Yineng Zhang 6d55f60e77 Revert "[1/2] Optimizations and refactors about quant kernel (#9534)" (#10292)

2025-09-10 18:24:23 -07:00

..

bench_activation.py

…

bench_awq_dequant.py

…

bench_cutlass_mla.py

…

bench_dsv3_fused_a_gemm.py

…

bench_dsv3_router_gemm.py

…

bench_fp4_gemm.py

…

bench_fp8_blockwise_gemm.py

…

bench_fp8_blockwise_group_gemm.py

fix benchmark fp8 blockwise group gemm (#8815)

2025-08-06 21:02:21 +08:00

bench_fp8_gemm.py

[Perf] Tunings for SM100 FP8 CUTLASS kernel (#8818)

2025-08-13 21:59:22 -07:00

bench_int8_gemm.py

…

bench_lightning_attention_decode.py

…

bench_moe_align_block_size.py

…

bench_moe_ep_post_reorder.py

[chore] Remove unused ep_moe cuda kernels (#9956)

2025-09-06 01:35:50 -07:00

bench_moe_fused_gate.py

…

bench_moe_topk_softmax.py

…

bench_nvfp4_scaled_gemm.py

…

bench_per_tensor_quant_fp8.py

…

bench_per_token_group_quant_8bit.py

Revert "[1/2] Optimizations and refactors about quant kernel (#9534)" (#10292)

2025-09-10 18:24:23 -07:00

bench_per_token_quant_fp8.py

…

bench_qserve_w4a8_gemm.py

…

bench_rotary_embedding.py

Fuse writing KV buffer into rope kernel (part 1: sgl-kernel) (#9077)

2025-08-12 01:46:40 -07:00

bench_top_k_top_p_sampling.py

[sgl-kernel] Support FlashInfer top_k_top_p_sampling_from_logits (#9060)

2025-08-14 10:56:36 -07:00