mirror of
https://github.com/saymrwulf/pytorch.git
synced 2026-05-14 20:57:59 +00:00
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/145206 Approved by: https://github.com/pytorchbot
308 lines
No EOL
30 KiB
JSON
308 lines
No EOL
30 KiB
JSON
{
|
|
"EndToEndLSTM (__main__.RNNTest)": 218.46899922688803,
|
|
"MultiheadAttention (__main__.ModulesTest)": 173.65766398111978,
|
|
"test_AllenaiLongformerBase_repro_cpu (__main__.CpuHalideTests)": 215.72766621907553,
|
|
"test__adaptive_avg_pool2d (__main__.CPUReproTests)": 160.06233300103082,
|
|
"test_adaptive_max_pool2d1_cpu (__main__.CpuHalideTests)": 114.19766489664714,
|
|
"test_after_aot_cpu_runtime_error (__main__.MinifierIsolateTests)": 62.27711062961154,
|
|
"test_alexnet_prefix_cpu (__main__.CpuHalideTests)": 191.4193318684896,
|
|
"test_aot_autograd_exhaustive_nn_functional_max_pool2d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 113.02799733479817,
|
|
"test_aot_autograd_symbolic_exhaustive_linalg_svd_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 66.00233332316081,
|
|
"test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool1d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 120.18766530354817,
|
|
"test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool2d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 141.22733561197916,
|
|
"test_aot_autograd_symbolic_exhaustive_nn_functional_max_pool3d_cpu_float32 (__main__.TestEagerFusionOpInfoCPU)": 103.69833119710286,
|
|
"test_aot_autograd_symbolic_module_exhaustive_nn_TransformerDecoderLayer_cpu_float32 (__main__.TestEagerFusionModuleInfoCPU)": 130.41566721598306,
|
|
"test_avg_pool3d_backward2_cpu (__main__.CpuTests)": 487.44966973198785,
|
|
"test_avg_pool3d_backward2_cuda (__main__.GPUTests)": 94.76033147176106,
|
|
"test_avg_pool3d_backward2_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 490.70132785373266,
|
|
"test_avg_pool3d_backward2_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 496.97710503472223,
|
|
"test_avg_pool3d_backward2_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 124.80966567993164,
|
|
"test_avg_pool3d_backward_cpu (__main__.CpuHalideTests)": 61.59099833170573,
|
|
"test_backward_nn_functional_multi_head_attention_forward_cpu_float32 (__main__.TestCompositeComplianceCPU)": 87.07666778564453,
|
|
"test_backward_nn_functional_multi_head_attention_forward_cuda_float32 (__main__.TestCompositeComplianceCUDA)": 68.67283248901367,
|
|
"test_basic_cpu (__main__.EfficientConvBNEvalCpuTests)": 244.37422349717883,
|
|
"test_basic_cuda (__main__.EfficientConvBNEvalGpuTests)": 161.94966761271158,
|
|
"test_builtin_equivalent_funcs (__main__.TorchFunctionModeTests)": 91.85369873046875,
|
|
"test_checkpoint_cast (__main__.TestFxToOnnx)": 367.8630065917969,
|
|
"test_collect_callgrind (__main__.TestBenchmarkUtils)": 357.23644680447046,
|
|
"test_comprehensive_constant_pad_nd_cpu_float16 (__main__.TestInductorOpInfoCPU)": 69.92699940999348,
|
|
"test_comprehensive_constant_pad_nd_cpu_float32 (__main__.TestInductorOpInfoCPU)": 75.00166575113933,
|
|
"test_comprehensive_constant_pad_nd_cpu_float64 (__main__.TestInductorOpInfoCPU)": 68.49166615804036,
|
|
"test_comprehensive_constant_pad_nd_cpu_int32 (__main__.TestInductorOpInfoCPU)": 65.78366597493489,
|
|
"test_comprehensive_constant_pad_nd_cpu_int64 (__main__.TestInductorOpInfoCPU)": 68.89199829101562,
|
|
"test_comprehensive_diff_cpu_bool (__main__.TestInductorOpInfoCPU)": 102.89200083414714,
|
|
"test_comprehensive_diff_cpu_float32 (__main__.TestInductorOpInfoCPU)": 102.76666768391927,
|
|
"test_comprehensive_diff_cpu_float64 (__main__.TestInductorOpInfoCPU)": 100.1219991048177,
|
|
"test_comprehensive_diff_cpu_int32 (__main__.TestInductorOpInfoCPU)": 102.89499918619792,
|
|
"test_comprehensive_diff_cpu_int64 (__main__.TestInductorOpInfoCPU)": 100.64933522542317,
|
|
"test_comprehensive_diff_cuda_complex128 (__main__.TestDecompCUDA)": 86.70000076293945,
|
|
"test_comprehensive_diff_cuda_complex64 (__main__.TestDecompCUDA)": 82.97133509318034,
|
|
"test_comprehensive_diff_cuda_float32 (__main__.TestDecompCUDA)": 98.83016777038574,
|
|
"test_comprehensive_diff_cuda_float64 (__main__.TestDecompCUDA)": 63.6163330078125,
|
|
"test_comprehensive_dist_cpu_float16 (__main__.TestInductorOpInfoCPU)": 80.70999908447266,
|
|
"test_comprehensive_dist_cpu_float32 (__main__.TestInductorOpInfoCPU)": 80.09666697184245,
|
|
"test_comprehensive_dist_cpu_float64 (__main__.TestInductorOpInfoCPU)": 85.40266927083333,
|
|
"test_comprehensive_eye_cpu_bool (__main__.TestInductorOpInfoCPU)": 124.63333384195964,
|
|
"test_comprehensive_eye_cpu_float16 (__main__.TestInductorOpInfoCPU)": 118.93233235677083,
|
|
"test_comprehensive_eye_cpu_float32 (__main__.TestInductorOpInfoCPU)": 119.12733459472656,
|
|
"test_comprehensive_eye_cpu_float64 (__main__.TestInductorOpInfoCPU)": 139.26000467936197,
|
|
"test_comprehensive_eye_cpu_int32 (__main__.TestInductorOpInfoCPU)": 129.03466796875,
|
|
"test_comprehensive_eye_cpu_int64 (__main__.TestInductorOpInfoCPU)": 121.75833129882812,
|
|
"test_comprehensive_grid_sampler_2d_cpu_bfloat16 (__main__.TestDecompCPU)": 69.67933400472005,
|
|
"test_comprehensive_grid_sampler_2d_cpu_float16 (__main__.TestDecompCPU)": 82.40866597493489,
|
|
"test_comprehensive_grid_sampler_2d_cpu_float16 (__main__.TestInductorOpInfoCPU)": 84.81233215332031,
|
|
"test_comprehensive_grid_sampler_2d_cpu_float32 (__main__.TestDecompCPU)": 357.16966756184894,
|
|
"test_comprehensive_grid_sampler_2d_cpu_float32 (__main__.TestInductorOpInfoCPU)": 85.7066650390625,
|
|
"test_comprehensive_grid_sampler_2d_cpu_float64 (__main__.TestDecompCPU)": 349.5823262532552,
|
|
"test_comprehensive_grid_sampler_2d_cpu_float64 (__main__.TestInductorOpInfoCPU)": 82.29266611735027,
|
|
"test_comprehensive_grid_sampler_2d_cuda_bfloat16 (__main__.TestDecompCUDA)": 262.3520024617513,
|
|
"test_comprehensive_grid_sampler_2d_cuda_float16 (__main__.TestDecompCUDA)": 247.61383819580078,
|
|
"test_comprehensive_grid_sampler_2d_cuda_float32 (__main__.TestDecompCUDA)": 1042.3961690266926,
|
|
"test_comprehensive_grid_sampler_2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 70.3201675415039,
|
|
"test_comprehensive_grid_sampler_2d_cuda_float64 (__main__.TestDecompCUDA)": 1023.5723164876302,
|
|
"test_comprehensive_grid_sampler_2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 73.51150004069011,
|
|
"test_comprehensive_linalg_lu_solve_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 78.84833399454753,
|
|
"test_comprehensive_linalg_lu_solve_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 71.58949788411458,
|
|
"test_comprehensive_linalg_solve_triangular_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 71.51049931844075,
|
|
"test_comprehensive_linalg_solve_triangular_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 66.26499875386556,
|
|
"test_comprehensive_linalg_svd_cuda_complex128 (__main__.TestDecompCUDA)": 63.65166664123535,
|
|
"test_comprehensive_linalg_vector_norm_cpu_float16 (__main__.TestInductorOpInfoCPU)": 194.29166158040366,
|
|
"test_comprehensive_linalg_vector_norm_cpu_float32 (__main__.TestInductorOpInfoCPU)": 205.24866739908853,
|
|
"test_comprehensive_linalg_vector_norm_cpu_float64 (__main__.TestInductorOpInfoCPU)": 196.55799865722656,
|
|
"test_comprehensive_linalg_vector_norm_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 74.55249977111816,
|
|
"test_comprehensive_linalg_vector_norm_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 75.83016713460286,
|
|
"test_comprehensive_logspace_cpu_float32 (__main__.TestInductorOpInfoCPU)": 422.2393290201823,
|
|
"test_comprehensive_logspace_cpu_float64 (__main__.TestInductorOpInfoCPU)": 419.15733846028644,
|
|
"test_comprehensive_logspace_cpu_int32 (__main__.TestInductorOpInfoCPU)": 407.1983337402344,
|
|
"test_comprehensive_logspace_cpu_int64 (__main__.TestInductorOpInfoCPU)": 396.66066487630206,
|
|
"test_comprehensive_logspace_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 75.42149861653645,
|
|
"test_comprehensive_logspace_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 75.69333330790202,
|
|
"test_comprehensive_masked_amax_cpu_float16 (__main__.TestInductorOpInfoCPU)": 97.0836664835612,
|
|
"test_comprehensive_masked_amax_cpu_float32 (__main__.TestInductorOpInfoCPU)": 92.19766743977864,
|
|
"test_comprehensive_masked_amax_cpu_float64 (__main__.TestInductorOpInfoCPU)": 101.15033213297527,
|
|
"test_comprehensive_masked_amax_cpu_int32 (__main__.TestInductorOpInfoCPU)": 89.56966908772786,
|
|
"test_comprehensive_masked_amax_cpu_int64 (__main__.TestInductorOpInfoCPU)": 88.81166585286458,
|
|
"test_comprehensive_masked_amin_cpu_float16 (__main__.TestInductorOpInfoCPU)": 95.51766713460286,
|
|
"test_comprehensive_masked_amin_cpu_float32 (__main__.TestInductorOpInfoCPU)": 94.93733469645183,
|
|
"test_comprehensive_masked_amin_cpu_float64 (__main__.TestInductorOpInfoCPU)": 94.22766367594402,
|
|
"test_comprehensive_masked_amin_cpu_int32 (__main__.TestInductorOpInfoCPU)": 90.8259989420573,
|
|
"test_comprehensive_masked_amin_cpu_int64 (__main__.TestInductorOpInfoCPU)": 92.13633473714192,
|
|
"test_comprehensive_masked_mean_cpu_float16 (__main__.TestInductorOpInfoCPU)": 95.29866536458333,
|
|
"test_comprehensive_masked_mean_cpu_float32 (__main__.TestInductorOpInfoCPU)": 92.53700256347656,
|
|
"test_comprehensive_masked_mean_cpu_float64 (__main__.TestInductorOpInfoCPU)": 95.22733306884766,
|
|
"test_comprehensive_masked_norm_cpu_float16 (__main__.TestInductorOpInfoCPU)": 471.0916748046875,
|
|
"test_comprehensive_masked_norm_cpu_float32 (__main__.TestInductorOpInfoCPU)": 446.25799560546875,
|
|
"test_comprehensive_masked_norm_cpu_float64 (__main__.TestInductorOpInfoCPU)": 446.1899922688802,
|
|
"test_comprehensive_masked_norm_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 167.7551638285319,
|
|
"test_comprehensive_masked_norm_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 148.79099909464517,
|
|
"test_comprehensive_masked_norm_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 162.5819994608561,
|
|
"test_comprehensive_masked_prod_cpu_bool (__main__.TestInductorOpInfoCPU)": 88.22800191243489,
|
|
"test_comprehensive_masked_prod_cpu_float16 (__main__.TestInductorOpInfoCPU)": 95.65499877929688,
|
|
"test_comprehensive_masked_prod_cpu_float32 (__main__.TestInductorOpInfoCPU)": 90.88400014241536,
|
|
"test_comprehensive_masked_prod_cpu_float64 (__main__.TestInductorOpInfoCPU)": 94.00266520182292,
|
|
"test_comprehensive_masked_prod_cpu_int32 (__main__.TestInductorOpInfoCPU)": 91.75599924723308,
|
|
"test_comprehensive_masked_prod_cpu_int64 (__main__.TestInductorOpInfoCPU)": 85.58166758219402,
|
|
"test_comprehensive_masked_sum_cpu_bool (__main__.TestInductorOpInfoCPU)": 87.07266743977864,
|
|
"test_comprehensive_masked_sum_cpu_float16 (__main__.TestInductorOpInfoCPU)": 91.46266428629558,
|
|
"test_comprehensive_masked_sum_cpu_float32 (__main__.TestInductorOpInfoCPU)": 88.94800059000652,
|
|
"test_comprehensive_masked_sum_cpu_float64 (__main__.TestInductorOpInfoCPU)": 94.90433502197266,
|
|
"test_comprehensive_masked_sum_cpu_int32 (__main__.TestInductorOpInfoCPU)": 99.29966735839844,
|
|
"test_comprehensive_masked_sum_cpu_int64 (__main__.TestInductorOpInfoCPU)": 85.29933166503906,
|
|
"test_comprehensive_nn_functional_gaussian_nll_loss_cuda_float32 (__main__.TestDecompCUDA)": 110.91299947102864,
|
|
"test_comprehensive_nn_functional_gaussian_nll_loss_cuda_float64 (__main__.TestDecompCUDA)": 87.41866683959961,
|
|
"test_comprehensive_nn_functional_glu_cpu_float16 (__main__.TestInductorOpInfoCPU)": 73.81366729736328,
|
|
"test_comprehensive_nn_functional_glu_cpu_float32 (__main__.TestInductorOpInfoCPU)": 72.70933532714844,
|
|
"test_comprehensive_nn_functional_glu_cpu_float64 (__main__.TestInductorOpInfoCPU)": 71.70566813151042,
|
|
"test_comprehensive_nn_functional_grid_sample_cpu_float32 (__main__.TestDecompCPU)": 101.97566731770833,
|
|
"test_comprehensive_nn_functional_grid_sample_cpu_float64 (__main__.TestDecompCPU)": 79.01466878255208,
|
|
"test_comprehensive_nn_functional_grid_sample_cuda_bfloat16 (__main__.TestDecompCUDA)": 60.61944495307075,
|
|
"test_comprehensive_nn_functional_grid_sample_cuda_float32 (__main__.TestDecompCUDA)": 249.51266479492188,
|
|
"test_comprehensive_nn_functional_grid_sample_cuda_float64 (__main__.TestDecompCUDA)": 204.8530019124349,
|
|
"test_comprehensive_nn_functional_interpolate_bicubic_cpu_uint8 (__main__.TestInductorOpInfoCPU)": 71.11166636149089,
|
|
"test_comprehensive_nn_functional_interpolate_bicubic_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 79.37683359781902,
|
|
"test_comprehensive_nn_functional_interpolate_bicubic_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 75.29683430989583,
|
|
"test_comprehensive_nn_functional_interpolate_trilinear_cuda_float32 (__main__.TestDecompCUDA)": 75.37983131408691,
|
|
"test_comprehensive_nn_functional_interpolate_trilinear_cuda_float64 (__main__.TestDecompCUDA)": 71.4200013478597,
|
|
"test_comprehensive_nn_functional_max_pool1d_cpu_float16 (__main__.TestInductorOpInfoCPU)": 182.4503377278646,
|
|
"test_comprehensive_nn_functional_max_pool1d_cpu_float32 (__main__.TestInductorOpInfoCPU)": 182.4470011393229,
|
|
"test_comprehensive_nn_functional_max_pool1d_cpu_float64 (__main__.TestInductorOpInfoCPU)": 180.7423299153646,
|
|
"test_comprehensive_nn_functional_max_pool2d_cpu_float16 (__main__.TestInductorOpInfoCPU)": 947.5219930013021,
|
|
"test_comprehensive_nn_functional_max_pool2d_cpu_float32 (__main__.TestInductorOpInfoCPU)": 888.4380086263021,
|
|
"test_comprehensive_nn_functional_max_pool2d_cpu_float64 (__main__.TestInductorOpInfoCPU)": 872.6106770833334,
|
|
"test_comprehensive_nn_functional_max_pool2d_cpu_int32 (__main__.TestInductorOpInfoCPU)": 873.1863199869791,
|
|
"test_comprehensive_nn_functional_max_pool2d_cpu_int64 (__main__.TestInductorOpInfoCPU)": 836.9976806640625,
|
|
"test_comprehensive_nn_functional_max_pool2d_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 914.9636637369791,
|
|
"test_comprehensive_nn_functional_max_pool2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 865.170664469401,
|
|
"test_comprehensive_nn_functional_max_pool2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 921.9736531575521,
|
|
"test_comprehensive_nn_functional_max_pool3d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 61.38200124104818,
|
|
"test_comprehensive_nn_functional_max_unpool2d_cpu_float16 (__main__.TestInductorOpInfoCPU)": 194.47033182779947,
|
|
"test_comprehensive_nn_functional_max_unpool2d_cpu_float32 (__main__.TestInductorOpInfoCPU)": 201.79733276367188,
|
|
"test_comprehensive_nn_functional_max_unpool2d_cpu_float64 (__main__.TestInductorOpInfoCPU)": 196.93966674804688,
|
|
"test_comprehensive_nn_functional_max_unpool2d_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 111.52166557312012,
|
|
"test_comprehensive_nn_functional_max_unpool2d_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 113.46616617838542,
|
|
"test_comprehensive_nn_functional_max_unpool2d_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 107.02900060017903,
|
|
"test_comprehensive_nn_functional_max_unpool3d_cpu_float16 (__main__.TestInductorOpInfoCPU)": 126.29766845703125,
|
|
"test_comprehensive_nn_functional_max_unpool3d_cpu_float32 (__main__.TestInductorOpInfoCPU)": 137.279665629069,
|
|
"test_comprehensive_nn_functional_max_unpool3d_cpu_float64 (__main__.TestInductorOpInfoCPU)": 156.32100423177084,
|
|
"test_comprehensive_nn_functional_pad_constant_cpu_float16 (__main__.TestInductorOpInfoCPU)": 68.2356669108073,
|
|
"test_comprehensive_nn_functional_pad_constant_cpu_float32 (__main__.TestInductorOpInfoCPU)": 68.04666392008464,
|
|
"test_comprehensive_nn_functional_pad_constant_cpu_float64 (__main__.TestInductorOpInfoCPU)": 72.65566762288411,
|
|
"test_comprehensive_nn_functional_pad_constant_cpu_int32 (__main__.TestInductorOpInfoCPU)": 71.84566497802734,
|
|
"test_comprehensive_nn_functional_pad_constant_cpu_int64 (__main__.TestInductorOpInfoCPU)": 67.30033365885417,
|
|
"test_comprehensive_nn_functional_poisson_nll_loss_cpu_float16 (__main__.TestInductorOpInfoCPU)": 116.07533264160156,
|
|
"test_comprehensive_nn_functional_poisson_nll_loss_cpu_float32 (__main__.TestInductorOpInfoCPU)": 121.11599985758464,
|
|
"test_comprehensive_nn_functional_poisson_nll_loss_cpu_float64 (__main__.TestInductorOpInfoCPU)": 126.1576639811198,
|
|
"test_comprehensive_nn_functional_poisson_nll_loss_cpu_int32 (__main__.TestInductorOpInfoCPU)": 111.02566528320312,
|
|
"test_comprehensive_nn_functional_poisson_nll_loss_cpu_int64 (__main__.TestInductorOpInfoCPU)": 110.67699940999348,
|
|
"test_comprehensive_nn_functional_unfold_cpu_bool (__main__.TestInductorOpInfoCPU)": 122.94300079345703,
|
|
"test_comprehensive_nn_functional_unfold_cpu_float16 (__main__.TestInductorOpInfoCPU)": 232.5183308919271,
|
|
"test_comprehensive_nn_functional_unfold_cpu_float32 (__main__.TestInductorOpInfoCPU)": 226.49100240071616,
|
|
"test_comprehensive_nn_functional_unfold_cpu_float64 (__main__.TestInductorOpInfoCPU)": 225.53233337402344,
|
|
"test_comprehensive_nn_functional_unfold_cuda_float16 (__main__.TestInductorOpInfoCUDA)": 80.8669999440511,
|
|
"test_comprehensive_nn_functional_unfold_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 84.27566655476888,
|
|
"test_comprehensive_nn_functional_unfold_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 78.59099960327148,
|
|
"test_comprehensive_ormqr_cuda_complex128 (__main__.TestDecompCUDA)": 97.90700022379558,
|
|
"test_comprehensive_ormqr_cuda_complex64 (__main__.TestDecompCUDA)": 116.58016713460286,
|
|
"test_comprehensive_ormqr_cuda_float32 (__main__.TestDecompCUDA)": 64.93249829610188,
|
|
"test_comprehensive_ormqr_cuda_float32 (__main__.TestInductorOpInfoCUDA)": 103.83033243815105,
|
|
"test_comprehensive_ormqr_cuda_float64 (__main__.TestDecompCUDA)": 61.22433217366537,
|
|
"test_comprehensive_ormqr_cuda_float64 (__main__.TestInductorOpInfoCUDA)": 95.78066635131836,
|
|
"test_comprehensive_svd_cuda_complex128 (__main__.TestDecompCUDA)": 68.0203348795573,
|
|
"test_comprehensive_svd_cuda_complex64 (__main__.TestDecompCUDA)": 67.12083435058594,
|
|
"test_cond_autograd_nested (__main__.TestControlFlow)": 86.52511257595486,
|
|
"test_constructor_autograd_SparseBSC_cuda (__main__.TestSparseAnyCUDA)": 124.19883473714192,
|
|
"test_constructor_autograd_SparseBSR_cuda (__main__.TestSparseAnyCUDA)": 124.81499989827473,
|
|
"test_constructor_autograd_SparseCSC_cuda (__main__.TestSparseAnyCUDA)": 96.18599955240886,
|
|
"test_constructor_autograd_SparseCSR_cuda (__main__.TestSparseAnyCUDA)": 80.51999982198079,
|
|
"test_conv1d_basic (__main__.TestXNNPACKConv1dTransformPass)": 281.4985597398546,
|
|
"test_conv1d_with_relu_fc (__main__.TestXNNPACKConv1dTransformPass)": 490.7274458143446,
|
|
"test_conv2d_unary_cpu_cpp_wrapper (__main__.TestCppWrapper)": 109.75666809082031,
|
|
"test_correctness_AdamW_use_closure_False_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 65.37083371480306,
|
|
"test_correctness_AdamW_use_closure_True_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 116.6316655476888,
|
|
"test_correctness_Adam_use_closure_False_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 64.48250007629395,
|
|
"test_correctness_Adam_use_closure_True_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 117.85650126139323,
|
|
"test_correctness_NAdam_use_closure_True_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 68.24049949645996,
|
|
"test_correctness_RAdam_use_closure_True_cuda_float32 (__main__.CompiledOptimizerParityTestsCUDA)": 60.16349983215332,
|
|
"test_count_nonzero_all (__main__.TestBool)": 626.1464369032118,
|
|
"test_custom_module_lstm (__main__.TestQuantizedOps)": 652.5093282063802,
|
|
"test_ddp_uneven_inputs (__main__.TestDistBackendWithSpawn)": 187.38933286815882,
|
|
"test_dispatch_symbolic_meta_outplace_all_strides_nn_functional_gaussian_nll_loss_cuda_float32 (__main__.TestMetaCUDA)": 79.42466608683269,
|
|
"test_eig_check_magma_cuda_float32 (__main__.TestLinalgCUDA)": 160.03483472267786,
|
|
"test_error_detection_and_propagation (__main__.NcclErrorHandlingTest)": 68.09466552734375,
|
|
"test_fail_creation_ops.py (__main__.TestTyping)": 61.745555029975044,
|
|
"test_fail_torch_size.py (__main__.TestTyping)": 72.09073282877604,
|
|
"test_fn_fwgrad_bwgrad_cumprod_cuda_complex128 (__main__.TestFwdGradientsCUDA)": 83.79666646321614,
|
|
"test_fn_gradgrad_cumprod_cuda_complex128 (__main__.TestBwdGradientsCUDA)": 102.75433349609375,
|
|
"test_fn_gradgrad_map_nested_cpu_float64 (__main__.TestBwdGradientsCPU)": 81.12766520182292,
|
|
"test_fn_gradgrad_map_nested_cuda_float64 (__main__.TestBwdGradientsCUDA)": 60.80604753040132,
|
|
"test_fn_gradgrad_map_triple_nested_cpu_float64 (__main__.TestBwdGradientsCPU)": 555.7903238932291,
|
|
"test_fn_gradgrad_map_triple_nested_cuda_float64 (__main__.TestBwdGradientsCUDA)": 383.1684977213542,
|
|
"test_fuse_large_params_cpu (__main__.CpuTests)": 62.148888481987846,
|
|
"test_fuse_large_params_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 90.62955390082465,
|
|
"test_fuse_large_params_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 93.76555548773871,
|
|
"test_fuse_large_params_dynamic_shapes_cuda (__main__.DynamicShapesCodegenGPUTests)": 61.563334147135414,
|
|
"test_fuse_large_params_dynamic_shapes_cuda (__main__.DynamicShapesGPUTests)": 70.02099990844727,
|
|
"test_grad_nn_Transformer_cuda_float64 (__main__.TestModuleCUDA)": 88.94833374023438,
|
|
"test_gradgrad_nn_LSTM_eval_mode_cuda_float64 (__main__.TestModuleCUDA)": 96.77166748046875,
|
|
"test_gradgrad_nn_LSTM_train_mode_cuda_float64 (__main__.TestModuleCUDA)": 94.92766825358073,
|
|
"test_gradgrad_nn_TransformerDecoderLayer_cuda_float64 (__main__.TestModuleCUDA)": 188.36566670735678,
|
|
"test_gradgrad_nn_TransformerEncoder_eval_mode_cuda_float64 (__main__.TestModuleCUDA)": 111.22516632080078,
|
|
"test_gradgrad_nn_TransformerEncoder_train_mode_cuda_float64 (__main__.TestModuleCUDA)": 130.82799911499023,
|
|
"test_gradgrad_nn_Transformer_cuda_float64 (__main__.TestModuleCUDA)": 551.7034359886533,
|
|
"test_grid_sampler_2d_cpu (__main__.CpuHalideTests)": 185.3376668294271,
|
|
"test_group_norm (__main__.TestQuantizedOps)": 127.55677774217394,
|
|
"test_indexing (__main__.TestAutogradWithCompiledAutograd)": 60.10233349270291,
|
|
"test_indirect_device_assert (__main__.TritonCodeGenTests)": 206.19866434733072,
|
|
"test_inductor_no_recursionerror_on_for_loops_dynamic_shapes (__main__.DynamicShapesReproTests)": 69.05733447604709,
|
|
"test_inplace_gradgrad_cumprod_cuda_complex128 (__main__.TestBwdGradientsCUDA)": 120.87516657511394,
|
|
"test_inputs_overlapping_with_mutation_stress_dynamic_shapes (__main__.DynamicShapesAotAutogradFallbackTests)": 136.26755608452692,
|
|
"test_jit_cuda_archflags (__main__.TestCppExtensionJIT)": 110.98100026448567,
|
|
"test_linalg_solve_triangular_large_cuda_complex128 (__main__.TestLinalgCUDA)": 632.4976641337076,
|
|
"test_linalg_solve_triangular_large_cuda_complex64 (__main__.TestLinalgCUDA)": 77.85983276367188,
|
|
"test_linalg_solve_triangular_large_cuda_float64 (__main__.TestLinalgCUDA)": 80.80400117238362,
|
|
"test_linear (__main__.TestStaticQuantizedModule)": 184.62911393907336,
|
|
"test_linear_binary_cpp_wrapper (__main__.TestCppWrapper)": 64.92466862996419,
|
|
"test_linear_binary_dynamic_shapes_cpp_wrapper (__main__.DynamicShapesCppWrapperCpuTests)": 68.9913330078125,
|
|
"test_linear_relu (__main__.TestStaticQuantizedModule)": 61.6213057386663,
|
|
"test_lobpcg_ortho_cuda_float64 (__main__.TestLinalgCUDA)": 86.48916784922282,
|
|
"test_lstm_cpu (__main__.TestMkldnnCPU)": 74.93866475423177,
|
|
"test_many_overlapping_inputs_does_not_explode_guards_dynamic_shapes (__main__.DynamicShapesReproTests)": 107.84700096978082,
|
|
"test_matmul_small_brute_force_tunableop_cuda_float32 (__main__.TestLinalgCUDA)": 226.24600219726562,
|
|
"test_matmul_small_brute_force_tunableop_cuda_float64 (__main__.TestLinalgCUDA)": 73.07600021362305,
|
|
"test_max_autotune_cutlass_backend_addmm_dynamic_False_max_autotune_gemm_backends_ATen,Triton,CUTLASS (__main__.TestCutlassBackend)": 84.08666483561198,
|
|
"test_max_pool2d_with_indices_backward4_dynamic_shapes_cpu (__main__.DynamicShapesCodegenCpuTests)": 61.81711112128364,
|
|
"test_max_pool2d_with_indices_backward4_dynamic_shapes_cpu (__main__.DynamicShapesCpuTests)": 63.886444091796875,
|
|
"test_proper_exit (__main__.TestDataLoader)": 230.7673314412435,
|
|
"test_proper_exit (__main__.TestDataLoaderPersistentWorkers)": 231.44683074951172,
|
|
"test_put_cuda_uint8 (__main__.TestTorchDeviceTypeCUDA)": 122.29238058200905,
|
|
"test_python_ref_executor__refs_special_zeta_executor_aten_cuda_float64 (__main__.TestCommonCUDA)": 67.51911120944553,
|
|
"test_qat_conv2d_unary (__main__.TestQuantizePT2EX86Inductor)": 144.9381103515625,
|
|
"test_qat_conv_bn_fusion_no_conv_bias (__main__.TestQuantizePT2EQAT_ConvBn1d)": 60.54057139442081,
|
|
"test_qat_mobilenet_v2 (__main__.TestQuantizePT2EQATModels)": 118.08699883355035,
|
|
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_False (__main__.TestPatternMatcher)": 66.50499979654948,
|
|
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_False_is_dynamic_True (__main__.TestPatternMatcher)": 64.51799901326497,
|
|
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_False (__main__.TestPatternMatcher)": 69.84199905395508,
|
|
"test_qlinear_add_int8_mixed_bf16_use_relu_False_is_qat_True_is_dynamic_True (__main__.TestPatternMatcher)": 63.13400141398112,
|
|
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_False (__main__.TestPatternMatcher)": 63.60199864705404,
|
|
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_False_is_dynamic_True (__main__.TestPatternMatcher)": 63.15833282470703,
|
|
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_False (__main__.TestPatternMatcher)": 61.97133255004883,
|
|
"test_qlinear_add_int8_mixed_bf16_use_relu_True_is_qat_True_is_dynamic_True (__main__.TestPatternMatcher)": 64.73333358764648,
|
|
"test_quick_core_backward__unsafe_masked_index_cpu_float64 (__main__.TestDecompCPU)": 329.5066630045573,
|
|
"test_quick_core_backward__unsafe_masked_index_cuda_float64 (__main__.TestDecompCUDA)": 700.787851969401,
|
|
"test_quick_core_backward__unsafe_masked_index_put_accumulate_cpu_float64 (__main__.TestDecompCPU)": 558.64599609375,
|
|
"test_quick_core_backward__unsafe_masked_index_put_accumulate_cuda_float64 (__main__.TestDecompCUDA)": 1100.5410054524739,
|
|
"test_quick_core_backward_expand_copy_cuda_float64 (__main__.TestDecompCUDA)": 61.14266777038574,
|
|
"test_quick_core_backward_nn_functional_max_unpool3d_grad_cpu_float64 (__main__.TestDecompCPU)": 64.54199854532878,
|
|
"test_quick_core_backward_nn_functional_max_unpool3d_grad_cuda_float64 (__main__.TestDecompCUDA)": 208.8625005086263,
|
|
"test_quick_core_backward_roll_cpu_float64 (__main__.TestDecompCPU)": 82.12933349609375,
|
|
"test_quick_core_backward_roll_cuda_float64 (__main__.TestDecompCUDA)": 190.0106684366862,
|
|
"test_quick_core_backward_select_scatter_cuda_float64 (__main__.TestDecompCUDA)": 117.40333302815755,
|
|
"test_quick_core_backward_split_cuda_float64 (__main__.TestDecompCUDA)": 61.65533320109049,
|
|
"test_quick_core_backward_split_with_sizes_copy_cpu_float64 (__main__.TestDecompCPU)": 67.09733327229817,
|
|
"test_quick_core_backward_split_with_sizes_copy_cuda_float64 (__main__.TestDecompCUDA)": 131.47850036621094,
|
|
"test_quick_core_backward_std_cuda_float64 (__main__.TestDecompCUDA)": 85.52533340454102,
|
|
"test_replicatepad_64bit_indexing_cuda_float16 (__main__.TestNNDeviceTypeCUDA)": 65.21066792805989,
|
|
"test_rosenbrock_sparse_with_lrsched_False_SGD_cuda_float64 (__main__.TestOptimRenewedCUDA)": 74.87366692225139,
|
|
"test_rosenbrock_sparse_with_lrsched_True_SGD_cuda_float64 (__main__.TestOptimRenewedCUDA)": 115.06016937891643,
|
|
"test_save_load_large_string_attribute (__main__.TestSaveLoad)": 109.29100290934245,
|
|
"test_shuffler_iterdatapipe (__main__.IntegrationTestDataLoaderDataPipe)": 133.14933607313367,
|
|
"test_slow_tasks (__main__.TestFunctionalAutogradBenchmark)": 141.9941143459744,
|
|
"test_sum_all_cpu_float64 (__main__.TestReductionsCPU)": 247.04196393972745,
|
|
"test_svd_lowrank_cuda_complex128 (__main__.TestLinalgCUDA)": 184.8358294169108,
|
|
"test_terminate_handler_on_crash (__main__.TestTorch)": 100.0895553694831,
|
|
"test_terminate_signal (__main__.ForkTest)": 136.60211210780673,
|
|
"test_terminate_signal (__main__.ParallelForkServerShouldWorkTest)": 135.93655212471882,
|
|
"test_terminate_signal (__main__.SpawnTest)": 138.0366676648458,
|
|
"test_torchvision_smoke (__main__.TestTensorBoardPytorchGraph)": 102.0588902367486,
|
|
"test_train_parity_multi_group (__main__.TestFullyShard1DTrainingCore)": 123.50458236188085,
|
|
"test_triton_bsr_scatter_mm_blocksize_64_cuda_bfloat16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 71.75666618347168,
|
|
"test_triton_bsr_scatter_mm_blocksize_64_cuda_float16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 61.13249969482422,
|
|
"test_triton_bsr_scatter_mm_blocksize_64_cuda_float32 (__main__.TestSparseCompressedTritonKernelsCUDA)": 83.78299967447917,
|
|
"test_triton_bsr_softmax_cuda_bfloat16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 160.55816777547201,
|
|
"test_triton_bsr_softmax_cuda_float16 (__main__.TestSparseCompressedTritonKernelsCUDA)": 145.50849787394205,
|
|
"test_triton_bsr_softmax_cuda_float32 (__main__.TestSparseCompressedTritonKernelsCUDA)": 116.74900182088216,
|
|
"test_unary_ops (__main__.TestTEFuserDynamic)": 172.8575553894043,
|
|
"test_unary_ops (__main__.TestTEFuserStatic)": 155.1940016216702,
|
|
"test_unwaited (__main__.CommTest)": 60.710333506266274,
|
|
"test_upsample_bicubic2d_cpu (__main__.CpuHalideTests)": 96.18333435058594,
|
|
"test_variant_consistency_jit_nn_functional_max_pool2d_cpu_float32 (__main__.TestJitCPU)": 88.48500061035156,
|
|
"test_variant_consistency_jit_nn_functional_max_pool2d_cuda_float32 (__main__.TestJitCUDA)": 75.4156665802002,
|
|
"test_vec_compare_op_cpu_only (__main__.CPUReproTests)": 64.22761005825467,
|
|
"test_vmapjvpvjp_diff_cuda_float32 (__main__.TestOperatorsCUDA)": 70.61666700575087,
|
|
"test_vmapjvpvjp_linalg_lu_solve_cuda_float32 (__main__.TestOperatorsCUDA)": 76.22133445739746,
|
|
"test_vmapjvpvjp_linalg_multi_dot_cuda_float32 (__main__.TestOperatorsCUDA)": 95.06100145975749,
|
|
"test_vmapjvpvjp_linalg_pinv_singular_cuda_float32 (__main__.TestOperatorsCUDA)": 66.50466728210449,
|
|
"test_vmapjvpvjp_linalg_solve_triangular_cuda_float32 (__main__.TestOperatorsCUDA)": 86.0706672668457,
|
|
"test_vmapjvpvjp_linalg_svd_cuda_float32 (__main__.TestOperatorsCUDA)": 83.06883366902669,
|
|
"test_vmapjvpvjp_max_pool2d_with_indices_backward_cpu_float32 (__main__.TestOperatorsCPU)": 86.38833363850911,
|
|
"test_vmapjvpvjp_max_pool2d_with_indices_backward_cuda_float32 (__main__.TestOperatorsCUDA)": 67.0398343404134,
|
|
"test_vmapjvpvjp_nn_functional_conv2d_cpu_float32 (__main__.TestOperatorsCPU)": 64.79333368937175,
|
|
"test_vmapjvpvjp_nn_functional_max_pool2d_cpu_float32 (__main__.TestOperatorsCPU)": 70.52966817220052,
|
|
"test_vmapjvpvjp_nn_functional_max_pool2d_cuda_float32 (__main__.TestOperatorsCUDA)": 76.59099833170573,
|
|
"test_vmapjvpvjp_svd_cuda_float32 (__main__.TestOperatorsCUDA)": 76.7548344930013,
|
|
"test_vmapjvpvjp_unbind_cpu_float32 (__main__.TestOperatorsCPU)": 65.50899887084961,
|
|
"test_vmapjvpvjp_unbind_cuda_float32 (__main__.TestOperatorsCUDA)": 86.91949971516927,
|
|
"test_vmapvjpvjp_meshgrid_list_of_tensors_cuda_float32 (__main__.TestOperatorsCUDA)": 174.04599571228027,
|
|
"test_vmapvjpvjp_meshgrid_variadic_tensors_cuda_float32 (__main__.TestOperatorsCUDA)": 72.79299926757812,
|
|
"test_vmapvjpvjp_nn_functional_bilinear_cuda_float32 (__main__.TestOperatorsCUDA)": 131.72166697184244
|
|
} |