Alexander Matveev a60418e6fb Sparse MLA on Hopper: Use SGLang's kernel for the sparse mla low latency runs ...

Signed-off-by: Alexander Matveev <amatveev@redhat.com>

2026-04-17 16:51:32 +00:00

..

cutlass_fa3.cmake

Sparse MLA on Hopper: Use SGLang's kernel for the sparse mla low latency runs

2026-04-17 16:51:32 +00:00

deepgemm.cmake

[UX] Integrate DeepGEMM into vLLM wheel via CMake (#37980)

2026-04-08 18:56:32 -07:00

flashmla.cmake

[BugFix] Fix Python 3.13 FlashMLA import error (#34548)

2026-02-15 20:09:18 -08:00

qutlass.cmake

[NVIDIA] Fix DGX Spark logic (#38126)

2026-03-27 15:26:07 -07:00

triton_kernels.cmake

[Release 2.10] Update to Torch 2.10 - final release (#30525)

2026-02-08 13:51:09 -08:00

vllm_flash_attn.cmake

[Attention] relax the head dim 512 and paged kv for sm90+FA4 (#38835)

2026-04-08 18:23:18 +00:00