Chunan Zeng 65c24c28f9 [Quant Kernel] refactored per token group quant fp8 to support int8 up-to 2x faster (#4396)

2025-03-23 23:44:17 -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

…

bench_fp8_blockwise_gemm.py

…

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

feat: support ep size < 32 for sgl kernel (#4348)

2025-03-12 20:50:46 -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

[Quant Kernel] refactored per token group quant fp8 to support int8 up-to 2x faster (#4396)

2025-03-23 23:44:17 -07:00

bench_per_token_quant_fp8.py

fix accuracy issue (#4376)

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