Compare commits

...

1 Commits

Author SHA1 Message Date
ad3261639b Update slow tests 2025-10-20 07:41:00 +00:00

View File

@ -1,237 +1,250 @@
{
"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
"EndToEndLSTM (__main__.RNNTest)": 192.82166544596353,
"MultiheadAttention (__main__.ModulesTest)": 139.0616658528646,
"test_AllenaiLongformerBase_repro_cpu_halide (__main__.HalideCpuTests)": 213.9806671142578,
"test__adaptive_avg_pool2d (__main__.CPUReproTests)": 86.71322038438585,
"test_adaptive_max_pool2d1_cpu_halide (__main__.HalideCpuTests)": 117.1020024617513,
"test_after_aot_cpu_runtime_error (__main__.MinifierIsolateTests)": 68.81311162312825,
"test_after_aot_gpu_runtime_error (__main__.MinifierIsolateTests)": 66.43533325195312,
"test_alexnet_prefix_cpu_halide (__main__.HalideCpuTests)": 178.21466573079428,
"test_aot_autograd_disable_functionalization_symbolic_exhaustive_linalg_svd_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 71.91361917768207,
"test_aot_autograd_disable_functionalization_symbolic_exhaustive_nn_functional_max_pool1d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 134.47433489844911,
"test_aot_autograd_disable_functionalization_symbolic_exhaustive_nn_functional_max_pool2d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 206.34494999476843,
"test_aot_autograd_disable_functionalization_symbolic_exhaustive_nn_functional_max_pool3d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 118.36671393258231,
"test_aot_autograd_disable_functionalization_symbolic_exhaustive_svd_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 62.320524124872115,
"test_aot_autograd_exhaustive_nn_functional_max_pool2d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 71.58866628011067,
"test_aot_autograd_symbolic_exhaustive_linalg_svd_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 76.54733276367188,
"test_aot_autograd_symbolic_exhaustive_masked_norm_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 61.88247626168387,
"test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool1d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 140.0749994913737,
"test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool2d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 198.51233418782553,
"test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool3d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 115.69099934895833,
"test_aot_autograd_symbolic_exhaustive_nn_functional_unfold_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 60.3687724200162,
"test_aot_autograd_symbolic_exhaustive_svd_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 70.80566660563152,
"test_aot_autograd_symbolic_module_exhaustive_nn_TransformerDecoderLayer_cpu_float32 (__main__.TestEagerFusionModuleInfoCPU)": 164.77466837565103,
"test_associative_scan_partial_grad_combine_mode_generic_compile_mode_compile_dynamic_shape_reverse_False_cpu (__main__.AssociativeScanTests)": 85.75333150227864,
"test_associative_scan_partial_grad_combine_mode_generic_compile_mode_compile_dynamic_shape_reverse_True_cpu (__main__.AssociativeScanTests)": 98.60916646321614,
"test_avg_pool3d_backward2_cpu (__main__.CpuTests)": 614.9288024902344,
"test_avg_pool3d_backward2_cuda (__main__.GPUTests)": 259.2257480621338,
"test_avg_pool3d_backward2_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 490.79433186848956,
"test_avg_pool3d_backward2_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 499.2715555826823,
"test_avg_pool3d_backward2_dynamic_shapes_cuda (__main__.DynamicShapesCodegenGPUTests)": 135.0522206624349,
"test_avg_pool3d_backward2_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 329.55533599853516,
"test_avg_pool3d_backward_cpu_halide (__main__.HalideCpuTests)": 62.32133356730143,
"test_backward_nn_functional_multi_head_attention_forward_cpu_float32 (__main__.TestCompositeComplianceCPU)": 90.28633371988933,
"test_backward_nn_functional_multi_head_attention_forward_cuda_float32 (__main__.TestCompositeComplianceCUDA)": 62.072333017985024,
"test_basic_cpu (__main__.EfficientConvBNEvalCpuTests)": 211.6552242702908,
"test_basic_cuda (__main__.EfficientConvBNEvalGpuTests)": 146.26183319091797,
"test_checkpointing_without_reentrant_input_requires_grad_False (__main__.TestAutogradWithCompiledAutograd)": 308.6877746582031,
"test_checkpointing_without_reentrant_input_requires_grad_True (__main__.TestAutogradWithCompiledAutograd)": 391.07589043511285,
"test_collect_callgrind (__main__.TestBenchmarkUtils)": 315.14866807725696,
"test_comprehensive_diff_cuda_complex128 (__main__.TestDecompCUDA)": 95.47699864705403,
"test_comprehensive_diff_cuda_complex64 (__main__.TestDecompCUDA)": 94.67116800944011,
"test_comprehensive_diff_cuda_float32 (__main__.TestDecompCUDA)": 66.1489995320638,
"test_comprehensive_diff_cuda_float64 (__main__.TestDecompCUDA)": 62.8696657816569,
"test_comprehensive_grid_sampler_2d_cpu_bfloat16 (__main__.TestDecompCPU)": 95.41166687011719,
"test_comprehensive_grid_sampler_2d_cpu_float16 (__main__.TestDecompCPU)": 111.63733418782552,
"test_comprehensive_grid_sampler_2d_cpu_float32 (__main__.TestDecompCPU)": 460.538330078125,
"test_comprehensive_grid_sampler_2d_cpu_float64 (__main__.TestDecompCPU)": 472.9026692708333,
"test_comprehensive_grid_sampler_2d_cuda_bfloat16 (__main__.TestDecompCUDA)": 231.80833689371744,
"test_comprehensive_grid_sampler_2d_cuda_float16 (__main__.TestDecompCUDA)": 245.19566599527994,
"test_comprehensive_grid_sampler_2d_cuda_float32 (__main__.TestDecompCUDA)": 1155.2738444010417,
"test_comprehensive_grid_sampler_2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 67.5636666615804,
"test_comprehensive_grid_sampler_2d_cuda_float64 (__main__.TestDecompCUDA)": 1143.9273376464844,
"test_comprehensive_grid_sampler_2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 70.44900067647298,
"test_comprehensive_linalg_lu_solve_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 72.42183176676433,
"test_comprehensive_linalg_lu_solve_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 70.32316780090332,
"test_comprehensive_linalg_solve_triangular_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 72.50600051879883,
"test_comprehensive_linalg_solve_triangular_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 73.64516703287761,
"test_comprehensive_linalg_svd_cuda_complex128 (__main__.TestDecompCUDA)": 62.23766644795736,
"test_comprehensive_linalg_svd_cuda_complex64 (__main__.TestDecompCUDA)": 66.52066548665364,
"test_comprehensive_masked_norm_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 109.27733484903972,
"test_comprehensive_masked_norm_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 108.4946657816569,
"test_comprehensive_masked_norm_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 112.19650141398112,
"test_comprehensive_nn_functional_conv_transpose3d_cuda_complex64 (__main__.TestDecompCUDA)": 60.465000788370766,
"test_comprehensive_nn_functional_gaussian_nll_loss_cpu_float32 (__main__.TestDecompCPU)": 60.50299962361654,
"test_comprehensive_nn_functional_gaussian_nll_loss_cuda_float32 (__main__.TestDecompCUDA)": 105.4928347269694,
"test_comprehensive_nn_functional_gaussian_nll_loss_cuda_float64 (__main__.TestDecompCUDA)": 108.20700200398763,
"test_comprehensive_nn_functional_grid_sample_cpu_float32 (__main__.TestDecompCPU)": 124.36166890462239,
"test_comprehensive_nn_functional_grid_sample_cpu_float64 (__main__.TestDecompCPU)": 121.77700297037761,
"test_comprehensive_nn_functional_grid_sample_cuda_bfloat16 (__main__.TestDecompCUDA)": 65.20566622416179,
"test_comprehensive_nn_functional_grid_sample_cuda_float32 (__main__.TestDecompCUDA)": 250.609499613444,
"test_comprehensive_nn_functional_grid_sample_cuda_float64 (__main__.TestDecompCUDA)": 256.65582784016925,
"test_comprehensive_nn_functional_interpolate_bicubic_cuda_float32 (__main__.TestDecompCUDA)": 77.13483428955078,
"test_comprehensive_nn_functional_interpolate_bicubic_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 81.49416605631511,
"test_comprehensive_nn_functional_interpolate_bicubic_cuda_float64 (__main__.TestDecompCUDA)": 76.5941645304362,
"test_comprehensive_nn_functional_interpolate_bicubic_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 81.30283482869466,
"test_comprehensive_nn_functional_interpolate_trilinear_cpu_float64 (__main__.TestDecompCPU)": 62.60033289591471,
"test_comprehensive_nn_functional_interpolate_trilinear_cuda_float32 (__main__.TestDecompCUDA)": 122.69799931844075,
"test_comprehensive_nn_functional_interpolate_trilinear_cuda_float64 (__main__.TestDecompCUDA)": 129.71950022379556,
"test_comprehensive_nn_functional_max_pool2d_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 1234.223164876302,
"test_comprehensive_nn_functional_max_pool2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 1235.4468383789062,
"test_comprehensive_nn_functional_max_pool2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 1290.6556803385417,
"test_comprehensive_nn_functional_max_pool3d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 549.6143239339193,
"test_comprehensive_nn_functional_max_pool3d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 566.3478291829427,
"test_comprehensive_nn_functional_max_unpool2d_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 63.483999252319336,
"test_comprehensive_nn_functional_max_unpool2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 63.42866579691569,
"test_comprehensive_nn_functional_max_unpool2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 61.613165537516274,
"test_comprehensive_ormqr_cpu_complex64 (__main__.TestDecompCPU)": 61.59733327229818,
"test_comprehensive_ormqr_cuda_complex128 (__main__.TestDecompCUDA)": 99.41866683959961,
"test_comprehensive_ormqr_cuda_complex64 (__main__.TestDecompCUDA)": 108.57150014241536,
"test_comprehensive_ormqr_cuda_float32 (__main__.TestDecompCUDA)": 65.55750020345052,
"test_comprehensive_ormqr_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 72.1978333791097,
"test_comprehensive_ormqr_cuda_float64 (__main__.TestDecompCUDA)": 66.09216499328613,
"test_comprehensive_svd_cuda_complex128 (__main__.TestDecompCUDA)": 68.24233309427898,
"test_comprehensive_svd_cuda_complex64 (__main__.TestDecompCUDA)": 68.49199930826823,
"test_constructor_autograd_SparseBSC_cuda (__main__.TestSparseAnyCUDA)": 88.46916643778484,
"test_constructor_autograd_SparseBSR_cuda (__main__.TestSparseAnyCUDA)": 83.7504997253418,
"test_constructor_autograd_SparseCSC_cuda (__main__.TestSparseAnyCUDA)": 70.30133374532063,
"test_conv1d_basic (__main__.TestXNNPACKConv1dTransformPass)": 246.74666425916882,
"test_conv1d_with_relu_fc (__main__.TestXNNPACKConv1dTransformPass)": 374.87755330403644,
"test_conv2d_binary_broadcast_shapes_cpu (__main__.TestPatternMatcherGenericCPU)": 76.72733306884766,
"test_conv3d_binary_broadcast_shapes_cpu (__main__.TestPatternMatcherGenericCPU)": 148.44099934895834,
"test_conv3d_binary_dynamic_shapes_cpu (__main__.TestDynamicPatternMatcherGenericCPU)": 65.76099904378255,
"test_conv3d_cuda (__main__.AOTInductorTestABICompatibleGpu)": 150.61966959635416,
"test_conv_bn_fuse_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 78.81699922349718,
"test_conv_transpose_with_output_size_and_no_batch_dim_ConvTranspose3d_cuda (__main__.TestConvolutionNNDeviceTypeCUDA)": 138.87466068503758,
"test_conv_unary_fusion_nnc (__main__.TestMkldnnFusion)": 73.0574442545573,
"test_correctness_AdamW_use_closure_True_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 82.54566828409831,
"test_correctness_Adam_use_closure_True_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 78.97233327229817,
"test_count_nonzero_all (__main__.TestBool)": 653.4341227213541,
"test_cp_flex_attention_document_mask (__main__.CPFlexAttentionTest)": 77.11900329589844,
"test_ddp_uneven_inputs (__main__.TestDistBackendWithSpawn)": 388.8182497024536,
"test_dispatch_symbolic_meta_outplace_all_strides_nn_functional_gaussian_nll_loss_cuda_float32 (__main__.TestMetaCUDA)": 86.69299952189128,
"test_dtensor_op_db_nn_functional_gaussian_nll_loss_cpu_float32 (__main__.TestLocalDTensorOpsCPU)": 659.3110148111979,
"test_dtensor_op_db_nn_functional_gaussian_nll_loss_cpu_float32 (__main__.TestMultiThreadedDTensorOpsCPU)": 85.84166717529297,
"test_eig_check_magma_cuda_float32 (__main__.TestLinalgCUDA)": 304.719674428304,
"test_error_detection_and_propagation (__main__.NcclErrorHandlingTest)": 66.78424835205078,
"test_fail_arithmetic_ops.py (__main__.TestTyping)": 65.23966683281793,
"test_fail_creation_ops.py (__main__.TestTyping)": 69.84653383890787,
"test_fn_fwgrad_bwgrad_cumprod_cuda_complex128 (__main__.TestFwdGradientsCUDA)": 71.1476656595866,
"test_fn_gradgrad_cumprod_cuda_complex128 (__main__.TestBwdGradientsCUDA)": 73.91016705830891,
"test_fuse_large_params_cpu (__main__.CpuTests)": 81.72079772949219,
"test_fuse_large_params_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 157.25733269585504,
"test_fuse_large_params_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 157.83978101942273,
"test_fuse_large_params_dynamic_shapes_cuda (__main__.DynamicShapesCodegenGPUTests)": 154.19133504231772,
"test_fuse_large_params_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 137.25949986775717,
"test_grad_nn_Transformer_cpu_float64 (__main__.TestModuleCPU)": 60.175332387288414,
"test_grad_nn_Transformer_cuda_float64 (__main__.TestModuleCUDA)": 79.77866617838542,
"test_gradgrad_nn_LSTM_eval_mode_cuda_float64 (__main__.TestModuleCUDA)": 119.29166412353516,
"test_gradgrad_nn_LSTM_train_mode_cuda_float64 (__main__.TestModuleCUDA)": 89.33333079020183,
"test_gradgrad_nn_TransformerDecoderLayer_cuda_float64 (__main__.TestModuleCUDA)": 177.53233337402344,
"test_gradgrad_nn_TransformerEncoder_eval_mode_cuda_float64 (__main__.TestModuleCUDA)": 135.1976661682129,
"test_gradgrad_nn_TransformerEncoder_train_mode_cuda_float64 (__main__.TestModuleCUDA)": 161.03666559855142,
"test_gradgrad_nn_Transformer_cuda_float64 (__main__.TestModuleCUDA)": 588.6106719970703,
"test_graph_partition_refcount_cuda (__main__.GPUTests)": 71.53293382326761,
"test_graph_partition_refcount_dynamic_shapes_cuda (__main__.DynamicShapesCodegenGPUTests)": 313.82437658309937,
"test_graph_partition_refcount_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 297.91300222608777,
"test_grid_sampler_2d_cpu_halide (__main__.HalideCpuTests)": 196.28067016601562,
"test_indirect_device_assert (__main__.TritonCodeGenTests)": 326.7076721191406,
"test_inductor_no_recursionerror_on_for_loops_dynamic_shapes (__main__.DynamicShapesReproTests)": 67.85766686333551,
"test_inplace_gradgrad_cumprod_cuda_complex128 (__main__.TestBwdGradientsCUDA)": 74.66950035095215,
"test_inputs_overlapping_with_mutation_stress_dynamic_shapes (__main__.DynamicShapesAotAutogradFallbackTests)": 125.63111284044054,
"test_jit_cuda_archflags (__main__.TestCppExtensionJIT)": 119.36500040690105,
"test_linalg_solve_triangular_large_cuda_complex128 (__main__.TestLinalgCUDA)": 141.70733388264975,
"test_linalg_solve_triangular_large_cuda_complex64 (__main__.TestLinalgCUDA)": 103.16299947102864,
"test_linear_binary_cpp_wrapper (__main__.TestCppWrapper)": 124.02166748046875,
"test_linear_binary_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 130.5843302408854,
"test_list_clearing_cuda (__main__.GPUTests)": 66.41853286425273,
"test_list_clearing_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 273.2784431245592,
"test_lobpcg_ortho_cuda_float64 (__main__.TestLinalgCUDA)": 95.71216630935669,
"test_longformer_chunk_dynamic_shapes (__main__.DynamicShapesReproTests)": 106.52733357747395,
"test_lstm_cpu (__main__.TestMkldnnCPU)": 105.37633260091145,
"test_many_overlapping_inputs_does_not_explode_guards_dynamic_shapes (__main__.DynamicShapesReproTests)": 127.99744415283203,
"test_max_autotune_addmm_max_autotune_gemm_backends_CK_x_shape2 (__main__.TestCKBackend)": 68.72466786702473,
"test_max_autotune_addmm_search_space_EXHAUSTIVE_dynamic_True (__main__.TestMaxAutotuneSubproc)": 83.392333984375,
"test_max_autotune_precompile_matmul_max_autotune_gemm_backends_CKTILE_autotune_in_subproc_False_use_aoti_False (__main__.TestCKBackend)": 81.58233388264973,
"test_max_autotune_precompile_matmul_max_autotune_gemm_backends_CKTILE_autotune_in_subproc_True_use_aoti_False (__main__.TestCKBackend)": 61.58650016784668,
"test_max_pool2d2_cpu_halide (__main__.HalideCpuTests)": 424.79600016276044,
"test_max_pool2d3_cpu_halide (__main__.HalideCpuTests)": 134.34966532389322,
"test_max_pool2d5_cpu_halide (__main__.HalideCpuTests)": 359.4373270670573,
"test_max_pool2d_with_indices_backward4_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 61.602111392550995,
"test_max_pool2d_with_indices_backward4_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 62.73311106363932,
"test_ordered_distribute_all_combination (__main__.DistributeWithDeviceOrderTest)": 103.11666615804036,
"test_ordered_redistribute_with_partial (__main__.DistributeWithDeviceOrderTest)": 186.85033162434897,
"test_proper_exit (__main__.TestDataLoader)": 226.87488894992404,
"test_proper_exit (__main__.TestDataLoaderPersistentWorkers)": 221.5507787068685,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 102.13633219401042,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 104.0336685180664,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_True (__main__.TestPatternMatcher)": 86.82899983723958,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 112.05333201090495,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 109.16433461507161,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_False (__main__.TestPatternMatcher)": 83.33633422851562,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 101.09633382161458,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 94.33700052897136,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_True (__main__.TestPatternMatcher)": 85.11466725667317,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 105.4913330078125,
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 99.86033376057942,
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_False (__main__.TestPatternMatcher)": 88.52466837565105,
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 104.58233388264973,
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 97.38966623942058,
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 105.92233276367188,
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 102.56833140055339,
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_False_cpp_wrapper (__main__.TestCppWrapper)": 95.02933247884114,
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_False_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 99.52566782633464,
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_True_cpp_wrapper (__main__.TestCppWrapper)": 110.53600056966145,
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_True_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 107.76433563232422,
"test_quick_core_backward__unsafe_masked_index_cpu_float64 (__main__.TestDecompCPU)": 552.8793436686198,
"test_quick_core_backward__unsafe_masked_index_cuda_float64 (__main__.TestDecompCUDA)": 1041.9803365071614,
"test_quick_core_backward__unsafe_masked_index_put_accumulate_cpu_float64 (__main__.TestDecompCPU)": 768.4703369140625,
"test_quick_core_backward__unsafe_masked_index_put_accumulate_cuda_float64 (__main__.TestDecompCUDA)": 1338.756815592448,
"test_quick_core_backward_nn_functional_max_unpool3d_grad_cpu_float64 (__main__.TestDecompCPU)": 84.73999786376953,
"test_quick_core_backward_nn_functional_max_unpool3d_grad_cuda_float64 (__main__.TestDecompCUDA)": 264.60900115966797,
"test_quick_core_backward_roll_cpu_float64 (__main__.TestDecompCPU)": 122.84067026774089,
"test_quick_core_backward_roll_cuda_float64 (__main__.TestDecompCUDA)": 219.9116668701172,
"test_quick_core_backward_select_scatter_cpu_float64 (__main__.TestDecompCPU)": 72.87866719563802,
"test_quick_core_backward_select_scatter_cuda_float64 (__main__.TestDecompCUDA)": 134.70382944742838,
"test_quick_core_backward_split_cuda_float64 (__main__.TestDecompCUDA)": 69.35233243306477,
"test_quick_core_backward_split_with_sizes_copy_cpu_float64 (__main__.TestDecompCPU)": 95.45300038655598,
"test_quick_core_backward_split_with_sizes_copy_cuda_float64 (__main__.TestDecompCUDA)": 169.19216664632162,
"test_quick_core_backward_std_cuda_float64 (__main__.TestDecompCUDA)": 148.97033309936523,
"test_register_spills_cuda (__main__.BenchmarkFusionCudaTest)": 95.12700017293294,
"test_replicatepad_64bit_indexing_cuda_float16 (__main__.TestNNDeviceTypeCUDA)": 89.11033121744792,
"test_rosenbrock_sparse_with_lrsched_True_SGD_cuda_float64 (__main__.TestOptimRenewedCUDA)": 117.2423316637675,
"test_runtime_checks_large_cpu (__main__.AOTInductorTestABICompatibleCpu)": 74.2721659342448,
"test_runtime_checks_large_cpu_with_stack_allocation (__main__.AOTInductorTestABICompatibleCpuWithStackAllocation)": 74.55088933308919,
"test_runtime_checks_large_cuda (__main__.AOTInductorTestABICompatibleGpu)": 319.85733795166016,
"test_save_load_large_string_attribute (__main__.TestSaveLoad)": 129.7136688232422,
"test_sdpa_kernel_ctx_manager2_dynamic_shapes (__main__.DynamicShapesCtxManagerTests)": 160.58777872721353,
"test_shuffler_iterdatapipe (__main__.IntegrationTestDataLoaderDataPipe)": 125.62933519151476,
"test_slow_tasks (__main__.TestFunctionalAutogradBenchmark)": 115.552000257704,
"test_sort_dynamic_shape_with_check_cuda (__main__.TestInductorDynamicCUDA)": 684.0326563517252,
"test_sort_stable_cpu (__main__.CpuTritonTests)": 1313.6716715494792,
"test_sort_stable_cuda (__main__.GPUTests)": 102.8017999013265,
"test_split_cumsum_cpu (__main__.CpuTritonTests)": 89.24633280436198,
"test_svd_lowrank_cuda_complex128 (__main__.TestLinalgCUDA)": 146.17883006731668,
"test_tensor_split (__main__.TestVmapOperators)": 77.83073042343194,
"test_terminate_handler_on_crash (__main__.TestTorch)": 111.19311171107822,
"test_terminate_signal (__main__.ForkTest)": 131.5424465744032,
"test_terminate_signal (__main__.ParallelForkServerShouldWorkTest)": 131.46288683431015,
"test_terminate_signal (__main__.SpawnTest)": 135.36799971262613,
"test_torchvision_smoke (__main__.TestTensorBoardPytorchGraph)": 117.69811164008246,
"test_train_parity_multi_group_unshard_async_op (__main__.TestFullyShard1DTrainingCore)": 62.17828478131975,
"test_triton_bsr_scatter_mm_blocksize_64_cuda_bfloat16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 63.68699963887533,
"test_triton_bsr_scatter_mm_blocksize_64_cuda_float16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 60.71983337402344,
"test_triton_bsr_scatter_mm_blocksize_64_cuda_float32 (__main__.TestSparseCompressedTritonKernelsCUDA)": 67.11616706848145,
"test_triton_bsr_softmax_cuda_bfloat16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 142.7560017903646,
"test_triton_bsr_softmax_cuda_float16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 137.82366307576498,
"test_triton_bsr_softmax_cuda_float32 (__main__.TestSparseCompressedTritonKernelsCUDA)": 103.55150032043457,
"test_unary_ops (__main__.TestTEFuserDynamic)": 93.15655668576558,
"test_unary_ops (__main__.TestTEFuserStatic)": 92.13944211271074,
"test_upsample_bicubic2d_cpu_halide (__main__.HalideCpuTests)": 97.97266642252605,
"test_variant_consistency_jit_nn_functional_max_pool2d_cpu_float32 (__main__.TestJitCPU)": 103.35733286539714,
"test_variant_consistency_jit_nn_functional_max_pool2d_cuda_float32 (__main__.TestJitCUDA)": 69.98999849955241,
"test_views1_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 93.9023323059082,
"test_vmapjvpvjp_linalg_lstsq_grad_oriented_cpu_float32 (__main__.TestOperatorsCPU)": 102.54166666666667,
"test_vmapjvpvjp_linalg_lstsq_grad_oriented_cuda_float32 (__main__.TestOperatorsCUDA)": 85.16200129191081,
"test_vmapjvpvjp_linalg_lu_solve_cpu_float32 (__main__.TestOperatorsCPU)": 75.42000071207683,
"test_vmapjvpvjp_linalg_lu_solve_cuda_float32 (__main__.TestOperatorsCUDA)": 67.41749954223633,
"test_vmapjvpvjp_linalg_multi_dot_cuda_float32 (__main__.TestOperatorsCUDA)": 61.618666330973305,
"test_vmapjvpvjp_linalg_pinv_singular_cpu_float32 (__main__.TestOperatorsCPU)": 67.23866844177246,
"test_vmapjvpvjp_linalg_svd_cuda_float32 (__main__.TestOperatorsCUDA)": 64.92733256022136,
"test_vmapjvpvjp_max_pool2d_with_indices_backward_cpu_float32 (__main__.TestOperatorsCPU)": 95.24866612752278,
"test_vmapjvpvjp_max_pool2d_with_indices_backward_cuda_float32 (__main__.TestOperatorsCUDA)": 74.90333302815755,
"test_vmapjvpvjp_nn_functional_conv2d_cpu_float32 (__main__.TestOperatorsCPU)": 63.24309576125372,
"test_vmapjvpvjp_nn_functional_max_pool2d_cuda_float32 (__main__.TestOperatorsCUDA)": 70.63316790262859,
"test_vmapjvpvjp_svd_cuda_float32 (__main__.TestOperatorsCUDA)": 62.29700024922689,
"test_vmapjvpvjp_unbind_cuda_float32 (__main__.TestOperatorsCUDA)": 71.01083246866862,
"test_vmapvjpvjp_meshgrid_list_of_tensors_cuda_float32 (__main__.TestOperatorsCUDA)": 70.97883288065593,
"test_vmapvjpvjp_meshgrid_variadic_tensors_cuda_float32 (__main__.TestOperatorsCUDA)": 77.57366689046223,
"test_vmapvjpvjp_nn_functional_bilinear_cuda_float32 (__main__.TestOperatorsCUDA)": 146.3556671142578
}