Yuan Luo 53dcc750b6 [sgl-kernel] Support FlashInfer top_k_top_p_sampling_from_logits (#9060) ...

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>

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

..

bench_activation.py

…

bench_awq_dequant.py

…

bench_cutlass_mla.py

…

bench_dsv3_fused_a_gemm.py

…

bench_dsv3_router_gemm.py

[Kimi K2] dsv3_router_gemm supports NUM_EXPERTS == 384 (#8013)

2025-08-01 22:01:24 +08:00

bench_fp4_gemm.py

…

bench_fp8_blockwise_gemm.py

…

bench_fp8_blockwise_group_gemm.py

…

bench_fp8_gemm.py

…

bench_int8_gemm.py

…

bench_lightning_attention_decode.py

…

bench_moe_align_block_size.py

update sgl-kernel for EP: kernel part (#8514)

2025-07-30 22:19:55 -07:00

bench_moe_ep_post_reorder.py

feat: integrate deepgemm into EPMoE (#6821)

2025-06-23 01:38:58 -07:00

bench_moe_ep_pre_reorder.py

fix ep_moe_reorder kernel bugs (#6858)

2025-06-04 19:13:59 +08:00

bench_moe_fused_gate.py

…

bench_moe_silu_and_mul.py

[sgl-kernel] Add cuda kernel for moe_ep_silu_and_mul (#6919)

2025-06-11 20:43:08 -07:00

bench_moe_topk_softmax.py

[optimize] fuse renormalize into moe_topk_softmax (#7744)

2025-07-03 12:42:44 -07:00

bench_nvfp4_scaled_gemm.py

Add nvfp4 scaled mm benchmark. (#8401)

2025-07-26 23:18:04 -07:00

bench_per_tensor_quant_fp8.py

…

bench_per_token_group_quant_8bit.py

…

bench_per_token_quant_fp8.py

…

bench_qserve_w4a8_gemm.py

[1/2] Support Qserve (#6457)

2025-05-21 19:48:59 -07:00

bench_rotary_embedding.py

…

bench_top_k_top_p_sampling.py

…