Wenbo Yang 75b656488a Support serving DeepSeek-R1-Channel-INT8 with 32 L40S. (#4418)

2025-03-17 00:03:43 -07:00

..

allreduce

fix custom allreduce performance/accuracy problem (#4477)

2025-03-16 12:16:30 -07:00

attention

Rename files in sgl kernel to avoid nested folder structure (#4213)

2025-03-08 22:54:51 -08:00

cutlass_extensions

Rename files in sgl kernel to avoid nested folder structure (#4213)

2025-03-08 22:54:51 -08:00

elementwise

Optimize rope in sgl kernel (#4267)

2025-03-10 10:07:45 -07:00

gemm

Support serving DeepSeek-R1-Channel-INT8 with 32 L40S. (#4418)

2025-03-17 00:03:43 -07:00

moe

Add moe topk softmax templated from vllm (#4302)

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

speculative

[Eagle] Remove the greedy branch and some redundant code (#4363)

2025-03-16 02:48:55 -07:00

torch_extension_rocm.cc

[ROCm] enable moe topk softmax in amd (#4448)

2025-03-16 18:16:55 -07:00

torch_extension.cc

Add greedy verification kernel (#4383)

2025-03-16 00:58:26 -07:00