Xiaoyu Zhang 90a55e2566 add deepgemm and sglang fp8 block-wise gemm benchmark (#3893)

2025-03-01 23:01:58 -08:00

..

decoding_attention_triton

benchmark decoding attention kernel with cudnn (#2467)

2024-12-17 03:31:57 -08:00

deepseek

add deepgemm and sglang fp8 block-wise gemm benchmark (#3893)

2025-03-01 23:01:58 -08:00

fused_moe_triton

Revert "[MOE] enable efficient moe_alignment multi-blocks execution (3x~6x)" (#3982)

2025-02-28 23:57:17 -08:00

minmax-text-01-lightning_attention

support lightning_attention_decode in sgl-kernel for MiniMax-Text-01 (#3030)

2025-01-23 15:29:20 +08:00

quantization

Tuning Script for Feature DeepSeek V3/R1 INT8 Quantization (block-wise) (#3922)

2025-02-27 10:59:46 +00:00

rmsnorm

[Benchmark] add a benchmark for hf/vllm/sglang rmsnorm (#2486)

2024-12-15 13:52:08 +08:00

scheduler_batch

[kernel optimize] benchmark write_req_to_token_pool_triton and optimize kernel (#2509)

2024-12-22 02:31:02 -08:00