "test_aot_autograd_exhaustive_nn_functional_max_pool2d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 61.22009531656901, - "test_aot_autograd_symbolic_exhaustive_linalg_svd_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 69.04500071207683, - "test_aot_autograd_symbolic_exhaustive_masked_norm_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 72.29609616597493, - "test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool1d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 148.70033264160156, - "test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool2d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 211.1353302001953, - "test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool3d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 123.71333567301433, - "test_aot_autograd_symbolic_exhaustive_nn_functional_unfold_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 62.16333262125651, - "test_aot_autograd_symbolic_exhaustive_ormqr_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 65.4426663716634, - "test_aot_autograd_symbolic_exhaustive_svd_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 100.13133239746094, - "test_aot_autograd_symbolic_module_exhaustive_nn_TransformerDecoderLayer_cpu_float32 (__main__.TestEagerFusionModuleInfoCPU)": 152.17533111572266, - "test_associative_scan_partial_grad_combine_mode_generic_compile_mode_compile_dynamic_shape_reverse_False_cpu (__main__.AssociativeScanTests)": 87.69433339436848, - "test_associative_scan_partial_grad_combine_mode_generic_compile_mode_compile_dynamic_shape_reverse_True_cpu (__main__.AssociativeScanTests)": 100.97316487630208, - "test_avg_pool3d_backward2_cpu (__main__.CpuTests)": 610.1386047363281, - "test_avg_pool3d_backward2_cuda (__main__.GPUTests)": 127.10489959716797, - "test_avg_pool3d_backward2_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 506.5771077473958, - "test_avg_pool3d_backward2_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 492.1573248969184, - "test_avg_pool3d_backward2_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 144.6948331197103, - "test_avg_pool3d_backward_cpu_halide (__main__.HalideCpuTests)": 61.63200124104818, - "test_backward_nn_functional_multi_head_attention_forward_cpu_float32 (__main__.TestCompositeComplianceCPU)": 93.15633392333984, - "test_backward_nn_functional_multi_head_attention_forward_cuda_float32 (__main__.TestCompositeComplianceCUDA)": 65.30966631571452, - "test_basic_cpu (__main__.EfficientConvBNEvalCpuTests)": 264.9088863796658, - "test_basic_cuda (__main__.EfficientConvBNEvalGpuTests)": 134.63433329264322, - "test_checkpointing_without_reentrant_input_requires_grad_False (__main__.TestAutogradWithCompiledAutograd)": 331.43299696180554, - "test_checkpointing_without_reentrant_input_requires_grad_True (__main__.TestAutogradWithCompiledAutograd)": 406.1637776692708, - "test_collect_callgrind (__main__.TestBenchmarkUtils)": 282.8108893500434, - "test_comprehensive_diff_cuda_complex128 (__main__.TestDecompCUDA)": 100.46050135294597, - "test_comprehensive_diff_cuda_complex64 (__main__.TestDecompCUDA)": 93.01183319091797, - "test_comprehensive_diff_cuda_float32 (__main__.TestDecompCUDA)": 75.01616668701172, - "test_comprehensive_diff_cuda_float64 (__main__.TestDecompCUDA)": 74.29783376057942, - "test_comprehensive_grid_sampler_2d_cpu_bfloat16 (__main__.TestDecompCPU)": 143.50833129882812, - "test_comprehensive_grid_sampler_2d_cpu_float16 (__main__.TestDecompCPU)": 125.7469965616862, - "test_comprehensive_grid_sampler_2d_cpu_float32 (__main__.TestDecompCPU)": 470.2953287760417, - "test_comprehensive_grid_sampler_2d_cpu_float64 (__main__.TestDecompCPU)": 457.1296691894531, - "test_comprehensive_grid_sampler_2d_cuda_bfloat16 (__main__.TestDecompCUDA)": 240.6798350016276, - "test_comprehensive_grid_sampler_2d_cuda_float16 (__main__.TestDecompCUDA)": 260.5936686197917, - "test_comprehensive_grid_sampler_2d_cuda_float32 (__main__.TestDecompCUDA)": 1124.753662109375, - "test_comprehensive_grid_sampler_2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 66.99483299255371, - "test_comprehensive_grid_sampler_2d_cuda_float64 (__main__.TestDecompCUDA)": 1264.2056884765625, - "test_comprehensive_grid_sampler_2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 76.98716608683269, - "test_comprehensive_linalg_lu_solve_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 75.25616709391277, - "test_comprehensive_linalg_lu_solve_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 75.80700047810872, - "test_comprehensive_linalg_solve_triangular_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 75.4755007425944, - "test_comprehensive_linalg_solve_triangular_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 76.71533330281575, - "test_comprehensive_linalg_svd_cuda_complex128 (__main__.TestDecompCUDA)": 73.72999827067058, - "test_comprehensive_linalg_svd_cuda_complex64 (__main__.TestDecompCUDA)": 63.12866528828939, - "test_comprehensive_masked_norm_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 118.51316452026367, - "test_comprehensive_masked_norm_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 113.66216659545898, - "test_comprehensive_masked_norm_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 107.28399912516277, - "test_comprehensive_nn_functional_conv_transpose3d_cuda_complex128 (__main__.TestDecompCUDA)": 63.821667989095054, - "test_comprehensive_nn_functional_conv_transpose3d_cuda_complex64 (__main__.TestDecompCUDA)": 70.22649955749512, - "test_comprehensive_nn_functional_gaussian_nll_loss_cpu_float32 (__main__.TestDecompCPU)": 67.39133199055989, - "test_comprehensive_nn_functional_gaussian_nll_loss_cpu_float64 (__main__.TestDecompCPU)": 61.59499867757162, - "test_comprehensive_nn_functional_gaussian_nll_loss_cuda_float32 (__main__.TestDecompCUDA)": 113.81933212280273, - "test_comprehensive_nn_functional_gaussian_nll_loss_cuda_float64 (__main__.TestDecompCUDA)": 117.18516667683919, - "test_comprehensive_nn_functional_grid_sample_cpu_float32 (__main__.TestDecompCPU)": 113.2913335164388, - "test_comprehensive_nn_functional_grid_sample_cpu_float64 (__main__.TestDecompCPU)": 110.78766377766927, - "test_comprehensive_nn_functional_grid_sample_cuda_bfloat16 (__main__.TestDecompCUDA)": 60.50283241271973, - "test_comprehensive_nn_functional_grid_sample_cuda_float16 (__main__.TestDecompCUDA)": 98.85449854532878, - "test_comprehensive_nn_functional_grid_sample_cuda_float32 (__main__.TestDecompCUDA)": 249.79983266194662, - "test_comprehensive_nn_functional_grid_sample_cuda_float64 (__main__.TestDecompCUDA)": 224.61499786376953, - "test_comprehensive_nn_functional_interpolate_bicubic_cuda_float32 (__main__.TestDecompCUDA)": 77.0316670735677, - "test_comprehensive_nn_functional_interpolate_bicubic_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 79.32850011189778, - "test_comprehensive_nn_functional_interpolate_bicubic_cuda_float64 (__main__.TestDecompCUDA)": 84.80683517456055, - "test_comprehensive_nn_functional_interpolate_bicubic_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 81.40266799926758, - "test_comprehensive_nn_functional_interpolate_trilinear_cuda_float32 (__main__.TestDecompCUDA)": 128.5533332824707, - "test_comprehensive_nn_functional_interpolate_trilinear_cuda_float64 (__main__.TestDecompCUDA)": 139.6883316040039, - "test_comprehensive_nn_functional_max_pool2d_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 1263.1241658528645, - "test_comprehensive_nn_functional_max_pool2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 1288.59619140625, - "test_comprehensive_nn_functional_max_pool2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 1255.9813435872395, - "test_comprehensive_nn_functional_max_pool3d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 512.7396748860677, - "test_comprehensive_nn_functional_max_pool3d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 529.6584981282552, - "test_comprehensive_nn_functional_max_unpool2d_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 67.26166661580403, - "test_comprehensive_nn_functional_max_unpool2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 63.762999852498375, - "test_comprehensive_nn_functional_max_unpool2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 62.132999420166016, - "test_comprehensive_ormqr_cpu_complex128 (__main__.TestDecompCPU)": 61.94059969584147, - "test_comprehensive_ormqr_cpu_complex64 (__main__.TestDecompCPU)": 61.69800059000651, - "test_comprehensive_ormqr_cuda_complex128 (__main__.TestDecompCUDA)": 129.1680005391439, - "test_comprehensive_ormqr_cuda_complex64 (__main__.TestDecompCUDA)": 100.96399943033855, - "test_comprehensive_ormqr_cuda_float32 (__main__.TestDecompCUDA)": 73.8378340403239, - "test_comprehensive_ormqr_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 76.0221659342448, - "test_comprehensive_ormqr_cuda_float64 (__main__.TestDecompCUDA)": 70.77316602071126, - "test_comprehensive_svd_cuda_complex128 (__main__.TestDecompCUDA)": 80.17649841308594, - "test_comprehensive_svd_cuda_complex64 (__main__.TestDecompCUDA)": 68.18916702270508, - "test_constructor_autograd_SparseBSC_cuda (__main__.TestSparseAnyCUDA)": 105.66150029500325, - "test_constructor_autograd_SparseBSR_cuda (__main__.TestSparseAnyCUDA)": 92.21050135294597, - "test_constructor_autograd_SparseCSC_cuda (__main__.TestSparseAnyCUDA)": 81.38250160217285, - "test_constructor_autograd_SparseCSR_cuda (__main__.TestSparseAnyCUDA)": 60.15933418273926, - "test_conv1d_basic (__main__.TestXNNPACKConv1dTransformPass)": 228.092889573839, - "test_conv1d_with_relu_fc (__main__.TestXNNPACKConv1dTransformPass)": 412.05389234754773, - "test_conv2d_binary_broadcast_shapes_cpu (__main__.TestPatternMatcherGenericCPU)": 78.01033274332683, - "test_conv3d_binary_broadcast_shapes_cpu (__main__.TestPatternMatcherGenericCPU)": 151.20733133951822, - "test_conv3d_binary_dynamic_shapes_cpu (__main__.TestDynamicPatternMatcherGenericCPU)": 61.65733337402344, - "test_conv3d_cuda (__main__.AOTInductorTestABICompatibleGpu)": 127.69299952189128, - "test_conv_bn_fuse_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 85.92033343844943, - "test_conv_transpose_with_output_size_and_no_batch_dim_ConvTranspose3d_cuda (__main__.TestConvolutionNNDeviceTypeCUDA)": 171.69888784451825, - "test_conv_unary_fusion_nnc (__main__.TestMkldnnFusion)": 77.14755460951064, - "test_correctness_AdamW_use_closure_True_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 83.75133260091145, - "test_correctness_Adam_use_closure_True_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 81.0783322652181, - "test_count_nonzero_all (__main__.TestBool)": 654.9482218424479, - "test_ddp_uneven_inputs (__main__.TestDistBackendWithSpawn)": 385.7187485694885, - "test_dispatch_symbolic_meta_outplace_all_strides_nn_functional_gaussian_nll_loss_cuda_float32 (__main__.TestMetaCUDA)": 85.74933369954427, - "test_dtensor_op_db_nn_functional_gaussian_nll_loss_cpu_float32 (__main__.TestDTensorOpsCPU)": 82.98500061035156, - "test_eig_check_magma_cuda_float32 (__main__.TestLinalgCUDA)": 237.72600301106772, - "test_error_detection_and_propagation (__main__.NcclErrorHandlingTest)": 66.79100036621094, - "test_fail_arithmetic_ops.py (__main__.TestTyping)": 65.94033304850261, - "test_fail_creation_ops.py (__main__.TestTyping)": 74.630965868632, - "test_fn_fwgrad_bwgrad_cumprod_cuda_complex128 (__main__.TestFwdGradientsCUDA)": 79.57700093587239, - "test_fn_gradgrad_cumprod_cuda_complex128 (__main__.TestBwdGradientsCUDA)": 86.1043332417806, - "test_forward_ad_svd_lowrank_cpu_float32 (__main__.TestCompositeComplianceCPU)": 60.11133321126302, - "test_fuse_large_params_cpu (__main__.CpuTests)": 134.67800013224283, - "test_fuse_large_params_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 162.69288889567056, - "test_fuse_large_params_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 158.78210957845053, - "test_fuse_large_params_dynamic_shapes_cuda (__main__.DynamicShapesCodegenGPUTests)": 155.22199503580728, - "test_fuse_large_params_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 122.35983276367188, - "test_grad_nn_Transformer_cpu_float64 (__main__.TestModuleCPU)": 89.12963204634816, - "test_grad_nn_Transformer_cuda_float64 (__main__.TestModuleCUDA)": 88.73866653442383, - "test_gradgrad_nn_LSTM_eval_mode_cuda_float64 (__main__.TestModuleCUDA)": 111.30266571044922, - "test_gradgrad_nn_LSTM_train_mode_cuda_float64 (__main__.TestModuleCUDA)": 114.47200012207031, - "test_gradgrad_nn_TransformerDecoderLayer_cuda_float64 (__main__.TestModuleCUDA)": 214.20233154296875, - "test_gradgrad_nn_TransformerEncoder_eval_mode_cuda_float64 (__main__.TestModuleCUDA)": 147.14099884033203, - "test_gradgrad_nn_TransformerEncoder_train_mode_cuda_float64 (__main__.TestModuleCUDA)": 148.1125030517578, - "test_gradgrad_nn_Transformer_cuda_float64 (__main__.TestModuleCUDA)": 671.3279927571615, - "test_grid_sampler_2d_cpu_halide (__main__.HalideCpuTests)": 194.77100118001303, - "test_indirect_device_assert (__main__.TritonCodeGenTests)": 326.58533732096356, - "test_inductor_no_recursionerror_on_for_loops_dynamic_shapes (__main__.DynamicShapesReproTests)": 68.14488940768771, - "test_inplace_gradgrad_cumprod_cuda_complex128 (__main__.TestBwdGradientsCUDA)": 82.70250002543132, - "test_inputs_overlapping_with_mutation_stress_dynamic_shapes (__main__.DynamicShapesAotAutogradFallbackTests)": 121.82255554199219, - "test_jit_cuda_archflags (__main__.TestCppExtensionJIT)": 134.68099721272787, - "test_linalg_solve_triangular_large_cuda_complex128 (__main__.TestLinalgCUDA)": 131.55699666341147, - "test_linalg_solve_triangular_large_cuda_complex64 (__main__.TestLinalgCUDA)": 95.03233337402344, - "test_linear_binary_cpp_wrapper (__main__.TestCppWrapper)": 113.44033304850261, - "test_linear_binary_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 135.57266743977866, - "test_lobpcg_ortho_cuda_float64 (__main__.TestLinalgCUDA)": 62.20383262634277, - "test_longformer_chunk_dynamic_shapes (__main__.DynamicShapesReproTests)": 106.95122188991971, - "test_lstm_cpu (__main__.TestMkldnnCPU)": 62.8009999593099, - "test_many_overlapping_inputs_does_not_explode_guards_dynamic_shapes (__main__.DynamicShapesReproTests)": 133.8374455769857, - "test_max_autotune_addmm_max_autotune_gemm_backends_CK_x_shape2 (__main__.TestCKBackend)": 72.11500040690105, - "test_max_autotune_addmm_search_space_EXHAUSTIVE_dynamic_True (__main__.TestMaxAutotuneSubproc)": 82.9066670735677, - "test_max_autotune_precompile_matmul_max_autotune_gemm_backends_CKTILE_autotune_in_subproc_False_use_aoti_False (__main__.TestCKBackend)": 86.69833374023438, - "test_max_autotune_precompile_matmul_max_autotune_gemm_backends_CKTILE_autotune_in_subproc_True_use_aoti_False (__main__.TestCKBackend)": 62.752166748046875, - "test_max_autotune_precompile_matmul_max_autotune_gemm_backends_CKTILE_autotune_in_subproc_True_use_aoti_True (__main__.TestCKBackend)": 74.72050031026204, - "test_max_pool2d2_cpu_halide (__main__.HalideCpuTests)": 422.8780008951823, - "test_max_pool2d3_cpu_halide (__main__.HalideCpuTests)": 133.37999979654947, - "test_max_pool2d5_cpu_halide (__main__.HalideCpuTests)": 358.6440022786458, - "test_max_pool2d_with_indices_backward4_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 62.8304443359375, - "test_max_pool2d_with_indices_backward4_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 66.12477747599284, - "test_proper_exit (__main__.TestDataLoader)": 201.04933081732855, - "test_proper_exit (__main__.TestDataLoaderPersistentWorkers)": 216.82066769070096, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 108.58233133951823, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 104.72800191243489, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_True (__main__.TestPatternMatcher)": 83.89166768391927, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 104.23666636149089, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 102.5836664835612, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_False (__main__.TestPatternMatcher)": 82.30966695149739, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 89.95899963378906, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 107.05433146158855, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_True (__main__.TestPatternMatcher)": 87.9943339029948, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 95.94033559163411, - "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 112.61300150553386, - "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_False (__main__.TestPatternMatcher)": 86.26266733805339, - "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 101.86633555094402, - "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 109.01599884033203, - "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 127.79766591389973, - "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 103.49066670735677, - "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 103.7183329264323, - "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 100.73733266194661, - "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 113.88333129882812, - "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 99.30833435058594, - "test_quick_core_backward__unsafe_masked_index_cpu_float64 (__main__.TestDecompCPU)": 543.4786783854166, - "test_quick_core_backward__unsafe_masked_index_cuda_float64 (__main__.TestDecompCUDA)": 1086.6808268229167, - "test_quick_core_backward__unsafe_masked_index_put_accumulate_cpu_float64 (__main__.TestDecompCPU)": 750.5633138020834, - "test_quick_core_backward__unsafe_masked_index_put_accumulate_cuda_float64 (__main__.TestDecompCUDA)": 1523.3708089192708, - "test_quick_core_backward_nn_functional_max_unpool3d_grad_cpu_float64 (__main__.TestDecompCPU)": 85.93766784667969, - "test_quick_core_backward_nn_functional_max_unpool3d_grad_cuda_float64 (__main__.TestDecompCUDA)": 288.513666788737, - "test_quick_core_backward_roll_cpu_float64 (__main__.TestDecompCPU)": 114.52266693115234, - "test_quick_core_backward_roll_cuda_float64 (__main__.TestDecompCUDA)": 243.95849609375, - "test_quick_core_backward_select_scatter_cpu_float64 (__main__.TestDecompCPU)": 71.62833404541016, - "test_quick_core_backward_select_scatter_cuda_float64 (__main__.TestDecompCUDA)": 153.4586664835612, - "test_quick_core_backward_split_cuda_float64 (__main__.TestDecompCUDA)": 71.8888333638509, - "test_quick_core_backward_split_with_sizes_copy_cpu_float64 (__main__.TestDecompCPU)": 86.57800038655598, - "test_quick_core_backward_split_with_sizes_copy_cuda_float64 (__main__.TestDecompCUDA)": 173.53899637858072, - "test_quick_core_backward_std_cuda_float64 (__main__.TestDecompCUDA)": 115.68783187866211, - "test_register_spills_cuda (__main__.BenchmarkFusionCudaTest)": 95.93583424886067, - "test_replicatepad_64bit_indexing_cuda_float16 (__main__.TestNNDeviceTypeCUDA)": 90.23633575439453, - "test_rosenbrock_sparse_with_lrsched_False_SGD_cuda_float64 (__main__.TestOptimRenewedCUDA)": 72.35433292388916, - "test_rosenbrock_sparse_with_lrsched_True_SGD_cuda_float64 (__main__.TestOptimRenewedCUDA)": 62.462000370025635, - "test_runtime_checks_large_cpu (__main__.AOTInductorTestABICompatibleCpu)": 82.4760004679362, - "test_runtime_checks_large_cpu_with_stack_allocation (__main__.AOTInductorTestABICompatibleCpuWithStackAllocation)": 74.86855612860785, - "test_runtime_checks_large_cuda (__main__.AOTInductorTestABICompatibleGpu)": 229.71883392333984, - "test_save_load_large_string_attribute (__main__.TestSaveLoad)": 120.88866678873698, - "test_sdpa_kernel_ctx_manager2_dynamic_shapes (__main__.DynamicShapesCtxManagerTests)": 160.74955579969617, - "test_shuffler_iterdatapipe (__main__.IntegrationTestDataLoaderDataPipe)": 112.91644626193576, - "test_slow_tasks (__main__.TestFunctionalAutogradBenchmark)": 142.431888156467, - "test_sort_stable_cpu (__main__.CpuTritonTests)": 77.32766723632812, - "test_split_cumsum_cpu (__main__.CpuTritonTests)": 89.65899912516277, - "test_svd_lowrank_cuda_complex128 (__main__.TestLinalgCUDA)": 159.24483482042947, - "test_tensor_split (__main__.TestVmapOperators)": 78.26266692144175, - "test_terminate_handler_on_crash (__main__.TestTorch)": 110.73689207765791, - "test_terminate_signal (__main__.ForkTest)": 130.3988852335347, - "test_terminate_signal (__main__.ParallelForkServerShouldWorkTest)": 130.34366810487376, - "test_terminate_signal (__main__.SpawnTest)": 134.24955691231622, - "test_torchvision_smoke (__main__.TestTensorBoardPytorchGraph)": 89.1145576900906, - "test_train_parity_multi_group_unshard_async_op (__main__.TestFullyShard1DTrainingCore)": 63.29414367675781, - "test_triton_bsr_scatter_mm_blocksize_64_cuda_bfloat16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 66.13816706339519, - "test_triton_bsr_scatter_mm_blocksize_64_cuda_float16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 61.474833170572914, - "test_triton_bsr_scatter_mm_blocksize_64_cuda_float32 (__main__.TestSparseCompressedTritonKernelsCUDA)": 63.66100056966146, - "test_triton_bsr_softmax_cuda_bfloat16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 138.59650166829428, - "test_triton_bsr_softmax_cuda_float16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 134.72383308410645, - "test_triton_bsr_softmax_cuda_float32 (__main__.TestSparseCompressedTritonKernelsCUDA)": 101.47983487447102, - "test_unary_ops (__main__.TestTEFuserDynamic)": 86.44255712297227, - "test_unary_ops (__main__.TestTEFuserStatic)": 87.88366595904033, - "test_upsample_bicubic2d_cpu_halide (__main__.HalideCpuTests)": 97.57233174641927, - "test_variant_consistency_jit_nn_functional_max_pool2d_cpu_float32 (__main__.TestJitCPU)": 86.79966481526692, - "test_variant_consistency_jit_nn_functional_max_pool2d_cuda_float32 (__main__.TestJitCUDA)": 78.25616645812988, - "test_views1_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 86.09200032552083, - "test_vmapjvpvjp_linalg_lstsq_grad_oriented_cpu_float32 (__main__.TestOperatorsCPU)": 93.0883305867513, - "test_vmapjvpvjp_linalg_lstsq_grad_oriented_cuda_float32 (__main__.TestOperatorsCUDA)": 64.61466725667317, - "test_vmapjvpvjp_linalg_lu_solve_cpu_float32 (__main__.TestOperatorsCPU)": 64.00000127156575, - "test_vmapjvpvjp_linalg_lu_solve_cuda_float32 (__main__.TestOperatorsCUDA)": 86.52750015258789, - "test_vmapjvpvjp_linalg_multi_dot_cuda_float32 (__main__.TestOperatorsCUDA)": 61.383832931518555, - "test_vmapjvpvjp_linalg_solve_triangular_cuda_float32 (__main__.TestOperatorsCUDA)": 66.71549987792969, - "test_vmapjvpvjp_linalg_svd_cuda_float32 (__main__.TestOperatorsCUDA)": 78.1248353322347, - "test_vmapjvpvjp_max_pool2d_with_indices_backward_cpu_float32 (__main__.TestOperatorsCPU)": 71.14666493733723, - "test_vmapjvpvjp_max_pool2d_with_indices_backward_cuda_float32 (__main__.TestOperatorsCUDA)": 70.01699956258138, - "test_vmapjvpvjp_nn_functional_conv2d_cpu_float32 (__main__.TestOperatorsCPU)": 65.63585671924409, - "test_vmapjvpvjp_nn_functional_max_pool2d_cpu_float32 (__main__.TestOperatorsCPU)": 82.29966735839844, - "test_vmapjvpvjp_nn_functional_max_pool2d_cuda_float32 (__main__.TestOperatorsCUDA)": 72.66933314005534, - "test_vmapjvpvjp_svd_cuda_float32 (__main__.TestOperatorsCUDA)": 84.87933286031087, - "test_vmapjvpvjp_unbind_cpu_float32 (__main__.TestOperatorsCPU)": 64.37099838256836, - "test_vmapjvpvjp_unbind_cuda_float32 (__main__.TestOperatorsCUDA)": 93.33683395385742, - "test_vmapvjpvjp_meshgrid_list_of_tensors_cuda_float32 (__main__.TestOperatorsCUDA)": 98.61116472880046, - "test_vmapvjpvjp_meshgrid_variadic_tensors_cuda_float32 (__main__.TestOperatorsCUDA)": 145.25766372680664, - "test_vmapvjpvjp_nn_functional_bilinear_cuda_float32 (__main__.TestOperatorsCUDA)": 141.7891642252604 + "EndToEndLSTM (__main__.RNNTest)": 155.6796646118164, + "MultiheadAttention (__main__.ModulesTest)": 133.05866495768228, + "test__adaptive_avg_pool2d (__main__.CPUReproTests)": 85.84300020005968, + "test_after_aot_cpu_runtime_error (__main__.MinifierIsolateTests)": 65.42522388034396, + "test_after_aot_gpu_runtime_error (__main__.MinifierIsolateTests)": 65.31233215332031, + "test_aot_autograd_exhaustive_nn_functional_max_pool2d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 79.9153340657552, + "test_aot_autograd_symbolic_exhaustive_linalg_svd_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 81.48433176676433, + "test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool1d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 186.04832967122397, + "test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool2d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 188.46499633789062, + "test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool3d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 115.20666758219402, + "test_aot_autograd_symbolic_exhaustive_ormqr_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 61.17433293660482, + "test_aot_autograd_symbolic_exhaustive_svd_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 86.86166890462239, + "test_aot_autograd_symbolic_module_exhaustive_nn_TransformerDecoderLayer_cpu_float32 (__main__.TestEagerFusionModuleInfoCPU)": 138.65032958984375, + "test_associative_scan_partial_grad_combine_mode_generic_compile_mode_compile_dynamic_shape_reverse_False_cpu (__main__.AssociativeScanTests)": 86.7721659342448, + "test_associative_scan_partial_grad_combine_mode_generic_compile_mode_compile_dynamic_shape_reverse_True_cpu (__main__.AssociativeScanTests)": 102.99050013224284, + "test_avg_pool3d_backward2_cpu (__main__.CpuTests)": 608.43359375, + "test_avg_pool3d_backward2_cuda (__main__.GPUTests)": 173.7251423427037, + "test_avg_pool3d_backward2_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 486.642333984375, + "test_avg_pool3d_backward2_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 491.10267130533856, + "test_avg_pool3d_backward2_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 138.62899780273438, + "test_backward_nn_functional_multi_head_attention_forward_cpu_float32 (__main__.TestCompositeComplianceCPU)": 81.7653325398763, + "test_backward_nn_functional_multi_head_attention_forward_cuda_float32 (__main__.TestCompositeComplianceCUDA)": 76.25450134277344, + "test_basic_cpu (__main__.EfficientConvBNEvalCpuTests)": 216.97666592068143, + "test_basic_cuda (__main__.EfficientConvBNEvalGpuTests)": 139.57733154296875, + "test_binary (__main__.StartProcessesListAsBinaryTest)": 1000.2024993896484, + "test_cat_2k_args (__main__.TestTEFuserDynamic)": 118.18855590663023, + "test_cat_2k_args (__main__.TestTEFuserStatic)": 111.97772413368027, + "test_checkpointing_without_reentrant_input_requires_grad_False (__main__.TestAutogradWithCompiledAutograd)": 320.02644517686633, + "test_checkpointing_without_reentrant_input_requires_grad_True (__main__.TestAutogradWithCompiledAutograd)": 402.67100016276044, + "test_collect_callgrind (__main__.TestBenchmarkUtils)": 300.41977945963544, + "test_comprehensive_diff_cuda_complex128 (__main__.TestDecompCUDA)": 96.34449895222981, + "test_comprehensive_diff_cuda_complex64 (__main__.TestDecompCUDA)": 93.42950057983398, + "test_comprehensive_diff_cuda_float32 (__main__.TestDecompCUDA)": 64.60500017801921, + "test_comprehensive_diff_cuda_float64 (__main__.TestDecompCUDA)": 65.14833323160808, + "test_comprehensive_grid_sampler_2d_cpu_bfloat16 (__main__.TestDecompCPU)": 114.05733489990234, + "test_comprehensive_grid_sampler_2d_cpu_float16 (__main__.TestDecompCPU)": 106.47933451334636, + "test_comprehensive_grid_sampler_2d_cpu_float32 (__main__.TestDecompCPU)": 451.4360046386719, + "test_comprehensive_grid_sampler_2d_cpu_float64 (__main__.TestDecompCPU)": 486.5513407389323, + "test_comprehensive_grid_sampler_2d_cuda_bfloat16 (__main__.TestDecompCUDA)": 231.9798355102539, + "test_comprehensive_grid_sampler_2d_cuda_float16 (__main__.TestDecompCUDA)": 263.60083770751953, + "test_comprehensive_grid_sampler_2d_cuda_float32 (__main__.TestDecompCUDA)": 1176.4216715494792, + "test_comprehensive_grid_sampler_2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 68.16366640726726, + "test_comprehensive_grid_sampler_2d_cuda_float64 (__main__.TestDecompCUDA)": 1090.5729878743489, + "test_comprehensive_grid_sampler_2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 70.57383346557617, + "test_comprehensive_linalg_lu_solve_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 73.59733327229817, + "test_comprehensive_linalg_lu_solve_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 72.14816729227702, + "test_comprehensive_linalg_solve_triangular_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 76.59983317057292, + "test_comprehensive_linalg_solve_triangular_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 73.8191655476888, + "test_comprehensive_linalg_svd_cuda_complex128 (__main__.TestDecompCUDA)": 61.655999501546226, + "test_comprehensive_linalg_svd_cuda_complex64 (__main__.TestDecompCUDA)": 63.2686653137207, + "test_comprehensive_linalg_vector_norm_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 81.11633337111701, + "test_comprehensive_linalg_vector_norm_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 79.07504544939313, + "test_comprehensive_masked_norm_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 116.84133275349934, + "test_comprehensive_masked_norm_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 117.59250005086263, + "test_comprehensive_masked_norm_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 114.76550165812175, + "test_comprehensive_nn_functional_conv_transpose3d_cuda_complex128 (__main__.TestDecompCUDA)": 63.56300036112467, + "test_comprehensive_nn_functional_conv_transpose3d_cuda_complex64 (__main__.TestDecompCUDA)": 60.701666514078774, + "test_comprehensive_nn_functional_gaussian_nll_loss_cpu_float32 (__main__.TestDecompCPU)": 61.75800069173177, + "test_comprehensive_nn_functional_gaussian_nll_loss_cpu_float64 (__main__.TestDecompCPU)": 65.33233261108398, + "test_comprehensive_nn_functional_gaussian_nll_loss_cuda_float32 (__main__.TestDecompCUDA)": 117.1604995727539, + "test_comprehensive_nn_functional_gaussian_nll_loss_cuda_float64 (__main__.TestDecompCUDA)": 104.54616800944011, + "test_comprehensive_nn_functional_grid_sample_cpu_float32 (__main__.TestDecompCPU)": 118.75366719563802, + "test_comprehensive_nn_functional_grid_sample_cpu_float64 (__main__.TestDecompCPU)": 113.73666636149089, + "test_comprehensive_nn_functional_grid_sample_cuda_bfloat16 (__main__.TestDecompCUDA)": 66.19416681925456, + "test_comprehensive_nn_functional_grid_sample_cuda_float32 (__main__.TestDecompCUDA)": 252.66549936930338, + "test_comprehensive_nn_functional_grid_sample_cuda_float64 (__main__.TestDecompCUDA)": 222.92949676513672, + "test_comprehensive_nn_functional_interpolate_bicubic_cuda_float32 (__main__.TestDecompCUDA)": 76.49983342488606, + "test_comprehensive_nn_functional_interpolate_bicubic_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 83.21616744995117, + "test_comprehensive_nn_functional_interpolate_bicubic_cuda_float64 (__main__.TestDecompCUDA)": 75.92899958292644, + "test_comprehensive_nn_functional_interpolate_bicubic_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 81.04449971516927, + "test_comprehensive_nn_functional_interpolate_trilinear_cpu_float32 (__main__.TestDecompCPU)": 60.393466313680015, + "test_comprehensive_nn_functional_interpolate_trilinear_cpu_float64 (__main__.TestDecompCPU)": 62.78193333943685, + "test_comprehensive_nn_functional_interpolate_trilinear_cuda_float32 (__main__.TestDecompCUDA)": 125.94333521525066, + "test_comprehensive_nn_functional_interpolate_trilinear_cuda_float64 (__main__.TestDecompCUDA)": 126.8844985961914, + "test_comprehensive_nn_functional_max_pool2d_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 1251.3123575846355, + "test_comprehensive_nn_functional_max_pool2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 1241.600850423177, + "test_comprehensive_nn_functional_max_pool2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 1243.9546712239583, + "test_comprehensive_nn_functional_max_pool3d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 542.0211639404297, + "test_comprehensive_nn_functional_max_pool3d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 549.787831624349, + "test_comprehensive_nn_functional_max_unpool2d_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 65.82033348083496, + "test_comprehensive_nn_functional_max_unpool2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 63.617666244506836, + "test_comprehensive_nn_functional_max_unpool2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 64.30649948120117, + "test_comprehensive_ormqr_cpu_complex64 (__main__.TestDecompCPU)": 63.736001332600914, + "test_comprehensive_ormqr_cuda_complex128 (__main__.TestDecompCUDA)": 112.08966573079427, + "test_comprehensive_ormqr_cuda_complex64 (__main__.TestDecompCUDA)": 110.03333409627278, + "test_comprehensive_ormqr_cuda_float32 (__main__.TestDecompCUDA)": 64.95533243815105, + "test_comprehensive_ormqr_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 73.05200068155925, + "test_comprehensive_ormqr_cuda_float64 (__main__.TestDecompCUDA)": 62.977165857950844, + "test_comprehensive_svd_cuda_complex128 (__main__.TestDecompCUDA)": 68.06733322143555, + "test_comprehensive_svd_cuda_complex64 (__main__.TestDecompCUDA)": 66.93033345540364, + "test_constructor_autograd_SparseBSC_cuda (__main__.TestSparseAnyCUDA)": 90.26883443196614, + "test_constructor_autograd_SparseBSR_cuda (__main__.TestSparseAnyCUDA)": 90.10899925231934, + "test_constructor_autograd_SparseCSC_cuda (__main__.TestSparseAnyCUDA)": 68.69099998474121, + "test_conv1d_basic (__main__.TestXNNPACKConv1dTransformPass)": 202.3588892618815, + "test_conv1d_with_relu_fc (__main__.TestXNNPACKConv1dTransformPass)": 422.32500712076825, + "test_conv2d_binary_broadcast_shapes_cpu (__main__.TestPatternMatcherGenericCPU)": 78.0239995320638, + "test_conv3d_binary_broadcast_shapes_cpu (__main__.TestPatternMatcherGenericCPU)": 155.38232930501303, + "test_conv3d_binary_dynamic_shapes_cpu (__main__.TestDynamicPatternMatcherGenericCPU)": 67.37766520182292, + "test_conv3d_cuda (__main__.AOTInductorTestABICompatibleGpu)": 149.59200541178384, + "test_conv3d_unary_dynamic_shapes_cpu (__main__.TestDynamicPatternMatcherGenericCPU)": 64.1897144317627, + "test_conv_bn_fuse_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 81.03766674465604, + "test_conv_transpose_with_output_size_and_no_batch_dim_ConvTranspose3d_cuda (__main__.TestConvolutionNNDeviceTypeCUDA)": 138.84200178955993, + "test_conv_unary_fusion_nnc (__main__.TestMkldnnFusion)": 71.52855597601996, + "test_correctness_AdamW_use_closure_True_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 82.29533131917317, + "test_correctness_Adam_use_closure_True_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 79.40083440144856, + "test_count_nonzero_all (__main__.TestBool)": 624.7655571831597, + "test_dispatch_symbolic_meta_outplace_all_strides_nn_functional_gaussian_nll_loss_cuda_float32 (__main__.TestMetaCUDA)": 84.02199935913086, + "test_eager_sequence_nr_dynamic_shapes (__main__.DynamicShapesAotAutogradFallbackTests)": 129.8006666274298, + "test_eig_check_magma_cuda_float32 (__main__.TestLinalgCUDA)": 285.8453318277995, + "test_fail_arithmetic_ops.py (__main__.TestTyping)": 64.87388865152995, + "test_fail_random.py (__main__.TestTyping)": 72.06940027872722, + "test_fn_fwgrad_bwgrad_cumprod_cuda_complex128 (__main__.TestFwdGradientsCUDA)": 78.02199872334798, + "test_fn_gradgrad_cumprod_cuda_complex128 (__main__.TestBwdGradientsCUDA)": 79.79700024922688, + "test_forward_ad_svd_lowrank_cpu_float32 (__main__.TestCompositeComplianceCPU)": 60.62166849772135, + "test_fractional_max_pool2d2_cpu (__main__.CpuTritonTests)": 75.23233540852864, + "test_fuse_large_params_cpu (__main__.CpuTests)": 129.14699935913086, + "test_fuse_large_params_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 155.2022221883138, + "test_fuse_large_params_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 154.08022223578558, + "test_fuse_large_params_dynamic_shapes_cuda (__main__.DynamicShapesCodegenGPUTests)": 154.93033091227213, + "test_fuse_large_params_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 117.5648307800293, + "test_grad_nn_Transformer_cpu_float64 (__main__.TestModuleCPU)": 61.67266718546549, + "test_grad_nn_Transformer_cuda_float64 (__main__.TestModuleCUDA)": 88.19633356730144, + "test_gradgrad_nn_LSTM_eval_mode_cuda_float64 (__main__.TestModuleCUDA)": 100.6306660970052, + "test_gradgrad_nn_LSTM_train_mode_cuda_float64 (__main__.TestModuleCUDA)": 98.57333119710286, + "test_gradgrad_nn_TransformerDecoderLayer_cuda_float64 (__main__.TestModuleCUDA)": 201.47283172607422, + "test_gradgrad_nn_TransformerEncoder_eval_mode_cuda_float64 (__main__.TestModuleCUDA)": 122.74483235677083, + "test_gradgrad_nn_TransformerEncoder_train_mode_cuda_float64 (__main__.TestModuleCUDA)": 140.73500061035156, + "test_gradgrad_nn_Transformer_cuda_float64 (__main__.TestModuleCUDA)": 536.5071665445963, + "test_indirect_device_assert (__main__.TritonCodeGenTests)": 325.43634033203125, + "test_inductor_dynamic_shapes_broadcasting_dynamic_shapes (__main__.DynamicShapesReproTests)": 104.2214485168457, + "test_inductor_no_recursionerror_on_for_loops_dynamic_shapes (__main__.DynamicShapesReproTests)": 68.84588962131076, + "test_inplace_gradgrad_cumprod_cuda_complex128 (__main__.TestBwdGradientsCUDA)": 84.7916653951009, + "test_inputs_overlapping_with_mutation_stress_dynamic_shapes (__main__.DynamicShapesAotAutogradFallbackTests)": 126.74522060818143, + "test_jit_cuda_archflags (__main__.TestCppExtensionJIT)": 118.65966796875, + "test_linalg_solve_triangular_large_cuda_complex128 (__main__.TestLinalgCUDA)": 128.35166676839194, + "test_linalg_solve_triangular_large_cuda_complex64 (__main__.TestLinalgCUDA)": 100.74166615804036, + "test_linear_binary_cpp_wrapper (__main__.TestCppWrapper)": 122.9943364461263, + "test_linear_binary_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 122.79266611735027, + "test_lobpcg_ortho_cuda_float64 (__main__.TestLinalgCUDA)": 65.5205005009969, + "test_longformer_chunk_dynamic_shapes (__main__.DynamicShapesReproTests)": 106.49955664740668, + "test_low_memory_max_pool_dilation_1_dim_3_cpu_halide (__main__.HalideCpuTests)": 583.9716796875, + "test_low_memory_max_pool_dilation_2_dim_3_cpu_halide (__main__.HalideCpuTests)": 506.6836751302083, + "test_lstm_cpu (__main__.TestMkldnnCPU)": 83.0096664428711, + "test_many_overlapping_inputs_does_not_explode_guards_dynamic_shapes (__main__.DynamicShapesReproTests)": 127.0445556640625, + "test_max_autotune_addmm_max_autotune_gemm_backends_CK_x_shape2 (__main__.TestCKBackend)": 68.56900024414062, + "test_max_autotune_precompile_matmul_max_autotune_gemm_backends_CKTILE_autotune_in_subproc_False_use_aoti_False (__main__.TestCKBackend)": 82.81600189208984, + "test_max_autotune_precompile_matmul_max_autotune_gemm_backends_CKTILE_autotune_in_subproc_False_use_aoti_True (__main__.TestCKBackend)": 92.80083401997884, + "test_max_pool2d_with_indices_backward4_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 61.992555406358505, + "test_max_pool2d_with_indices_backward4_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 63.72611067030165, + "test_pattern_matcher_multi_user_cpu (__main__.CpuTritonTests)": 147.29766845703125, + "test_proper_exit (__main__.TestDataLoader)": 216.4836629231771, + "test_proper_exit (__main__.TestDataLoaderPersistentWorkers)": 210.3760011461046, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 104.63733418782552, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 102.59466552734375, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_True (__main__.TestPatternMatcher)": 94.32133229573567, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 111.68400065104167, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 103.05666605631511, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_False (__main__.TestPatternMatcher)": 85.2760009765625, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 96.23033142089844, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 99.38433329264323, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_True (__main__.TestPatternMatcher)": 81.68533325195312, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 100.20899963378906, + "test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 97.05566660563152, + "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_False (__main__.TestPatternMatcher)": 89.3759994506836, + "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 100.7616678873698, + "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 102.47166697184245, + "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 104.16033172607422, + "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 103.2269999186198, + "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 97.83200073242188, + "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 92.10933176676433, + "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 108.74566650390625, + "test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 103.50166575113933, + "test_quick_core_backward__unsafe_masked_index_cpu_float64 (__main__.TestDecompCPU)": 649.3369954427084, + "test_quick_core_backward__unsafe_masked_index_cuda_float64 (__main__.TestDecompCUDA)": 1067.1208394368489, + "test_quick_core_backward__unsafe_masked_index_put_accumulate_cpu_float64 (__main__.TestDecompCPU)": 795.9996541341146, + "test_quick_core_backward__unsafe_masked_index_put_accumulate_cuda_float64 (__main__.TestDecompCUDA)": 1375.9844970703125, + "test_quick_core_backward_nn_functional_max_unpool3d_grad_cpu_float64 (__main__.TestDecompCPU)": 97.88966623942058, + "test_quick_core_backward_nn_functional_max_unpool3d_grad_cuda_float64 (__main__.TestDecompCUDA)": 302.8671620686849, + "test_quick_core_backward_roll_cpu_float64 (__main__.TestDecompCPU)": 151.6493352254232, + "test_quick_core_backward_roll_cuda_float64 (__main__.TestDecompCUDA)": 255.09516398111978, + "test_quick_core_backward_select_scatter_cpu_float64 (__main__.TestDecompCPU)": 74.62466684977214, + "test_quick_core_backward_select_scatter_cuda_float64 (__main__.TestDecompCUDA)": 141.4095001220703, + "test_quick_core_backward_split_cuda_float64 (__main__.TestDecompCUDA)": 67.56100082397461, + "test_quick_core_backward_split_with_sizes_copy_cpu_float64 (__main__.TestDecompCPU)": 96.26366678873698, + "test_quick_core_backward_split_with_sizes_copy_cuda_float64 (__main__.TestDecompCUDA)": 175.37733459472656, + "test_quick_core_backward_std_cpu_float64 (__main__.TestDecompCPU)": 61.822133255004886, + "test_quick_core_backward_std_cuda_float64 (__main__.TestDecompCUDA)": 109.6198336283366, + "test_register_spills_cuda (__main__.BenchmarkFusionCudaTest)": 86.16349983215332, + "test_replicatepad_64bit_indexing_cuda_float16 (__main__.TestNNDeviceTypeCUDA)": 86.66866556803386, + "test_rosenbrock_sparse_with_lrsched_False_SGD_cuda_float64 (__main__.TestOptimRenewedCUDA)": 66.37899923324585, + "test_rosenbrock_sparse_with_lrsched_True_SGD_cuda_float64 (__main__.TestOptimRenewedCUDA)": 66.62250057856242, + "test_runtime_checks_large_cpu (__main__.AOTInductorTestABICompatibleCpu)": 70.87766647338867, + "test_runtime_checks_large_cpu_with_stack_allocation (__main__.AOTInductorTestABICompatibleCpuWithStackAllocation)": 75.49255498250325, + "test_runtime_checks_large_cuda (__main__.AOTInductorTestABICompatibleGpu)": 202.91549682617188, + "test_save_load_large_string_attribute (__main__.TestSaveLoad)": 123.50400034586589, + "test_sdpa_kernel_ctx_manager2_dynamic_shapes (__main__.DynamicShapesCtxManagerTests)": 160.74310980902777, + "test_shuffler_iterdatapipe (__main__.IntegrationTestDataLoaderDataPipe)": 123.230222913954, + "test_slow_tasks (__main__.TestFunctionalAutogradBenchmark)": 145.21744367811414, + "test_sort_bool_cpu (__main__.CpuTritonTests)": 342.22166951497394, + "test_sort_transpose_cpu (__main__.CpuTritonTests)": 381.2273356119792, + "test_svd_lowrank_cuda_complex128 (__main__.TestLinalgCUDA)": 148.22866336504617, + "test_terminate_handler_on_crash (__main__.TestTorch)": 110.12833338313632, + "test_terminate_signal (__main__.ForkTest)": 129.44544405076238, + "test_terminate_signal (__main__.ParallelForkServerShouldWorkTest)": 129.49844242301253, + "test_terminate_signal (__main__.SpawnTest)": 133.55011155870227, + "test_torchvision_smoke (__main__.TestTensorBoardPytorchGraph)": 61.563889821370445, + "test_train_parity_multi_group (__main__.TestFullyShard1DTrainingCore)": 160.7593755722046, + "test_triton_bsr_scatter_mm_blocksize_64_cuda_bfloat16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 73.10299809773763, + "test_triton_bsr_scatter_mm_blocksize_64_cuda_float16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 60.93416659037272, + "test_triton_bsr_scatter_mm_blocksize_64_cuda_float32 (__main__.TestSparseCompressedTritonKernelsCUDA)": 69.97583262125652, + "test_triton_bsr_softmax_cuda_bfloat16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 145.3736661275228, + "test_triton_bsr_softmax_cuda_float16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 138.5906670888265, + "test_triton_bsr_softmax_cuda_float32 (__main__.TestSparseCompressedTritonKernelsCUDA)": 102.26050313313802, + "test_unary_ops (__main__.TestTEFuserDynamic)": 83.80188674396939, + "test_unary_ops (__main__.TestTEFuserStatic)": 84.91933458381229, + "test_variant_consistency_jit_nn_functional_max_pool2d_cpu_float32 (__main__.TestJitCPU)": 89.42000071207683, + "test_variant_consistency_jit_nn_functional_max_pool2d_cuda_float32 (__main__.TestJitCUDA)": 69.1251672108968, + "test_views1_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 81.20116551717122, + "test_vmapjvpvjp_linalg_lstsq_grad_oriented_cpu_float32 (__main__.TestOperatorsCPU)": 92.86866505940755, + "test_vmapjvpvjp_linalg_lstsq_grad_oriented_cuda_float32 (__main__.TestOperatorsCUDA)": 494.2426821390788, + "test_vmapjvpvjp_linalg_lu_solve_cpu_float32 (__main__.TestOperatorsCPU)": 61.2226676940918, + "test_vmapjvpvjp_linalg_lu_solve_cuda_float32 (__main__.TestOperatorsCUDA)": 72.78116671244304, + "test_vmapjvpvjp_linalg_multi_dot_cuda_float32 (__main__.TestOperatorsCUDA)": 71.29816627502441, + "test_vmapjvpvjp_linalg_svd_cuda_float32 (__main__.TestOperatorsCUDA)": 66.16583188374837, + "test_vmapjvpvjp_max_pool2d_with_indices_backward_cpu_float32 (__main__.TestOperatorsCPU)": 71.66399892171223, + "test_vmapjvpvjp_max_pool2d_with_indices_backward_cuda_float32 (__main__.TestOperatorsCUDA)": 70.33449935913086, + "test_vmapjvpvjp_nn_functional_max_pool2d_cpu_float32 (__main__.TestOperatorsCPU)": 66.33299891153972, + "test_vmapjvpvjp_nn_functional_max_pool2d_cuda_float32 (__main__.TestOperatorsCUDA)": 70.65683428446452, + "test_vmapjvpvjp_svd_cuda_float32 (__main__.TestOperatorsCUDA)": 66.23549969991048, + "test_vmapjvpvjp_unbind_cpu_float32 (__main__.TestOperatorsCPU)": 61.09966786702474, + "test_vmapjvpvjp_unbind_cuda_float32 (__main__.TestOperatorsCUDA)": 71.27083333333333, + "test_vmapvjpvjp_linalg_lstsq_cuda_float32 (__main__.TestOperatorsCUDA)": 61.08866659800211, + "test_vmapvjpvjp_meshgrid_list_of_tensors_cuda_float32 (__main__.TestOperatorsCUDA)": 75.7148323059082, + "test_vmapvjpvjp_meshgrid_variadic_tensors_cuda_float32 (__main__.TestOperatorsCUDA)": 74.89849853515625, + "test_vmapvjpvjp_nn_functional_bilinear_cuda_float32 (__main__.TestOperatorsCUDA)": 148.47533162434897 } \ No newline at end of file