Yuan Luoandluoyuan.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

..

allreduce

…

attention

Fix typos and unify size(s)/stride(s) API calls (#8799)

2025-08-08 00:18:08 -07:00

cpu

…

cutlass_extensions

[sgl-kernel] 1/N Refactor sglang cutlass 3x - gemm fp8 blockwise sm90 (#8913)

2025-08-14 10:55:54 -07:00

elementwise

Fuse writing KV buffer into rope kernel (part 1: sgl-kernel) (#9077)

2025-08-12 01:46:40 -07:00

gemm

[sgl-kernel] 1/N Refactor sglang cutlass 3x - gemm fp8 blockwise sm90 (#8913)

2025-08-14 10:55:54 -07:00

grammar

…

kvcacheio

fix page first per layer pf2lf kernel (#8915)

2025-08-09 17:16:11 -07:00

memory

[Feature] Support custom set kv buffer kernel (#8884)

2025-08-12 16:56:51 -07:00

moe

[2/n]decouple quantization implementation from vLLM dependency (#8112)

2025-08-14 03:19:03 -07:00

spatial

Runtime check CUDA driver version to avoid unresolved green context symbols (#9021)

2025-08-12 09:26:10 -07:00

speculative

…

common_extension_rocm.cc

Clean up allocators (#9134)

2025-08-13 13:56:04 -07:00

common_extension.cc

[sgl-kernel] Support FlashInfer top_k_top_p_sampling_from_logits (#9060)

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

flash_extension.cc

Update fa3 interface and add unit test (#9150)

2025-08-13 20:05:02 +08:00