From 35a928a5162ee82ec605d38f55d1de21f99c6e91 Mon Sep 17 00:00:00 2001 From: Aharrypotter Date: Wed, 9 Sep 2026 16:38:33 +0800 Subject: [PATCH] chore: pin shipped text formats to LF Everything in this repository runs on Linux accelerator hosts, and campaign receipts record the SHA-256 of the harness files that produced them. With Git's default autocrlf on Windows a checkout rewrites the shell drivers with CRLF, which breaks them outright on the target host and changes every recorded digest. The two inventory CSVs are renormalized here because their content is unchanged; the remaining files normalize as part of the commits that actually modify them. Co-Authored-By: Claude Opus 5 --- .gitattributes | 12 + ops/inventory_main.csv | 2032 ++++++++++++++++++++-------------------- ops/inventory_vllm.csv | 218 ++--- 3 files changed, 1137 insertions(+), 1125 deletions(-) create mode 100644 .gitattributes diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..200c7e4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,12 @@ +# Everything here runs on Linux accelerator hosts, and campaign receipts record +# the SHA-256 of the harness files they were produced by. A CRLF checkout on +# Windows would both break the shell drivers and change every recorded digest, +# so pin the text formats this repository ships. +*.py text eol=lf +*.sh text eol=lf +*.json text eol=lf +*.yaml text eol=lf +*.csv text eol=lf +*.tsv text eol=lf +*.txt text eol=lf +*.md text eol=lf diff --git a/ops/inventory_main.csv b/ops/inventory_main.csv index 2e714a7..0dc0a1a 100644 --- a/ops/inventory_main.csv +++ b/ops/inventory_main.csv @@ -1,1016 +1,1016 @@ -repo,op,op_file,file,marked_skip,collected,op_names -main,Concat,Concat,benchmark/test_Concat.py,,yes,concat -main,perf_chunk_gated_delta_rule_fwd,FLA/test_chunk_gated_delta_rule_fwd,benchmark/test_FLA/test_chunk_gated_delta_rule_fwd.py,,yes,chunk_gated_delta_rule_fwd -main,perf_chunk_gated_delta_rule,FLA/test_chunk_gated_delta_rule_perf,benchmark/test_FLA/test_chunk_gated_delta_rule_perf.py,,yes,chunk_gated_delta_rule -main,perf_fused_recurrent_gated_delta_rule,FLA/test_fused_recurrent_gated_delta_rule_perf,benchmark/test_FLA/test_fused_recurrent_gated_delta_rule_perf.py,,yes,fused_recurrent_gated_delta_rule -main,_reshape_alias,_reshape_alias,benchmark/test__reshape_alias.py,,yes,_reshape_alias -main,abs,abs,benchmark/test_abs.py,,yes,abs -main,abs_inplace,abs,benchmark/test_abs.py,,yes,abs_ -main,absolute,absolute,benchmark/test_absolute.py,,yes,absolute -main,acos,acos,benchmark/test_acos.py,,yes,acos -main,acosh,acosh,benchmark/test_acosh.py,,yes,acosh -main,acosh_,acosh,benchmark/test_acosh.py,,yes,acosh_ -main,act_quant_perf,act_quant,benchmark/test_act_quant.py,,yes,act_quant_triton -main,perf_adaptive_avg_pool2d,adaptive_avg_pool2d,benchmark/test_adaptive_avg_pool2d.py,,yes,adaptive_avg_pool2d -main,adaptive_avg_pool2d_backward,adaptive_avg_pool2d_backward,benchmark/test_adaptive_avg_pool2d_backward.py,,yes,adaptive_avg_pool2d_backward -main,adaptive_max_pool2d_backward,adaptive_max_pool2d_backward,benchmark/test_adaptive_max_pool2d_backward.py,,yes,adaptive_max_pool2d_backward -main,adaptive_max_pool3d_backward,adaptive_max_pool3d_backward,benchmark/test_adaptive_max_pool3d_backward.py,,yes,adaptive_max_pool3d_backward -main,add,add,benchmark/test_add.py,,yes,add -main,add_inplace,add,benchmark/test_add.py,,yes,add_ -main,add_relu,add_relu,benchmark/test_add_relu.py,,yes,add_relu -main,add_rms_norm,add_rms_norm,benchmark/test_add_rms_norm.py,,yes,add_rms_norm -main,addbmm,addbmm,benchmark/test_addbmm.py,,yes,addbmm -main,addcdiv,addcdiv,benchmark/test_addcdiv.py,,yes,addcdiv -main,addcdiv_out,addcdiv,benchmark/test_addcdiv.py,,yes,addcdiv_out -main,addcdiv_,addcdiv_,benchmark/test_addcdiv_.py,,yes,addcdiv_ -main,addcmul,addcmul,benchmark/test_addcmul.py,,yes,addcmul -main,addcmul_out,addcmul,benchmark/test_addcmul.py,,yes,addcmul_out -main,addcmul_,addcmul_,benchmark/test_addcmul_.py,,yes,addcmul_ -main,addmm,addmm,benchmark/test_addmm.py,,yes,addmm -main,addmm_dtype,addmm,benchmark/test_addmm.py,,yes,addmm_dtype -main,addmm_dtype_out,addmm,benchmark/test_addmm.py,,yes,addmm_dtype_out -main,addmm_out,addmm,benchmark/test_addmm.py,,yes,addmm_out -main,addmm_,addmm_,benchmark/test_addmm_.py,,yes,addmm_ -main,addmv,addmv,benchmark/test_addmv.py,,yes,addmv -main,addmv_out,addmv,benchmark/test_addmv.py,,yes,addmv_out -main,addr,addr,benchmark/test_addr.py,,yes,addr -main,affine_grid_generator,affine_grid_generator,benchmark/test_affine_grid_generator.py,,yes,affine_grid_generator -main,alias,alias,benchmark/test_alias.py,,yes,alias -main,alias_copy,alias_copy,benchmark/test_alias_copy.py,,yes,alias_copy -main,alias_copy_out,alias_copy,benchmark/test_alias_copy.py,,yes,alias_copy_out -main,all,all,benchmark/test_all.py,,yes,all -main,all_dim,all,benchmark/test_all.py,,yes,all_dim -main,all_dims,all,benchmark/test_all.py,,yes,all_dims -main,allclose,allclose,benchmark/test_allclose.py,,yes,allclose -main,alpha_dropout,alpha_dropout,benchmark/test_alpha_dropout.py,,yes,alpha_dropout -main,amax,amax,benchmark/test_amax.py,,yes,amax -main,amin,amin,benchmark/test_amin.py,,yes,amin -main,amin_,amin,benchmark/test_amin.py,,yes,amin_ -main,aminmax,aminmax,benchmark/test_aminmax.py,,yes,aminmax -main,amp_foreach_non_finite_check_and_unscale_,amp_foreach_non_finite_check_and_unscale_,benchmark/test_amp_foreach_non_finite_check_and_unscale_.py,,yes,amp_foreach_non_finite_check_and_unscale_ -main,angle,angle,benchmark/test_angle.py,,yes,angle -main,any,any,benchmark/test_any.py,,yes,any -main,any_dim,any,benchmark/test_any.py,,yes,any_dim -main,any_dims,any,benchmark/test_any.py,,yes,any_dims -main,apply_repetition_penalties,apply_repetition_penalties,benchmark/test_apply_repetition_penalties.py,,yes,apply_repetition_penalties -main,apply_rotary_pos_emb,apply_rotary_pos_emb,benchmark/test_apply_rotary_pos_emb.py,,yes,apply_rotary_pos_emb -main,arange,arange,benchmark/test_arange.py,,yes,arange -main,arange_start,arange,benchmark/test_arange.py,,yes,arange_start -main,arange_start_step,arange,benchmark/test_arange.py,,yes,arange_start_step -main,arccos,arccos,benchmark/test_arccos.py,,yes,arccos -main,arccos_,arccos,benchmark/test_arccos.py,,yes,arccos_ -main,arccosh,arccosh,benchmark/test_arccosh.py,,yes,arccosh -main,arccosh_out,arccosh,benchmark/test_arccosh.py,,yes,arccosh_out -main,arccosh_,arccosh_,benchmark/test_arccosh_.py,,yes,arccosh_ -main,arcsin,arcsin,benchmark/test_arcsin.py,,yes,arcsin -main,arcsin_,arcsin,benchmark/test_arcsin.py,,yes,arcsin_ -main,arcsin_out,arcsin,benchmark/test_arcsin.py,,yes,arcsin_out -main,arcsinh,arcsinh,benchmark/test_arcsinh.py,,yes,arcsinh -main,arcsinh_inplace,arcsinh,benchmark/test_arcsinh.py,,yes,arcsinh_ -main,arcsinh_out,arcsinh,benchmark/test_arcsinh.py,,yes,arcsinh_out -main,arctan2,arctan2,benchmark/test_arctan2.py,,yes,arctan2 -main,arctan2_,arctan2,benchmark/test_arctan2.py,,yes,arctan2_ -main,arctan,arctan_,benchmark/test_arctan_.py,,yes,arctan -main,arctan_,arctan_,benchmark/test_arctan_.py,,yes,arctan_ -main,arctanh_inplace,arctanh,benchmark/test_arctanh.py,,yes,arctanh_ -main,argmax,argmax,benchmark/test_argmax.py,,yes,argmax -main,argmin,argmin,benchmark/test_argmin.py,,yes,argmin -main,argsort,argsort,benchmark/test_argsort.py,,yes,argsort -main,as_strided_copy,as_strided_copy,benchmark/test_as_strided_copy.py,,yes,as_strided_copy -main,as_strided_copy_out,as_strided_copy,benchmark/test_as_strided_copy.py,,yes,as_strided_copy_out -main,asin,asin,benchmark/test_asin.py,,yes,asin -main,asin_,asin,benchmark/test_asin.py,,yes,asin_ -main,asinh,asinh,benchmark/test_asinh.py,,yes,asinh -main,asinh_inplace,asinh,benchmark/test_asinh.py,,yes,asinh_ -main,assert_async,assert_async,benchmark/test_assert_async.py,,yes,assert_async -main,atan,atan,benchmark/test_atan.py,,yes,atan -main,atan_inplace,atan,benchmark/test_atan.py,,yes,atan_ -main,atan2,atan2,benchmark/test_atan2.py,,yes,atan2 -main,atan2_out,atan2,benchmark/test_atan2.py,,yes,atan2_out -main,atan2_,atan2_,benchmark/test_atan2_.py,,yes,atan2_ -main,atanh,atanh,benchmark/test_atanh.py,,yes,atanh -main,atanh_,atanh_,benchmark/test_atanh_.py,,yes,atanh_ -main,avg_pool2d,avg_pool2d,benchmark/test_avg_pool2d.py,,yes,avg_pool2d -main,avg_pool2d_backward,avg_pool2d,benchmark/test_avg_pool2d.py,,yes,avg_pool2d_backward -main,perf_avg_pool3d,avg_pool3d_perf,benchmark/test_avg_pool3d_perf.py,,yes,avg_pool3d -main,perf_avg_pool3d_backward,avg_pool3d_perf,benchmark/test_avg_pool3d_perf.py,,yes,avg_pool3d -main,baddbmm,baddbmm,benchmark/test_baddbmm.py,,yes,baddbmm -main,baddbmm_out,baddbmm,benchmark/test_baddbmm.py,,yes,baddbmm_out -main,baddbmm_,baddbmm_,benchmark/test_baddbmm_.py,,yes,baddbmm_ -main,batch_norm,batch_norm,benchmark/test_batch_norm.py,,yes,batch_norm -main,batch_norm_backward,batch_norm_backward,benchmark/test_batch_norm_backward.py,,yes,batch_norm_backward -main,batch_norm_no_update,batch_norm_no_update,benchmark/test_batch_norm_no_update.py,,yes,batch_norm_no_update -main,beam_search_score,beam_search_score,benchmark/test_beam_search_score.py,,yes,beam_search_score -main,beam_search_score_,beam_search_score,benchmark/test_beam_search_score.py,,yes,beam_search_score_ -main,bernoulli_inplace,bernoulli,benchmark/test_bernoulli.py,,yes,bernoulli_ -main,bernoulli,bernoulli,benchmark/test_bernoulli.py,,yes,bernoulli -main,bf16_paged_mqa_logits,bf16_paged_mqa_logits,benchmark/test_bf16_paged_mqa_logits.py,,yes,bf16_paged_mqa_logits -main,binary_cross_entropy_backward,binary_cross_entropy_backward,benchmark/test_binary_cross_entropy_backward.py,,yes,binary_cross_entropy_backward -main,binary_cross_entropy_with_logits,binary_cross_entropy_with_logits,benchmark/test_binary_cross_entropy_with_logits.py,,yes,binary_cross_entropy_with_logits -main,bincount,bincount,benchmark/test_bincount.py,,yes,bincount -main,bincount_weighted,bincount,benchmark/test_bincount.py,,yes,bincount_weighted -main,bitwise_and,bitwise_and,benchmark/test_bitwise_and.py,,yes,bitwise_and_tensor -main,bitwise_and_inplace,bitwise_and,benchmark/test_bitwise_and.py,,yes,bitwise_and_tensor_ -main,bitwise_and_scalar,bitwise_and,benchmark/test_bitwise_and.py,,yes,bitwise_and_scalar -main,bitwise_and_scalar_,bitwise_and,benchmark/test_bitwise_and.py,,yes,bitwise_and_scalar_ -main,bitwise_and_scalar_tensor,bitwise_and,benchmark/test_bitwise_and.py,,yes,bitwise_and_scalar_tensor -main,bitwise_left_shift,bitwise_left_shift,benchmark/test_bitwise_left_shift.py,,yes,bitwise_left_shift -main,bitwise_left_shift_,bitwise_left_shift_,benchmark/test_bitwise_left_shift_.py,,yes,bitwise_left_shift_ -main,bitwise_not,bitwise_not,benchmark/test_bitwise_not.py,,yes,bitwise_not -main,bitwise_not_inplace,bitwise_not,benchmark/test_bitwise_not.py,,yes,bitwise_not_ -main,bitwise_or_tensor,bitwise_or,benchmark/test_bitwise_or.py,,yes,bitwise_or_tensor -main,bitwise_or_inplace,bitwise_or,benchmark/test_bitwise_or.py,,yes,bitwise_or_tensor_ -main,bitwise_or_scalar,bitwise_or,benchmark/test_bitwise_or.py,,yes,bitwise_or_scalar -main,bitwise_or_scalar_,bitwise_or,benchmark/test_bitwise_or.py,,yes,bitwise_or_scalar_ -main,bitwise_or_scalar_tensor,bitwise_or,benchmark/test_bitwise_or.py,,yes,bitwise_or_scalar_tensor -main,bitwise_right_shift,bitwise_right_shift,benchmark/test_bitwise_right_shift.py,,yes,bitwise_right_shift -main,bitwise_right_shift_,bitwise_right_shift_,benchmark/test_bitwise_right_shift_.py,,yes,bitwise_right_shift_ -main,bitwise_xor_tensor,bitwise_xor,benchmark/test_bitwise_xor.py,,yes,bitwise_xor_tensor -main,bitwise_xor_inplace,bitwise_xor,benchmark/test_bitwise_xor.py,,yes,bitwise_xor_tensor_ -main,bitwise_xor_scalar,bitwise_xor,benchmark/test_bitwise_xor.py,,yes,bitwise_xor_scalar -main,bitwise_xor_scalar_,bitwise_xor,benchmark/test_bitwise_xor.py,,yes,bitwise_xor_scalar_ -main,bitwise_xor_scalar_tensor,bitwise_xor,benchmark/test_bitwise_xor.py,,yes,bitwise_xor_scalar_tensor -main,blas_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, -main,perf_w8a8_block_fp8_matmul,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,w8a8_block_fp8_matmul -main,perf_w8a8_block_fp8_matmul_deepgemm,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,w8a8_block_fp8_matmul_deepgemm -main,perf_sparse_attention,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,sparse_attention -main,perf_mul,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,mul -main,mv_and_outer_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, -main,addmv_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, -main,vdot_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,vdot -main,addr_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,addr -main,perf_router_gemm,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,router_gemm -main,block_diag,block_diag,benchmark/test_block_diag.py,,yes,block_diag -main,bmm,bmm,benchmark/test_bmm.py,,yes,bmm -main,bmm_out,bmm,benchmark/test_bmm.py,,yes,bmm_out -main,broadcast_tensors,broadcast_tensors,benchmark/test_broadcast_tensors.py,,yes,broadcast_tensors -main,broadcast_to,broadcast_to,benchmark/test_broadcast_to.py,,yes,broadcast_to -main,bucketize_perf,bucketize,benchmark/test_bucketize.py,,yes,bucketize -main,cat,cat,benchmark/test_cat.py,,yes,cat -main,cat_out,cat,benchmark/test_cat.py,,yes,cat_out -main,cauchy_inplace,cauchy,benchmark/test_cauchy.py,,yes,cauchy_ -main,cauchy_out,cauchy,benchmark/test_cauchy.py,,yes,cauchy -main,cdist_backward,cdist_backward,benchmark/test_cdist_backward.py,,yes,cdist_backward -main,cdist_forward,cdist_forward,benchmark/test_cdist_forward.py,,yes,cdist_forward -main,ceil,ceil,benchmark/test_ceil.py,,yes,ceil -main,ceil_inplace,ceil,benchmark/test_ceil.py,,yes,ceil_ -main,ceil_out,ceil,benchmark/test_ceil.py,,yes,ceil_out -main,celu,celu,benchmark/test_celu.py,,yes,celu -main,celu_inplace,celu,benchmark/test_celu.py,,yes,celu_ -main,channel_shuffle,channel_shuffle,benchmark/test_channel_shuffle.py,,yes,channel_shuffle -main,cholesky_inverse,cholesky_inverse,benchmark/test_cholesky_inverse.py,,yes,cholesky_inverse -main,cholesky_solve,cholesky_solve,benchmark/test_cholesky_solve.py,,yes,cholesky_solve -main,cholesky_solve_out,cholesky_solve,benchmark/test_cholesky_solve.py,,yes,cholesky_solve_out -main,chunk,chunk,benchmark/test_chunk.py,,yes,chunk -main,chunk_cat,chunk_cat,benchmark/test_chunk_cat.py,,yes,chunk_cat -main,clamp,clamp,benchmark/test_clamp.py,,yes,clamp -main,clamp_inplace,clamp,benchmark/test_clamp.py,,yes,clamp_ -main,clamp_tensor,clamp,benchmark/test_clamp.py,,yes,clamp_tensor -main,clamp_tensor_inplace,clamp,benchmark/test_clamp.py,,yes,clamp_tensor_ -main,clamp_max,clamp_max,benchmark/test_clamp_max.py,,yes,clamp_max -main,clamp_max_inplace,clamp_max,benchmark/test_clamp_max.py,,yes,clamp_max_ -main,clamp_min,clamp_min,benchmark/test_clamp_min.py,,yes,clamp_min -main,clamp_min_inplace,clamp_min,benchmark/test_clamp_min.py,,yes,clamp_min_ -main,clip,clip,benchmark/test_clip.py,,yes,clip -main,clip_inplace,clip,benchmark/test_clip.py,,yes,clip_ -main,col2im,col2im,benchmark/test_col2im.py,,yes,col2im -main,concat_and_cache_mla,concat_and_cache_mla,benchmark/test_concat_and_cache_mla.py,,yes,concat_and_cache_mla -main,concatenate,concatenate,benchmark/test_concatenate.py,,yes,concatenate -main,conj,conj,benchmark/test_conj.py,,yes,conj -main,conj_physical,conj_physical,benchmark/test_conj_physical.py,,yes,conj_physical -main,constant_pad_nd,constant_pad_nd,benchmark/test_constant_pad_nd.py,,yes,constant_pad_nd -main,contiguous,contiguous,benchmark/test_contiguous.py,,yes,contiguous -main,conv1d,conv1d,benchmark/test_conv1d.py,,yes,conv1d -main,conv1d_padding,conv1d,benchmark/test_conv1d.py,,yes,conv1d_padding -main,conv2d,conv2d,benchmark/test_conv2d.py,,yes,conv2d -main,conv2d_padding,conv2d,benchmark/test_conv2d.py,,yes,conv2d_padding -main,conv3d,conv3d,benchmark/test_conv3d.py,,yes,conv3d -main,conv3d_padding,conv3d,benchmark/test_conv3d.py,,yes,conv3d_padding -main,conv_depthwise2d,conv_depthwise2d,benchmark/test_conv_depthwise2d.py,,yes,conv_depthwise2d -main,conv_transpose1d,conv_transpose1d,benchmark/test_conv_transpose1d.py,,yes,conv_transpose1d -main,perf_conv_transpose2d,conv_transpose2d,benchmark/test_conv_transpose2d.py,,yes,conv_transpose2d -main,convert_weight_to_int4pack,convert_weight_to_int4pack,benchmark/test_convert_weight_to_int4pack.py,,yes,convert_weight_to_int4pack -main,copy_inplace,copy,benchmark/test_copy.py,,yes,copy_ -main,copy_functional,copy,benchmark/test_copy.py,,yes,copy -main,copysign,copysign,benchmark/test_copysign.py,,yes,copysign -main,copysign_out,copysign,benchmark/test_copysign.py,,yes,copysign_out -main,copysign_,copysign_,benchmark/test_copysign_.py,,yes,copysign_ -main,cos,cos,benchmark/test_cos.py,,yes,cos -main,cos_inplace,cos,benchmark/test_cos.py,,yes,cos_ -main,cosh,cosh,benchmark/test_cosh.py,,yes,cosh -main,cosh_inplace,cosh,benchmark/test_cosh.py,,yes,cosh_ -main,cosh_out,cosh,benchmark/test_cosh.py,,yes,cosh_out -main,count_nonzero,count_nonzero,benchmark/test_count_nonzero.py,,yes,count_nonzero -main,cp_gather_indexer_k_quant_cache_benchmark,cp_gather_indexer_k_quant_cache,benchmark/test_cp_gather_indexer_k_quant_cache.py,,yes, -main,cross_entropy_loss,cross_entropy_loss,benchmark/test_cross_entropy_loss.py,,yes,cross_entropy_loss -main,ctc_loss,ctc_loss,benchmark/test_ctc_loss.py,,yes,ctc_loss -main,ctc_loss_backward,ctc_loss,benchmark/test_ctc_loss.py,,yes,ctc_loss -main,perf_cudnn_attention_forward,cudnn_attention_forward,benchmark/test_cudnn_attention_forward.py,,yes,cudnn_attention_forward -main,cudnn_batch_norm_backward,cudnn_batch_norm_backward,benchmark/test_cudnn_batch_norm_backward.py,,yes,cudnn_batch_norm_backward -main,cudnn_convolution,cudnn_convolution,benchmark/test_cudnn_convolution.py,,yes,cudnn_convolution -main,cummax,cummax,benchmark/test_cummax.py,,yes,cummax -main,cummin,cummin,benchmark/test_cummin.py,,yes,cummin -main,cumprod_perf,cumprod,benchmark/test_cumprod.py,,yes,cumprod -main,cumprod_inplace_perf,cumprod,benchmark/test_cumprod.py,,yes,cumprod_ -main,cumsum,cumsum,benchmark/test_cumsum.py,,yes,cumsum -main,cumsum_out,cumsum,benchmark/test_cumsum.py,,yes,cumsum_out -main,cutlass_scaled_mm_benchmark,cutlass_scaled_mm,benchmark/test_cutlass_scaled_mm.py,,yes, -main,combine_topk_swa_indices_benchmark,deepseek_v4_attention_combine_topk_swa_indices,benchmark/test_deepseek_v4_attention_combine_topk_swa_indices.py,,yes, -main,compute_global_topk_indices_and_lens_benchmark,deepseek_v4_attention_compute_global_topk_indices_and_lens,benchmark/test_deepseek_v4_attention_compute_global_topk_indices_and_lens.py,,yes, -main,dequantize_and_gather_k_cache_benchmark,deepseek_v4_attention_dequantize_and_gather_k_cache,benchmark/test_deepseek_v4_attention_dequantize_and_gather_k_cache.py,,yes, -main,fused_q_kv_rmsnorm_benchmark,deepseek_v4_attention_fused_q_kv_rmsnorm,benchmark/test_deepseek_v4_attention_fused_q_kv_rmsnorm.py,,yes, -main,deg2rad,deg2rad,benchmark/test_deg2rad.py,,yes,deg2rad -main,deg2rad_,deg2rad,benchmark/test_deg2rad.py,,yes,deg2rad_ -main,deg2rad_out,deg2rad,benchmark/test_deg2rad.py,,yes,deg2rad_out -main,dequantize,dequantize,benchmark/test_dequantize.py,,yes,dequantize -main,dgeglu,dgeglu,benchmark/test_dgeglu.py,,yes,dgeglu -main,diag,diag,benchmark/test_diag.py,,yes,diag -main,diag_embed,diag_embed,benchmark/test_diag_embed.py,,yes,diag_embed -main,diagonal_backward,diagonal,benchmark/test_diagonal.py,,yes,diagonal_backward -main,diagonal_copy,diagonal_copy,benchmark/test_diagonal_copy.py,,yes,diagonal_copy -main,diagonal_scatter,diagonal_scatter,benchmark/test_diagonal_scatter.py,,yes,diagonal_scatter -main,diff,diff,benchmark/test_diff.py,,yes,diff -main,diff_n2,diff,benchmark/test_diff.py,,yes,diff -main,digamma,digamma,benchmark/test_digamma.py,,yes,digamma -main,digamma_inplace,digamma,benchmark/test_digamma.py,,yes,digamma_ -main,div,div,benchmark/test_div.py,,yes,div_tensor -main,div_inplace,div,benchmark/test_div.py,,yes,div_tensor_ -main,div_tensor_mode,div,benchmark/test_div.py,,yes,div_tensor_mode -main,div_tensor_mode_inplace,div,benchmark/test_div.py,,yes,div_tensor_mode_ -main,div_scalar_mode,div,benchmark/test_div.py,,yes,div_scalar_mode -main,div_scalar_mode_inplace,div,benchmark/test_div.py,,yes,div_scalar_mode_ -main,div_scalar_inplace,div,benchmark/test_div.py,,yes,div_scalar_ -main,div_out,div,benchmark/test_div.py,,yes,div_out -main,dot,dot,benchmark/test_dot.py,,yes,dot -main,dreglu,dreglu,benchmark/test_dreglu.py,,yes,dreglu -main,dropout,dropout,benchmark/test_dropout.py,,yes,dropout -main,dropout_backward,dropout,benchmark/test_dropout.py,,yes,dropout_backward -main,dswiglu,dswiglu,benchmark/test_dswiglu.py,,yes,dswiglu -main,dunder_ior_inplace,dunder_ior,benchmark/test_dunder_ior.py,,yes,dunder_ior_tensor -main,dunder_ior_scalar_inplace,dunder_ior,benchmark/test_dunder_ior.py,,yes,dunder_ior_scalar -main,dunder_or_tensor,dunder_or,benchmark/test_dunder_or.py,,yes,dunder_or_tensor -main,dunder_or_scalar,dunder_or,benchmark/test_dunder_or.py,,yes,dunder_or_scalar -main,dyn_quant_pack_4bit_weight,dyn_quant_pack_4bit_weight,benchmark/test_dyn_quant_pack_4bit_weight.py,,yes,dyn_quant_pack_4bit_weight -main,einsum_matmul,einsum,benchmark/test_einsum.py,,yes,einsum -main,einsum_bmm,einsum,benchmark/test_einsum.py,,yes,einsum -main,einsum_dot,einsum,benchmark/test_einsum.py,,yes,einsum -main,einsum_outer,einsum,benchmark/test_einsum.py,,yes,einsum -main,einsum_trace,einsum,benchmark/test_einsum.py,,yes,einsum -main,einsum_diagonal,einsum,benchmark/test_einsum.py,,yes,einsum -main,einsum_transpose,einsum,benchmark/test_einsum.py,,yes,einsum -main,einsum_sum_all,einsum,benchmark/test_einsum.py,,yes,einsum -main,einsum_sum_dim,einsum,benchmark/test_einsum.py,,yes,einsum -main,einsum_ellipsis,einsum,benchmark/test_einsum.py,,yes,einsum -main,elu,elu,benchmark/test_elu.py,,yes,elu -main,elu_inplace,elu,benchmark/test_elu.py,,yes,elu_ -main,elu_backward,elu,benchmark/test_elu.py,,yes,elu_backward -main,embedding,embedding,benchmark/test_embedding.py,,yes,embedding -main,embedding_backward,embedding,benchmark/test_embedding.py,,yes,embedding_backward -main,embedding_bag_dense_backward,embedding_bag_dense_backward,benchmark/test_embedding_bag_dense_backward.py,,yes,embedding_bag_dense_backward -main,embedding_bag_per_sample_weights_backward,embedding_bag_per_sample_weights_backward,benchmark/test_embedding_bag_per_sample_weights_backward.py,,yes,_embedding_bag_per_sample_weights_backward -main,embedding_dense_backward,embedding_dense_backward,benchmark/test_embedding_dense_backward.py,,yes,embedding_dense_backward -main,empty,empty,benchmark/test_empty.py,,yes,empty -main,eq,eq,benchmark/test_eq.py,,yes,eq -main,eq_scalar,eq,benchmark/test_eq.py,,yes,eq_scalar -main,eq_,eq_,benchmark/test_eq_.py,,yes,eq_ -main,eq_scalar_,eq_,benchmark/test_eq_.py,,yes,eq_scalar_ -main,equal,equal,benchmark/test_equal.py,,yes,equal -main,special_erf,erf,benchmark/test_erf.py,,yes,special_erf -main,erf,erf,benchmark/test_erf.py,,yes,erf -main,erf_inplace,erf,benchmark/test_erf.py,,yes,erf_ -main,erfinv,erfinv_,benchmark/test_erfinv_.py,,yes,erfinv -main,erfinv_,erfinv_,benchmark/test_erfinv_.py,,yes,erfinv_ -main,euclidean_dist,euclidean_dist,benchmark/test_euclidean_dist.py,,yes,euclidean_dist -main,exp,exp,benchmark/test_exp.py,,yes,exp -main,exp_inplace,exp,benchmark/test_exp.py,,yes,exp_ -main,exp_out,exp,benchmark/test_exp.py,,yes,exp_out -main,special_exp2,exp2,benchmark/test_exp2.py,,yes,special_exp2 -main,exp2,exp2,benchmark/test_exp2.py,,yes,exp2 -main,exp2_inplace,exp2,benchmark/test_exp2.py,,yes,exp2_ -main,expand,expand,benchmark/test_expand.py,,yes,expand -main,expand_,expand,benchmark/test_expand.py,,yes,expand_ -main,expand_as,expand_as,benchmark/test_expand_as.py,,yes,expand_as -main,expm1,expm1,benchmark/test_expm1.py,,yes,expm1 -main,expm1_inplace,expm1,benchmark/test_expm1.py,,yes,expm1_ -main,expm1_out,expm1,benchmark/test_expm1.py,,yes,expm1_out -main,exponential_inplace,exponential,benchmark/test_exponential.py,,yes,exponential_ -main,eye,eye,benchmark/test_eye.py,,yes,eye -main,eye_m,eye,benchmark/test_eye.py,,yes,eye_m -main,feature_dropout,feature_dropout,benchmark/test_feature_dropout.py,,yes,feature_dropout -main,feature_dropout_,feature_dropout,benchmark/test_feature_dropout.py,,yes,feature_dropout_ -main,perf_fft,fft,benchmark/test_fft.py,,yes,fft -main,fill_scalar,fill,benchmark/test_fill.py,,yes,fill_scalar -main,fill_tensor,fill,benchmark/test_fill.py,,yes,fill_tensor -main,fill_tensor_inplace,fill,benchmark/test_fill.py,,yes,fill_tensor_ -main,fill_tensor_out,fill,benchmark/test_fill.py,,yes,fill_tensor_out -main,fill_scalar_inplace,fill,benchmark/test_fill.py,,yes,fill_scalar_ -main,fill_scalar_out,fill,benchmark/test_fill.py,,yes,fill_scalar_out -main,fix,fix,benchmark/test_fix.py,,yes,fix -main,fix_,fix_,benchmark/test_fix_.py,,yes,fix_ -main,perf_flash_attention_backward,flash_attention_backward,benchmark/test_flash_attention_backward.py,,yes,flash_attention_backward -main,perf_scaled_dot_product_flash_attention_backward,flash_attention_backward,benchmark/test_flash_attention_backward.py,,yes,scaled_dot_product_flash_attention_backward -main,perf_scaled_dot_product_cudnn_attention_backward,flash_attention_backward,benchmark/test_flash_attention_backward.py,,yes,scaled_dot_product_cudnn_attention_backward -main,perf_efficient_attention_backward,flash_attention_backward,benchmark/test_flash_attention_backward.py,,yes,efficient_attention_backward -main,perf_scaled_dot_product_efficient_attention_backward,flash_attention_backward,benchmark/test_flash_attention_backward.py,,yes,scaled_dot_product_efficient_attention_backward -main,_flash_attention_forward,flash_attention_forward,benchmark/test_flash_attention_forward.py,,yes,_flash_attention_forward -main,flash_attention_forward,flash_attention_forward,benchmark/test_flash_attention_forward.py,,yes,flash_attention_forward -main,flash_attn_varlen_func,flash_attn_varlen_func,benchmark/test_flash_attn_varlen_func.py,,yes,flash_attn_varlen_func -main,flash_attn_varlen_func_noncontig,flash_attn_varlen_func,benchmark/test_flash_attn_varlen_func.py,,yes,flash_attn_varlen_func_noncontig -main,flash_attn_varlen_opt_func,flash_attn_varlen_opt_init_func,benchmark/test_flash_attn_varlen_opt_init_func.py,,yes,flash_attn_varlen_func -main,flash_mla,flash_mla,benchmark/test_flash_mla.py,,yes,flash_mla -main,flash_mla_sparse_fwd,flash_mla_sparse_fwd,benchmark/test_flash_mla_sparse_fwd.py,,yes, -main,flash_mla_with_kvcache,flash_mla_with_kvcache,benchmark/test_flash_mla_with_kvcache.py,,yes, -main,flatten,flatten,benchmark/test_flatten.py,,yes,flatten.using_ints -main,flip,flip,benchmark/test_flip.py,,yes,flip -main,float_power_,float_power_,benchmark/test_float_power_.py,,yes,float_power_ -main,floor,floor,benchmark/test_floor.py,,yes,floor -main,floor_inplace,floor,benchmark/test_floor.py,,yes,floor_ -main,floor_out,floor,benchmark/test_floor.py,,yes,floor_out -main,floor_divide,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide -main,floor_divide_inplace,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide_ -main,floor_divide_scalar,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide_scalar -main,floor_divide_scalar_,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide_scalar_ -main,floor_divide_tensor,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide_tensor -main,floor_divide_tensor_inplace,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide_tensor_ -main,fmax,fmax,benchmark/test_fmax.py,,yes,fmax -main,fmax_out,fmax,benchmark/test_fmax.py,,yes,fmax_out -main,fmin,fmin,benchmark/test_fmin.py,,yes,fmin -main,fmin_out,fmin,benchmark/test_fmin.py,,yes,fmin_out -main,fmod_tensor,fmod,benchmark/test_fmod.py,,yes,fmod_tensor -main,fmod_scalar,fmod,benchmark/test_fmod.py,,yes,fmod_scalar -main,fmod_tensor_,fmod,benchmark/test_fmod.py,,yes,fmod_tensor_ -main,fmod_scalar_,fmod,benchmark/test_fmod.py,,yes,fmod_scalar_ -main,fmod_,fmod_,benchmark/test_fmod_.py,,yes,fmod_ -main,perf_fp8_einsum_gems_vs_deepgemm,fp8_einsum,benchmark/test_fp8_einsum.py,,yes,fp8_einsum -main,fp8_fp4_mega_moe_vllm,fp8_fp4_mega_moe,benchmark/test_fp8_fp4_mega_moe.py,,yes,fp8_fp4_mega_moe -main,fp8_fp4_mega_moe_torch_ref,fp8_fp4_mega_moe,benchmark/test_fp8_fp4_mega_moe.py,,yes,fp8_fp4_mega_moe_torch_ref -main,fp8_fp4_mqa_logits,fp8_fp4_mqa_logits,benchmark/test_fp8_fp4_mqa_logits.py,,yes,fp8_fp4_mqa_logits -main,fp8_fp4_paged_mqa_logits,fp8_fp4_paged_mqa_logits,benchmark/test_fp8_fp4_paged_mqa_logits.py,,yes,fp8_fp4_paged_mqa_logits -main,fp8_mqa_logits,fp8_mqa_logits,benchmark/test_fp8_mqa_logits.py,,yes,fp8_mqa_logits -main,perf_fp8_paged_mqa_logits_gems_vs_deepgemm,fp8_paged_mqa_logits_perf,benchmark/test_fp8_paged_mqa_logits_perf.py,,yes, -main,frac,frac,benchmark/test_frac.py,,yes,frac -main,frac_,frac_,benchmark/test_frac_.py,,yes,frac_ -main,fractional_max_pool2d,fractional_max_pool2d,benchmark/test_fractional_max_pool2d.py,,yes,fractional_max_pool2d -main,fractional_max_pool2d_backward,fractional_max_pool2d,benchmark/test_fractional_max_pool2d.py,,yes,fractional_max_pool2d_backward -main,full,full,benchmark/test_full.py,,yes,full -main,full_like,full_like,benchmark/test_full_like.py,,yes,full_like -main,functional_assert_async,functional_assert_async,benchmark/test_functional_assert_async.py,,yes,functional_assert_async -main,functional_sym_constrain_range,functional_sym_constrain_range,benchmark/test_functional_sym_constrain_range.py,,yes,functional_sym_constrain_range -main,functional_sym_constrain_range_for_size,functional_sym_constrain_range_for_size,benchmark/test_functional_sym_constrain_range_for_size.py,,yes,functional_sym_constrain_range_for_size -main,fused_adam,fused_adam,benchmark/test_fused_adam.py,,yes,fused_adam -main,fused_adam_,fused_adam,benchmark/test_fused_adam.py,,yes,fused_adam_ -main,fused_add_rms_norm,fused_add_rms_norm,benchmark/test_fused_add_rms_norm.py,,yes,fused_add_rms_norm -main,fused_deepseek_v4_qnorm_rope_kv_rope_insert,fused_deepseek_v4_qnorm_rope_kv_rope_insert,benchmark/test_fused_deepseek_v4_qnorm_rope_kv_rope_insert.py,,yes,fused_deepseek_v4_qnorm_rope_kv_rope_insert -main,fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert,fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert,benchmark/test_fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert.py,,yes, -main,fused_indexer_q_rope_quant,fused_indexer_q_rope_quant,benchmark/test_fused_indexer_q_rope_quant.py,,yes,fused_indexer_q_rope_quant -main,fused_inv_rope_fp8_quant,fused_inv_rope_fp8_quant,benchmark/test_fused_inv_rope_fp8_quant.py,,yes,fused_inv_rope_fp8_quant -main,fused_marlin_moe,fused_marlin_moe,benchmark/test_fused_marlin_moe.py,,yes,fused_marlin_moe -main,fused_marlin_moe_int8,fused_marlin_moe,benchmark/test_fused_marlin_moe.py,,yes,fused_marlin_moe_int8 -main,fused_marlin_moe_mxfp4,fused_marlin_moe,benchmark/test_fused_marlin_moe.py,,yes,fused_marlin_moe_mxfp4 -main,fused_moe_impl_gems_vs_vllm,fused_moe,benchmark/test_fused_moe.py,,yes,fused_experts_impl -main,dispatch_fused_moe_kernel,fused_moe,benchmark/test_fused_moe.py,,yes,dispatch_fused_moe_kernel -main,fused_moe_fp8,fused_moe_fp8,benchmark/test_fused_moe_fp8.py,,yes,fused_experts_impl -main,fused_moe_fp8_blockwise,fused_moe_fp8_blockwise,benchmark/test_fused_moe_fp8_blockwise.py,,yes,fused_experts_impl -main,fused_moe_int4_w4a16,fused_moe_int4_w4a16,benchmark/test_fused_moe_int4_w4a16.py,,yes,fused_experts_impl -main,fused_experts_impl_int8,fused_moe_int8,benchmark/test_fused_moe_int8.py,,yes,fused_experts_impl -main,fused_experts_impl_int8_w8a16,fused_moe_int8_w8a16,benchmark/test_fused_moe_int8_w8a16.py,,yes,fused_moe_int8_w8a16_gems_vs_bf16_deq -main,fused_moe_w8a16_mxq,fused_moe_w8a16,benchmark/test_fused_moe_w8a16.py,,yes,fused_moe -main,fused_moe_w8a16_mxq_gems_vs_vllm,fused_moe_w8a16,benchmark/test_fused_moe_w8a16.py,,yes,fused_moe -main,fused_rms_norm,fused_rms_norm,benchmark/test_fused_rms_norm.py,,yes,fused_rms_norm -main,gather,gather,benchmark/test_gather.py,,yes,gather -main,gather_backward,gather,benchmark/test_gather.py,,yes,gather_backward -main,gather_block_quantized,gather_block_quantized,benchmark/test_gather_block_quantized.py,,yes,gather_block_quantized -main,gcd,gcd,benchmark/test_gcd.py,,yes,gcd -main,gcd_out,gcd,benchmark/test_gcd.py,,yes,gcd_out -main,gcd_,gcd_,benchmark/test_gcd_.py,,yes,gcd_ -main,ge,ge,benchmark/test_ge.py,,yes,ge -main,ge_scalar,ge,benchmark/test_ge.py,,yes,ge_scalar -main,geglu,geglu,benchmark/test_geglu.py,,yes,geglu -main,gelu,gelu,benchmark/test_gelu.py,,yes,gelu -main,gelu_inplace,gelu,benchmark/test_gelu.py,,yes,gelu_ -main,gelu_backward,gelu,benchmark/test_gelu.py,,yes,gelu_backward -main,gelu_and_mul,gelu_and_mul,benchmark/test_gelu_and_mul.py,,yes,gelu_and_mul -main,geometric_inplace,geometric,benchmark/test_geometric.py,,yes,geometric_ -main,geometric,geometric,benchmark/test_geometric.py,,yes,geometric -main,get_paged_mqa_logits_metadata,get_paged_mql_logits_metadata,benchmark/test_get_paged_mql_logits_metadata.py,,yes,get_paged_mqa_logits_metadata -main,get_scheduler_metadata,get_scheduler_metadata,benchmark/test_get_scheduler_metadata.py,,yes,get_scheduler_metadata -main,glu,glu,benchmark/test_glu.py,,yes,glu -main,glu_backward,glu,benchmark/test_glu.py,,yes,glu_backward -main,greater,greater,benchmark/test_greater.py,,yes,greater -main,greater_out,greater,benchmark/test_greater.py,,yes,greater_out -main,greater_scalar,greater,benchmark/test_greater.py,,yes,greater_scalar -main,greater_scalar_out,greater,benchmark/test_greater.py,,yes,greater_scalar_out -main,greater_equal,greater_equal,benchmark/test_greater_equal.py,,yes,greater_equal -main,greater_equal_,greater_equal,benchmark/test_greater_equal.py,,yes,greater_equal_ -main,greater_equal_scalar,greater_equal,benchmark/test_greater_equal.py,,yes,greater_equal_scalar -main,grid_sample,grid_sample,benchmark/test_grid_sample.py,,yes,grid_sample -main,group_norm,group_norm,benchmark/test_group_norm.py,,yes,group_norm -main,grouped_mm,grouped_mm,benchmark/test_grouped_mm.py,,yes,grouped_mm -main,grouped_topk_no_renorm,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk -main,grouped_topk_score_0,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk -main,grouped_topk_score_1,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk -main,gt,gt,benchmark/test_gt.py,,yes,gt -main,gt_scalar,gt,benchmark/test_gt.py,,yes,gt_scalar -main,gt_scalar_,gt_scalar_,benchmark/test_gt_scalar_.py,,yes,gt_scalar_ -main,gt_tensor_,gt_tensor_,benchmark/test_gt_tensor_.py,,yes,gt_tensor_ -main,hadamard_transform,hadamard_transform,benchmark/test_hadamard_transform.py,,yes,hadamard_transform -main,hadamard_transform_mn,hadamard_transform,benchmark/test_hadamard_transform.py,,yes,hadamard_transform_mn -main,hardshrink,hardshrink,benchmark/test_hardshrink.py,,yes,hardshrink -main,hardshrink_out,hardshrink,benchmark/test_hardshrink.py,,yes,hardshrink_out -main,hardsigmoid_inplace,hardsigmoid,benchmark/test_hardsigmoid.py,,yes,hardsigmoid_ -main,hardsigmoid,hardsigmoid,benchmark/test_hardsigmoid.py,,yes,hardsigmoid -main,hardsigmoid_out,hardsigmoid,benchmark/test_hardsigmoid.py,,yes,hardsigmoid_out -main,hardswish_inplace,hardswish,benchmark/test_hardswish.py,,yes,hardswish_ -main,hardtanh_inplace,hardtanh_,benchmark/test_hardtanh_.py,,yes,hardtanh_ -main,has_compatible_shallow_copy_type,has_compatible_shallow_copy_type,benchmark/test_has_compatible_shallow_copy_type.py,,yes,has_compatible_shallow_copy_type -main,heaviside_,heaviside_,benchmark/test_heaviside_.py,,yes,heaviside_ -main,histc,histc,benchmark/test_histc.py,,yes,histc -main,hstack,hstack,benchmark/test_hstack.py,,yes,hstack -main,huber_loss,huber_loss,benchmark/test_huber_loss.py,,yes,huber_loss -main,hypot,hypot,benchmark/test_hypot.py,,yes,hypot -main,hypot_out,hypot,benchmark/test_hypot.py,,yes,hypot_out -main,hypot_,hypot_,benchmark/test_hypot_.py,,yes,hypot_ -main,i0,i0,benchmark/test_i0.py,,yes,i0 -main,i0_inplace,i0,benchmark/test_i0.py,,yes,i0_ -main,i0_out,i0,benchmark/test_i0.py,,yes,i0_out -main,igamma_,igamma_,benchmark/test_igamma_.py,,yes,igamma_ -main,igammac,igammac,benchmark/test_igammac.py,,yes,igammac -main,igammac_out,igammac,benchmark/test_igammac.py,,yes,igammac_out -main,igammac_,igammac_,benchmark/test_igammac_.py,,yes,igammac_ -main,ilshift,ilshift,benchmark/test_ilshift.py,,yes,ilshift -main,im2col,im2col,benchmark/test_im2col.py,,yes,im2col -main,index_acc_perf,index,benchmark/test_index.py,,yes,index -main,index_add,index_add,benchmark/test_index_add.py,,yes,index_add -main,index_add_,index_add,benchmark/test_index_add.py,,yes,index_add_ -main,index_copy,index_copy,benchmark/test_index_copy.py,,yes,index_copy -main,index_copy_,index_copy,benchmark/test_index_copy.py,,yes,index_copy_ -main,index_put_acc_false,index_put,benchmark/test_index_put.py,,yes,index_put -main,index_put__acc_false,index_put,benchmark/test_index_put.py,,yes,index_put_ -main,index_put_acc_true,index_put,benchmark/test_index_put.py,,yes,index_put -main,index_put__acc_true,index_put,benchmark/test_index_put.py,,yes,index_put_ -main,index_put_impl_acc_false,index_put_impl,benchmark/test_index_put_impl.py,,yes,index_put_impl -main,index_put_impl_acc_true,index_put_impl,benchmark/test_index_put_impl.py,,yes,index_put_impl -main,index_reduce_prod,index_reduce,benchmark/test_index_reduce.py,,yes, -main,index_reduce_mean,index_reduce,benchmark/test_index_reduce.py,,yes, -main,index_reduce_amax,index_reduce,benchmark/test_index_reduce.py,,yes, -main,index_reduce_amin,index_reduce,benchmark/test_index_reduce.py,,yes, -main,index_select,index_select,benchmark/test_index_select.py,,yes,index_select -main,index_select_backward,index_select_backward,benchmark/test_index_select_backward.py,,yes,index_select_backward -main,indexer_k_quant_and_cache_benchmark,indexer_k_quant_and_cache,benchmark/test_indexer_k_quant_and_cache.py,,yes, -main,inplace_fused_experts_gems_vs_vllm,inplace_fused_experts,benchmark/test_inplace_fused_experts.py,,yes,inplace_fused_experts -main,instance_norm,instance_norm,benchmark/test_instance_norm.py,,yes,instance_norm -main,irshift__,irshift,benchmark/test_irshift.py,,yes,irshift__ -main,is_all_true,is_all_true,benchmark/test_is_all_true.py,,yes,is_all_true -main,is_nonzero,is_nonzero,benchmark/test_is_nonzero.py,,yes,is_nonzero -main,isclose,isclose,benchmark/test_isclose.py,,yes,isclose -main,isfinite,isfinite,benchmark/test_isfinite.py,,yes,isfinite -main,isin,isin,benchmark/test_isin.py,,yes,isin -main,isin_scalar_tensor,isin,benchmark/test_isin.py,,yes,isin_scalar_tensor -main,isin_tensor_scalar,isin,benchmark/test_isin.py,,yes,isin_tensor_scalar -main,isinf,isinf,benchmark/test_isinf.py,,yes,isinf -main,isnan,isnan,benchmark/test_isnan.py,,yes,isnan -main,isneginf,isneginf,benchmark/test_isneginf.py,,yes,isneginf -main,isneginf_out,isneginf,benchmark/test_isneginf.py,yes,yes,isneginf_out -main,isposinf,isposinf,benchmark/test_isposinf.py,,yes,isposinf -main,jagged_to_padded_dense_forward,jagged_to_padded_dense_forward,benchmark/test_jagged_to_padded_dense_forward.py,,yes,jagged_to_padded_dense_forward -main,kron,kron,benchmark/test_kron.py,,yes,kron -main,kthvalue,kthvalue,benchmark/test_kthvalue.py,,yes,kthvalue -main,native_layer_norm,layer_norm,benchmark/test_layer_norm.py,,yes,native_layer_norm -main,layer_norm,layer_norm,benchmark/test_layer_norm.py,,yes,layer_norm -main,layer_norm_backward,layer_norm,benchmark/test_layer_norm.py,,yes,layer_norm_backward -main,lcm,lcm,benchmark/test_lcm.py,,yes,lcm -main,lcm_,lcm_,benchmark/test_lcm_.py,,yes,lcm_ -main,le,le,benchmark/test_le.py,,yes,le -main,le_scalar,le,benchmark/test_le.py,,yes,le_scalar -main,le_,le_,benchmark/test_le_.py,,yes,le_ -main,le_scalar_,le_,benchmark/test_le_.py,,yes,le_scalar_ -main,leaky_relu,leaky_relu,benchmark/test_leaky_relu.py,,yes,leaky_relu -main,leaky_relu_inplace,leaky_relu,benchmark/test_leaky_relu.py,,yes,leaky_relu_ -main,leaky_relu_out,leaky_relu,benchmark/test_leaky_relu.py,,yes,leaky_relu_out -main,lerp_tensor,lerp,benchmark/test_lerp.py,,yes,lerp_tensor -main,lerp_tensor_inplace,lerp,benchmark/test_lerp.py,,yes,lerp_tensor_ -main,lerp_scalar,lerp,benchmark/test_lerp.py,,yes,lerp_scalar -main,lerp_scalar_inplace,lerp,benchmark/test_lerp.py,,yes,lerp_scalar_ -main,less,less,benchmark/test_less.py,,yes,less -main,less_scalar,less,benchmark/test_less.py,,yes,less_scalar -main,less_,less_,benchmark/test_less_.py,,yes,less_ -main,less_scalar_,less_,benchmark/test_less_.py,,yes,less_scalar_ -main,less_equal,less_equal,benchmark/test_less_equal.py,,yes,less_equal -main,less_equal_scalar,less_equal,benchmark/test_less_equal.py,,yes,less_equal_scalar -main,less_equal_,less_equal_,benchmark/test_less_equal_.py,,yes,less_equal_ -main,less_equal_scalar_,less_equal_,benchmark/test_less_equal_.py,,yes,less_equal_scalar_ -main,lgamma,lgamma_,benchmark/test_lgamma_.py,,yes,lgamma -main,lgamma_,lgamma_,benchmark/test_lgamma_.py,,yes,lgamma_ -main,lift,lift,benchmark/test_lift.py,,yes,lift -main,lift_out,lift,benchmark/test_lift.py,,yes,lift_out -main,lift_fresh,lift_fresh,benchmark/test_lift_fresh.py,,yes,lift_fresh -main,lift_fresh_copy,lift_fresh_copy,benchmark/test_lift_fresh_copy.py,,yes,lift_fresh_copy -main,linalg_cholesky,linalg_cholesky,benchmark/test_linalg_cholesky.py,,yes,linalg_cholesky -main,linalg_eigvals,linalg_eigvals,benchmark/test_linalg_eigvals.py,,yes,linalg_eigvals -main,linalg_ldl_factor,linalg_ldl_factor,benchmark/test_linalg_ldl_factor.py,,yes,linalg_ldl_factor -main,linalg_ldl_factor_ex,linalg_ldl_factor_ex,benchmark/test_linalg_ldl_factor_ex.py,,yes,linalg_ldl_factor_ex -main,linalg_ldl_solve,linalg_ldl_solve,benchmark/test_linalg_ldl_solve.py,,yes,linalg_ldl_solve -main,linalg_lstsq,linalg_lstsq,benchmark/test_linalg_lstsq.py,,yes,linalg_lstsq -main,linalg_lu_factor,linalg_lu_factor,benchmark/test_linalg_lu_factor.py,,yes,linalg_lu_factor -main,linalg_lu_factor_out,linalg_lu_factor,benchmark/test_linalg_lu_factor.py,,yes,linalg_lu_factor_out -main,linalg_lu_factor_ex,linalg_lu_factor_ex,benchmark/test_linalg_lu_factor_ex.py,,yes,linalg_lu_factor_ex -main,linalg_lu_factor_ex_out,linalg_lu_factor_ex,benchmark/test_linalg_lu_factor_ex.py,,yes,linalg_lu_factor_ex_out -main,linalg_slogdet,linalg_slogdet,benchmark/test_linalg_slogdet.py,,yes,linalg_slogdet -main,linalg_svdvals,linalg_svdvals,benchmark/test_linalg_svdvals.py,,yes,linalg_svdvals -main,linear,linear,benchmark/test_linear.py,,yes,linear -main,linear_backward,linear_backward,benchmark/test_linear_backward.py,,yes,linear_backward -main,linspace,linspace,benchmark/test_linspace.py,,yes,linspace -main,log,log,benchmark/test_log.py,,yes,log -main,log10,log10,benchmark/test_log10.py,,yes,log10 -main,log10_inplace,log10,benchmark/test_log10.py,,yes,log10_ -main,log10_out,log10,benchmark/test_log10.py,,yes,log10_out -main,log1p,log1p,benchmark/test_log1p.py,,yes,log1p -main,log1p_inplace,log1p,benchmark/test_log1p.py,,yes,log1p_ -main,log2,log2,benchmark/test_log2.py,,yes,log2 -main,log2_,log2,benchmark/test_log2.py,,yes,log2_ -main,log_inplace,log_,benchmark/test_log_.py,,yes,log_ -main,log_normal_,log_normal_,benchmark/test_log_normal_.py,,yes,log_normal_ -main,log_sigmoid,log_sigmoid,benchmark/test_log_sigmoid.py,,yes,log_sigmoid -main,log_sigmoid_forward,log_sigmoid_forward,benchmark/test_log_sigmoid_forward.py,,yes,log_sigmoid_forward -main,log_softmax,log_softmax,benchmark/test_log_softmax.py,,yes,log_softmax -main,log_softmax_out,log_softmax,benchmark/test_log_softmax.py,,yes,log_softmax_out -main,log_softmax_backward_data,log_softmax,benchmark/test_log_softmax.py,,yes,log_softmax_backward_data -main,log_softmax_backward_data_out,log_softmax,benchmark/test_log_softmax.py,,yes,log_softmax_backward_data_out -main,logaddexp,logaddexp,benchmark/test_logaddexp.py,,yes,logaddexp -main,logaddexp_out,logaddexp,benchmark/test_logaddexp.py,,yes,logaddexp_out -main,logaddexp2,logaddexp2,benchmark/test_logaddexp2.py,,yes,logaddexp2 -main,logaddexp2_out,logaddexp2,benchmark/test_logaddexp2.py,,yes,logaddexp2_out -main,logcumsumexp,logcumsumexp,benchmark/test_logcumsumexp.py,,yes,logcumsumexp -main,logcumsumexp_out,logcumsumexp,benchmark/test_logcumsumexp.py,,yes,logcumsumexp_out -main,logical_and,logical_and,benchmark/test_logical_and.py,,yes,logical_and -main,logical_and_inplace,logical_and,benchmark/test_logical_and.py,,yes,logical_and_ -main,logical_not,logical_not,benchmark/test_logical_not.py,,yes,logical_not -main,logical_not_,logical_not,benchmark/test_logical_not.py,,yes,logical_not_ -main,logical_or,logical_or,benchmark/test_logical_or.py,,yes,logical_or -main,logical_or_inplace,logical_or,benchmark/test_logical_or.py,,yes,logical_or_ -main,logical_xor,logical_xor,benchmark/test_logical_xor.py,,yes,logical_xor -main,logical_xor_,logical_xor_,benchmark/test_logical_xor_.py,,yes,logical_xor_ -main,logit,logit,benchmark/test_logit.py,,yes,logit -main,logit_inplace,logit,benchmark/test_logit.py,,yes,logit_ -main,logit_out,logit,benchmark/test_logit.py,,yes,logit_out -main,logspace,logspace,benchmark/test_logspace.py,,yes,logspace -main,logsumexp,logsumexp,benchmark/test_logsumexp.py,,yes,logsumexp -main,lshift,lshift,benchmark/test_lshift.py,,yes,lshift -main,lstm,lstm,benchmark/test_lstm.py,,yes,lstm -main,lt,lt,benchmark/test_lt.py,,yes,lt -main,lt_scalar,lt,benchmark/test_lt.py,,yes,lt_scalar -main,lt_,lt_,benchmark/test_lt_.py,,yes,lt_ -main,lt_scalar_,lt_,benchmark/test_lt_.py,,yes,lt_scalar_ -main,lu_unpack,lu_unpack,benchmark/test_lu_unpack.py,,yes,lu_unpack -main,make_dep_token,make_dep_token,benchmark/test_make_dep_token.py,,yes,make_dep_token -main,margin_ranking_loss,margin_ranking_loss,benchmark/test_margin_ranking_loss.py,,yes,margin_ranking_loss -main,margin_ranking_loss_backward,margin_ranking_loss,benchmark/test_margin_ranking_loss.py,,yes,margin_ranking_loss -main,masked_fill,masked_fill,benchmark/test_masked_fill.py,,yes,masked_fill -main,masked_fill_inplace,masked_fill,benchmark/test_masked_fill.py,,yes,masked_fill_ -main,masked_fill_scalar,masked_fill,benchmark/test_masked_fill.py,,yes,masked_fill_scalar -main,masked_fill_scalar_inplace,masked_fill,benchmark/test_masked_fill.py,,yes,masked_fill_scalar_ -main,masked_scale,masked_scale,benchmark/test_masked_scale.py,,yes,masked_scale -main,masked_scatter,masked_scatter,benchmark/test_masked_scatter.py,,yes,masked_scatter -main,masked_scatter_inplace,masked_scatter,benchmark/test_masked_scatter.py,,yes,masked_scatter_ -main,masked_select,masked_select,benchmark/test_masked_select.py,,yes,masked_select -main,matmul_bias_activation,matmul_bias_activation,benchmark/test_matmul_bias_activation.py,,yes,matmul_bias_activation -main,matmuladd,matmuladd,benchmark/test_matmuladd.py,,yes,matmuladd -main,max,max,benchmark/test_max.py,,yes,max -main,max_dim,max,benchmark/test_max.py,,yes,max_dim -main,max_pool2d_with_indices,max_pool2d,benchmark/test_max_pool2d.py,,yes,max_pool2d_with_indices -main,max_pool2d_backward,max_pool2d,benchmark/test_max_pool2d.py,,yes,max_pool2d_backward -main,max_pool2d_with_indices_backward,max_pool2d,benchmark/test_max_pool2d.py,,yes,max_pool2d_with_indices_backward -main,perf_max_pool3d,max_pool3d,benchmark/test_max_pool3d.py,,yes,max_pool3d -main,perf_max_pool3d_backward,max_pool3d,benchmark/test_max_pool3d.py,,yes,max_pool3d_backward -main,max_unpool2d,max_unpool2d,benchmark/test_max_unpool2d.py,,yes,max_unpool2d -main,max_unpool3d,max_unpool3d,benchmark/test_max_unpool3d.py,,yes,max_unpool3d -main,maximum,maximum,benchmark/test_maximum.py,,yes,maximum -main,mean,mean,benchmark/test_mean.py,,yes,mean -main,mean_dim,mean,benchmark/test_mean.py,,yes,mean_dim -main,median,median,benchmark/test_median.py,,yes,median -main,median_dim,median,benchmark/test_median.py,,yes,median_dim -main,mhc_post,mhc,benchmark/test_mhc.py,,yes,mhc_post -main,mhc_pre,mhc,benchmark/test_mhc.py,,yes,mhc_pre -main,hc_split_sinkhorn_forward,mhc,benchmark/test_mhc.py,,yes,hc_split_sinkhorn_forward -main,mhc_bwd,mhc,benchmark/test_mhc.py,,yes,mhc_bwd -main,hc_head_fused_kernel,mhc,benchmark/test_mhc.py,,yes,hc_head_fused_kernel -main,min,min,benchmark/test_min.py,,yes,min -main,min_dim,min,benchmark/test_min.py,,yes,min_dim -main,minimum,minimum,benchmark/test_minimum.py,,yes,minimum -main,miopen_batch_norm_backward,miopen_batch_norm_backward,benchmark/test_miopen_batch_norm_backward.py,,yes,miopen_batch_norm_backward -main,mish,mish,benchmark/test_mish.py,,yes,mish -main,mish_inplace,mish,benchmark/test_mish.py,,yes,mish_ -main,mish_backward,mish,benchmark/test_mish.py,,yes,mish_backward -main,mm,mm,benchmark/test_mm.py,,yes,mm -main,mm_self_transpose_benchmark,mm,benchmark/test_mm.py,,yes,mm_self_transpose -main,mm_out,mm,benchmark/test_mm.py,,yes,mm_out -main,perf_mode,mode,benchmark/test_mode.py,,yes,mode -main,moe_align_block_size_triton,moe_align_block_size_triton,benchmark/test_moe_align_block_size_triton.py,,yes,moe_align_block_size_triton -main,moe_align_block_size_fast_paths,moe_align_block_size_triton,benchmark/test_moe_align_block_size_triton.py,,yes,moe_align_block_size_fast_paths -main,moe_sum,moe_sum,benchmark/test_moe_sum.py,,yes,moe_sum -main,mrope_gems_vs_torch,mrope,benchmark/test_mrope.py,,yes,mrope -main,mse_loss,mse_loss,benchmark/test_mse_loss.py,,yes,mse_loss -main,mse_loss_backward,mse_loss_backward,benchmark/test_mse_loss_backward.py,,yes,mse_loss_backward -main,mul,mul,benchmark/test_mul.py,,yes,mul -main,mul_inplace,mul,benchmark/test_mul.py,,yes,mul_ -main,multinomial_with_replacement,multinomial,benchmark/test_multinomial.py,,yes,multinomial -main,multiply,multiply,benchmark/test_multiply.py,,yes,multiply -main,multiply_,multiply_,benchmark/test_multiply_.py,,yes,multiply_ -main,mv,mv,benchmark/test_mv.py,,yes,mv -main,mvlgamma,mvlgamma,benchmark/test_mvlgamma.py,,yes,mvlgamma -main,mvlgamma_,mvlgamma_,benchmark/test_mvlgamma_.py,,yes,mvlgamma_ -main,nan_to_num,nan_to_num,benchmark/test_nan_to_num.py,,yes,nan_to_num -main,nan_to_num_,nan_to_num_,benchmark/test_nan_to_num_.py,,yes,nan_to_num_ -main,nanmedian,nanmedian,benchmark/test_nanmedian.py,,yes,nanmedian -main,nanmedian_out,nanmedian,benchmark/test_nanmedian.py,,yes,nanmedian_out -main,nanmedian_dim,nanmedian,benchmark/test_nanmedian.py,,yes,nanmedian_dim -main,nanmedian_dim_values,nanmedian,benchmark/test_nanmedian.py,,yes,nanmedian_dim_values -main,benchmark_nansum,nansum,benchmark/test_nansum.py,,yes,nansum -main,narrow,narrow,benchmark/test_narrow.py,,yes,narrow -main,narrow_copy_perf,narrow_copy,benchmark/test_narrow_copy.py,,yes,narrow_copy -main,native_batch_norm_legit_functional,native_batch_norm_legit_functional,benchmark/test_native_batch_norm_legit_functional.py,,yes,native_batch_norm_legit_functional -main,ne,ne,benchmark/test_ne.py,,yes,ne -main,ne_scalar,ne,benchmark/test_ne.py,,yes,ne_scalar -main,ne_,ne_,benchmark/test_ne_.py,,yes,ne_ -main,ne_scalar_,ne_,benchmark/test_ne_.py,,yes,ne_scalar_ -main,neg,neg,benchmark/test_neg.py,,yes,neg -main,neg_inplace,neg,benchmark/test_neg.py,,yes,neg_ -main,negative,negative,benchmark/test_negative.py,,yes,negative -main,negative_,negative_,benchmark/test_negative_.py,,yes,negative_ -main,nested_view_from_buffer_copy,nested_view_from_buffer_copy,benchmark/test_nested_view_from_buffer_copy.py,,yes,nested_view_from_buffer_copy -main,new_full,new_full,benchmark/test_new_full.py,,yes,new_full -main,new_ones,new_ones,benchmark/test_new_ones.py,,yes,new_ones -main,nextafter,nextafter,benchmark/test_nextafter.py,,yes,nextafter -main,nextafter_,nextafter,benchmark/test_nextafter.py,,yes,nextafter_ -main,nextafter_,nextafter_,benchmark/test_nextafter_.py,,yes,nextafter_ -main,nll_loss_forward,nll_loss,benchmark/test_nll_loss.py,,yes,nll_loss_forward -main,nll_loss_backward,nll_loss,benchmark/test_nll_loss.py,,yes,nll_loss_backward -main,nll_loss2d_forward,nll_loss2d,benchmark/test_nll_loss2d.py,,yes,nll_loss2d_forward -main,nll_loss2d_backward,nll_loss2d,benchmark/test_nll_loss2d.py,,yes,nll_loss2d_backward -main,nll_loss_nd_forward,nll_loss_nd,benchmark/test_nll_loss_nd.py,,yes,nll_loss_nd_forward -main,nll_loss_nd_backward,nll_loss_nd,benchmark/test_nll_loss_nd.py,,yes,nll_loss_nd_backward -main,nonzero,nonzero,benchmark/test_nonzero.py,,yes,nonzero -main,nonzero_numpy,nonzero_numpy,benchmark/test_nonzero_numpy.py,,yes,nonzero_numpy -main,perf_nonzero_static,nonzero_static,benchmark/test_nonzero_static.py,,yes,nonzero_static -main,norm,norm,benchmark/test_norm.py,,yes,norm -main,norm_scalar,norm,benchmark/test_norm.py,,yes,norm_scalar -main,norm_scalaropt_dim,norm,benchmark/test_norm.py,,yes,norm_scalaropt_dim -main,normal_tensor_tensor,normal,benchmark/test_normal.py,,yes,normal_tensor_tensor -main,normal_tensor_float,normal,benchmark/test_normal.py,,yes,normal_tensor_float -main,normal_inplace,normal,benchmark/test_normal.py,,yes,normal_float_float_ -main,normal_float_tensor,normal,benchmark/test_normal.py,,yes,normal_float_tensor -main,normed_cumsum,normed_cumsum,benchmark/test_normed_cumsum.py,,yes,normed_cumsum -main,not_equal,not_equal,benchmark/test_not_equal.py,,yes,not_equal -main,not_equal_scalar,not_equal,benchmark/test_not_equal.py,,yes,not_equal_scalar -main,not_equal_,not_equal_,benchmark/test_not_equal_.py,,yes,not_equal_ -main,not_equal_scalar_,not_equal_,benchmark/test_not_equal_.py,,yes,not_equal_scalar_ -main,one_hot,one_hot,benchmark/test_one_hot.py,,yes,one_hot -main,ones,ones,benchmark/test_ones.py,,yes,ones -main,ones_like,ones_like,benchmark/test_ones_like.py,,yes,ones_like -main,outer,outer,benchmark/test_outer.py,,yes,outer -main,outplace_fused_experts_gems_vs_vllm,outplace_fused_experts,benchmark/test_outplace_fused_experts.py,,yes,outplace_fused_experts -main,pack_seq,pack_seq,benchmark/test_pack_seq.py,,yes,pack_seq_triton -main,pack_seq_fp8,pack_seq,benchmark/test_pack_seq.py,,yes,pack_seq_triton -main,pad,pad,benchmark/test_pad.py,,yes,pad -main,pairwise_distance,pairwise_distance,benchmark/test_pairwise_distance.py,,yes,pairwise_distance -main,pdist,pdist,benchmark/test_pdist.py,,yes,pdist -main,pdist_backward,pdist_backward,benchmark/test_pdist_backward.py,,yes,pdist_backward -main,pdist_forward,pdist_forward_perf,benchmark/test_pdist_forward_perf.py,,yes,pdist_forward -main,per_token_group_quant_fp8,per_token_group_quant_fp8,benchmark/test_per_token_group_quant_fp8.py,,yes,per_token_group_quant_fp8 -main,permute_copy,permute_copy,benchmark/test_permute_copy.py,,yes,permute_copy -main,pixel_shuffle,pixel_shuffle,benchmark/test_pixel_shuffle.py,,yes,pixel_shuffle -main,pixel_shuffle_out,pixel_shuffle,benchmark/test_pixel_shuffle.py,,yes,pixel_shuffle_out -main,pixel_unshuffle,pixel_unshuffle,benchmark/test_pixel_unshuffle.py,,yes,pixel_unshuffle -main,pixel_unshuffle_out,pixel_unshuffle,benchmark/test_pixel_unshuffle.py,,yes,pixel_unshuffle_out -main,poisson,poisson,benchmark/test_poisson.py,,yes,poisson -main,polar,polar,benchmark/test_polar.py,,yes,polar -main,polygamma,polygamma,benchmark/test_polygamma.py,,yes,polygamma -main,polygamma_inplace,polygamma,benchmark/test_polygamma.py,,yes,polygamma_ -main,polygamma_out,polygamma,benchmark/test_polygamma.py,,yes,polygamma_out -main,pow_tensor_tensor,pow,benchmark/test_pow.py,,yes,pow_tensor_tensor -main,pow_inplace,pow,benchmark/test_pow.py,,yes,pow_tensor_tensor_ -main,pow_scalar,pow,benchmark/test_pow.py,,yes,pow_scalar -main,pow_tensor_scalar,pow,benchmark/test_pow.py,,yes,pow_tensor_scalar -main,pow_tensor_scalar_inplace,pow,benchmark/test_pow.py,,yes,pow_tensor_scalar_ -main,prelu,prelu,benchmark/test_prelu.py,,yes,prelu -main,prelu_kernel,prelu_kernel,benchmark/test_prelu_kernel.py,,yes,prelu_kernel -main,prelu_kernel_backward,prelu_kernel_backward,benchmark/test_prelu_kernel_backward.py,,yes,prelu_kernel_backward -main,prod,prod,benchmark/test_prod.py,,yes,prod -main,quantile,quantile,benchmark/test_quantile.py,,yes,quantile -main,rad2deg,rad2deg,benchmark/test_rad2deg.py,,yes,rad2deg -main,rad2deg_,rad2deg,benchmark/test_rad2deg.py,,yes,rad2deg_ -main,rand,rand,benchmark/test_rand.py,,yes,rand -main,rand_like,rand_like,benchmark/test_rand_like.py,,yes,rand_like -main,randint,randint,benchmark/test_randint.py,,yes,randint -main,randint_like,randint_like,benchmark/test_randint_like.py,,yes,randint_like -main,randn,randn,benchmark/test_randn.py,,yes,randn -main,randn_like,randn_like,benchmark/test_randn_like.py,,yes,randn_like -main,randperm,randperm,benchmark/test_randperm.py,,yes,randperm -main,range,range,benchmark/test_range.py,,yes,range -main,reciprocal,reciprocal,benchmark/test_reciprocal.py,,yes,reciprocal -main,reciprocal_inplace,reciprocal,benchmark/test_reciprocal.py,,yes,reciprocal_ -main,reflection_pad1d,reflection_pad1d,benchmark/test_reflection_pad1d.py,,yes,reflection_pad1d -main,reflection_pad1d_out,reflection_pad1d,benchmark/test_reflection_pad1d.py,,yes,reflection_pad1d_out -main,reflection_pad1d_backward,reflection_pad1d_backward,benchmark/test_reflection_pad1d_backward.py,,yes,reflection_pad1d_backward -main,reflection_pad2d,reflection_pad2d,benchmark/test_reflection_pad2d.py,,yes,reflection_pad2d -main,reflection_pad2d_out,reflection_pad2d,benchmark/test_reflection_pad2d.py,,yes,reflection_pad2d_out -main,reflection_pad2d_backward,reflection_pad2d_backward,benchmark/test_reflection_pad2d_backward.py,,yes,reflection_pad2d_backward -main,reflection_pad3d,reflection_pad3d,benchmark/test_reflection_pad3d.py,,yes,reflection_pad3d -main,reflection_pad3d_out,reflection_pad3d,benchmark/test_reflection_pad3d.py,,yes,reflection_pad3d_out -main,reflection_pad3d_backward,reflection_pad3d_backward,benchmark/test_reflection_pad3d_backward.py,,yes,reflection_pad3d_backward -main,reglu,reglu,benchmark/test_reglu.py,,yes,reglu -main,relu,relu,benchmark/test_relu.py,,yes,relu -main,relu_inplace,relu,benchmark/test_relu.py,,yes,relu_ -main,relu6,relu6,benchmark/test_relu6.py,,yes,relu6 -main,remainder,remainder,benchmark/test_remainder.py,,yes,remainder -main,remainder_tensor,remainder,benchmark/test_remainder.py,,yes,remainder_tensor -main,remainder_tensor_inplace,remainder,benchmark/test_remainder.py,,yes,remainder_tensor_ -main,remainder_scalar,remainder,benchmark/test_remainder.py,,yes,remainder_scalar -main,remainder_scalar_inplace,remainder,benchmark/test_remainder.py,,yes,remainder_scalar_ -main,remainder_scalar_tensor,remainder,benchmark/test_remainder.py,,yes,remainder_scalar_tensor -main,renorm,renorm,benchmark/test_renorm.py,,yes,renorm -main,renorm_,renorm_,benchmark/test_renorm_.py,,yes,renorm_ -main,repeat,repeat,benchmark/test_repeat.py,,yes,repeat -main,repeat_interleave_self_int,repeat_interleave,benchmark/test_repeat_interleave.py,,yes,repeat_interleave_self_int -main,repeat_interleave_self_tensor,repeat_interleave,benchmark/test_repeat_interleave.py,,yes,repeat_interleave_self_tensor -main,repeat_interleave_tensor,repeat_interleave,benchmark/test_repeat_interleave.py,,yes,repeat_interleave_tensor -main,replication_pad1d,replication_pad1d,benchmark/test_replication_pad1d.py,,yes,replication_pad1d -main,replication_pad2d,replication_pad2d,benchmark/test_replication_pad2d.py,,yes,replication_pad2d -main,replication_pad2d_out,replication_pad2d,benchmark/test_replication_pad2d.py,,yes,replication_pad2d_out -main,replication_pad2d_backward,replication_pad2d_backward,benchmark/test_replication_pad2d_backward.py,,yes,replication_pad2d_backward -main,replication_pad3d,replication_pad3d,benchmark/test_replication_pad3d.py,,yes,replication_pad3d -main,replication_pad3d_backward,replication_pad3d_backward,benchmark/test_replication_pad3d_backward.py,,yes,replication_pad3d_backward -main,reshape_and_cache,reshape_and_cache,benchmark/test_reshape_and_cache.py,,yes,reshape_and_cache -main,reshape_and_cache_flash,reshape_and_cache_flash,benchmark/test_reshape_and_cache_flash.py,,yes,reshape_and_cache_flash -main,resize,resize,benchmark/test_resize.py,,yes,resize -main,resize_,resize,benchmark/test_resize.py,,yes,resize_ -main,resize_as,resize_as,benchmark/test_resize_as.py,,yes,resize_as -main,resize_as_,resize_as,benchmark/test_resize_as.py,,yes,resize_as_ -main,resize_output,resize_output,benchmark/test_resize_output.py,,yes,resize_output -main,resolve_conj,resolve_conj,benchmark/test_resolve_conj.py,,yes,resolve_conj -main,resolve_neg,resolve_neg,benchmark/test_resolve_neg.py,,yes,resolve_neg -main,rms_norm,rms_norm,benchmark/test_rms_norm.py,,yes,rms_norm -main,rnn_relu,rnn_relu,benchmark/test_rnn_relu.py,,yes,rnn_relu -main,roll,roll,benchmark/test_roll.py,,yes,roll -main,rot90,rot90,benchmark/test_rot90.py,,yes,rot90 -main,round,round,benchmark/test_round.py,,yes,round -main,round_inplace,round,benchmark/test_round.py,,yes,round_ -main,round_out,round,benchmark/test_round.py,,yes,round_out -main,perf_router_gemm,router_gemm,benchmark/test_router_gemm.py,,yes,router_gemm -main,rrelu_with_noise_backward,rrelu_with_noise_backward,benchmark/test_rrelu_with_noise_backward.py,,yes,rrelu_with_noise_backward -main,rrelu_with_noise_functional,rrelu_with_noise_functional,benchmark/test_rrelu_with_noise_functional.py,,yes,rrelu_with_noise_functional -main,rsqrt,rsqrt,benchmark/test_rsqrt.py,,yes,rsqrt -main,rsqrt_inplace,rsqrt,benchmark/test_rsqrt.py,,yes,rsqrt_ -main,rsub_tensor,rsub,benchmark/test_rsub.py,,yes,rsub_tensor -main,rsub_scalar,rsub,benchmark/test_rsub.py,,yes,rsub_scalar -main,rwkv_ka_fusion,rwkv_ka_fusion,benchmark/test_rwkv_ka_fusion.py,,yes,rwkv_ka_fusion -main,rwkv_mm_sparsity,rwkv_mm_sparsity,benchmark/test_rwkv_mm_sparsity.py,,yes,rwkv_mm_sparsity -main,safe_softmax,safe_softmax,benchmark/test_safe_softmax.py,,yes,safe_softmax -main,scalar_tensor,scalar_tensor,benchmark/test_scalar_tensor.py,,yes,scalar_tensor -main,scaled_dot_product_flash_attention,scaled_dot_product_attention,benchmark/test_scaled_dot_product_attention.py,,yes,scaled_dot_product_flash_attention -main,scaled_dot_product_attention,scaled_dot_product_attention,benchmark/test_scaled_dot_product_attention.py,,yes,scaled_dot_product_attention -main,scaled_dot_product_fused_attention_overrideable,scaled_dot_product_fused_attention_overrideable,benchmark/test_scaled_dot_product_fused_attention_overrideable.py,,yes,scaled_dot_product_fused_attention_overrideable -main,scaled_grouped_mm_benchmark,scaled_grouped_mm,benchmark/test_scaled_grouped_mm.py,,yes, -main,scaled_mm_benchmark,scaled_mm,benchmark/test_scaled_mm.py,,yes,scaled_mm -main,scaled_mm_out_benchmark,scaled_mm,benchmark/test_scaled_mm.py,,yes,scaled_mm_out -main,scaled_softmax_forward,scaled_softmax,benchmark/test_scaled_softmax.py,,yes,scaled_softmax_forward -main,perf_scaled_softmax_backward,scaled_softmax,benchmark/test_scaled_softmax.py,,yes,scaled_softmax_backward -main,scatter_add_inplace,scatter_add,benchmark/test_scatter_add.py,,yes,scatter_add_ -main,scatter_add,scatter_add,benchmark/test_scatter_add.py,,yes,scatter_add -main,scatter_reduce_add,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce -main,scatter_reduce_multiply,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce -main,scatter_reduce_add_inplace,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce_ -main,scatter_reduce_multiply_inplace,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce_ -main,scatter_reduce_two_sum,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce.two -main,scatter_reduce_two_amax,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce.two -main,scatter_reduce_two_inplace_sum,scatter_reduce_two,benchmark/test_scatter_reduce_two.py,,yes,scatter_reduce_ -main,scatter_reduce_two_inplace_amax,scatter_reduce_two,benchmark/test_scatter_reduce_two.py,,yes,scatter_reduce_ -main,scatter_reduce_two_inplace_amin,scatter_reduce_two,benchmark/test_scatter_reduce_two.py,,yes,scatter_reduce_ -main,scatter_reduce_two_inplace_mean,scatter_reduce_two,benchmark/test_scatter_reduce_two.py,,yes,scatter_reduce_ -main,scatter_src,scatter_src,benchmark/test_scatter_src.py,,yes,scatter_src -main,scatter_src_inplace,scatter_src,benchmark/test_scatter_src.py,,yes,scatter_src_ -main,searchsorted,searchsorted,benchmark/test_searchsorted.py,,yes,searchsorted -main,searchsorted_scalar,searchsorted,benchmark/test_searchsorted.py,,yes,searchsorted_scalar -main,searchsorted_out,searchsorted,benchmark/test_searchsorted.py,,yes,searchsorted_out -main,searchsorted_scalar_out,searchsorted,benchmark/test_searchsorted.py,,yes,searchsorted_scalar_out -main,segment_reduce,segment_reduce,benchmark/test_segment_reduce.py,,yes,segment_reduce -main,segment_reduce_out,segment_reduce,benchmark/test_segment_reduce.py,,yes,segment_reduce_out -main,segment_reduce_backward,segment_reduce,benchmark/test_segment_reduce.py,,yes,segment_reduce_backward -main,segment_reduce_backward_out,segment_reduce,benchmark/test_segment_reduce.py,,yes,segment_reduce_backward_out -main,select_backward,select_backward,benchmark/test_select_backward.py,,yes,select_backward -main,select_scatter,select_scatter,benchmark/test_select_scatter.py,,yes,select_scatter -main,selu,selu,benchmark/test_selu.py,,yes,selu -main,selu_inplace,selu,benchmark/test_selu.py,,yes,selu_ -main,sgn,sgn,benchmark/test_sgn.py,,yes,sgn -main,sgn_inplace,sgn,benchmark/test_sgn.py,,yes,sgn_ -main,sgn_out,sgn,benchmark/test_sgn.py,,yes,sgn_out -main,sigmoid,sigmoid,benchmark/test_sigmoid.py,,yes,sigmoid -main,sigmoid_inplace,sigmoid,benchmark/test_sigmoid.py,,yes,sigmoid_ -main,sigmoid_backward,sigmoid,benchmark/test_sigmoid.py,,yes,sigmoid_backward -main,sign,sign,benchmark/test_sign.py,,yes,sign -main,sign_out,sign,benchmark/test_sign.py,,yes,sign_out -main,signbit,signbit,benchmark/test_signbit.py,,yes,signbit -main,signbit_out,signbit,benchmark/test_signbit.py,yes,yes,signbit_out -main,silu,silu,benchmark/test_silu.py,,yes,silu -main,silu_inplace,silu,benchmark/test_silu.py,,yes,silu_ -main,silu_backward,silu,benchmark/test_silu.py,,yes,silu_backward -main,silu_and_mul,silu_and_mul,benchmark/test_silu_and_mul.py,,yes,silu_and_mul -main,silu_and_mul_out,silu_and_mul,benchmark/test_silu_and_mul.py,,yes,silu_and_mul_out -main,silu_and_mul_with_clamp,silu_and_mul_with_clamp,benchmark/test_silu_and_mul_with_clamp.py,,yes,silu_and_mul_with_clamp -main,silu_and_mul_with_clamp_out,silu_and_mul_with_clamp,benchmark/test_silu_and_mul_with_clamp.py,,yes,silu_and_mul_with_clamp_out -main,sin,sin,benchmark/test_sin.py,,yes,sin -main,sin_inplace,sin,benchmark/test_sin.py,,yes,sin_ -main,sinc,sinc,benchmark/test_sinc.py,,yes,sinc -main,sinc_,sinc,benchmark/test_sinc.py,,yes,sinc_ -main,sinh,sinh,benchmark/test_sinh.py,,yes,sinh -main,sinh_inplace,sinh,benchmark/test_sinh.py,,yes,sinh_ -main,skip_layernorm,skip_layer_norm,benchmark/test_skip_layer_norm.py,,yes,skip_layer_norm -main,slice_backward,slice_backward,benchmark/test_slice_backward.py,,yes,slice_backward -main,slice_scatter,slice_scatter,benchmark/test_slice_scatter.py,,yes,slice_scatter -main,smooth_l1_loss,smooth_l1_loss,benchmark/test_smooth_l1_loss.py,,yes,smooth_l1_loss -main,smooth_l1_loss_backward,smooth_l1_loss,benchmark/test_smooth_l1_loss.py,,yes,smooth_l1_loss_backward -main,soft_margin_loss,soft_margin_loss,benchmark/test_soft_margin_loss.py,,yes,soft_margin_loss -main,soft_margin_loss_backward,soft_margin_loss_backward,benchmark/test_soft_margin_loss_backward.py,,yes,soft_margin_loss_backward -main,softmax,softmax,benchmark/test_softmax.py,,yes,softmax -main,softmax_backward,softmax,benchmark/test_softmax.py,,yes,softmax -main,softmax_backward_out,softmax,benchmark/test_softmax.py,,yes,softmax_backward_out -main,softmax_out,softmax,benchmark/test_softmax.py,,yes,softmax_out -main,softplus,softplus,benchmark/test_softplus.py,,yes,softplus -main,softplus_backward,softplus,benchmark/test_softplus.py,,yes,softplus_backward -main,softshrink,softshrink,benchmark/test_softshrink.py,,yes,softshrink -main,softshrink_out,softshrink,benchmark/test_softshrink.py,,yes,softshrink_out -main,perf_sort,sort,benchmark/test_sort.py,,yes,sort -main,perf_sort_stable,sort,benchmark/test_sort.py,,yes,sort_stable -main,sparse_attn_triton,sparse_attention,benchmark/test_sparse_attention.py,,yes,sparse_attention -main,sparse_mla_fwd_interface,sparse_mla_fwd_interface,benchmark/test_sparse_mla_fwd_interface.py,,yes,sparse_mla_fwd_interface -main,sparse_semi_structured_mm,sparse_semi_structured_mm,benchmark/test_sparse_semi_structured_mm.py,,yes,sparse_semi_structured_mm -main,special_airy_ai,special_airy_ai,benchmark/test_special_airy_ai.py,,yes,special_airy_ai -main,special_airy_ai_out,special_airy_ai,benchmark/test_special_airy_ai.py,,yes,special_airy_ai_out -main,special_bessel_j0,special_bessel_j0,benchmark/test_special_bessel_j0.py,,yes,special_bessel_j0 -main,special_bessel_j1,special_bessel_j1,benchmark/test_special_bessel_j1.py,,yes,special_bessel_j1 -main,special_chebyshev_polynomial_u,special_chebyshev_polynomial_u,benchmark/test_special_chebyshev_polynomial_u.py,,yes,special_chebyshev_polynomial_u -main,special_chebyshev_polynomial_v,special_chebyshev_polynomial_v,benchmark/test_special_chebyshev_polynomial_v.py,,yes,special_chebyshev_polynomial_v -main,special_chebyshev_polynomial_w,special_chebyshev_polynomial_w,benchmark/test_special_chebyshev_polynomial_w.py,,yes,special_chebyshev_polynomial_w -main,special_chebyshev_polynomial_w_out,special_chebyshev_polynomial_w,benchmark/test_special_chebyshev_polynomial_w.py,,yes,special_chebyshev_polynomial_w_out -main,special_digamma,special_digamma,benchmark/test_special_digamma.py,,yes,special_digamma -main,special_erfc,special_erfc,benchmark/test_special_erfc.py,,yes,special_erfc -main,erfc,special_erfc,benchmark/test_special_erfc.py,,yes,erfc -main,erfc_,special_erfc,benchmark/test_special_erfc.py,,yes,erfc_ -main,special_erfcx,special_erfcx,benchmark/test_special_erfcx.py,,yes,special_erfcx -main,special_erfinv,special_erfinv,benchmark/test_special_erfinv.py,,yes,special_erfinv -main,special_erfinv_out,special_erfinv,benchmark/test_special_erfinv.py,,yes,special_erfinv_out -main,special_gammainc,special_gammainc,benchmark/test_special_gammainc.py,,yes,special_gammainc -main,special_gammaln,special_gammaln,benchmark/test_special_gammaln.py,,yes,special_gammaln -main,special_gammaln_out,special_gammaln,benchmark/test_special_gammaln.py,,yes,special_gammaln_out -main,special_hermite_polynomial_h,special_hermite_polynomial_h,benchmark/test_special_hermite_polynomial_h.py,,yes,special_hermite_polynomial_h -main,special_i0e,special_i0e,benchmark/test_special_i0e.py,,yes,special_i0e -main,special_i0e_out,special_i0e,benchmark/test_special_i0e.py,,yes,special_i0e_out -main,special_i1,special_i1,benchmark/test_special_i1.py,,yes,special_i1 -main,special_i1_out,special_i1,benchmark/test_special_i1.py,,yes,special_i1_out -main,special_i1e,special_i1e,benchmark/test_special_i1e.py,,yes,special_i1e -main,special_legendre_polynomial_p,special_legendre_polynomial_p,benchmark/test_special_legendre_polynomial_p.py,,yes,special_legendre_polynomial_p -main,special_log1p,special_log1p,benchmark/test_special_log1p.py,,yes,special_log1p -main,special_log1p_out,special_log1p,benchmark/test_special_log1p.py,,yes,special_log1p_out -main,special_log1p_non_tensor,special_log1p,benchmark/test_special_log1p.py,,yes, -main,special_log_softmax,special_log_softmax,benchmark/test_special_log_softmax.py,,yes,special_log_softmax -main,special_logsumexp,special_logsumexp,benchmark/test_special_logsumexp.py,,yes,special_logsumexp -main,special_modified_bessel_k0,special_modified_bessel_k0,benchmark/test_special_modified_bessel_k0.py,,yes,special_modified_bessel_k0 -main,special_modified_bessel_k0_out,special_modified_bessel_k0,benchmark/test_special_modified_bessel_k0.py,,yes,special_modified_bessel_k0_out -main,special_modified_bessel_k1,special_modified_bessel_k1,benchmark/test_special_modified_bessel_k1.py,,yes,special_modified_bessel_k1 -main,special_modified_bessel_k1_out,special_modified_bessel_k1,benchmark/test_special_modified_bessel_k1.py,,yes,special_modified_bessel_k1_out -main,special_round,special_round,benchmark/test_special_round.py,,yes,special_round -main,special_round_out,special_round,benchmark/test_special_round.py,,yes,special_round_out -main,special_scaled_modified_bessel_k1,special_scaled_modified_bessel_k1,benchmark/test_special_scaled_modified_bessel_k1.py,,yes,special_scaled_modified_bessel_k1 -main,special_scaled_modified_bessel_k1_out,special_scaled_modified_bessel_k1,benchmark/test_special_scaled_modified_bessel_k1.py,,yes,special_scaled_modified_bessel_k1_out -main,special_shifted_chebyshev_polynomial_u,special_shifted_chebyshev_polynomial_u,benchmark/test_special_shifted_chebyshev_polynomial_u.py,,yes,special_shifted_chebyshev_polynomial_u -main,special_shifted_chebyshev_polynomial_u_,special_shifted_chebyshev_polynomial_u,benchmark/test_special_shifted_chebyshev_polynomial_u.py,,yes,special_shifted_chebyshev_polynomial_u_ -main,special_shifted_chebyshev_polynomial_v,special_shifted_chebyshev_polynomial_v,benchmark/test_special_shifted_chebyshev_polynomial_v.py,,yes,special_shifted_chebyshev_polynomial_v -main,special_shifted_chebyshev_polynomial_w,special_shifted_chebyshev_polynomial_w,benchmark/test_special_shifted_chebyshev_polynomial_w.py,,yes,special_shifted_chebyshev_polynomial_w -main,special_sinc,special_sinc,benchmark/test_special_sinc.py,,yes,special_sinc -main,special_xlog1py,special_xlog1py,benchmark/test_special_xlog1py.py,,yes,special_xlog1py -main,split_with_sizes_copy,split_with_sizes_copy,benchmark/test_split_with_sizes_copy.py,,yes,split_with_sizes_copy -main,sqrt,sqrt,benchmark/test_sqrt.py,,yes,sqrt -main,sqrt_inplace,sqrt,benchmark/test_sqrt.py,,yes,sqrt_ -main,square,square,benchmark/test_square.py,,yes,square -main,square_inplace,square,benchmark/test_square.py,,yes,square_ -main,square_out,square,benchmark/test_square.py,,yes,square_out -main,squeeze_copy,squeeze_copy,benchmark/test_squeeze_copy.py,,yes,squeeze_copy -main,stack,stack,benchmark/test_stack.py,,yes,stack -main,stage_deepseek_v4_mega_moe_inputs_benchmark,stage_deepseek_v4_mega_moe_inputs,benchmark/test_stage_deepseek_v4_mega_moe_inputs.py,,yes, -main,std,std,benchmark/test_std.py,,yes,std -main,sub,sub,benchmark/test_sub.py,,yes,sub -main,sub_inplace,sub,benchmark/test_sub.py,,yes,sub_ -main,subtract,subtract_,benchmark/test_subtract_.py,,yes,subtract -main,subtract_,subtract_,benchmark/test_subtract_.py,,yes,subtract_ -main,sum,sum,benchmark/test_sum.py,,yes,sum -main,sum_dim_out,sum,benchmark/test_sum.py,,yes,sum_dim_out -main,sum_out,sum,benchmark/test_sum.py,,yes,sum_out -main,sum_dim,sum_dim,benchmark/test_sum_dim.py,,yes,sum_dim -main,svd,svd,benchmark/test_svd.py,,yes,svd -main,swiglu,swiglu,benchmark/test_swiglu.py,,yes,swiglu -main,sym_storage_offset,sym_storage_offset,benchmark/test_sym_storage_offset.py,,yes,sym_storage_offset -main,sym_stride,sym_stride,benchmark/test_sym_stride.py,,yes,sym_stride -main,t_copy,t_copy,benchmark/test_t_copy.py,,yes,t_copy -main,t_copy_out,t_copy,benchmark/test_t_copy.py,,yes,t_copy_out -main,take,take,benchmark/test_take.py,,yes,take -main,take_out,take,benchmark/test_take.py,,yes,take_out -main,tan,tan,benchmark/test_tan.py,,yes,tan -main,tan_inplace,tan,benchmark/test_tan.py,,yes,tan_ -main,tanh,tanh,benchmark/test_tanh.py,,yes,tanh -main,tanh_inplace,tanh,benchmark/test_tanh.py,,yes,tanh_ -main,tanh_backward,tanh,benchmark/test_tanh.py,,yes,tanh_backward -main,te_rmsnorm_fwd,te_rmsnorm,benchmark/test_te_rmsnorm.py,,yes,te_rmsnorm_fwd -main,te_rmsnorm_bwd,te_rmsnorm,benchmark/test_te_rmsnorm.py,,yes,te_rmsnorm_bwd -main,tensor_split,tensor_split,benchmark/test_tensor_split.py,,yes,tensor_split -main,thnn_fused_lstm_cell,thnn_fused_lstm_cell,benchmark/test_thnn_fused_lstm_cell.py,,yes,thnn_fused_lstm_cell -main,thnn_fused_lstm_cell_backward_impl,thnn_fused_lstm_cell_backward_impl,benchmark/test_thnn_fused_lstm_cell_backward_impl.py,,yes,thnn_fused_lstm_cell_backward_impl -main,threshold,threshold,benchmark/test_threshold.py,,yes,threshold -main,threshold_backward,threshold,benchmark/test_threshold.py,,yes,threshold_backward -main,threshold_,threshold_,benchmark/test_threshold_.py,,yes,threshold_ -main,tile,tile,benchmark/test_tile.py,,yes,tile -main,to_copy,to_copy,benchmark/test_to_copy.py,,yes, -main,top_k_per_row_decode,top_k_per_row_decode,benchmark/test_top_k_per_row_decode.py,,yes,top_k_per_row_decode -main,top_k_per_row_prefill,top_k_per_row_prefill,benchmark/test_top_k_per_row_prefill.py,,yes,top_k_per_row_prefill -main,topk,topk,benchmark/test_topk.py,,yes,topk -main,topk_softmax,topk_softmax,benchmark/test_topk_softmax.py,,yes,topk_softmax -main,topk_softplus_sqrt,topk_softplus_sqrt,benchmark/test_topk_softplus_sqrt.py,,yes,topk_softplus_sqrt -main,trace,trace,benchmark/test_trace.py,,yes,trace -main,transpose,transpose,benchmark/test_transpose.py,,yes,transpose -main,tril,tril,benchmark/test_tril.py,,yes,tril -main,tril_extreme_diagonal,tril,benchmark/test_tril.py,,yes,tril -main,tril_out_transposed,tril,benchmark/test_tril.py,,yes,tril_out -main,tril_out_sliced,tril,benchmark/test_tril.py,,yes,tril_out -main,tril_inplace,tril,benchmark/test_tril.py,,yes,tril_ -main,triu,triu,benchmark/test_triu.py,,yes,triu -main,triu_inplace,triu,benchmark/test_triu.py,,yes,triu_ -main,true_divide,true_divide,benchmark/test_true_divide.py,,yes,div_tensor -main,true_divide_scalar,true_divide,benchmark/test_true_divide.py,,yes,div_scalar -main,true_divide_inplace_scalar,true_divide,benchmark/test_true_divide.py,,yes,div_scalar_ -main,trunc,trunc_,benchmark/test_trunc_.py,,yes,trunc -main,trunc_,trunc_,benchmark/test_trunc_.py,,yes,trunc_ -main,trunc_divide,trunc_divide,benchmark/test_trunc_divide.py,,yes,trunc_divide -main,trunc_divide_inplace,trunc_divide,benchmark/test_trunc_divide.py,,yes,trunc_divide_ -main,unbind,unbind,benchmark/test_unbind.py,,yes,unbind -main,unbind_copy,unbind_copy,benchmark/test_unbind_copy.py,,yes,unbind_copy -main,unfold_backward,unfold,benchmark/test_unfold.py,,yes,unfold_backward -main,unfold_copy,unfold_copy,benchmark/test_unfold_copy.py,,yes,unfold_copy -main,unfold_view,unfold_view,benchmark/test_unfold_view.py,,yes,unfold -main,uniform_inplace,uniform,benchmark/test_uniform.py,,yes,uniform_ -main,uniform_,uniform_,benchmark/test_uniform_.py,,yes,uniform_ -main,unique2,unique,benchmark/test_unique.py,,yes,unique2 -main,unique_consecutive,unique_consecutive,benchmark/test_unique_consecutive.py,,yes,unique_consecutive -main,unique_dim_dim0,unique_dim,benchmark/test_unique_dim.py,,yes,unique_dim -main,unique_dim_dim1,unique_dim,benchmark/test_unique_dim.py,,yes,unique_dim -main,unpack_seq,unpack_seq,benchmark/test_unpack_seq.py,,yes,unpack_seq_triton -main,unpack_seq_fp8,unpack_seq,benchmark/test_unpack_seq.py,,yes,unpack_seq_triton -main,unsafe_chunk,unsafe_chunk,benchmark/test_unsafe_chunk.py,,yes,unsafe_chunk -main,unsafe_masked_index,unsafe_masked_index,benchmark/test_unsafe_masked_index.py,,yes,unsafe_masked_index -main,unsafe_masked_index_put_accumulate,unsafe_masked_index_put_accumulate,benchmark/test_unsafe_masked_index_put_accumulate.py,,yes,unsafe_masked_index_put_accumulate -main,unsafe_view,unsafe_view,benchmark/test_unsafe_view.py,,yes,unsafe_view -main,unsqueeze,unsqueeze,benchmark/test_unsqueeze.py,,yes,unsqueeze -main,unsqueeze_,unsqueeze,benchmark/test_unsqueeze.py,,yes,unsqueeze_ -main,upsample_bicubic2d,upsample_bicubic2d,benchmark/test_upsample_bicubic2d.py,yes,yes,upsample_bicubic2d -main,upsample_bicubic2d_aa,upsample_bicubic2d_aa,benchmark/test_upsample_bicubic2d_aa.py,,yes,upsample_bicubic2d_aa -main,upsample_bicubic2d_aa_backward,upsample_bicubic2d_aa,benchmark/test_upsample_bicubic2d_aa.py,,yes,upsample_bicubic2d_aa_backward -main,upsample_bilinear2d_aa,upsample_bilinear2d_aa,benchmark/test_upsample_bilinear2d_aa.py,,yes,upsample_bilinear2d_aa -main,upsample_linear1d,upsample_linear1d,benchmark/test_upsample_linear1d.py,,yes,upsample_linear1d -main,upsample_linear1d_backward,upsample_linear1d,benchmark/test_upsample_linear1d.py,,yes,upsample_linear1d_backward -main,upsample_nearest1d,upsample_nearest1d,benchmark/test_upsample_nearest1d.py,,yes,upsample_nearest1d -main,upsample_nearest2d,upsample_nearest2d,benchmark/test_upsample_nearest2d.py,,yes,upsample_nearest2d -main,upsample_nearest3d,upsample_nearest3d,benchmark/test_upsample_nearest3d.py,,yes,upsample_nearest3d -main,upsample_nearest_exact1d,upsample_nearest_exact1d,benchmark/test_upsample_nearest_exact1d.py,,yes,upsample_nearest_exact1d -main,upsample_nearest_exact2d,upsample_nearest_exact2d,benchmark/test_upsample_nearest_exact2d.py,,yes,upsample_nearest_exact2d -main,upsample_nearest_exact2d_out,upsample_nearest_exact2d,benchmark/test_upsample_nearest_exact2d.py,,yes,upsample_nearest_exact2d -main,upsample_nearest_exact2d_backward,upsample_nearest_exact2d_backward,benchmark/test_upsample_nearest_exact2d_backward.py,,yes,upsample_nearest_exact2d_backward -main,upsample_nearest_exact3d,upsample_nearest_exact3d,benchmark/test_upsample_nearest_exact3d.py,,yes,_upsample_nearest_exact3d -main,upsample_trilinear3d,upsample_trilinear3d,benchmark/test_upsample_trilinear3d.py,,yes,upsample_trilinear3d -main,var,var,benchmark/test_var.py,,yes,var -main,var_dim,var,benchmark/test_var.py,,yes,var_dim -main,var_correction,var,benchmark/test_var.py,,yes,var_correction -main,var_mean,var_mean,benchmark/test_var_mean.py,,yes,var_mean -main,vdot,vdot,benchmark/test_vdot.py,,yes,vdot -main,vector_norm,vector_norm,benchmark/test_vector_norm.py,,yes,vector_norm -main,view_copy,view_copy,benchmark/test_view_copy.py,,yes,view_copy -main,vstack,vstack,benchmark/test_vstack.py,,yes,vstack -main,perf_w8a8_block_fp8_matmul,w8a8_block_fp8_matmul,benchmark/test_w8a8_block_fp8_matmul.py,,yes,w8a8_block_fp8_matmul -main,weight_int4pack_mm_with_scales_and_zeros,weight_int4pack_mm_with_scales_and_zeros,benchmark/test_weight_int4pack_mm_with_scales_and_zeros.py,,yes,weight_int4pack_mm_with_scales_and_zeros -main,weight_norm_dim0,weight_norm,benchmark/test_weight_norm.py,,yes,weight_norm -main,weight_norm_dim_last,weight_norm,benchmark/test_weight_norm.py,,yes,weight_norm -main,weight_norm_interface,weight_norm_interface,benchmark/test_weight_norm_interface.py,,yes,weight_norm_interface -main,weight_norm_interface_backward,weight_norm_interface,benchmark/test_weight_norm_interface.py,,yes,weight_norm_interface_backward -main,where_self,where,benchmark/test_where.py,,yes,where_self -main,where_self_out,where,benchmark/test_where.py,,yes,where_self_out -main,xlogy,xlogy,benchmark/test_xlogy.py,,yes,xlogy -main,xlogy_out,xlogy,benchmark/test_xlogy.py,,yes,xlogy_out -main,xlogy_tensor_scalar,xlogy,benchmark/test_xlogy.py,,yes,xlogy_tensor_scalar -main,xlogy_tensor_scalar_out,xlogy,benchmark/test_xlogy.py,,yes,xlogy_tensor_scalar_out -main,xlogy_scalar_tensor,xlogy,benchmark/test_xlogy.py,,yes,xlogy_scalar_tensor -main,xlogy_scalar_tensor_out,xlogy,benchmark/test_xlogy.py,,yes,xlogy_scalar_tensor_out -main,xlogy_,xlogy_,benchmark/test_xlogy_.py,,yes,xlogy_ -main,xlogy_scalar_other_,xlogy_,benchmark/test_xlogy_.py,,yes,xlogy_scalar_other_ -main,xor__,xor__,benchmark/test_xor__.py,,yes,xor__ -main,zero,zero,benchmark/test_zero.py,,yes,zero -main,zero_inplace,zero,benchmark/test_zero.py,,yes,zero_ -main,zero_out,zero,benchmark/test_zero.py,,yes,zero_out -main,zeros,zeros,benchmark/test_zeros.py,,yes,zeros -main,zeros_like,zeros_like,benchmark/test_zeros_like.py,,yes,zeros_like +repo,op,op_file,file,marked_skip,collected,op_names +main,Concat,Concat,benchmark/test_Concat.py,,yes,concat +main,perf_chunk_gated_delta_rule_fwd,FLA/test_chunk_gated_delta_rule_fwd,benchmark/test_FLA/test_chunk_gated_delta_rule_fwd.py,,yes,chunk_gated_delta_rule_fwd +main,perf_chunk_gated_delta_rule,FLA/test_chunk_gated_delta_rule_perf,benchmark/test_FLA/test_chunk_gated_delta_rule_perf.py,,yes,chunk_gated_delta_rule +main,perf_fused_recurrent_gated_delta_rule,FLA/test_fused_recurrent_gated_delta_rule_perf,benchmark/test_FLA/test_fused_recurrent_gated_delta_rule_perf.py,,yes,fused_recurrent_gated_delta_rule +main,_reshape_alias,_reshape_alias,benchmark/test__reshape_alias.py,,yes,_reshape_alias +main,abs,abs,benchmark/test_abs.py,,yes,abs +main,abs_inplace,abs,benchmark/test_abs.py,,yes,abs_ +main,absolute,absolute,benchmark/test_absolute.py,,yes,absolute +main,acos,acos,benchmark/test_acos.py,,yes,acos +main,acosh,acosh,benchmark/test_acosh.py,,yes,acosh +main,acosh_,acosh,benchmark/test_acosh.py,,yes,acosh_ +main,act_quant_perf,act_quant,benchmark/test_act_quant.py,,yes,act_quant_triton +main,perf_adaptive_avg_pool2d,adaptive_avg_pool2d,benchmark/test_adaptive_avg_pool2d.py,,yes,adaptive_avg_pool2d +main,adaptive_avg_pool2d_backward,adaptive_avg_pool2d_backward,benchmark/test_adaptive_avg_pool2d_backward.py,,yes,adaptive_avg_pool2d_backward +main,adaptive_max_pool2d_backward,adaptive_max_pool2d_backward,benchmark/test_adaptive_max_pool2d_backward.py,,yes,adaptive_max_pool2d_backward +main,adaptive_max_pool3d_backward,adaptive_max_pool3d_backward,benchmark/test_adaptive_max_pool3d_backward.py,,yes,adaptive_max_pool3d_backward +main,add,add,benchmark/test_add.py,,yes,add +main,add_inplace,add,benchmark/test_add.py,,yes,add_ +main,add_relu,add_relu,benchmark/test_add_relu.py,,yes,add_relu +main,add_rms_norm,add_rms_norm,benchmark/test_add_rms_norm.py,,yes,add_rms_norm +main,addbmm,addbmm,benchmark/test_addbmm.py,,yes,addbmm +main,addcdiv,addcdiv,benchmark/test_addcdiv.py,,yes,addcdiv +main,addcdiv_out,addcdiv,benchmark/test_addcdiv.py,,yes,addcdiv_out +main,addcdiv_,addcdiv_,benchmark/test_addcdiv_.py,,yes,addcdiv_ +main,addcmul,addcmul,benchmark/test_addcmul.py,,yes,addcmul +main,addcmul_out,addcmul,benchmark/test_addcmul.py,,yes,addcmul_out +main,addcmul_,addcmul_,benchmark/test_addcmul_.py,,yes,addcmul_ +main,addmm,addmm,benchmark/test_addmm.py,,yes,addmm +main,addmm_dtype,addmm,benchmark/test_addmm.py,,yes,addmm_dtype +main,addmm_dtype_out,addmm,benchmark/test_addmm.py,,yes,addmm_dtype_out +main,addmm_out,addmm,benchmark/test_addmm.py,,yes,addmm_out +main,addmm_,addmm_,benchmark/test_addmm_.py,,yes,addmm_ +main,addmv,addmv,benchmark/test_addmv.py,,yes,addmv +main,addmv_out,addmv,benchmark/test_addmv.py,,yes,addmv_out +main,addr,addr,benchmark/test_addr.py,,yes,addr +main,affine_grid_generator,affine_grid_generator,benchmark/test_affine_grid_generator.py,,yes,affine_grid_generator +main,alias,alias,benchmark/test_alias.py,,yes,alias +main,alias_copy,alias_copy,benchmark/test_alias_copy.py,,yes,alias_copy +main,alias_copy_out,alias_copy,benchmark/test_alias_copy.py,,yes,alias_copy_out +main,all,all,benchmark/test_all.py,,yes,all +main,all_dim,all,benchmark/test_all.py,,yes,all_dim +main,all_dims,all,benchmark/test_all.py,,yes,all_dims +main,allclose,allclose,benchmark/test_allclose.py,,yes,allclose +main,alpha_dropout,alpha_dropout,benchmark/test_alpha_dropout.py,,yes,alpha_dropout +main,amax,amax,benchmark/test_amax.py,,yes,amax +main,amin,amin,benchmark/test_amin.py,,yes,amin +main,amin_,amin,benchmark/test_amin.py,,yes,amin_ +main,aminmax,aminmax,benchmark/test_aminmax.py,,yes,aminmax +main,amp_foreach_non_finite_check_and_unscale_,amp_foreach_non_finite_check_and_unscale_,benchmark/test_amp_foreach_non_finite_check_and_unscale_.py,,yes,amp_foreach_non_finite_check_and_unscale_ +main,angle,angle,benchmark/test_angle.py,,yes,angle +main,any,any,benchmark/test_any.py,,yes,any +main,any_dim,any,benchmark/test_any.py,,yes,any_dim +main,any_dims,any,benchmark/test_any.py,,yes,any_dims +main,apply_repetition_penalties,apply_repetition_penalties,benchmark/test_apply_repetition_penalties.py,,yes,apply_repetition_penalties +main,apply_rotary_pos_emb,apply_rotary_pos_emb,benchmark/test_apply_rotary_pos_emb.py,,yes,apply_rotary_pos_emb +main,arange,arange,benchmark/test_arange.py,,yes,arange +main,arange_start,arange,benchmark/test_arange.py,,yes,arange_start +main,arange_start_step,arange,benchmark/test_arange.py,,yes,arange_start_step +main,arccos,arccos,benchmark/test_arccos.py,,yes,arccos +main,arccos_,arccos,benchmark/test_arccos.py,,yes,arccos_ +main,arccosh,arccosh,benchmark/test_arccosh.py,,yes,arccosh +main,arccosh_out,arccosh,benchmark/test_arccosh.py,,yes,arccosh_out +main,arccosh_,arccosh_,benchmark/test_arccosh_.py,,yes,arccosh_ +main,arcsin,arcsin,benchmark/test_arcsin.py,,yes,arcsin +main,arcsin_,arcsin,benchmark/test_arcsin.py,,yes,arcsin_ +main,arcsin_out,arcsin,benchmark/test_arcsin.py,,yes,arcsin_out +main,arcsinh,arcsinh,benchmark/test_arcsinh.py,,yes,arcsinh +main,arcsinh_inplace,arcsinh,benchmark/test_arcsinh.py,,yes,arcsinh_ +main,arcsinh_out,arcsinh,benchmark/test_arcsinh.py,,yes,arcsinh_out +main,arctan2,arctan2,benchmark/test_arctan2.py,,yes,arctan2 +main,arctan2_,arctan2,benchmark/test_arctan2.py,,yes,arctan2_ +main,arctan,arctan_,benchmark/test_arctan_.py,,yes,arctan +main,arctan_,arctan_,benchmark/test_arctan_.py,,yes,arctan_ +main,arctanh_inplace,arctanh,benchmark/test_arctanh.py,,yes,arctanh_ +main,argmax,argmax,benchmark/test_argmax.py,,yes,argmax +main,argmin,argmin,benchmark/test_argmin.py,,yes,argmin +main,argsort,argsort,benchmark/test_argsort.py,,yes,argsort +main,as_strided_copy,as_strided_copy,benchmark/test_as_strided_copy.py,,yes,as_strided_copy +main,as_strided_copy_out,as_strided_copy,benchmark/test_as_strided_copy.py,,yes,as_strided_copy_out +main,asin,asin,benchmark/test_asin.py,,yes,asin +main,asin_,asin,benchmark/test_asin.py,,yes,asin_ +main,asinh,asinh,benchmark/test_asinh.py,,yes,asinh +main,asinh_inplace,asinh,benchmark/test_asinh.py,,yes,asinh_ +main,assert_async,assert_async,benchmark/test_assert_async.py,,yes,assert_async +main,atan,atan,benchmark/test_atan.py,,yes,atan +main,atan_inplace,atan,benchmark/test_atan.py,,yes,atan_ +main,atan2,atan2,benchmark/test_atan2.py,,yes,atan2 +main,atan2_out,atan2,benchmark/test_atan2.py,,yes,atan2_out +main,atan2_,atan2_,benchmark/test_atan2_.py,,yes,atan2_ +main,atanh,atanh,benchmark/test_atanh.py,,yes,atanh +main,atanh_,atanh_,benchmark/test_atanh_.py,,yes,atanh_ +main,avg_pool2d,avg_pool2d,benchmark/test_avg_pool2d.py,,yes,avg_pool2d +main,avg_pool2d_backward,avg_pool2d,benchmark/test_avg_pool2d.py,,yes,avg_pool2d_backward +main,perf_avg_pool3d,avg_pool3d_perf,benchmark/test_avg_pool3d_perf.py,,yes,avg_pool3d +main,perf_avg_pool3d_backward,avg_pool3d_perf,benchmark/test_avg_pool3d_perf.py,,yes,avg_pool3d +main,baddbmm,baddbmm,benchmark/test_baddbmm.py,,yes,baddbmm +main,baddbmm_out,baddbmm,benchmark/test_baddbmm.py,,yes,baddbmm_out +main,baddbmm_,baddbmm_,benchmark/test_baddbmm_.py,,yes,baddbmm_ +main,batch_norm,batch_norm,benchmark/test_batch_norm.py,,yes,batch_norm +main,batch_norm_backward,batch_norm_backward,benchmark/test_batch_norm_backward.py,,yes,batch_norm_backward +main,batch_norm_no_update,batch_norm_no_update,benchmark/test_batch_norm_no_update.py,,yes,batch_norm_no_update +main,beam_search_score,beam_search_score,benchmark/test_beam_search_score.py,,yes,beam_search_score +main,beam_search_score_,beam_search_score,benchmark/test_beam_search_score.py,,yes,beam_search_score_ +main,bernoulli_inplace,bernoulli,benchmark/test_bernoulli.py,,yes,bernoulli_ +main,bernoulli,bernoulli,benchmark/test_bernoulli.py,,yes,bernoulli +main,bf16_paged_mqa_logits,bf16_paged_mqa_logits,benchmark/test_bf16_paged_mqa_logits.py,,yes,bf16_paged_mqa_logits +main,binary_cross_entropy_backward,binary_cross_entropy_backward,benchmark/test_binary_cross_entropy_backward.py,,yes,binary_cross_entropy_backward +main,binary_cross_entropy_with_logits,binary_cross_entropy_with_logits,benchmark/test_binary_cross_entropy_with_logits.py,,yes,binary_cross_entropy_with_logits +main,bincount,bincount,benchmark/test_bincount.py,,yes,bincount +main,bincount_weighted,bincount,benchmark/test_bincount.py,,yes,bincount_weighted +main,bitwise_and,bitwise_and,benchmark/test_bitwise_and.py,,yes,bitwise_and_tensor +main,bitwise_and_inplace,bitwise_and,benchmark/test_bitwise_and.py,,yes,bitwise_and_tensor_ +main,bitwise_and_scalar,bitwise_and,benchmark/test_bitwise_and.py,,yes,bitwise_and_scalar +main,bitwise_and_scalar_,bitwise_and,benchmark/test_bitwise_and.py,,yes,bitwise_and_scalar_ +main,bitwise_and_scalar_tensor,bitwise_and,benchmark/test_bitwise_and.py,,yes,bitwise_and_scalar_tensor +main,bitwise_left_shift,bitwise_left_shift,benchmark/test_bitwise_left_shift.py,,yes,bitwise_left_shift +main,bitwise_left_shift_,bitwise_left_shift_,benchmark/test_bitwise_left_shift_.py,,yes,bitwise_left_shift_ +main,bitwise_not,bitwise_not,benchmark/test_bitwise_not.py,,yes,bitwise_not +main,bitwise_not_inplace,bitwise_not,benchmark/test_bitwise_not.py,,yes,bitwise_not_ +main,bitwise_or_tensor,bitwise_or,benchmark/test_bitwise_or.py,,yes,bitwise_or_tensor +main,bitwise_or_inplace,bitwise_or,benchmark/test_bitwise_or.py,,yes,bitwise_or_tensor_ +main,bitwise_or_scalar,bitwise_or,benchmark/test_bitwise_or.py,,yes,bitwise_or_scalar +main,bitwise_or_scalar_,bitwise_or,benchmark/test_bitwise_or.py,,yes,bitwise_or_scalar_ +main,bitwise_or_scalar_tensor,bitwise_or,benchmark/test_bitwise_or.py,,yes,bitwise_or_scalar_tensor +main,bitwise_right_shift,bitwise_right_shift,benchmark/test_bitwise_right_shift.py,,yes,bitwise_right_shift +main,bitwise_right_shift_,bitwise_right_shift_,benchmark/test_bitwise_right_shift_.py,,yes,bitwise_right_shift_ +main,bitwise_xor_tensor,bitwise_xor,benchmark/test_bitwise_xor.py,,yes,bitwise_xor_tensor +main,bitwise_xor_inplace,bitwise_xor,benchmark/test_bitwise_xor.py,,yes,bitwise_xor_tensor_ +main,bitwise_xor_scalar,bitwise_xor,benchmark/test_bitwise_xor.py,,yes,bitwise_xor_scalar +main,bitwise_xor_scalar_,bitwise_xor,benchmark/test_bitwise_xor.py,,yes,bitwise_xor_scalar_ +main,bitwise_xor_scalar_tensor,bitwise_xor,benchmark/test_bitwise_xor.py,,yes,bitwise_xor_scalar_tensor +main,blas_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, +main,perf_w8a8_block_fp8_matmul,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,w8a8_block_fp8_matmul +main,perf_w8a8_block_fp8_matmul_deepgemm,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,w8a8_block_fp8_matmul_deepgemm +main,perf_sparse_attention,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,sparse_attention +main,perf_mul,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,mul +main,mv_and_outer_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, +main,addmv_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, +main,vdot_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,vdot +main,addr_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,addr +main,perf_router_gemm,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,router_gemm +main,block_diag,block_diag,benchmark/test_block_diag.py,,yes,block_diag +main,bmm,bmm,benchmark/test_bmm.py,,yes,bmm +main,bmm_out,bmm,benchmark/test_bmm.py,,yes,bmm_out +main,broadcast_tensors,broadcast_tensors,benchmark/test_broadcast_tensors.py,,yes,broadcast_tensors +main,broadcast_to,broadcast_to,benchmark/test_broadcast_to.py,,yes,broadcast_to +main,bucketize_perf,bucketize,benchmark/test_bucketize.py,,yes,bucketize +main,cat,cat,benchmark/test_cat.py,,yes,cat +main,cat_out,cat,benchmark/test_cat.py,,yes,cat_out +main,cauchy_inplace,cauchy,benchmark/test_cauchy.py,,yes,cauchy_ +main,cauchy_out,cauchy,benchmark/test_cauchy.py,,yes,cauchy +main,cdist_backward,cdist_backward,benchmark/test_cdist_backward.py,,yes,cdist_backward +main,cdist_forward,cdist_forward,benchmark/test_cdist_forward.py,,yes,cdist_forward +main,ceil,ceil,benchmark/test_ceil.py,,yes,ceil +main,ceil_inplace,ceil,benchmark/test_ceil.py,,yes,ceil_ +main,ceil_out,ceil,benchmark/test_ceil.py,,yes,ceil_out +main,celu,celu,benchmark/test_celu.py,,yes,celu +main,celu_inplace,celu,benchmark/test_celu.py,,yes,celu_ +main,channel_shuffle,channel_shuffle,benchmark/test_channel_shuffle.py,,yes,channel_shuffle +main,cholesky_inverse,cholesky_inverse,benchmark/test_cholesky_inverse.py,,yes,cholesky_inverse +main,cholesky_solve,cholesky_solve,benchmark/test_cholesky_solve.py,,yes,cholesky_solve +main,cholesky_solve_out,cholesky_solve,benchmark/test_cholesky_solve.py,,yes,cholesky_solve_out +main,chunk,chunk,benchmark/test_chunk.py,,yes,chunk +main,chunk_cat,chunk_cat,benchmark/test_chunk_cat.py,,yes,chunk_cat +main,clamp,clamp,benchmark/test_clamp.py,,yes,clamp +main,clamp_inplace,clamp,benchmark/test_clamp.py,,yes,clamp_ +main,clamp_tensor,clamp,benchmark/test_clamp.py,,yes,clamp_tensor +main,clamp_tensor_inplace,clamp,benchmark/test_clamp.py,,yes,clamp_tensor_ +main,clamp_max,clamp_max,benchmark/test_clamp_max.py,,yes,clamp_max +main,clamp_max_inplace,clamp_max,benchmark/test_clamp_max.py,,yes,clamp_max_ +main,clamp_min,clamp_min,benchmark/test_clamp_min.py,,yes,clamp_min +main,clamp_min_inplace,clamp_min,benchmark/test_clamp_min.py,,yes,clamp_min_ +main,clip,clip,benchmark/test_clip.py,,yes,clip +main,clip_inplace,clip,benchmark/test_clip.py,,yes,clip_ +main,col2im,col2im,benchmark/test_col2im.py,,yes,col2im +main,concat_and_cache_mla,concat_and_cache_mla,benchmark/test_concat_and_cache_mla.py,,yes,concat_and_cache_mla +main,concatenate,concatenate,benchmark/test_concatenate.py,,yes,concatenate +main,conj,conj,benchmark/test_conj.py,,yes,conj +main,conj_physical,conj_physical,benchmark/test_conj_physical.py,,yes,conj_physical +main,constant_pad_nd,constant_pad_nd,benchmark/test_constant_pad_nd.py,,yes,constant_pad_nd +main,contiguous,contiguous,benchmark/test_contiguous.py,,yes,contiguous +main,conv1d,conv1d,benchmark/test_conv1d.py,,yes,conv1d +main,conv1d_padding,conv1d,benchmark/test_conv1d.py,,yes,conv1d_padding +main,conv2d,conv2d,benchmark/test_conv2d.py,,yes,conv2d +main,conv2d_padding,conv2d,benchmark/test_conv2d.py,,yes,conv2d_padding +main,conv3d,conv3d,benchmark/test_conv3d.py,,yes,conv3d +main,conv3d_padding,conv3d,benchmark/test_conv3d.py,,yes,conv3d_padding +main,conv_depthwise2d,conv_depthwise2d,benchmark/test_conv_depthwise2d.py,,yes,conv_depthwise2d +main,conv_transpose1d,conv_transpose1d,benchmark/test_conv_transpose1d.py,,yes,conv_transpose1d +main,perf_conv_transpose2d,conv_transpose2d,benchmark/test_conv_transpose2d.py,,yes,conv_transpose2d +main,convert_weight_to_int4pack,convert_weight_to_int4pack,benchmark/test_convert_weight_to_int4pack.py,,yes,convert_weight_to_int4pack +main,copy_inplace,copy,benchmark/test_copy.py,,yes,copy_ +main,copy_functional,copy,benchmark/test_copy.py,,yes,copy +main,copysign,copysign,benchmark/test_copysign.py,,yes,copysign +main,copysign_out,copysign,benchmark/test_copysign.py,,yes,copysign_out +main,copysign_,copysign_,benchmark/test_copysign_.py,,yes,copysign_ +main,cos,cos,benchmark/test_cos.py,,yes,cos +main,cos_inplace,cos,benchmark/test_cos.py,,yes,cos_ +main,cosh,cosh,benchmark/test_cosh.py,,yes,cosh +main,cosh_inplace,cosh,benchmark/test_cosh.py,,yes,cosh_ +main,cosh_out,cosh,benchmark/test_cosh.py,,yes,cosh_out +main,count_nonzero,count_nonzero,benchmark/test_count_nonzero.py,,yes,count_nonzero +main,cp_gather_indexer_k_quant_cache_benchmark,cp_gather_indexer_k_quant_cache,benchmark/test_cp_gather_indexer_k_quant_cache.py,,yes, +main,cross_entropy_loss,cross_entropy_loss,benchmark/test_cross_entropy_loss.py,,yes,cross_entropy_loss +main,ctc_loss,ctc_loss,benchmark/test_ctc_loss.py,,yes,ctc_loss +main,ctc_loss_backward,ctc_loss,benchmark/test_ctc_loss.py,,yes,ctc_loss +main,perf_cudnn_attention_forward,cudnn_attention_forward,benchmark/test_cudnn_attention_forward.py,,yes,cudnn_attention_forward +main,cudnn_batch_norm_backward,cudnn_batch_norm_backward,benchmark/test_cudnn_batch_norm_backward.py,,yes,cudnn_batch_norm_backward +main,cudnn_convolution,cudnn_convolution,benchmark/test_cudnn_convolution.py,,yes,cudnn_convolution +main,cummax,cummax,benchmark/test_cummax.py,,yes,cummax +main,cummin,cummin,benchmark/test_cummin.py,,yes,cummin +main,cumprod_perf,cumprod,benchmark/test_cumprod.py,,yes,cumprod +main,cumprod_inplace_perf,cumprod,benchmark/test_cumprod.py,,yes,cumprod_ +main,cumsum,cumsum,benchmark/test_cumsum.py,,yes,cumsum +main,cumsum_out,cumsum,benchmark/test_cumsum.py,,yes,cumsum_out +main,cutlass_scaled_mm_benchmark,cutlass_scaled_mm,benchmark/test_cutlass_scaled_mm.py,,yes, +main,combine_topk_swa_indices_benchmark,deepseek_v4_attention_combine_topk_swa_indices,benchmark/test_deepseek_v4_attention_combine_topk_swa_indices.py,,yes, +main,compute_global_topk_indices_and_lens_benchmark,deepseek_v4_attention_compute_global_topk_indices_and_lens,benchmark/test_deepseek_v4_attention_compute_global_topk_indices_and_lens.py,,yes, +main,dequantize_and_gather_k_cache_benchmark,deepseek_v4_attention_dequantize_and_gather_k_cache,benchmark/test_deepseek_v4_attention_dequantize_and_gather_k_cache.py,,yes, +main,fused_q_kv_rmsnorm_benchmark,deepseek_v4_attention_fused_q_kv_rmsnorm,benchmark/test_deepseek_v4_attention_fused_q_kv_rmsnorm.py,,yes, +main,deg2rad,deg2rad,benchmark/test_deg2rad.py,,yes,deg2rad +main,deg2rad_,deg2rad,benchmark/test_deg2rad.py,,yes,deg2rad_ +main,deg2rad_out,deg2rad,benchmark/test_deg2rad.py,,yes,deg2rad_out +main,dequantize,dequantize,benchmark/test_dequantize.py,,yes,dequantize +main,dgeglu,dgeglu,benchmark/test_dgeglu.py,,yes,dgeglu +main,diag,diag,benchmark/test_diag.py,,yes,diag +main,diag_embed,diag_embed,benchmark/test_diag_embed.py,,yes,diag_embed +main,diagonal_backward,diagonal,benchmark/test_diagonal.py,,yes,diagonal_backward +main,diagonal_copy,diagonal_copy,benchmark/test_diagonal_copy.py,,yes,diagonal_copy +main,diagonal_scatter,diagonal_scatter,benchmark/test_diagonal_scatter.py,,yes,diagonal_scatter +main,diff,diff,benchmark/test_diff.py,,yes,diff +main,diff_n2,diff,benchmark/test_diff.py,,yes,diff +main,digamma,digamma,benchmark/test_digamma.py,,yes,digamma +main,digamma_inplace,digamma,benchmark/test_digamma.py,,yes,digamma_ +main,div,div,benchmark/test_div.py,,yes,div_tensor +main,div_inplace,div,benchmark/test_div.py,,yes,div_tensor_ +main,div_tensor_mode,div,benchmark/test_div.py,,yes,div_tensor_mode +main,div_tensor_mode_inplace,div,benchmark/test_div.py,,yes,div_tensor_mode_ +main,div_scalar_mode,div,benchmark/test_div.py,,yes,div_scalar_mode +main,div_scalar_mode_inplace,div,benchmark/test_div.py,,yes,div_scalar_mode_ +main,div_scalar_inplace,div,benchmark/test_div.py,,yes,div_scalar_ +main,div_out,div,benchmark/test_div.py,,yes,div_out +main,dot,dot,benchmark/test_dot.py,,yes,dot +main,dreglu,dreglu,benchmark/test_dreglu.py,,yes,dreglu +main,dropout,dropout,benchmark/test_dropout.py,,yes,dropout +main,dropout_backward,dropout,benchmark/test_dropout.py,,yes,dropout_backward +main,dswiglu,dswiglu,benchmark/test_dswiglu.py,,yes,dswiglu +main,dunder_ior_inplace,dunder_ior,benchmark/test_dunder_ior.py,,yes,dunder_ior_tensor +main,dunder_ior_scalar_inplace,dunder_ior,benchmark/test_dunder_ior.py,,yes,dunder_ior_scalar +main,dunder_or_tensor,dunder_or,benchmark/test_dunder_or.py,,yes,dunder_or_tensor +main,dunder_or_scalar,dunder_or,benchmark/test_dunder_or.py,,yes,dunder_or_scalar +main,dyn_quant_pack_4bit_weight,dyn_quant_pack_4bit_weight,benchmark/test_dyn_quant_pack_4bit_weight.py,,yes,dyn_quant_pack_4bit_weight +main,einsum_matmul,einsum,benchmark/test_einsum.py,,yes,einsum +main,einsum_bmm,einsum,benchmark/test_einsum.py,,yes,einsum +main,einsum_dot,einsum,benchmark/test_einsum.py,,yes,einsum +main,einsum_outer,einsum,benchmark/test_einsum.py,,yes,einsum +main,einsum_trace,einsum,benchmark/test_einsum.py,,yes,einsum +main,einsum_diagonal,einsum,benchmark/test_einsum.py,,yes,einsum +main,einsum_transpose,einsum,benchmark/test_einsum.py,,yes,einsum +main,einsum_sum_all,einsum,benchmark/test_einsum.py,,yes,einsum +main,einsum_sum_dim,einsum,benchmark/test_einsum.py,,yes,einsum +main,einsum_ellipsis,einsum,benchmark/test_einsum.py,,yes,einsum +main,elu,elu,benchmark/test_elu.py,,yes,elu +main,elu_inplace,elu,benchmark/test_elu.py,,yes,elu_ +main,elu_backward,elu,benchmark/test_elu.py,,yes,elu_backward +main,embedding,embedding,benchmark/test_embedding.py,,yes,embedding +main,embedding_backward,embedding,benchmark/test_embedding.py,,yes,embedding_backward +main,embedding_bag_dense_backward,embedding_bag_dense_backward,benchmark/test_embedding_bag_dense_backward.py,,yes,embedding_bag_dense_backward +main,embedding_bag_per_sample_weights_backward,embedding_bag_per_sample_weights_backward,benchmark/test_embedding_bag_per_sample_weights_backward.py,,yes,_embedding_bag_per_sample_weights_backward +main,embedding_dense_backward,embedding_dense_backward,benchmark/test_embedding_dense_backward.py,,yes,embedding_dense_backward +main,empty,empty,benchmark/test_empty.py,,yes,empty +main,eq,eq,benchmark/test_eq.py,,yes,eq +main,eq_scalar,eq,benchmark/test_eq.py,,yes,eq_scalar +main,eq_,eq_,benchmark/test_eq_.py,,yes,eq_ +main,eq_scalar_,eq_,benchmark/test_eq_.py,,yes,eq_scalar_ +main,equal,equal,benchmark/test_equal.py,,yes,equal +main,special_erf,erf,benchmark/test_erf.py,,yes,special_erf +main,erf,erf,benchmark/test_erf.py,,yes,erf +main,erf_inplace,erf,benchmark/test_erf.py,,yes,erf_ +main,erfinv,erfinv_,benchmark/test_erfinv_.py,,yes,erfinv +main,erfinv_,erfinv_,benchmark/test_erfinv_.py,,yes,erfinv_ +main,euclidean_dist,euclidean_dist,benchmark/test_euclidean_dist.py,,yes,euclidean_dist +main,exp,exp,benchmark/test_exp.py,,yes,exp +main,exp_inplace,exp,benchmark/test_exp.py,,yes,exp_ +main,exp_out,exp,benchmark/test_exp.py,,yes,exp_out +main,special_exp2,exp2,benchmark/test_exp2.py,,yes,special_exp2 +main,exp2,exp2,benchmark/test_exp2.py,,yes,exp2 +main,exp2_inplace,exp2,benchmark/test_exp2.py,,yes,exp2_ +main,expand,expand,benchmark/test_expand.py,,yes,expand +main,expand_,expand,benchmark/test_expand.py,,yes,expand_ +main,expand_as,expand_as,benchmark/test_expand_as.py,,yes,expand_as +main,expm1,expm1,benchmark/test_expm1.py,,yes,expm1 +main,expm1_inplace,expm1,benchmark/test_expm1.py,,yes,expm1_ +main,expm1_out,expm1,benchmark/test_expm1.py,,yes,expm1_out +main,exponential_inplace,exponential,benchmark/test_exponential.py,,yes,exponential_ +main,eye,eye,benchmark/test_eye.py,,yes,eye +main,eye_m,eye,benchmark/test_eye.py,,yes,eye_m +main,feature_dropout,feature_dropout,benchmark/test_feature_dropout.py,,yes,feature_dropout +main,feature_dropout_,feature_dropout,benchmark/test_feature_dropout.py,,yes,feature_dropout_ +main,perf_fft,fft,benchmark/test_fft.py,,yes,fft +main,fill_scalar,fill,benchmark/test_fill.py,,yes,fill_scalar +main,fill_tensor,fill,benchmark/test_fill.py,,yes,fill_tensor +main,fill_tensor_inplace,fill,benchmark/test_fill.py,,yes,fill_tensor_ +main,fill_tensor_out,fill,benchmark/test_fill.py,,yes,fill_tensor_out +main,fill_scalar_inplace,fill,benchmark/test_fill.py,,yes,fill_scalar_ +main,fill_scalar_out,fill,benchmark/test_fill.py,,yes,fill_scalar_out +main,fix,fix,benchmark/test_fix.py,,yes,fix +main,fix_,fix_,benchmark/test_fix_.py,,yes,fix_ +main,perf_flash_attention_backward,flash_attention_backward,benchmark/test_flash_attention_backward.py,,yes,flash_attention_backward +main,perf_scaled_dot_product_flash_attention_backward,flash_attention_backward,benchmark/test_flash_attention_backward.py,,yes,scaled_dot_product_flash_attention_backward +main,perf_scaled_dot_product_cudnn_attention_backward,flash_attention_backward,benchmark/test_flash_attention_backward.py,,yes,scaled_dot_product_cudnn_attention_backward +main,perf_efficient_attention_backward,flash_attention_backward,benchmark/test_flash_attention_backward.py,,yes,efficient_attention_backward +main,perf_scaled_dot_product_efficient_attention_backward,flash_attention_backward,benchmark/test_flash_attention_backward.py,,yes,scaled_dot_product_efficient_attention_backward +main,_flash_attention_forward,flash_attention_forward,benchmark/test_flash_attention_forward.py,,yes,_flash_attention_forward +main,flash_attention_forward,flash_attention_forward,benchmark/test_flash_attention_forward.py,,yes,flash_attention_forward +main,flash_attn_varlen_func,flash_attn_varlen_func,benchmark/test_flash_attn_varlen_func.py,,yes,flash_attn_varlen_func +main,flash_attn_varlen_func_noncontig,flash_attn_varlen_func,benchmark/test_flash_attn_varlen_func.py,,yes,flash_attn_varlen_func_noncontig +main,flash_attn_varlen_opt_func,flash_attn_varlen_opt_init_func,benchmark/test_flash_attn_varlen_opt_init_func.py,,yes,flash_attn_varlen_func +main,flash_mla,flash_mla,benchmark/test_flash_mla.py,,yes,flash_mla +main,flash_mla_sparse_fwd,flash_mla_sparse_fwd,benchmark/test_flash_mla_sparse_fwd.py,,yes, +main,flash_mla_with_kvcache,flash_mla_with_kvcache,benchmark/test_flash_mla_with_kvcache.py,,yes, +main,flatten,flatten,benchmark/test_flatten.py,,yes,flatten.using_ints +main,flip,flip,benchmark/test_flip.py,,yes,flip +main,float_power_,float_power_,benchmark/test_float_power_.py,,yes,float_power_ +main,floor,floor,benchmark/test_floor.py,,yes,floor +main,floor_inplace,floor,benchmark/test_floor.py,,yes,floor_ +main,floor_out,floor,benchmark/test_floor.py,,yes,floor_out +main,floor_divide,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide +main,floor_divide_inplace,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide_ +main,floor_divide_scalar,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide_scalar +main,floor_divide_scalar_,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide_scalar_ +main,floor_divide_tensor,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide_tensor +main,floor_divide_tensor_inplace,floor_divide,benchmark/test_floor_divide.py,,yes,floor_divide_tensor_ +main,fmax,fmax,benchmark/test_fmax.py,,yes,fmax +main,fmax_out,fmax,benchmark/test_fmax.py,,yes,fmax_out +main,fmin,fmin,benchmark/test_fmin.py,,yes,fmin +main,fmin_out,fmin,benchmark/test_fmin.py,,yes,fmin_out +main,fmod_tensor,fmod,benchmark/test_fmod.py,,yes,fmod_tensor +main,fmod_scalar,fmod,benchmark/test_fmod.py,,yes,fmod_scalar +main,fmod_tensor_,fmod,benchmark/test_fmod.py,,yes,fmod_tensor_ +main,fmod_scalar_,fmod,benchmark/test_fmod.py,,yes,fmod_scalar_ +main,fmod_,fmod_,benchmark/test_fmod_.py,,yes,fmod_ +main,perf_fp8_einsum_gems_vs_deepgemm,fp8_einsum,benchmark/test_fp8_einsum.py,,yes,fp8_einsum +main,fp8_fp4_mega_moe_vllm,fp8_fp4_mega_moe,benchmark/test_fp8_fp4_mega_moe.py,,yes,fp8_fp4_mega_moe +main,fp8_fp4_mega_moe_torch_ref,fp8_fp4_mega_moe,benchmark/test_fp8_fp4_mega_moe.py,,yes,fp8_fp4_mega_moe_torch_ref +main,fp8_fp4_mqa_logits,fp8_fp4_mqa_logits,benchmark/test_fp8_fp4_mqa_logits.py,,yes,fp8_fp4_mqa_logits +main,fp8_fp4_paged_mqa_logits,fp8_fp4_paged_mqa_logits,benchmark/test_fp8_fp4_paged_mqa_logits.py,,yes,fp8_fp4_paged_mqa_logits +main,fp8_mqa_logits,fp8_mqa_logits,benchmark/test_fp8_mqa_logits.py,,yes,fp8_mqa_logits +main,perf_fp8_paged_mqa_logits_gems_vs_deepgemm,fp8_paged_mqa_logits_perf,benchmark/test_fp8_paged_mqa_logits_perf.py,,yes, +main,frac,frac,benchmark/test_frac.py,,yes,frac +main,frac_,frac_,benchmark/test_frac_.py,,yes,frac_ +main,fractional_max_pool2d,fractional_max_pool2d,benchmark/test_fractional_max_pool2d.py,,yes,fractional_max_pool2d +main,fractional_max_pool2d_backward,fractional_max_pool2d,benchmark/test_fractional_max_pool2d.py,,yes,fractional_max_pool2d_backward +main,full,full,benchmark/test_full.py,,yes,full +main,full_like,full_like,benchmark/test_full_like.py,,yes,full_like +main,functional_assert_async,functional_assert_async,benchmark/test_functional_assert_async.py,,yes,functional_assert_async +main,functional_sym_constrain_range,functional_sym_constrain_range,benchmark/test_functional_sym_constrain_range.py,,yes,functional_sym_constrain_range +main,functional_sym_constrain_range_for_size,functional_sym_constrain_range_for_size,benchmark/test_functional_sym_constrain_range_for_size.py,,yes,functional_sym_constrain_range_for_size +main,fused_adam,fused_adam,benchmark/test_fused_adam.py,,yes,fused_adam +main,fused_adam_,fused_adam,benchmark/test_fused_adam.py,,yes,fused_adam_ +main,fused_add_rms_norm,fused_add_rms_norm,benchmark/test_fused_add_rms_norm.py,,yes,fused_add_rms_norm +main,fused_deepseek_v4_qnorm_rope_kv_rope_insert,fused_deepseek_v4_qnorm_rope_kv_rope_insert,benchmark/test_fused_deepseek_v4_qnorm_rope_kv_rope_insert.py,,yes,fused_deepseek_v4_qnorm_rope_kv_rope_insert +main,fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert,fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert,benchmark/test_fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert.py,,yes, +main,fused_indexer_q_rope_quant,fused_indexer_q_rope_quant,benchmark/test_fused_indexer_q_rope_quant.py,,yes,fused_indexer_q_rope_quant +main,fused_inv_rope_fp8_quant,fused_inv_rope_fp8_quant,benchmark/test_fused_inv_rope_fp8_quant.py,,yes,fused_inv_rope_fp8_quant +main,fused_marlin_moe,fused_marlin_moe,benchmark/test_fused_marlin_moe.py,,yes,fused_marlin_moe +main,fused_marlin_moe_int8,fused_marlin_moe,benchmark/test_fused_marlin_moe.py,,yes,fused_marlin_moe_int8 +main,fused_marlin_moe_mxfp4,fused_marlin_moe,benchmark/test_fused_marlin_moe.py,,yes,fused_marlin_moe_mxfp4 +main,fused_moe_impl_gems_vs_vllm,fused_moe,benchmark/test_fused_moe.py,,yes,fused_experts_impl +main,dispatch_fused_moe_kernel,fused_moe,benchmark/test_fused_moe.py,,yes,dispatch_fused_moe_kernel +main,fused_moe_fp8,fused_moe_fp8,benchmark/test_fused_moe_fp8.py,,yes,fused_experts_impl +main,fused_moe_fp8_blockwise,fused_moe_fp8_blockwise,benchmark/test_fused_moe_fp8_blockwise.py,,yes,fused_experts_impl +main,fused_moe_int4_w4a16,fused_moe_int4_w4a16,benchmark/test_fused_moe_int4_w4a16.py,,yes,fused_experts_impl +main,fused_experts_impl_int8,fused_moe_int8,benchmark/test_fused_moe_int8.py,,yes,fused_experts_impl +main,fused_experts_impl_int8_w8a16,fused_moe_int8_w8a16,benchmark/test_fused_moe_int8_w8a16.py,,yes,fused_moe_int8_w8a16_gems_vs_bf16_deq +main,fused_moe_w8a16_mxq,fused_moe_w8a16,benchmark/test_fused_moe_w8a16.py,,yes,fused_moe +main,fused_moe_w8a16_mxq_gems_vs_vllm,fused_moe_w8a16,benchmark/test_fused_moe_w8a16.py,,yes,fused_moe +main,fused_rms_norm,fused_rms_norm,benchmark/test_fused_rms_norm.py,,yes,fused_rms_norm +main,gather,gather,benchmark/test_gather.py,,yes,gather +main,gather_backward,gather,benchmark/test_gather.py,,yes,gather_backward +main,gather_block_quantized,gather_block_quantized,benchmark/test_gather_block_quantized.py,,yes,gather_block_quantized +main,gcd,gcd,benchmark/test_gcd.py,,yes,gcd +main,gcd_out,gcd,benchmark/test_gcd.py,,yes,gcd_out +main,gcd_,gcd_,benchmark/test_gcd_.py,,yes,gcd_ +main,ge,ge,benchmark/test_ge.py,,yes,ge +main,ge_scalar,ge,benchmark/test_ge.py,,yes,ge_scalar +main,geglu,geglu,benchmark/test_geglu.py,,yes,geglu +main,gelu,gelu,benchmark/test_gelu.py,,yes,gelu +main,gelu_inplace,gelu,benchmark/test_gelu.py,,yes,gelu_ +main,gelu_backward,gelu,benchmark/test_gelu.py,,yes,gelu_backward +main,gelu_and_mul,gelu_and_mul,benchmark/test_gelu_and_mul.py,,yes,gelu_and_mul +main,geometric_inplace,geometric,benchmark/test_geometric.py,,yes,geometric_ +main,geometric,geometric,benchmark/test_geometric.py,,yes,geometric +main,get_paged_mqa_logits_metadata,get_paged_mql_logits_metadata,benchmark/test_get_paged_mql_logits_metadata.py,,yes,get_paged_mqa_logits_metadata +main,get_scheduler_metadata,get_scheduler_metadata,benchmark/test_get_scheduler_metadata.py,,yes,get_scheduler_metadata +main,glu,glu,benchmark/test_glu.py,,yes,glu +main,glu_backward,glu,benchmark/test_glu.py,,yes,glu_backward +main,greater,greater,benchmark/test_greater.py,,yes,greater +main,greater_out,greater,benchmark/test_greater.py,,yes,greater_out +main,greater_scalar,greater,benchmark/test_greater.py,,yes,greater_scalar +main,greater_scalar_out,greater,benchmark/test_greater.py,,yes,greater_scalar_out +main,greater_equal,greater_equal,benchmark/test_greater_equal.py,,yes,greater_equal +main,greater_equal_,greater_equal,benchmark/test_greater_equal.py,,yes,greater_equal_ +main,greater_equal_scalar,greater_equal,benchmark/test_greater_equal.py,,yes,greater_equal_scalar +main,grid_sample,grid_sample,benchmark/test_grid_sample.py,,yes,grid_sample +main,group_norm,group_norm,benchmark/test_group_norm.py,,yes,group_norm +main,grouped_mm,grouped_mm,benchmark/test_grouped_mm.py,,yes,grouped_mm +main,grouped_topk_no_renorm,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk +main,grouped_topk_score_0,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk +main,grouped_topk_score_1,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk +main,gt,gt,benchmark/test_gt.py,,yes,gt +main,gt_scalar,gt,benchmark/test_gt.py,,yes,gt_scalar +main,gt_scalar_,gt_scalar_,benchmark/test_gt_scalar_.py,,yes,gt_scalar_ +main,gt_tensor_,gt_tensor_,benchmark/test_gt_tensor_.py,,yes,gt_tensor_ +main,hadamard_transform,hadamard_transform,benchmark/test_hadamard_transform.py,,yes,hadamard_transform +main,hadamard_transform_mn,hadamard_transform,benchmark/test_hadamard_transform.py,,yes,hadamard_transform_mn +main,hardshrink,hardshrink,benchmark/test_hardshrink.py,,yes,hardshrink +main,hardshrink_out,hardshrink,benchmark/test_hardshrink.py,,yes,hardshrink_out +main,hardsigmoid_inplace,hardsigmoid,benchmark/test_hardsigmoid.py,,yes,hardsigmoid_ +main,hardsigmoid,hardsigmoid,benchmark/test_hardsigmoid.py,,yes,hardsigmoid +main,hardsigmoid_out,hardsigmoid,benchmark/test_hardsigmoid.py,,yes,hardsigmoid_out +main,hardswish_inplace,hardswish,benchmark/test_hardswish.py,,yes,hardswish_ +main,hardtanh_inplace,hardtanh_,benchmark/test_hardtanh_.py,,yes,hardtanh_ +main,has_compatible_shallow_copy_type,has_compatible_shallow_copy_type,benchmark/test_has_compatible_shallow_copy_type.py,,yes,has_compatible_shallow_copy_type +main,heaviside_,heaviside_,benchmark/test_heaviside_.py,,yes,heaviside_ +main,histc,histc,benchmark/test_histc.py,,yes,histc +main,hstack,hstack,benchmark/test_hstack.py,,yes,hstack +main,huber_loss,huber_loss,benchmark/test_huber_loss.py,,yes,huber_loss +main,hypot,hypot,benchmark/test_hypot.py,,yes,hypot +main,hypot_out,hypot,benchmark/test_hypot.py,,yes,hypot_out +main,hypot_,hypot_,benchmark/test_hypot_.py,,yes,hypot_ +main,i0,i0,benchmark/test_i0.py,,yes,i0 +main,i0_inplace,i0,benchmark/test_i0.py,,yes,i0_ +main,i0_out,i0,benchmark/test_i0.py,,yes,i0_out +main,igamma_,igamma_,benchmark/test_igamma_.py,,yes,igamma_ +main,igammac,igammac,benchmark/test_igammac.py,,yes,igammac +main,igammac_out,igammac,benchmark/test_igammac.py,,yes,igammac_out +main,igammac_,igammac_,benchmark/test_igammac_.py,,yes,igammac_ +main,ilshift,ilshift,benchmark/test_ilshift.py,,yes,ilshift +main,im2col,im2col,benchmark/test_im2col.py,,yes,im2col +main,index_acc_perf,index,benchmark/test_index.py,,yes,index +main,index_add,index_add,benchmark/test_index_add.py,,yes,index_add +main,index_add_,index_add,benchmark/test_index_add.py,,yes,index_add_ +main,index_copy,index_copy,benchmark/test_index_copy.py,,yes,index_copy +main,index_copy_,index_copy,benchmark/test_index_copy.py,,yes,index_copy_ +main,index_put_acc_false,index_put,benchmark/test_index_put.py,,yes,index_put +main,index_put__acc_false,index_put,benchmark/test_index_put.py,,yes,index_put_ +main,index_put_acc_true,index_put,benchmark/test_index_put.py,,yes,index_put +main,index_put__acc_true,index_put,benchmark/test_index_put.py,,yes,index_put_ +main,index_put_impl_acc_false,index_put_impl,benchmark/test_index_put_impl.py,,yes,index_put_impl +main,index_put_impl_acc_true,index_put_impl,benchmark/test_index_put_impl.py,,yes,index_put_impl +main,index_reduce_prod,index_reduce,benchmark/test_index_reduce.py,,yes, +main,index_reduce_mean,index_reduce,benchmark/test_index_reduce.py,,yes, +main,index_reduce_amax,index_reduce,benchmark/test_index_reduce.py,,yes, +main,index_reduce_amin,index_reduce,benchmark/test_index_reduce.py,,yes, +main,index_select,index_select,benchmark/test_index_select.py,,yes,index_select +main,index_select_backward,index_select_backward,benchmark/test_index_select_backward.py,,yes,index_select_backward +main,indexer_k_quant_and_cache_benchmark,indexer_k_quant_and_cache,benchmark/test_indexer_k_quant_and_cache.py,,yes, +main,inplace_fused_experts_gems_vs_vllm,inplace_fused_experts,benchmark/test_inplace_fused_experts.py,,yes,inplace_fused_experts +main,instance_norm,instance_norm,benchmark/test_instance_norm.py,,yes,instance_norm +main,irshift__,irshift,benchmark/test_irshift.py,,yes,irshift__ +main,is_all_true,is_all_true,benchmark/test_is_all_true.py,,yes,is_all_true +main,is_nonzero,is_nonzero,benchmark/test_is_nonzero.py,,yes,is_nonzero +main,isclose,isclose,benchmark/test_isclose.py,,yes,isclose +main,isfinite,isfinite,benchmark/test_isfinite.py,,yes,isfinite +main,isin,isin,benchmark/test_isin.py,,yes,isin +main,isin_scalar_tensor,isin,benchmark/test_isin.py,,yes,isin_scalar_tensor +main,isin_tensor_scalar,isin,benchmark/test_isin.py,,yes,isin_tensor_scalar +main,isinf,isinf,benchmark/test_isinf.py,,yes,isinf +main,isnan,isnan,benchmark/test_isnan.py,,yes,isnan +main,isneginf,isneginf,benchmark/test_isneginf.py,,yes,isneginf +main,isneginf_out,isneginf,benchmark/test_isneginf.py,yes,yes,isneginf_out +main,isposinf,isposinf,benchmark/test_isposinf.py,,yes,isposinf +main,jagged_to_padded_dense_forward,jagged_to_padded_dense_forward,benchmark/test_jagged_to_padded_dense_forward.py,,yes,jagged_to_padded_dense_forward +main,kron,kron,benchmark/test_kron.py,,yes,kron +main,kthvalue,kthvalue,benchmark/test_kthvalue.py,,yes,kthvalue +main,native_layer_norm,layer_norm,benchmark/test_layer_norm.py,,yes,native_layer_norm +main,layer_norm,layer_norm,benchmark/test_layer_norm.py,,yes,layer_norm +main,layer_norm_backward,layer_norm,benchmark/test_layer_norm.py,,yes,layer_norm_backward +main,lcm,lcm,benchmark/test_lcm.py,,yes,lcm +main,lcm_,lcm_,benchmark/test_lcm_.py,,yes,lcm_ +main,le,le,benchmark/test_le.py,,yes,le +main,le_scalar,le,benchmark/test_le.py,,yes,le_scalar +main,le_,le_,benchmark/test_le_.py,,yes,le_ +main,le_scalar_,le_,benchmark/test_le_.py,,yes,le_scalar_ +main,leaky_relu,leaky_relu,benchmark/test_leaky_relu.py,,yes,leaky_relu +main,leaky_relu_inplace,leaky_relu,benchmark/test_leaky_relu.py,,yes,leaky_relu_ +main,leaky_relu_out,leaky_relu,benchmark/test_leaky_relu.py,,yes,leaky_relu_out +main,lerp_tensor,lerp,benchmark/test_lerp.py,,yes,lerp_tensor +main,lerp_tensor_inplace,lerp,benchmark/test_lerp.py,,yes,lerp_tensor_ +main,lerp_scalar,lerp,benchmark/test_lerp.py,,yes,lerp_scalar +main,lerp_scalar_inplace,lerp,benchmark/test_lerp.py,,yes,lerp_scalar_ +main,less,less,benchmark/test_less.py,,yes,less +main,less_scalar,less,benchmark/test_less.py,,yes,less_scalar +main,less_,less_,benchmark/test_less_.py,,yes,less_ +main,less_scalar_,less_,benchmark/test_less_.py,,yes,less_scalar_ +main,less_equal,less_equal,benchmark/test_less_equal.py,,yes,less_equal +main,less_equal_scalar,less_equal,benchmark/test_less_equal.py,,yes,less_equal_scalar +main,less_equal_,less_equal_,benchmark/test_less_equal_.py,,yes,less_equal_ +main,less_equal_scalar_,less_equal_,benchmark/test_less_equal_.py,,yes,less_equal_scalar_ +main,lgamma,lgamma_,benchmark/test_lgamma_.py,,yes,lgamma +main,lgamma_,lgamma_,benchmark/test_lgamma_.py,,yes,lgamma_ +main,lift,lift,benchmark/test_lift.py,,yes,lift +main,lift_out,lift,benchmark/test_lift.py,,yes,lift_out +main,lift_fresh,lift_fresh,benchmark/test_lift_fresh.py,,yes,lift_fresh +main,lift_fresh_copy,lift_fresh_copy,benchmark/test_lift_fresh_copy.py,,yes,lift_fresh_copy +main,linalg_cholesky,linalg_cholesky,benchmark/test_linalg_cholesky.py,,yes,linalg_cholesky +main,linalg_eigvals,linalg_eigvals,benchmark/test_linalg_eigvals.py,,yes,linalg_eigvals +main,linalg_ldl_factor,linalg_ldl_factor,benchmark/test_linalg_ldl_factor.py,,yes,linalg_ldl_factor +main,linalg_ldl_factor_ex,linalg_ldl_factor_ex,benchmark/test_linalg_ldl_factor_ex.py,,yes,linalg_ldl_factor_ex +main,linalg_ldl_solve,linalg_ldl_solve,benchmark/test_linalg_ldl_solve.py,,yes,linalg_ldl_solve +main,linalg_lstsq,linalg_lstsq,benchmark/test_linalg_lstsq.py,,yes,linalg_lstsq +main,linalg_lu_factor,linalg_lu_factor,benchmark/test_linalg_lu_factor.py,,yes,linalg_lu_factor +main,linalg_lu_factor_out,linalg_lu_factor,benchmark/test_linalg_lu_factor.py,,yes,linalg_lu_factor_out +main,linalg_lu_factor_ex,linalg_lu_factor_ex,benchmark/test_linalg_lu_factor_ex.py,,yes,linalg_lu_factor_ex +main,linalg_lu_factor_ex_out,linalg_lu_factor_ex,benchmark/test_linalg_lu_factor_ex.py,,yes,linalg_lu_factor_ex_out +main,linalg_slogdet,linalg_slogdet,benchmark/test_linalg_slogdet.py,,yes,linalg_slogdet +main,linalg_svdvals,linalg_svdvals,benchmark/test_linalg_svdvals.py,,yes,linalg_svdvals +main,linear,linear,benchmark/test_linear.py,,yes,linear +main,linear_backward,linear_backward,benchmark/test_linear_backward.py,,yes,linear_backward +main,linspace,linspace,benchmark/test_linspace.py,,yes,linspace +main,log,log,benchmark/test_log.py,,yes,log +main,log10,log10,benchmark/test_log10.py,,yes,log10 +main,log10_inplace,log10,benchmark/test_log10.py,,yes,log10_ +main,log10_out,log10,benchmark/test_log10.py,,yes,log10_out +main,log1p,log1p,benchmark/test_log1p.py,,yes,log1p +main,log1p_inplace,log1p,benchmark/test_log1p.py,,yes,log1p_ +main,log2,log2,benchmark/test_log2.py,,yes,log2 +main,log2_,log2,benchmark/test_log2.py,,yes,log2_ +main,log_inplace,log_,benchmark/test_log_.py,,yes,log_ +main,log_normal_,log_normal_,benchmark/test_log_normal_.py,,yes,log_normal_ +main,log_sigmoid,log_sigmoid,benchmark/test_log_sigmoid.py,,yes,log_sigmoid +main,log_sigmoid_forward,log_sigmoid_forward,benchmark/test_log_sigmoid_forward.py,,yes,log_sigmoid_forward +main,log_softmax,log_softmax,benchmark/test_log_softmax.py,,yes,log_softmax +main,log_softmax_out,log_softmax,benchmark/test_log_softmax.py,,yes,log_softmax_out +main,log_softmax_backward_data,log_softmax,benchmark/test_log_softmax.py,,yes,log_softmax_backward_data +main,log_softmax_backward_data_out,log_softmax,benchmark/test_log_softmax.py,,yes,log_softmax_backward_data_out +main,logaddexp,logaddexp,benchmark/test_logaddexp.py,,yes,logaddexp +main,logaddexp_out,logaddexp,benchmark/test_logaddexp.py,,yes,logaddexp_out +main,logaddexp2,logaddexp2,benchmark/test_logaddexp2.py,,yes,logaddexp2 +main,logaddexp2_out,logaddexp2,benchmark/test_logaddexp2.py,,yes,logaddexp2_out +main,logcumsumexp,logcumsumexp,benchmark/test_logcumsumexp.py,,yes,logcumsumexp +main,logcumsumexp_out,logcumsumexp,benchmark/test_logcumsumexp.py,,yes,logcumsumexp_out +main,logical_and,logical_and,benchmark/test_logical_and.py,,yes,logical_and +main,logical_and_inplace,logical_and,benchmark/test_logical_and.py,,yes,logical_and_ +main,logical_not,logical_not,benchmark/test_logical_not.py,,yes,logical_not +main,logical_not_,logical_not,benchmark/test_logical_not.py,,yes,logical_not_ +main,logical_or,logical_or,benchmark/test_logical_or.py,,yes,logical_or +main,logical_or_inplace,logical_or,benchmark/test_logical_or.py,,yes,logical_or_ +main,logical_xor,logical_xor,benchmark/test_logical_xor.py,,yes,logical_xor +main,logical_xor_,logical_xor_,benchmark/test_logical_xor_.py,,yes,logical_xor_ +main,logit,logit,benchmark/test_logit.py,,yes,logit +main,logit_inplace,logit,benchmark/test_logit.py,,yes,logit_ +main,logit_out,logit,benchmark/test_logit.py,,yes,logit_out +main,logspace,logspace,benchmark/test_logspace.py,,yes,logspace +main,logsumexp,logsumexp,benchmark/test_logsumexp.py,,yes,logsumexp +main,lshift,lshift,benchmark/test_lshift.py,,yes,lshift +main,lstm,lstm,benchmark/test_lstm.py,,yes,lstm +main,lt,lt,benchmark/test_lt.py,,yes,lt +main,lt_scalar,lt,benchmark/test_lt.py,,yes,lt_scalar +main,lt_,lt_,benchmark/test_lt_.py,,yes,lt_ +main,lt_scalar_,lt_,benchmark/test_lt_.py,,yes,lt_scalar_ +main,lu_unpack,lu_unpack,benchmark/test_lu_unpack.py,,yes,lu_unpack +main,make_dep_token,make_dep_token,benchmark/test_make_dep_token.py,,yes,make_dep_token +main,margin_ranking_loss,margin_ranking_loss,benchmark/test_margin_ranking_loss.py,,yes,margin_ranking_loss +main,margin_ranking_loss_backward,margin_ranking_loss,benchmark/test_margin_ranking_loss.py,,yes,margin_ranking_loss +main,masked_fill,masked_fill,benchmark/test_masked_fill.py,,yes,masked_fill +main,masked_fill_inplace,masked_fill,benchmark/test_masked_fill.py,,yes,masked_fill_ +main,masked_fill_scalar,masked_fill,benchmark/test_masked_fill.py,,yes,masked_fill_scalar +main,masked_fill_scalar_inplace,masked_fill,benchmark/test_masked_fill.py,,yes,masked_fill_scalar_ +main,masked_scale,masked_scale,benchmark/test_masked_scale.py,,yes,masked_scale +main,masked_scatter,masked_scatter,benchmark/test_masked_scatter.py,,yes,masked_scatter +main,masked_scatter_inplace,masked_scatter,benchmark/test_masked_scatter.py,,yes,masked_scatter_ +main,masked_select,masked_select,benchmark/test_masked_select.py,,yes,masked_select +main,matmul_bias_activation,matmul_bias_activation,benchmark/test_matmul_bias_activation.py,,yes,matmul_bias_activation +main,matmuladd,matmuladd,benchmark/test_matmuladd.py,,yes,matmuladd +main,max,max,benchmark/test_max.py,,yes,max +main,max_dim,max,benchmark/test_max.py,,yes,max_dim +main,max_pool2d_with_indices,max_pool2d,benchmark/test_max_pool2d.py,,yes,max_pool2d_with_indices +main,max_pool2d_backward,max_pool2d,benchmark/test_max_pool2d.py,,yes,max_pool2d_backward +main,max_pool2d_with_indices_backward,max_pool2d,benchmark/test_max_pool2d.py,,yes,max_pool2d_with_indices_backward +main,perf_max_pool3d,max_pool3d,benchmark/test_max_pool3d.py,,yes,max_pool3d +main,perf_max_pool3d_backward,max_pool3d,benchmark/test_max_pool3d.py,,yes,max_pool3d_backward +main,max_unpool2d,max_unpool2d,benchmark/test_max_unpool2d.py,,yes,max_unpool2d +main,max_unpool3d,max_unpool3d,benchmark/test_max_unpool3d.py,,yes,max_unpool3d +main,maximum,maximum,benchmark/test_maximum.py,,yes,maximum +main,mean,mean,benchmark/test_mean.py,,yes,mean +main,mean_dim,mean,benchmark/test_mean.py,,yes,mean_dim +main,median,median,benchmark/test_median.py,,yes,median +main,median_dim,median,benchmark/test_median.py,,yes,median_dim +main,mhc_post,mhc,benchmark/test_mhc.py,,yes,mhc_post +main,mhc_pre,mhc,benchmark/test_mhc.py,,yes,mhc_pre +main,hc_split_sinkhorn_forward,mhc,benchmark/test_mhc.py,,yes,hc_split_sinkhorn_forward +main,mhc_bwd,mhc,benchmark/test_mhc.py,,yes,mhc_bwd +main,hc_head_fused_kernel,mhc,benchmark/test_mhc.py,,yes,hc_head_fused_kernel +main,min,min,benchmark/test_min.py,,yes,min +main,min_dim,min,benchmark/test_min.py,,yes,min_dim +main,minimum,minimum,benchmark/test_minimum.py,,yes,minimum +main,miopen_batch_norm_backward,miopen_batch_norm_backward,benchmark/test_miopen_batch_norm_backward.py,,yes,miopen_batch_norm_backward +main,mish,mish,benchmark/test_mish.py,,yes,mish +main,mish_inplace,mish,benchmark/test_mish.py,,yes,mish_ +main,mish_backward,mish,benchmark/test_mish.py,,yes,mish_backward +main,mm,mm,benchmark/test_mm.py,,yes,mm +main,mm_self_transpose_benchmark,mm,benchmark/test_mm.py,,yes,mm_self_transpose +main,mm_out,mm,benchmark/test_mm.py,,yes,mm_out +main,perf_mode,mode,benchmark/test_mode.py,,yes,mode +main,moe_align_block_size_triton,moe_align_block_size_triton,benchmark/test_moe_align_block_size_triton.py,,yes,moe_align_block_size_triton +main,moe_align_block_size_fast_paths,moe_align_block_size_triton,benchmark/test_moe_align_block_size_triton.py,,yes,moe_align_block_size_fast_paths +main,moe_sum,moe_sum,benchmark/test_moe_sum.py,,yes,moe_sum +main,mrope_gems_vs_torch,mrope,benchmark/test_mrope.py,,yes,mrope +main,mse_loss,mse_loss,benchmark/test_mse_loss.py,,yes,mse_loss +main,mse_loss_backward,mse_loss_backward,benchmark/test_mse_loss_backward.py,,yes,mse_loss_backward +main,mul,mul,benchmark/test_mul.py,,yes,mul +main,mul_inplace,mul,benchmark/test_mul.py,,yes,mul_ +main,multinomial_with_replacement,multinomial,benchmark/test_multinomial.py,,yes,multinomial +main,multiply,multiply,benchmark/test_multiply.py,,yes,multiply +main,multiply_,multiply_,benchmark/test_multiply_.py,,yes,multiply_ +main,mv,mv,benchmark/test_mv.py,,yes,mv +main,mvlgamma,mvlgamma,benchmark/test_mvlgamma.py,,yes,mvlgamma +main,mvlgamma_,mvlgamma_,benchmark/test_mvlgamma_.py,,yes,mvlgamma_ +main,nan_to_num,nan_to_num,benchmark/test_nan_to_num.py,,yes,nan_to_num +main,nan_to_num_,nan_to_num_,benchmark/test_nan_to_num_.py,,yes,nan_to_num_ +main,nanmedian,nanmedian,benchmark/test_nanmedian.py,,yes,nanmedian +main,nanmedian_out,nanmedian,benchmark/test_nanmedian.py,,yes,nanmedian_out +main,nanmedian_dim,nanmedian,benchmark/test_nanmedian.py,,yes,nanmedian_dim +main,nanmedian_dim_values,nanmedian,benchmark/test_nanmedian.py,,yes,nanmedian_dim_values +main,benchmark_nansum,nansum,benchmark/test_nansum.py,,yes,nansum +main,narrow,narrow,benchmark/test_narrow.py,,yes,narrow +main,narrow_copy_perf,narrow_copy,benchmark/test_narrow_copy.py,,yes,narrow_copy +main,native_batch_norm_legit_functional,native_batch_norm_legit_functional,benchmark/test_native_batch_norm_legit_functional.py,,yes,native_batch_norm_legit_functional +main,ne,ne,benchmark/test_ne.py,,yes,ne +main,ne_scalar,ne,benchmark/test_ne.py,,yes,ne_scalar +main,ne_,ne_,benchmark/test_ne_.py,,yes,ne_ +main,ne_scalar_,ne_,benchmark/test_ne_.py,,yes,ne_scalar_ +main,neg,neg,benchmark/test_neg.py,,yes,neg +main,neg_inplace,neg,benchmark/test_neg.py,,yes,neg_ +main,negative,negative,benchmark/test_negative.py,,yes,negative +main,negative_,negative_,benchmark/test_negative_.py,,yes,negative_ +main,nested_view_from_buffer_copy,nested_view_from_buffer_copy,benchmark/test_nested_view_from_buffer_copy.py,,yes,nested_view_from_buffer_copy +main,new_full,new_full,benchmark/test_new_full.py,,yes,new_full +main,new_ones,new_ones,benchmark/test_new_ones.py,,yes,new_ones +main,nextafter,nextafter,benchmark/test_nextafter.py,,yes,nextafter +main,nextafter_,nextafter,benchmark/test_nextafter.py,,yes,nextafter_ +main,nextafter_,nextafter_,benchmark/test_nextafter_.py,,yes,nextafter_ +main,nll_loss_forward,nll_loss,benchmark/test_nll_loss.py,,yes,nll_loss_forward +main,nll_loss_backward,nll_loss,benchmark/test_nll_loss.py,,yes,nll_loss_backward +main,nll_loss2d_forward,nll_loss2d,benchmark/test_nll_loss2d.py,,yes,nll_loss2d_forward +main,nll_loss2d_backward,nll_loss2d,benchmark/test_nll_loss2d.py,,yes,nll_loss2d_backward +main,nll_loss_nd_forward,nll_loss_nd,benchmark/test_nll_loss_nd.py,,yes,nll_loss_nd_forward +main,nll_loss_nd_backward,nll_loss_nd,benchmark/test_nll_loss_nd.py,,yes,nll_loss_nd_backward +main,nonzero,nonzero,benchmark/test_nonzero.py,,yes,nonzero +main,nonzero_numpy,nonzero_numpy,benchmark/test_nonzero_numpy.py,,yes,nonzero_numpy +main,perf_nonzero_static,nonzero_static,benchmark/test_nonzero_static.py,,yes,nonzero_static +main,norm,norm,benchmark/test_norm.py,,yes,norm +main,norm_scalar,norm,benchmark/test_norm.py,,yes,norm_scalar +main,norm_scalaropt_dim,norm,benchmark/test_norm.py,,yes,norm_scalaropt_dim +main,normal_tensor_tensor,normal,benchmark/test_normal.py,,yes,normal_tensor_tensor +main,normal_tensor_float,normal,benchmark/test_normal.py,,yes,normal_tensor_float +main,normal_inplace,normal,benchmark/test_normal.py,,yes,normal_float_float_ +main,normal_float_tensor,normal,benchmark/test_normal.py,,yes,normal_float_tensor +main,normed_cumsum,normed_cumsum,benchmark/test_normed_cumsum.py,,yes,normed_cumsum +main,not_equal,not_equal,benchmark/test_not_equal.py,,yes,not_equal +main,not_equal_scalar,not_equal,benchmark/test_not_equal.py,,yes,not_equal_scalar +main,not_equal_,not_equal_,benchmark/test_not_equal_.py,,yes,not_equal_ +main,not_equal_scalar_,not_equal_,benchmark/test_not_equal_.py,,yes,not_equal_scalar_ +main,one_hot,one_hot,benchmark/test_one_hot.py,,yes,one_hot +main,ones,ones,benchmark/test_ones.py,,yes,ones +main,ones_like,ones_like,benchmark/test_ones_like.py,,yes,ones_like +main,outer,outer,benchmark/test_outer.py,,yes,outer +main,outplace_fused_experts_gems_vs_vllm,outplace_fused_experts,benchmark/test_outplace_fused_experts.py,,yes,outplace_fused_experts +main,pack_seq,pack_seq,benchmark/test_pack_seq.py,,yes,pack_seq_triton +main,pack_seq_fp8,pack_seq,benchmark/test_pack_seq.py,,yes,pack_seq_triton +main,pad,pad,benchmark/test_pad.py,,yes,pad +main,pairwise_distance,pairwise_distance,benchmark/test_pairwise_distance.py,,yes,pairwise_distance +main,pdist,pdist,benchmark/test_pdist.py,,yes,pdist +main,pdist_backward,pdist_backward,benchmark/test_pdist_backward.py,,yes,pdist_backward +main,pdist_forward,pdist_forward_perf,benchmark/test_pdist_forward_perf.py,,yes,pdist_forward +main,per_token_group_quant_fp8,per_token_group_quant_fp8,benchmark/test_per_token_group_quant_fp8.py,,yes,per_token_group_quant_fp8 +main,permute_copy,permute_copy,benchmark/test_permute_copy.py,,yes,permute_copy +main,pixel_shuffle,pixel_shuffle,benchmark/test_pixel_shuffle.py,,yes,pixel_shuffle +main,pixel_shuffle_out,pixel_shuffle,benchmark/test_pixel_shuffle.py,,yes,pixel_shuffle_out +main,pixel_unshuffle,pixel_unshuffle,benchmark/test_pixel_unshuffle.py,,yes,pixel_unshuffle +main,pixel_unshuffle_out,pixel_unshuffle,benchmark/test_pixel_unshuffle.py,,yes,pixel_unshuffle_out +main,poisson,poisson,benchmark/test_poisson.py,,yes,poisson +main,polar,polar,benchmark/test_polar.py,,yes,polar +main,polygamma,polygamma,benchmark/test_polygamma.py,,yes,polygamma +main,polygamma_inplace,polygamma,benchmark/test_polygamma.py,,yes,polygamma_ +main,polygamma_out,polygamma,benchmark/test_polygamma.py,,yes,polygamma_out +main,pow_tensor_tensor,pow,benchmark/test_pow.py,,yes,pow_tensor_tensor +main,pow_inplace,pow,benchmark/test_pow.py,,yes,pow_tensor_tensor_ +main,pow_scalar,pow,benchmark/test_pow.py,,yes,pow_scalar +main,pow_tensor_scalar,pow,benchmark/test_pow.py,,yes,pow_tensor_scalar +main,pow_tensor_scalar_inplace,pow,benchmark/test_pow.py,,yes,pow_tensor_scalar_ +main,prelu,prelu,benchmark/test_prelu.py,,yes,prelu +main,prelu_kernel,prelu_kernel,benchmark/test_prelu_kernel.py,,yes,prelu_kernel +main,prelu_kernel_backward,prelu_kernel_backward,benchmark/test_prelu_kernel_backward.py,,yes,prelu_kernel_backward +main,prod,prod,benchmark/test_prod.py,,yes,prod +main,quantile,quantile,benchmark/test_quantile.py,,yes,quantile +main,rad2deg,rad2deg,benchmark/test_rad2deg.py,,yes,rad2deg +main,rad2deg_,rad2deg,benchmark/test_rad2deg.py,,yes,rad2deg_ +main,rand,rand,benchmark/test_rand.py,,yes,rand +main,rand_like,rand_like,benchmark/test_rand_like.py,,yes,rand_like +main,randint,randint,benchmark/test_randint.py,,yes,randint +main,randint_like,randint_like,benchmark/test_randint_like.py,,yes,randint_like +main,randn,randn,benchmark/test_randn.py,,yes,randn +main,randn_like,randn_like,benchmark/test_randn_like.py,,yes,randn_like +main,randperm,randperm,benchmark/test_randperm.py,,yes,randperm +main,range,range,benchmark/test_range.py,,yes,range +main,reciprocal,reciprocal,benchmark/test_reciprocal.py,,yes,reciprocal +main,reciprocal_inplace,reciprocal,benchmark/test_reciprocal.py,,yes,reciprocal_ +main,reflection_pad1d,reflection_pad1d,benchmark/test_reflection_pad1d.py,,yes,reflection_pad1d +main,reflection_pad1d_out,reflection_pad1d,benchmark/test_reflection_pad1d.py,,yes,reflection_pad1d_out +main,reflection_pad1d_backward,reflection_pad1d_backward,benchmark/test_reflection_pad1d_backward.py,,yes,reflection_pad1d_backward +main,reflection_pad2d,reflection_pad2d,benchmark/test_reflection_pad2d.py,,yes,reflection_pad2d +main,reflection_pad2d_out,reflection_pad2d,benchmark/test_reflection_pad2d.py,,yes,reflection_pad2d_out +main,reflection_pad2d_backward,reflection_pad2d_backward,benchmark/test_reflection_pad2d_backward.py,,yes,reflection_pad2d_backward +main,reflection_pad3d,reflection_pad3d,benchmark/test_reflection_pad3d.py,,yes,reflection_pad3d +main,reflection_pad3d_out,reflection_pad3d,benchmark/test_reflection_pad3d.py,,yes,reflection_pad3d_out +main,reflection_pad3d_backward,reflection_pad3d_backward,benchmark/test_reflection_pad3d_backward.py,,yes,reflection_pad3d_backward +main,reglu,reglu,benchmark/test_reglu.py,,yes,reglu +main,relu,relu,benchmark/test_relu.py,,yes,relu +main,relu_inplace,relu,benchmark/test_relu.py,,yes,relu_ +main,relu6,relu6,benchmark/test_relu6.py,,yes,relu6 +main,remainder,remainder,benchmark/test_remainder.py,,yes,remainder +main,remainder_tensor,remainder,benchmark/test_remainder.py,,yes,remainder_tensor +main,remainder_tensor_inplace,remainder,benchmark/test_remainder.py,,yes,remainder_tensor_ +main,remainder_scalar,remainder,benchmark/test_remainder.py,,yes,remainder_scalar +main,remainder_scalar_inplace,remainder,benchmark/test_remainder.py,,yes,remainder_scalar_ +main,remainder_scalar_tensor,remainder,benchmark/test_remainder.py,,yes,remainder_scalar_tensor +main,renorm,renorm,benchmark/test_renorm.py,,yes,renorm +main,renorm_,renorm_,benchmark/test_renorm_.py,,yes,renorm_ +main,repeat,repeat,benchmark/test_repeat.py,,yes,repeat +main,repeat_interleave_self_int,repeat_interleave,benchmark/test_repeat_interleave.py,,yes,repeat_interleave_self_int +main,repeat_interleave_self_tensor,repeat_interleave,benchmark/test_repeat_interleave.py,,yes,repeat_interleave_self_tensor +main,repeat_interleave_tensor,repeat_interleave,benchmark/test_repeat_interleave.py,,yes,repeat_interleave_tensor +main,replication_pad1d,replication_pad1d,benchmark/test_replication_pad1d.py,,yes,replication_pad1d +main,replication_pad2d,replication_pad2d,benchmark/test_replication_pad2d.py,,yes,replication_pad2d +main,replication_pad2d_out,replication_pad2d,benchmark/test_replication_pad2d.py,,yes,replication_pad2d_out +main,replication_pad2d_backward,replication_pad2d_backward,benchmark/test_replication_pad2d_backward.py,,yes,replication_pad2d_backward +main,replication_pad3d,replication_pad3d,benchmark/test_replication_pad3d.py,,yes,replication_pad3d +main,replication_pad3d_backward,replication_pad3d_backward,benchmark/test_replication_pad3d_backward.py,,yes,replication_pad3d_backward +main,reshape_and_cache,reshape_and_cache,benchmark/test_reshape_and_cache.py,,yes,reshape_and_cache +main,reshape_and_cache_flash,reshape_and_cache_flash,benchmark/test_reshape_and_cache_flash.py,,yes,reshape_and_cache_flash +main,resize,resize,benchmark/test_resize.py,,yes,resize +main,resize_,resize,benchmark/test_resize.py,,yes,resize_ +main,resize_as,resize_as,benchmark/test_resize_as.py,,yes,resize_as +main,resize_as_,resize_as,benchmark/test_resize_as.py,,yes,resize_as_ +main,resize_output,resize_output,benchmark/test_resize_output.py,,yes,resize_output +main,resolve_conj,resolve_conj,benchmark/test_resolve_conj.py,,yes,resolve_conj +main,resolve_neg,resolve_neg,benchmark/test_resolve_neg.py,,yes,resolve_neg +main,rms_norm,rms_norm,benchmark/test_rms_norm.py,,yes,rms_norm +main,rnn_relu,rnn_relu,benchmark/test_rnn_relu.py,,yes,rnn_relu +main,roll,roll,benchmark/test_roll.py,,yes,roll +main,rot90,rot90,benchmark/test_rot90.py,,yes,rot90 +main,round,round,benchmark/test_round.py,,yes,round +main,round_inplace,round,benchmark/test_round.py,,yes,round_ +main,round_out,round,benchmark/test_round.py,,yes,round_out +main,perf_router_gemm,router_gemm,benchmark/test_router_gemm.py,,yes,router_gemm +main,rrelu_with_noise_backward,rrelu_with_noise_backward,benchmark/test_rrelu_with_noise_backward.py,,yes,rrelu_with_noise_backward +main,rrelu_with_noise_functional,rrelu_with_noise_functional,benchmark/test_rrelu_with_noise_functional.py,,yes,rrelu_with_noise_functional +main,rsqrt,rsqrt,benchmark/test_rsqrt.py,,yes,rsqrt +main,rsqrt_inplace,rsqrt,benchmark/test_rsqrt.py,,yes,rsqrt_ +main,rsub_tensor,rsub,benchmark/test_rsub.py,,yes,rsub_tensor +main,rsub_scalar,rsub,benchmark/test_rsub.py,,yes,rsub_scalar +main,rwkv_ka_fusion,rwkv_ka_fusion,benchmark/test_rwkv_ka_fusion.py,,yes,rwkv_ka_fusion +main,rwkv_mm_sparsity,rwkv_mm_sparsity,benchmark/test_rwkv_mm_sparsity.py,,yes,rwkv_mm_sparsity +main,safe_softmax,safe_softmax,benchmark/test_safe_softmax.py,,yes,safe_softmax +main,scalar_tensor,scalar_tensor,benchmark/test_scalar_tensor.py,,yes,scalar_tensor +main,scaled_dot_product_flash_attention,scaled_dot_product_attention,benchmark/test_scaled_dot_product_attention.py,,yes,scaled_dot_product_flash_attention +main,scaled_dot_product_attention,scaled_dot_product_attention,benchmark/test_scaled_dot_product_attention.py,,yes,scaled_dot_product_attention +main,scaled_dot_product_fused_attention_overrideable,scaled_dot_product_fused_attention_overrideable,benchmark/test_scaled_dot_product_fused_attention_overrideable.py,,yes,scaled_dot_product_fused_attention_overrideable +main,scaled_grouped_mm_benchmark,scaled_grouped_mm,benchmark/test_scaled_grouped_mm.py,,yes, +main,scaled_mm_benchmark,scaled_mm,benchmark/test_scaled_mm.py,,yes,scaled_mm +main,scaled_mm_out_benchmark,scaled_mm,benchmark/test_scaled_mm.py,,yes,scaled_mm_out +main,scaled_softmax_forward,scaled_softmax,benchmark/test_scaled_softmax.py,,yes,scaled_softmax_forward +main,perf_scaled_softmax_backward,scaled_softmax,benchmark/test_scaled_softmax.py,,yes,scaled_softmax_backward +main,scatter_add_inplace,scatter_add,benchmark/test_scatter_add.py,,yes,scatter_add_ +main,scatter_add,scatter_add,benchmark/test_scatter_add.py,,yes,scatter_add +main,scatter_reduce_add,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce +main,scatter_reduce_multiply,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce +main,scatter_reduce_add_inplace,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce_ +main,scatter_reduce_multiply_inplace,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce_ +main,scatter_reduce_two_sum,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce.two +main,scatter_reduce_two_amax,scatter_reduce,benchmark/test_scatter_reduce.py,,yes,scatter_reduce.two +main,scatter_reduce_two_inplace_sum,scatter_reduce_two,benchmark/test_scatter_reduce_two.py,,yes,scatter_reduce_ +main,scatter_reduce_two_inplace_amax,scatter_reduce_two,benchmark/test_scatter_reduce_two.py,,yes,scatter_reduce_ +main,scatter_reduce_two_inplace_amin,scatter_reduce_two,benchmark/test_scatter_reduce_two.py,,yes,scatter_reduce_ +main,scatter_reduce_two_inplace_mean,scatter_reduce_two,benchmark/test_scatter_reduce_two.py,,yes,scatter_reduce_ +main,scatter_src,scatter_src,benchmark/test_scatter_src.py,,yes,scatter_src +main,scatter_src_inplace,scatter_src,benchmark/test_scatter_src.py,,yes,scatter_src_ +main,searchsorted,searchsorted,benchmark/test_searchsorted.py,,yes,searchsorted +main,searchsorted_scalar,searchsorted,benchmark/test_searchsorted.py,,yes,searchsorted_scalar +main,searchsorted_out,searchsorted,benchmark/test_searchsorted.py,,yes,searchsorted_out +main,searchsorted_scalar_out,searchsorted,benchmark/test_searchsorted.py,,yes,searchsorted_scalar_out +main,segment_reduce,segment_reduce,benchmark/test_segment_reduce.py,,yes,segment_reduce +main,segment_reduce_out,segment_reduce,benchmark/test_segment_reduce.py,,yes,segment_reduce_out +main,segment_reduce_backward,segment_reduce,benchmark/test_segment_reduce.py,,yes,segment_reduce_backward +main,segment_reduce_backward_out,segment_reduce,benchmark/test_segment_reduce.py,,yes,segment_reduce_backward_out +main,select_backward,select_backward,benchmark/test_select_backward.py,,yes,select_backward +main,select_scatter,select_scatter,benchmark/test_select_scatter.py,,yes,select_scatter +main,selu,selu,benchmark/test_selu.py,,yes,selu +main,selu_inplace,selu,benchmark/test_selu.py,,yes,selu_ +main,sgn,sgn,benchmark/test_sgn.py,,yes,sgn +main,sgn_inplace,sgn,benchmark/test_sgn.py,,yes,sgn_ +main,sgn_out,sgn,benchmark/test_sgn.py,,yes,sgn_out +main,sigmoid,sigmoid,benchmark/test_sigmoid.py,,yes,sigmoid +main,sigmoid_inplace,sigmoid,benchmark/test_sigmoid.py,,yes,sigmoid_ +main,sigmoid_backward,sigmoid,benchmark/test_sigmoid.py,,yes,sigmoid_backward +main,sign,sign,benchmark/test_sign.py,,yes,sign +main,sign_out,sign,benchmark/test_sign.py,,yes,sign_out +main,signbit,signbit,benchmark/test_signbit.py,,yes,signbit +main,signbit_out,signbit,benchmark/test_signbit.py,yes,yes,signbit_out +main,silu,silu,benchmark/test_silu.py,,yes,silu +main,silu_inplace,silu,benchmark/test_silu.py,,yes,silu_ +main,silu_backward,silu,benchmark/test_silu.py,,yes,silu_backward +main,silu_and_mul,silu_and_mul,benchmark/test_silu_and_mul.py,,yes,silu_and_mul +main,silu_and_mul_out,silu_and_mul,benchmark/test_silu_and_mul.py,,yes,silu_and_mul_out +main,silu_and_mul_with_clamp,silu_and_mul_with_clamp,benchmark/test_silu_and_mul_with_clamp.py,,yes,silu_and_mul_with_clamp +main,silu_and_mul_with_clamp_out,silu_and_mul_with_clamp,benchmark/test_silu_and_mul_with_clamp.py,,yes,silu_and_mul_with_clamp_out +main,sin,sin,benchmark/test_sin.py,,yes,sin +main,sin_inplace,sin,benchmark/test_sin.py,,yes,sin_ +main,sinc,sinc,benchmark/test_sinc.py,,yes,sinc +main,sinc_,sinc,benchmark/test_sinc.py,,yes,sinc_ +main,sinh,sinh,benchmark/test_sinh.py,,yes,sinh +main,sinh_inplace,sinh,benchmark/test_sinh.py,,yes,sinh_ +main,skip_layernorm,skip_layer_norm,benchmark/test_skip_layer_norm.py,,yes,skip_layer_norm +main,slice_backward,slice_backward,benchmark/test_slice_backward.py,,yes,slice_backward +main,slice_scatter,slice_scatter,benchmark/test_slice_scatter.py,,yes,slice_scatter +main,smooth_l1_loss,smooth_l1_loss,benchmark/test_smooth_l1_loss.py,,yes,smooth_l1_loss +main,smooth_l1_loss_backward,smooth_l1_loss,benchmark/test_smooth_l1_loss.py,,yes,smooth_l1_loss_backward +main,soft_margin_loss,soft_margin_loss,benchmark/test_soft_margin_loss.py,,yes,soft_margin_loss +main,soft_margin_loss_backward,soft_margin_loss_backward,benchmark/test_soft_margin_loss_backward.py,,yes,soft_margin_loss_backward +main,softmax,softmax,benchmark/test_softmax.py,,yes,softmax +main,softmax_backward,softmax,benchmark/test_softmax.py,,yes,softmax +main,softmax_backward_out,softmax,benchmark/test_softmax.py,,yes,softmax_backward_out +main,softmax_out,softmax,benchmark/test_softmax.py,,yes,softmax_out +main,softplus,softplus,benchmark/test_softplus.py,,yes,softplus +main,softplus_backward,softplus,benchmark/test_softplus.py,,yes,softplus_backward +main,softshrink,softshrink,benchmark/test_softshrink.py,,yes,softshrink +main,softshrink_out,softshrink,benchmark/test_softshrink.py,,yes,softshrink_out +main,perf_sort,sort,benchmark/test_sort.py,,yes,sort +main,perf_sort_stable,sort,benchmark/test_sort.py,,yes,sort_stable +main,sparse_attn_triton,sparse_attention,benchmark/test_sparse_attention.py,,yes,sparse_attention +main,sparse_mla_fwd_interface,sparse_mla_fwd_interface,benchmark/test_sparse_mla_fwd_interface.py,,yes,sparse_mla_fwd_interface +main,sparse_semi_structured_mm,sparse_semi_structured_mm,benchmark/test_sparse_semi_structured_mm.py,,yes,sparse_semi_structured_mm +main,special_airy_ai,special_airy_ai,benchmark/test_special_airy_ai.py,,yes,special_airy_ai +main,special_airy_ai_out,special_airy_ai,benchmark/test_special_airy_ai.py,,yes,special_airy_ai_out +main,special_bessel_j0,special_bessel_j0,benchmark/test_special_bessel_j0.py,,yes,special_bessel_j0 +main,special_bessel_j1,special_bessel_j1,benchmark/test_special_bessel_j1.py,,yes,special_bessel_j1 +main,special_chebyshev_polynomial_u,special_chebyshev_polynomial_u,benchmark/test_special_chebyshev_polynomial_u.py,,yes,special_chebyshev_polynomial_u +main,special_chebyshev_polynomial_v,special_chebyshev_polynomial_v,benchmark/test_special_chebyshev_polynomial_v.py,,yes,special_chebyshev_polynomial_v +main,special_chebyshev_polynomial_w,special_chebyshev_polynomial_w,benchmark/test_special_chebyshev_polynomial_w.py,,yes,special_chebyshev_polynomial_w +main,special_chebyshev_polynomial_w_out,special_chebyshev_polynomial_w,benchmark/test_special_chebyshev_polynomial_w.py,,yes,special_chebyshev_polynomial_w_out +main,special_digamma,special_digamma,benchmark/test_special_digamma.py,,yes,special_digamma +main,special_erfc,special_erfc,benchmark/test_special_erfc.py,,yes,special_erfc +main,erfc,special_erfc,benchmark/test_special_erfc.py,,yes,erfc +main,erfc_,special_erfc,benchmark/test_special_erfc.py,,yes,erfc_ +main,special_erfcx,special_erfcx,benchmark/test_special_erfcx.py,,yes,special_erfcx +main,special_erfinv,special_erfinv,benchmark/test_special_erfinv.py,,yes,special_erfinv +main,special_erfinv_out,special_erfinv,benchmark/test_special_erfinv.py,,yes,special_erfinv_out +main,special_gammainc,special_gammainc,benchmark/test_special_gammainc.py,,yes,special_gammainc +main,special_gammaln,special_gammaln,benchmark/test_special_gammaln.py,,yes,special_gammaln +main,special_gammaln_out,special_gammaln,benchmark/test_special_gammaln.py,,yes,special_gammaln_out +main,special_hermite_polynomial_h,special_hermite_polynomial_h,benchmark/test_special_hermite_polynomial_h.py,,yes,special_hermite_polynomial_h +main,special_i0e,special_i0e,benchmark/test_special_i0e.py,,yes,special_i0e +main,special_i0e_out,special_i0e,benchmark/test_special_i0e.py,,yes,special_i0e_out +main,special_i1,special_i1,benchmark/test_special_i1.py,,yes,special_i1 +main,special_i1_out,special_i1,benchmark/test_special_i1.py,,yes,special_i1_out +main,special_i1e,special_i1e,benchmark/test_special_i1e.py,,yes,special_i1e +main,special_legendre_polynomial_p,special_legendre_polynomial_p,benchmark/test_special_legendre_polynomial_p.py,,yes,special_legendre_polynomial_p +main,special_log1p,special_log1p,benchmark/test_special_log1p.py,,yes,special_log1p +main,special_log1p_out,special_log1p,benchmark/test_special_log1p.py,,yes,special_log1p_out +main,special_log1p_non_tensor,special_log1p,benchmark/test_special_log1p.py,,yes, +main,special_log_softmax,special_log_softmax,benchmark/test_special_log_softmax.py,,yes,special_log_softmax +main,special_logsumexp,special_logsumexp,benchmark/test_special_logsumexp.py,,yes,special_logsumexp +main,special_modified_bessel_k0,special_modified_bessel_k0,benchmark/test_special_modified_bessel_k0.py,,yes,special_modified_bessel_k0 +main,special_modified_bessel_k0_out,special_modified_bessel_k0,benchmark/test_special_modified_bessel_k0.py,,yes,special_modified_bessel_k0_out +main,special_modified_bessel_k1,special_modified_bessel_k1,benchmark/test_special_modified_bessel_k1.py,,yes,special_modified_bessel_k1 +main,special_modified_bessel_k1_out,special_modified_bessel_k1,benchmark/test_special_modified_bessel_k1.py,,yes,special_modified_bessel_k1_out +main,special_round,special_round,benchmark/test_special_round.py,,yes,special_round +main,special_round_out,special_round,benchmark/test_special_round.py,,yes,special_round_out +main,special_scaled_modified_bessel_k1,special_scaled_modified_bessel_k1,benchmark/test_special_scaled_modified_bessel_k1.py,,yes,special_scaled_modified_bessel_k1 +main,special_scaled_modified_bessel_k1_out,special_scaled_modified_bessel_k1,benchmark/test_special_scaled_modified_bessel_k1.py,,yes,special_scaled_modified_bessel_k1_out +main,special_shifted_chebyshev_polynomial_u,special_shifted_chebyshev_polynomial_u,benchmark/test_special_shifted_chebyshev_polynomial_u.py,,yes,special_shifted_chebyshev_polynomial_u +main,special_shifted_chebyshev_polynomial_u_,special_shifted_chebyshev_polynomial_u,benchmark/test_special_shifted_chebyshev_polynomial_u.py,,yes,special_shifted_chebyshev_polynomial_u_ +main,special_shifted_chebyshev_polynomial_v,special_shifted_chebyshev_polynomial_v,benchmark/test_special_shifted_chebyshev_polynomial_v.py,,yes,special_shifted_chebyshev_polynomial_v +main,special_shifted_chebyshev_polynomial_w,special_shifted_chebyshev_polynomial_w,benchmark/test_special_shifted_chebyshev_polynomial_w.py,,yes,special_shifted_chebyshev_polynomial_w +main,special_sinc,special_sinc,benchmark/test_special_sinc.py,,yes,special_sinc +main,special_xlog1py,special_xlog1py,benchmark/test_special_xlog1py.py,,yes,special_xlog1py +main,split_with_sizes_copy,split_with_sizes_copy,benchmark/test_split_with_sizes_copy.py,,yes,split_with_sizes_copy +main,sqrt,sqrt,benchmark/test_sqrt.py,,yes,sqrt +main,sqrt_inplace,sqrt,benchmark/test_sqrt.py,,yes,sqrt_ +main,square,square,benchmark/test_square.py,,yes,square +main,square_inplace,square,benchmark/test_square.py,,yes,square_ +main,square_out,square,benchmark/test_square.py,,yes,square_out +main,squeeze_copy,squeeze_copy,benchmark/test_squeeze_copy.py,,yes,squeeze_copy +main,stack,stack,benchmark/test_stack.py,,yes,stack +main,stage_deepseek_v4_mega_moe_inputs_benchmark,stage_deepseek_v4_mega_moe_inputs,benchmark/test_stage_deepseek_v4_mega_moe_inputs.py,,yes, +main,std,std,benchmark/test_std.py,,yes,std +main,sub,sub,benchmark/test_sub.py,,yes,sub +main,sub_inplace,sub,benchmark/test_sub.py,,yes,sub_ +main,subtract,subtract_,benchmark/test_subtract_.py,,yes,subtract +main,subtract_,subtract_,benchmark/test_subtract_.py,,yes,subtract_ +main,sum,sum,benchmark/test_sum.py,,yes,sum +main,sum_dim_out,sum,benchmark/test_sum.py,,yes,sum_dim_out +main,sum_out,sum,benchmark/test_sum.py,,yes,sum_out +main,sum_dim,sum_dim,benchmark/test_sum_dim.py,,yes,sum_dim +main,svd,svd,benchmark/test_svd.py,,yes,svd +main,swiglu,swiglu,benchmark/test_swiglu.py,,yes,swiglu +main,sym_storage_offset,sym_storage_offset,benchmark/test_sym_storage_offset.py,,yes,sym_storage_offset +main,sym_stride,sym_stride,benchmark/test_sym_stride.py,,yes,sym_stride +main,t_copy,t_copy,benchmark/test_t_copy.py,,yes,t_copy +main,t_copy_out,t_copy,benchmark/test_t_copy.py,,yes,t_copy_out +main,take,take,benchmark/test_take.py,,yes,take +main,take_out,take,benchmark/test_take.py,,yes,take_out +main,tan,tan,benchmark/test_tan.py,,yes,tan +main,tan_inplace,tan,benchmark/test_tan.py,,yes,tan_ +main,tanh,tanh,benchmark/test_tanh.py,,yes,tanh +main,tanh_inplace,tanh,benchmark/test_tanh.py,,yes,tanh_ +main,tanh_backward,tanh,benchmark/test_tanh.py,,yes,tanh_backward +main,te_rmsnorm_fwd,te_rmsnorm,benchmark/test_te_rmsnorm.py,,yes,te_rmsnorm_fwd +main,te_rmsnorm_bwd,te_rmsnorm,benchmark/test_te_rmsnorm.py,,yes,te_rmsnorm_bwd +main,tensor_split,tensor_split,benchmark/test_tensor_split.py,,yes,tensor_split +main,thnn_fused_lstm_cell,thnn_fused_lstm_cell,benchmark/test_thnn_fused_lstm_cell.py,,yes,thnn_fused_lstm_cell +main,thnn_fused_lstm_cell_backward_impl,thnn_fused_lstm_cell_backward_impl,benchmark/test_thnn_fused_lstm_cell_backward_impl.py,,yes,thnn_fused_lstm_cell_backward_impl +main,threshold,threshold,benchmark/test_threshold.py,,yes,threshold +main,threshold_backward,threshold,benchmark/test_threshold.py,,yes,threshold_backward +main,threshold_,threshold_,benchmark/test_threshold_.py,,yes,threshold_ +main,tile,tile,benchmark/test_tile.py,,yes,tile +main,to_copy,to_copy,benchmark/test_to_copy.py,,yes, +main,top_k_per_row_decode,top_k_per_row_decode,benchmark/test_top_k_per_row_decode.py,,yes,top_k_per_row_decode +main,top_k_per_row_prefill,top_k_per_row_prefill,benchmark/test_top_k_per_row_prefill.py,,yes,top_k_per_row_prefill +main,topk,topk,benchmark/test_topk.py,,yes,topk +main,topk_softmax,topk_softmax,benchmark/test_topk_softmax.py,,yes,topk_softmax +main,topk_softplus_sqrt,topk_softplus_sqrt,benchmark/test_topk_softplus_sqrt.py,,yes,topk_softplus_sqrt +main,trace,trace,benchmark/test_trace.py,,yes,trace +main,transpose,transpose,benchmark/test_transpose.py,,yes,transpose +main,tril,tril,benchmark/test_tril.py,,yes,tril +main,tril_extreme_diagonal,tril,benchmark/test_tril.py,,yes,tril +main,tril_out_transposed,tril,benchmark/test_tril.py,,yes,tril_out +main,tril_out_sliced,tril,benchmark/test_tril.py,,yes,tril_out +main,tril_inplace,tril,benchmark/test_tril.py,,yes,tril_ +main,triu,triu,benchmark/test_triu.py,,yes,triu +main,triu_inplace,triu,benchmark/test_triu.py,,yes,triu_ +main,true_divide,true_divide,benchmark/test_true_divide.py,,yes,div_tensor +main,true_divide_scalar,true_divide,benchmark/test_true_divide.py,,yes,div_scalar +main,true_divide_inplace_scalar,true_divide,benchmark/test_true_divide.py,,yes,div_scalar_ +main,trunc,trunc_,benchmark/test_trunc_.py,,yes,trunc +main,trunc_,trunc_,benchmark/test_trunc_.py,,yes,trunc_ +main,trunc_divide,trunc_divide,benchmark/test_trunc_divide.py,,yes,trunc_divide +main,trunc_divide_inplace,trunc_divide,benchmark/test_trunc_divide.py,,yes,trunc_divide_ +main,unbind,unbind,benchmark/test_unbind.py,,yes,unbind +main,unbind_copy,unbind_copy,benchmark/test_unbind_copy.py,,yes,unbind_copy +main,unfold_backward,unfold,benchmark/test_unfold.py,,yes,unfold_backward +main,unfold_copy,unfold_copy,benchmark/test_unfold_copy.py,,yes,unfold_copy +main,unfold_view,unfold_view,benchmark/test_unfold_view.py,,yes,unfold +main,uniform_inplace,uniform,benchmark/test_uniform.py,,yes,uniform_ +main,uniform_,uniform_,benchmark/test_uniform_.py,,yes,uniform_ +main,unique2,unique,benchmark/test_unique.py,,yes,unique2 +main,unique_consecutive,unique_consecutive,benchmark/test_unique_consecutive.py,,yes,unique_consecutive +main,unique_dim_dim0,unique_dim,benchmark/test_unique_dim.py,,yes,unique_dim +main,unique_dim_dim1,unique_dim,benchmark/test_unique_dim.py,,yes,unique_dim +main,unpack_seq,unpack_seq,benchmark/test_unpack_seq.py,,yes,unpack_seq_triton +main,unpack_seq_fp8,unpack_seq,benchmark/test_unpack_seq.py,,yes,unpack_seq_triton +main,unsafe_chunk,unsafe_chunk,benchmark/test_unsafe_chunk.py,,yes,unsafe_chunk +main,unsafe_masked_index,unsafe_masked_index,benchmark/test_unsafe_masked_index.py,,yes,unsafe_masked_index +main,unsafe_masked_index_put_accumulate,unsafe_masked_index_put_accumulate,benchmark/test_unsafe_masked_index_put_accumulate.py,,yes,unsafe_masked_index_put_accumulate +main,unsafe_view,unsafe_view,benchmark/test_unsafe_view.py,,yes,unsafe_view +main,unsqueeze,unsqueeze,benchmark/test_unsqueeze.py,,yes,unsqueeze +main,unsqueeze_,unsqueeze,benchmark/test_unsqueeze.py,,yes,unsqueeze_ +main,upsample_bicubic2d,upsample_bicubic2d,benchmark/test_upsample_bicubic2d.py,yes,yes,upsample_bicubic2d +main,upsample_bicubic2d_aa,upsample_bicubic2d_aa,benchmark/test_upsample_bicubic2d_aa.py,,yes,upsample_bicubic2d_aa +main,upsample_bicubic2d_aa_backward,upsample_bicubic2d_aa,benchmark/test_upsample_bicubic2d_aa.py,,yes,upsample_bicubic2d_aa_backward +main,upsample_bilinear2d_aa,upsample_bilinear2d_aa,benchmark/test_upsample_bilinear2d_aa.py,,yes,upsample_bilinear2d_aa +main,upsample_linear1d,upsample_linear1d,benchmark/test_upsample_linear1d.py,,yes,upsample_linear1d +main,upsample_linear1d_backward,upsample_linear1d,benchmark/test_upsample_linear1d.py,,yes,upsample_linear1d_backward +main,upsample_nearest1d,upsample_nearest1d,benchmark/test_upsample_nearest1d.py,,yes,upsample_nearest1d +main,upsample_nearest2d,upsample_nearest2d,benchmark/test_upsample_nearest2d.py,,yes,upsample_nearest2d +main,upsample_nearest3d,upsample_nearest3d,benchmark/test_upsample_nearest3d.py,,yes,upsample_nearest3d +main,upsample_nearest_exact1d,upsample_nearest_exact1d,benchmark/test_upsample_nearest_exact1d.py,,yes,upsample_nearest_exact1d +main,upsample_nearest_exact2d,upsample_nearest_exact2d,benchmark/test_upsample_nearest_exact2d.py,,yes,upsample_nearest_exact2d +main,upsample_nearest_exact2d_out,upsample_nearest_exact2d,benchmark/test_upsample_nearest_exact2d.py,,yes,upsample_nearest_exact2d +main,upsample_nearest_exact2d_backward,upsample_nearest_exact2d_backward,benchmark/test_upsample_nearest_exact2d_backward.py,,yes,upsample_nearest_exact2d_backward +main,upsample_nearest_exact3d,upsample_nearest_exact3d,benchmark/test_upsample_nearest_exact3d.py,,yes,_upsample_nearest_exact3d +main,upsample_trilinear3d,upsample_trilinear3d,benchmark/test_upsample_trilinear3d.py,,yes,upsample_trilinear3d +main,var,var,benchmark/test_var.py,,yes,var +main,var_dim,var,benchmark/test_var.py,,yes,var_dim +main,var_correction,var,benchmark/test_var.py,,yes,var_correction +main,var_mean,var_mean,benchmark/test_var_mean.py,,yes,var_mean +main,vdot,vdot,benchmark/test_vdot.py,,yes,vdot +main,vector_norm,vector_norm,benchmark/test_vector_norm.py,,yes,vector_norm +main,view_copy,view_copy,benchmark/test_view_copy.py,,yes,view_copy +main,vstack,vstack,benchmark/test_vstack.py,,yes,vstack +main,perf_w8a8_block_fp8_matmul,w8a8_block_fp8_matmul,benchmark/test_w8a8_block_fp8_matmul.py,,yes,w8a8_block_fp8_matmul +main,weight_int4pack_mm_with_scales_and_zeros,weight_int4pack_mm_with_scales_and_zeros,benchmark/test_weight_int4pack_mm_with_scales_and_zeros.py,,yes,weight_int4pack_mm_with_scales_and_zeros +main,weight_norm_dim0,weight_norm,benchmark/test_weight_norm.py,,yes,weight_norm +main,weight_norm_dim_last,weight_norm,benchmark/test_weight_norm.py,,yes,weight_norm +main,weight_norm_interface,weight_norm_interface,benchmark/test_weight_norm_interface.py,,yes,weight_norm_interface +main,weight_norm_interface_backward,weight_norm_interface,benchmark/test_weight_norm_interface.py,,yes,weight_norm_interface_backward +main,where_self,where,benchmark/test_where.py,,yes,where_self +main,where_self_out,where,benchmark/test_where.py,,yes,where_self_out +main,xlogy,xlogy,benchmark/test_xlogy.py,,yes,xlogy +main,xlogy_out,xlogy,benchmark/test_xlogy.py,,yes,xlogy_out +main,xlogy_tensor_scalar,xlogy,benchmark/test_xlogy.py,,yes,xlogy_tensor_scalar +main,xlogy_tensor_scalar_out,xlogy,benchmark/test_xlogy.py,,yes,xlogy_tensor_scalar_out +main,xlogy_scalar_tensor,xlogy,benchmark/test_xlogy.py,,yes,xlogy_scalar_tensor +main,xlogy_scalar_tensor_out,xlogy,benchmark/test_xlogy.py,,yes,xlogy_scalar_tensor_out +main,xlogy_,xlogy_,benchmark/test_xlogy_.py,,yes,xlogy_ +main,xlogy_scalar_other_,xlogy_,benchmark/test_xlogy_.py,,yes,xlogy_scalar_other_ +main,xor__,xor__,benchmark/test_xor__.py,,yes,xor__ +main,zero,zero,benchmark/test_zero.py,,yes,zero +main,zero_inplace,zero,benchmark/test_zero.py,,yes,zero_ +main,zero_out,zero,benchmark/test_zero.py,,yes,zero_out +main,zeros,zeros,benchmark/test_zeros.py,,yes,zeros +main,zeros_like,zeros_like,benchmark/test_zeros_like.py,,yes,zeros_like diff --git a/ops/inventory_vllm.csv b/ops/inventory_vllm.csv index 8a7ed81..b0e5a97 100644 --- a/ops/inventory_vllm.csv +++ b/ops/inventory_vllm.csv @@ -1,109 +1,109 @@ -repo,op,op_file,file,marked_skip,collected,op_names -vllm,perf_chunk_gated_delta_rule_fwd,FLA/test_chunk_gated_delta_rule_fwd,benchmark/test_FLA/test_chunk_gated_delta_rule_fwd.py,,yes,chunk_gated_delta_rule_fwd -vllm,perf_chunk_gated_delta_rule,FLA/test_chunk_gated_delta_rule_perf,benchmark/test_FLA/test_chunk_gated_delta_rule_perf.py,,yes,chunk_gated_delta_rule -vllm,chunk_gdn2,FLA/test_chunk_gdn2,benchmark/test_FLA/test_chunk_gdn2.py,,yes,chunk_gdn2 -vllm,perf_chunk_gla,FLA/test_chunk_gla_perf,benchmark/test_FLA/test_chunk_gla_perf.py,,yes, -vllm,chunk_kda,FLA/test_chunk_kda,benchmark/test_FLA/test_chunk_kda.py,,yes,chunk_kda -vllm,perf_fused_recurrent_gated_delta_rule,FLA/test_fused_recurrent_gated_delta_rule_perf,benchmark/test_FLA/test_fused_recurrent_gated_delta_rule_perf.py,,yes,fused_recurrent_gated_delta_rule -vllm,act_quant_perf,act_quant,benchmark/test_act_quant.py,,yes,act_quant_triton -vllm,add_rms_norm,add_rms_norm,benchmark/test_add_rms_norm.py,,yes,add_rms_norm -vllm,apply_repetition_penalties,apply_repetition_penalties,benchmark/test_apply_repetition_penalties.py,,yes,apply_repetition_penalties -vllm,apply_rotary_pos_emb,apply_rotary_pos_emb,benchmark/test_apply_rotary_pos_emb.py,,yes,apply_rotary_pos_emb -vllm,beam_search_score,beam_search_score,benchmark/test_beam_search_score.py,,yes,beam_search_score -vllm,beam_search_score_,beam_search_score,benchmark/test_beam_search_score.py,,yes,beam_search_score_ -vllm,bincount,bincount,benchmark/test_bincount.py,,yes,bincount -vllm,bincount_weighted,bincount,benchmark/test_bincount.py,,yes,bincount_weighted -vllm,blas_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, -vllm,perf_w8a8_block_fp8_matmul,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,w8a8_block_fp8_matmul -vllm,perf_w8a8_block_fp8_matmul_deepgemm,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,w8a8_block_fp8_matmul_deepgemm -vllm,perf_sparse_attention,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,sparse_attention -vllm,mv_and_outer_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, -vllm,addmv_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, -vllm,vdot_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,vdot -vllm,addr_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,addr -vllm,perf_router_gemm,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,router_gemm -vllm,concat_and_cache_mla,concat_and_cache_mla,benchmark/test_concat_and_cache_mla.py,,yes,concat_and_cache_mla -vllm,cp_gather_indexer_k_quant_cache_benchmark,cp_gather_indexer_k_quant_cache,benchmark/test_cp_gather_indexer_k_quant_cache.py,,yes, -vllm,cross_entropy_loss,cross_entropy_loss,benchmark/test_cross_entropy_loss.py,,yes,cross_entropy_loss -vllm,cutlass_scaled_mm_benchmark,cutlass_scaled_mm,benchmark/test_cutlass_scaled_mm.py,,yes, -vllm,combine_topk_swa_indices_benchmark,deepseek_v4_attention_combine_topk_swa_indices,benchmark/test_deepseek_v4_attention_combine_topk_swa_indices.py,,yes, -vllm,compute_global_topk_indices_and_lens_benchmark,deepseek_v4_attention_compute_global_topk_indices_and_lens,benchmark/test_deepseek_v4_attention_compute_global_topk_indices_and_lens.py,,yes, -vllm,dequantize_and_gather_k_cache_benchmark,deepseek_v4_attention_dequantize_and_gather_k_cache,benchmark/test_deepseek_v4_attention_dequantize_and_gather_k_cache.py,,yes, -vllm,fused_q_kv_rmsnorm_benchmark,deepseek_v4_attention_fused_q_kv_rmsnorm,benchmark/test_deepseek_v4_attention_fused_q_kv_rmsnorm.py,,yes, -vllm,dgeglu,dgeglu,benchmark/test_dgeglu.py,,yes,dgeglu -vllm,dreglu,dreglu,benchmark/test_dreglu.py,,yes,dreglu -vllm,dswiglu,dswiglu,benchmark/test_dswiglu.py,,yes,dswiglu -vllm,flash_attention_forward,flash_attention_forward,benchmark/test_flash_attention_forward.py,,yes,flash_attention_forward -vllm,flash_attn_varlen_func,flash_attn_varlen_func,benchmark/test_flash_attn_varlen_func.py,,yes,flash_attn_varlen_func -vllm,flash_attn_varlen_opt_func,flash_attn_varlen_opt_init_func,benchmark/test_flash_attn_varlen_opt_init_func.py,,yes,flash_attn_varlen_func -vllm,flash_mla,flash_mla,benchmark/test_flash_mla.py,,yes,flash_mla -vllm,flash_mla_sparse_fwd,flash_mla_sparse_fwd,benchmark/test_flash_mla_sparse_fwd.py,,yes, -vllm,flash_mla_with_kvcache,flash_mla_with_kvcache,benchmark/test_flash_mla_with_kvcache.py,,yes, -vllm,fp8_fp4_mqa_logits,fp8_fp4_mqa_logits,benchmark/test_fp8_fp4_mqa_logits.py,,yes,fp8_fp4_mqa_logits -vllm,fp8_fp4_paged_mqa_logits,fp8_fp4_paged_mqa_logits,benchmark/test_fp8_fp4_paged_mqa_logits.py,,yes,fp8_fp4_paged_mqa_logits -vllm,fused_add_rms_norm,fused_add_rms_norm,benchmark/test_fused_add_rms_norm.py,,yes,fused_add_rms_norm -vllm,fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert,fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert,benchmark/test_fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert.py,,yes, -vllm,fused_indexer_q_rope_quant,fused_indexer_q_rope_quant,benchmark/test_fused_indexer_q_rope_quant.py,,yes,fused_indexer_q_rope_quant -vllm,fused_inv_rope_fp8_quant,fused_inv_rope_fp8_quant,benchmark/test_fused_inv_rope_fp8_quant.py,,yes,fused_inv_rope_fp8_quant -vllm,fused_marlin_moe,fused_marlin_moe,benchmark/test_fused_marlin_moe.py,,yes,fused_marlin_moe -vllm,fused_moe_impl_gems_vs_vllm,fused_moe,benchmark/test_fused_moe.py,,yes,fused_experts_impl -vllm,fused_moe_fp8,fused_moe_fp8,benchmark/test_fused_moe_fp8.py,,yes,fused_experts_impl -vllm,fused_moe_fp8_blockwise,fused_moe_fp8_blockwise,benchmark/test_fused_moe_fp8_blockwise.py,,yes,fused_experts_impl -vllm,fused_moe_int4_w4a16,fused_moe_int4_w4a16,benchmark/test_fused_moe_int4_w4a16.py,,yes,fused_experts_impl -vllm,fused_experts_impl_int8,fused_moe_int8,benchmark/test_fused_moe_int8.py,,yes,fused_experts_impl -vllm,fused_experts_impl_int8_w8a16,fused_moe_int8_w8a16,benchmark/test_fused_moe_int8_w8a16.py,,yes,fused_moe_int8_w8a16_gems_vs_bf16_deq -vllm,fused_moe_w8a16_mxq,fused_moe_w8a16,benchmark/test_fused_moe_w8a16.py,,yes,fused_moe_w8a16_mxq_gems_vs_bf16_deq -vllm,fused_moe_w8a16_mxq_gems_vs_vllm,fused_moe_w8a16,benchmark/test_fused_moe_w8a16.py,,yes,fused_moe_w8a16_mxq_gems_vs_vllm -vllm,geglu,geglu,benchmark/test_geglu.py,,yes,geglu -vllm,gelu_and_mul,gelu_and_mul,benchmark/test_gelu_and_mul.py,,yes,gelu_and_mul -vllm,grouped_topk_no_renorm,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk -vllm,grouped_topk_score_0,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk -vllm,grouped_topk_score_1,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk -vllm,indexer_k_quant_and_cache_benchmark,indexer_k_quant_and_cache,benchmark/test_indexer_k_quant_and_cache.py,,yes, -vllm,inplace_fused_experts_gems_vs_vllm,inplace_fused_experts,benchmark/test_inplace_fused_experts.py,,yes,inplace_fused_experts -vllm,instance_norm,instance_norm,benchmark/test_instance_norm.py,,yes,instance_norm -vllm,mhc_post,mhc,benchmark/test_mhc.py,,yes,mhc_post -vllm,mhc_pre,mhc,benchmark/test_mhc.py,,yes,mhc_pre -vllm,hc_split_sinkhorn_forward,mhc,benchmark/test_mhc.py,,yes,hc_split_sinkhorn_forward -vllm,mhc_bwd,mhc,benchmark/test_mhc.py,,yes,mhc_bwd -vllm,hc_head_fused_kernel,mhc,benchmark/test_mhc.py,,yes,hc_head_fused_kernel -vllm,moe_align_block_size_triton,moe_align_block_size_triton,benchmark/test_moe_align_block_size_triton.py,,yes,moe_align_block_size_triton -vllm,moe_sum,moe_sum,benchmark/test_moe_sum.py,,yes,moe_sum -vllm,mrope_gems_vs_torch,mrope,benchmark/test_mrope.py,,yes,mrope -vllm,outer,outer,benchmark/test_outer.py,,yes,outer -vllm,outplace_fused_experts_gems_vs_vllm,outplace_fused_experts,benchmark/test_outplace_fused_experts.py,,yes,outplace_fused_experts -vllm,pack_seq,pack_seq,benchmark/test_pack_seq.py,,yes,pack_seq_triton -vllm,pack_seq_fp8,pack_seq,benchmark/test_pack_seq.py,,yes,pack_seq_triton -vllm,perf_parallel_nsa,parallel_nsa,benchmark/test_parallel_nsa.py,,yes,parallel_nsa -vllm,perf_parallel_nsa_compression,parallel_nsa_compression,benchmark/test_parallel_nsa_compression.py,,yes,parallel_nsa_compression -vllm,per_token_group_quant_fp8,per_token_group_quant_fp8,benchmark/test_per_token_group_quant_fp8.py,,yes,per_token_group_quant_fp8 -vllm,persistent_topk,persistent_topk,benchmark/test_persistent_topk.py,,yes,persistent_topk -vllm,reglu,reglu,benchmark/test_reglu.py,,yes,reglu -vllm,reshape_and_cache,reshape_and_cache,benchmark/test_reshape_and_cache.py,,yes,reshape_and_cache -vllm,reshape_and_cache_flash,reshape_and_cache_flash,benchmark/test_reshape_and_cache_flash.py,,yes,reshape_and_cache_flash -vllm,perf_router_gemm,router_gemm,benchmark/test_router_gemm.py,,yes,router_gemm -vllm,rwkv_ka_fusion,rwkv_ka_fusion,benchmark/test_rwkv_ka_fusion.py,,yes,rwkv_ka_fusion -vllm,rwkv_mm_sparsity,rwkv_mm_sparsity,benchmark/test_rwkv_mm_sparsity.py,,yes,rwkv_mm_sparsity -vllm,dynamic_scaled_int8_quant,scaled_int8_quant,benchmark/test_scaled_int8_quant.py,,yes,dynamic_scaled_int8_quant -vllm,static_scaled_int8_quant,scaled_int8_quant,benchmark/test_scaled_int8_quant.py,,yes,static_scaled_int8_quant -vllm,silu_and_mul,silu_and_mul,benchmark/test_silu_and_mul.py,,yes,silu_and_mul -vllm,silu_and_mul_out,silu_and_mul,benchmark/test_silu_and_mul.py,,yes,silu_and_mul_out -vllm,silu_and_mul_with_clamp,silu_and_mul_with_clamp,benchmark/test_silu_and_mul_with_clamp.py,,yes,silu_and_mul_with_clamp -vllm,silu_and_mul_with_clamp_out,silu_and_mul_with_clamp,benchmark/test_silu_and_mul_with_clamp.py,,yes,silu_and_mul_with_clamp_out -vllm,skip_layernorm,skip_layer_norm,benchmark/test_skip_layer_norm.py,,yes,skip_layer_norm -vllm,sparse_attn_triton,sparse_attention,benchmark/test_sparse_attention.py,yes,yes,sparse_attention -vllm,sparse_mla_fwd_interface,sparse_mla_fwd_interface,benchmark/test_sparse_mla_fwd_interface.py,,yes,sparse_mla_fwd_interface -vllm,stage_deepseek_v4_mega_moe_inputs_benchmark,stage_deepseek_v4_mega_moe_inputs,benchmark/test_stage_deepseek_v4_mega_moe_inputs.py,,yes, -vllm,swiglu,swiglu,benchmark/test_swiglu.py,,yes,swiglu -vllm,top_k_per_row_decode,top_k_per_row_decode,benchmark/test_top_k_per_row_decode.py,,yes,top_k_per_row_decode -vllm,top_k_per_row_prefill,top_k_per_row_prefill,benchmark/test_top_k_per_row_prefill.py,,yes,top_k_per_row_prefill -vllm,topk_softmax,topk_softmax,benchmark/test_topk_softmax.py,,yes,topk_softmax -vllm,topk_softplus_sqrt,topk_softplus_sqrt,benchmark/test_topk_softplus_sqrt.py,,yes,topk_softplus_sqrt -vllm,triton_scaled_mm_benchmark,triton_scaled_mm,benchmark/test_triton_scaled_mm.py,,yes,triton_scaled_mm -vllm,triton_unified_attention_perf,triton_unified_attention_perf,benchmark/test_triton_unified_attention_perf.py,,yes, -vllm,unpack_seq,unpack_seq,benchmark/test_unpack_seq.py,,yes,unpack_seq_triton -vllm,unpack_seq_fp8,unpack_seq,benchmark/test_unpack_seq.py,,yes,unpack_seq_triton -vllm,weight_norm_dim0,weight_norm,benchmark/test_weight_norm.py,,yes,weight_norm -vllm,weight_norm_dim_last,weight_norm,benchmark/test_weight_norm.py,,yes,weight_norm -vllm,weight_norm_interface,weight_norm_interface,benchmark/test_weight_norm_interface.py,,yes,weight_norm_interface -vllm,weight_norm_interface_backward,weight_norm_interface,benchmark/test_weight_norm_interface.py,,yes,weight_norm_interface_backward +repo,op,op_file,file,marked_skip,collected,op_names +vllm,perf_chunk_gated_delta_rule_fwd,FLA/test_chunk_gated_delta_rule_fwd,benchmark/test_FLA/test_chunk_gated_delta_rule_fwd.py,,yes,chunk_gated_delta_rule_fwd +vllm,perf_chunk_gated_delta_rule,FLA/test_chunk_gated_delta_rule_perf,benchmark/test_FLA/test_chunk_gated_delta_rule_perf.py,,yes,chunk_gated_delta_rule +vllm,chunk_gdn2,FLA/test_chunk_gdn2,benchmark/test_FLA/test_chunk_gdn2.py,,yes,chunk_gdn2 +vllm,perf_chunk_gla,FLA/test_chunk_gla_perf,benchmark/test_FLA/test_chunk_gla_perf.py,,yes, +vllm,chunk_kda,FLA/test_chunk_kda,benchmark/test_FLA/test_chunk_kda.py,,yes,chunk_kda +vllm,perf_fused_recurrent_gated_delta_rule,FLA/test_fused_recurrent_gated_delta_rule_perf,benchmark/test_FLA/test_fused_recurrent_gated_delta_rule_perf.py,,yes,fused_recurrent_gated_delta_rule +vllm,act_quant_perf,act_quant,benchmark/test_act_quant.py,,yes,act_quant_triton +vllm,add_rms_norm,add_rms_norm,benchmark/test_add_rms_norm.py,,yes,add_rms_norm +vllm,apply_repetition_penalties,apply_repetition_penalties,benchmark/test_apply_repetition_penalties.py,,yes,apply_repetition_penalties +vllm,apply_rotary_pos_emb,apply_rotary_pos_emb,benchmark/test_apply_rotary_pos_emb.py,,yes,apply_rotary_pos_emb +vllm,beam_search_score,beam_search_score,benchmark/test_beam_search_score.py,,yes,beam_search_score +vllm,beam_search_score_,beam_search_score,benchmark/test_beam_search_score.py,,yes,beam_search_score_ +vllm,bincount,bincount,benchmark/test_bincount.py,,yes,bincount +vllm,bincount_weighted,bincount,benchmark/test_bincount.py,,yes,bincount_weighted +vllm,blas_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, +vllm,perf_w8a8_block_fp8_matmul,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,w8a8_block_fp8_matmul +vllm,perf_w8a8_block_fp8_matmul_deepgemm,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,w8a8_block_fp8_matmul_deepgemm +vllm,perf_sparse_attention,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,sparse_attention +vllm,mv_and_outer_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, +vllm,addmv_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes, +vllm,vdot_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,vdot +vllm,addr_benchmark,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,addr +vllm,perf_router_gemm,blas_perf_parallel,benchmark/test_blas_perf_parallel.py,,yes,router_gemm +vllm,concat_and_cache_mla,concat_and_cache_mla,benchmark/test_concat_and_cache_mla.py,,yes,concat_and_cache_mla +vllm,cp_gather_indexer_k_quant_cache_benchmark,cp_gather_indexer_k_quant_cache,benchmark/test_cp_gather_indexer_k_quant_cache.py,,yes, +vllm,cross_entropy_loss,cross_entropy_loss,benchmark/test_cross_entropy_loss.py,,yes,cross_entropy_loss +vllm,cutlass_scaled_mm_benchmark,cutlass_scaled_mm,benchmark/test_cutlass_scaled_mm.py,,yes, +vllm,combine_topk_swa_indices_benchmark,deepseek_v4_attention_combine_topk_swa_indices,benchmark/test_deepseek_v4_attention_combine_topk_swa_indices.py,,yes, +vllm,compute_global_topk_indices_and_lens_benchmark,deepseek_v4_attention_compute_global_topk_indices_and_lens,benchmark/test_deepseek_v4_attention_compute_global_topk_indices_and_lens.py,,yes, +vllm,dequantize_and_gather_k_cache_benchmark,deepseek_v4_attention_dequantize_and_gather_k_cache,benchmark/test_deepseek_v4_attention_dequantize_and_gather_k_cache.py,,yes, +vllm,fused_q_kv_rmsnorm_benchmark,deepseek_v4_attention_fused_q_kv_rmsnorm,benchmark/test_deepseek_v4_attention_fused_q_kv_rmsnorm.py,,yes, +vllm,dgeglu,dgeglu,benchmark/test_dgeglu.py,,yes,dgeglu +vllm,dreglu,dreglu,benchmark/test_dreglu.py,,yes,dreglu +vllm,dswiglu,dswiglu,benchmark/test_dswiglu.py,,yes,dswiglu +vllm,flash_attention_forward,flash_attention_forward,benchmark/test_flash_attention_forward.py,,yes,flash_attention_forward +vllm,flash_attn_varlen_func,flash_attn_varlen_func,benchmark/test_flash_attn_varlen_func.py,,yes,flash_attn_varlen_func +vllm,flash_attn_varlen_opt_func,flash_attn_varlen_opt_init_func,benchmark/test_flash_attn_varlen_opt_init_func.py,,yes,flash_attn_varlen_func +vllm,flash_mla,flash_mla,benchmark/test_flash_mla.py,,yes,flash_mla +vllm,flash_mla_sparse_fwd,flash_mla_sparse_fwd,benchmark/test_flash_mla_sparse_fwd.py,,yes, +vllm,flash_mla_with_kvcache,flash_mla_with_kvcache,benchmark/test_flash_mla_with_kvcache.py,,yes, +vllm,fp8_fp4_mqa_logits,fp8_fp4_mqa_logits,benchmark/test_fp8_fp4_mqa_logits.py,,yes,fp8_fp4_mqa_logits +vllm,fp8_fp4_paged_mqa_logits,fp8_fp4_paged_mqa_logits,benchmark/test_fp8_fp4_paged_mqa_logits.py,,yes,fp8_fp4_paged_mqa_logits +vllm,fused_add_rms_norm,fused_add_rms_norm,benchmark/test_fused_add_rms_norm.py,,yes,fused_add_rms_norm +vllm,fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert,fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert,benchmark/test_fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert.py,,yes, +vllm,fused_indexer_q_rope_quant,fused_indexer_q_rope_quant,benchmark/test_fused_indexer_q_rope_quant.py,,yes,fused_indexer_q_rope_quant +vllm,fused_inv_rope_fp8_quant,fused_inv_rope_fp8_quant,benchmark/test_fused_inv_rope_fp8_quant.py,,yes,fused_inv_rope_fp8_quant +vllm,fused_marlin_moe,fused_marlin_moe,benchmark/test_fused_marlin_moe.py,,yes,fused_marlin_moe +vllm,fused_moe_impl_gems_vs_vllm,fused_moe,benchmark/test_fused_moe.py,,yes,fused_experts_impl +vllm,fused_moe_fp8,fused_moe_fp8,benchmark/test_fused_moe_fp8.py,,yes,fused_experts_impl +vllm,fused_moe_fp8_blockwise,fused_moe_fp8_blockwise,benchmark/test_fused_moe_fp8_blockwise.py,,yes,fused_experts_impl +vllm,fused_moe_int4_w4a16,fused_moe_int4_w4a16,benchmark/test_fused_moe_int4_w4a16.py,,yes,fused_experts_impl +vllm,fused_experts_impl_int8,fused_moe_int8,benchmark/test_fused_moe_int8.py,,yes,fused_experts_impl +vllm,fused_experts_impl_int8_w8a16,fused_moe_int8_w8a16,benchmark/test_fused_moe_int8_w8a16.py,,yes,fused_moe_int8_w8a16_gems_vs_bf16_deq +vllm,fused_moe_w8a16_mxq,fused_moe_w8a16,benchmark/test_fused_moe_w8a16.py,,yes,fused_moe_w8a16_mxq_gems_vs_bf16_deq +vllm,fused_moe_w8a16_mxq_gems_vs_vllm,fused_moe_w8a16,benchmark/test_fused_moe_w8a16.py,,yes,fused_moe_w8a16_mxq_gems_vs_vllm +vllm,geglu,geglu,benchmark/test_geglu.py,,yes,geglu +vllm,gelu_and_mul,gelu_and_mul,benchmark/test_gelu_and_mul.py,,yes,gelu_and_mul +vllm,grouped_topk_no_renorm,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk +vllm,grouped_topk_score_0,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk +vllm,grouped_topk_score_1,grouped_topk,benchmark/test_grouped_topk.py,,yes,grouped_topk +vllm,indexer_k_quant_and_cache_benchmark,indexer_k_quant_and_cache,benchmark/test_indexer_k_quant_and_cache.py,,yes, +vllm,inplace_fused_experts_gems_vs_vllm,inplace_fused_experts,benchmark/test_inplace_fused_experts.py,,yes,inplace_fused_experts +vllm,instance_norm,instance_norm,benchmark/test_instance_norm.py,,yes,instance_norm +vllm,mhc_post,mhc,benchmark/test_mhc.py,,yes,mhc_post +vllm,mhc_pre,mhc,benchmark/test_mhc.py,,yes,mhc_pre +vllm,hc_split_sinkhorn_forward,mhc,benchmark/test_mhc.py,,yes,hc_split_sinkhorn_forward +vllm,mhc_bwd,mhc,benchmark/test_mhc.py,,yes,mhc_bwd +vllm,hc_head_fused_kernel,mhc,benchmark/test_mhc.py,,yes,hc_head_fused_kernel +vllm,moe_align_block_size_triton,moe_align_block_size_triton,benchmark/test_moe_align_block_size_triton.py,,yes,moe_align_block_size_triton +vllm,moe_sum,moe_sum,benchmark/test_moe_sum.py,,yes,moe_sum +vllm,mrope_gems_vs_torch,mrope,benchmark/test_mrope.py,,yes,mrope +vllm,outer,outer,benchmark/test_outer.py,,yes,outer +vllm,outplace_fused_experts_gems_vs_vllm,outplace_fused_experts,benchmark/test_outplace_fused_experts.py,,yes,outplace_fused_experts +vllm,pack_seq,pack_seq,benchmark/test_pack_seq.py,,yes,pack_seq_triton +vllm,pack_seq_fp8,pack_seq,benchmark/test_pack_seq.py,,yes,pack_seq_triton +vllm,perf_parallel_nsa,parallel_nsa,benchmark/test_parallel_nsa.py,,yes,parallel_nsa +vllm,perf_parallel_nsa_compression,parallel_nsa_compression,benchmark/test_parallel_nsa_compression.py,,yes,parallel_nsa_compression +vllm,per_token_group_quant_fp8,per_token_group_quant_fp8,benchmark/test_per_token_group_quant_fp8.py,,yes,per_token_group_quant_fp8 +vllm,persistent_topk,persistent_topk,benchmark/test_persistent_topk.py,,yes,persistent_topk +vllm,reglu,reglu,benchmark/test_reglu.py,,yes,reglu +vllm,reshape_and_cache,reshape_and_cache,benchmark/test_reshape_and_cache.py,,yes,reshape_and_cache +vllm,reshape_and_cache_flash,reshape_and_cache_flash,benchmark/test_reshape_and_cache_flash.py,,yes,reshape_and_cache_flash +vllm,perf_router_gemm,router_gemm,benchmark/test_router_gemm.py,,yes,router_gemm +vllm,rwkv_ka_fusion,rwkv_ka_fusion,benchmark/test_rwkv_ka_fusion.py,,yes,rwkv_ka_fusion +vllm,rwkv_mm_sparsity,rwkv_mm_sparsity,benchmark/test_rwkv_mm_sparsity.py,,yes,rwkv_mm_sparsity +vllm,dynamic_scaled_int8_quant,scaled_int8_quant,benchmark/test_scaled_int8_quant.py,,yes,dynamic_scaled_int8_quant +vllm,static_scaled_int8_quant,scaled_int8_quant,benchmark/test_scaled_int8_quant.py,,yes,static_scaled_int8_quant +vllm,silu_and_mul,silu_and_mul,benchmark/test_silu_and_mul.py,,yes,silu_and_mul +vllm,silu_and_mul_out,silu_and_mul,benchmark/test_silu_and_mul.py,,yes,silu_and_mul_out +vllm,silu_and_mul_with_clamp,silu_and_mul_with_clamp,benchmark/test_silu_and_mul_with_clamp.py,,yes,silu_and_mul_with_clamp +vllm,silu_and_mul_with_clamp_out,silu_and_mul_with_clamp,benchmark/test_silu_and_mul_with_clamp.py,,yes,silu_and_mul_with_clamp_out +vllm,skip_layernorm,skip_layer_norm,benchmark/test_skip_layer_norm.py,,yes,skip_layer_norm +vllm,sparse_attn_triton,sparse_attention,benchmark/test_sparse_attention.py,yes,yes,sparse_attention +vllm,sparse_mla_fwd_interface,sparse_mla_fwd_interface,benchmark/test_sparse_mla_fwd_interface.py,,yes,sparse_mla_fwd_interface +vllm,stage_deepseek_v4_mega_moe_inputs_benchmark,stage_deepseek_v4_mega_moe_inputs,benchmark/test_stage_deepseek_v4_mega_moe_inputs.py,,yes, +vllm,swiglu,swiglu,benchmark/test_swiglu.py,,yes,swiglu +vllm,top_k_per_row_decode,top_k_per_row_decode,benchmark/test_top_k_per_row_decode.py,,yes,top_k_per_row_decode +vllm,top_k_per_row_prefill,top_k_per_row_prefill,benchmark/test_top_k_per_row_prefill.py,,yes,top_k_per_row_prefill +vllm,topk_softmax,topk_softmax,benchmark/test_topk_softmax.py,,yes,topk_softmax +vllm,topk_softplus_sqrt,topk_softplus_sqrt,benchmark/test_topk_softplus_sqrt.py,,yes,topk_softplus_sqrt +vllm,triton_scaled_mm_benchmark,triton_scaled_mm,benchmark/test_triton_scaled_mm.py,,yes,triton_scaled_mm +vllm,triton_unified_attention_perf,triton_unified_attention_perf,benchmark/test_triton_unified_attention_perf.py,,yes, +vllm,unpack_seq,unpack_seq,benchmark/test_unpack_seq.py,,yes,unpack_seq_triton +vllm,unpack_seq_fp8,unpack_seq,benchmark/test_unpack_seq.py,,yes,unpack_seq_triton +vllm,weight_norm_dim0,weight_norm,benchmark/test_weight_norm.py,,yes,weight_norm +vllm,weight_norm_dim_last,weight_norm,benchmark/test_weight_norm.py,,yes,weight_norm +vllm,weight_norm_interface,weight_norm_interface,benchmark/test_weight_norm_interface.py,,yes,weight_norm_interface +vllm,weight_norm_interface_backward,weight_norm_interface,benchmark/test_weight_norm_interface.py,,yes,weight_norm_interface_backward