benchmarks/kernels · tduncan/Nvidia-Optimization-Stack-VLLM · siGit Code & Deploy

@tduncan / Nvidia-Optimization-Stack-VLLM

Code Commits Issues Pulls Cloud Agent CI/CD

main

cpu

deepgemm

ir

__init__.py

bench_concat_mla_q.py

bench_cp_gather_fp8.py

bench_cpu_sampling.py

benchmark_2d_silu_mul_fp8_quant.py

benchmark_activation.py

benchmark_block_fp8_gemm.py

benchmark_cp_gather.py

benchmark_cutlass_moe_fp8.py

benchmark_cutlass_moe_nvfp4.py

benchmark_device_communicators.py

benchmark_dsv41_mega_attn.py

benchmark_flydsl_moe_w4a16.py

benchmark_fp8_gemm.py

benchmark_fused_collective.py

benchmark_fused_moe_lora_one_shot.py

benchmark_fused_q_cutedsl.py

benchmark_fused_topk.py

benchmark_gelu_and_mul_sparse.py

benchmark_gemm_rs_ar.py

benchmark_grouped_gemm_cutlass.py

benchmark_host_buffer_kv_copy.py

benchmark_hy_v4_ihc.py

benchmark_inkling_qkvr_prep.py

benchmark_int8_gemm.py

benchmark_k3_cutedsl_residual.py

benchmark_kimi_k3_attn_res.py

benchmark_kimi_k3_kda_decode.py

benchmark_kimi_k3_kda_projection.py

benchmark_kimi_k3_latent_moe_tail.py

benchmark_kimi_k3_sp_collectives.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_multimem_reduce_scatter.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_persistent_topk.py

benchmark_quant.py

benchmark_rdna_hybrid_w4a16_gemm.py

benchmark_relu_squared.py

benchmark_reshape_and_cache.py

benchmark_reshape_and_cache_flash.py

benchmark_rope.py

benchmark_router_gemm.py

benchmark_selective_state_update.py

benchmark_shapes.py

benchmark_silu_mul_fp8_quant.py

benchmark_thinking_budget.py

benchmark_top_k_per_row_decode.py

benchmark_trtllm_decode_attention.py

benchmark_trtllm_prefill_attention.py

benchmark_vit_aiter_fp8_attn.py

benchmark_vit_bilinear_pos_embed.py

benchmark_vit_fp8_attn.py

benchmark_vocab_parallel_embedding.py

benchmark_w8a8_block_fp8.py

graph_machete_bench.py

requirements.txt

utils.py

weight_shapes.py