Directory listing for /vllm/benchmarks/kernels/

• __init__.py
• bench_concat_mla_q.py
• bench_cp_gather_fp8.py
• benchmark_2d_silu_mul_fp8_quant.py
• benchmark_activation.py
• benchmark_block_fp8_gemm.py
• benchmark_cutlass_moe_fp8.py
• benchmark_cutlass_moe_nvfp4.py
• benchmark_device_communicators.py
• benchmark_fp8_gemm.py
• benchmark_fused_collective.py
• benchmark_fused_moe_lora_one_shot.py
• benchmark_fused_topk.py
• benchmark_grouped_gemm_cutlass.py
• benchmark_int8_gemm.py
• benchmark_layernorm.py
• benchmark_lora.py
• benchmark_machete.py
• benchmark_marlin.py
• benchmark_mla_k_concat.py
• benchmark_moe.py
• benchmark_moe_align_block_size.py
• benchmark_moe_defaults.py
• benchmark_moe_permute_unpermute.py
• benchmark_mrope.py
• benchmark_mxfp4_qutlass.py
• benchmark_nvfp4_gemm.py
• benchmark_nvfp4_quant.py
• benchmark_nvfp4_qutlass.py
• benchmark_paged_attention.py
• benchmark_per_token_group_quant.py
• benchmark_per_token_quant_fp8.py
• benchmark_quant.py
• benchmark_reshape_and_cache.py
• benchmark_reshape_and_cache_flash.py
• benchmark_rmsnorm.py
• benchmark_rope.py
• benchmark_router_gemm.py
• benchmark_selective_state_update.py
• benchmark_shapes.py
• benchmark_silu_mul_fp8_quant.py
• benchmark_trtllm_decode_attention.py
• benchmark_trtllm_prefill_attention.py
• benchmark_vit_bilinear_pos_embed.py
• benchmark_vit_fp8_attn.py
• benchmark_w8a8_block_fp8.py
• cpu/
• deepgemm/
• graph_machete_bench.py
• ir/
• requirements.txt
• utils.py
• weight_shapes.py