vllm/vllm_v0.10.0/benchmarks/kernels
hailin 38d813617c first commit 2025-08-03 20:28:19 +08:00
..
deepgemm first commit 2025-08-03 20:28:19 +08:00
bench_fp8_gemm.py first commit 2025-08-03 20:28:19 +08:00
bench_int8_gemm.py first commit 2025-08-03 20:28:19 +08:00
bench_nvfp4_gemm.py first commit 2025-08-03 20:28:19 +08:00
bench_per_token_quant_fp8.py first commit 2025-08-03 20:28:19 +08:00
benchmark_aqlm.py first commit 2025-08-03 20:28:19 +08:00
benchmark_bitblas.py first commit 2025-08-03 20:28:19 +08:00
benchmark_cutlass_fp4_moe.py first commit 2025-08-03 20:28:19 +08:00
benchmark_grouped_gemm_cutlass.py first commit 2025-08-03 20:28:19 +08:00
benchmark_layernorm.py first commit 2025-08-03 20:28:19 +08:00
benchmark_lora.py first commit 2025-08-03 20:28:19 +08:00
benchmark_machete.py first commit 2025-08-03 20:28:19 +08:00
benchmark_marlin.py first commit 2025-08-03 20:28:19 +08:00
benchmark_moe.py first commit 2025-08-03 20:28:19 +08:00
benchmark_moe_align_block_size.py first commit 2025-08-03 20:28:19 +08:00
benchmark_moe_permute_unpermute.py first commit 2025-08-03 20:28:19 +08:00
benchmark_paged_attention.py first commit 2025-08-03 20:28:19 +08:00
benchmark_quant.py first commit 2025-08-03 20:28:19 +08:00
benchmark_rmsnorm.py first commit 2025-08-03 20:28:19 +08:00
benchmark_rope.py first commit 2025-08-03 20:28:19 +08:00
benchmark_shapes.py first commit 2025-08-03 20:28:19 +08:00
benchmark_trtllm_attention.py first commit 2025-08-03 20:28:19 +08:00
benchmark_w8a8_block_fp8.py first commit 2025-08-03 20:28:19 +08:00
graph_machete_bench.py first commit 2025-08-03 20:28:19 +08:00
requirements.txt first commit 2025-08-03 20:28:19 +08:00
utils.py first commit 2025-08-03 20:28:19 +08:00
weight_shapes.py first commit 2025-08-03 20:28:19 +08:00