Xiaoyu Zhang f730362ee2 reduce moe_align_block_size_kernel small batch mode overhead (#5086)

2025-04-09 17:59:35 -07:00

..

bench_awq_dequant.py

Add awq dequantize kernel to sgl with 1x to 3x speedup (#4104)

2025-03-12 00:10:02 -07:00

bench_cublas_grouped_gemm.py

[Feature] Apply Cublas Grouped Gemm kernel (#3629)

2025-02-18 15:18:31 +08:00

bench_fp8_blockwise_gemm.py

sgl-kernel use cutlass latest version for fp8 blockwise gemm (#5207)

2025-04-09 11:47:04 -07:00

bench_fp8_gemm.py

…

bench_int8_gemm.py

…

bench_lightning_attention_decode.py

[Fix] use torch.cat instead of torch.concat to prevent entering the Autograd backends. (#4466)

2025-03-16 00:02:47 -07:00

bench_moe_align_block_size.py

reduce moe_align_block_size_kernel small batch mode overhead (#5086)

2025-04-09 17:59:35 -07:00

bench_moe_fused_gate.py

Add deepseek style fused moe group gate selection kernel (#4530)

2025-03-29 11:51:45 -07:00

bench_moe_topk_softmax.py

Add moe topk softmax templated from vllm (#4302)

2025-03-14 12:03:33 -07:00

bench_per_tensor_quant_fp8.py

[quant kernel] sgl-kernel support per_tensor_quant fp8 (#3786)

2025-03-06 18:05:43 -08:00

bench_per_token_group_quant_8bit.py

[sgl-kernel] per token group quant support COLUMN MAJOR (#4817)

2025-04-02 18:29:59 -07:00

bench_per_token_quant_fp8.py

fix accuracy issue (#4376)

2025-03-13 02:06:22 -07:00