Yongye ZhuandClaude Opus 5 8263ea12bd [Build] Move DeepGEMM pin to the vLLM fork and update the Mega MoE call convention (#56876) ...

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-15 00:57:18 -07:00

..

deepgemm.cmake

[Build] Move DeepGEMM pin to the vLLM fork and update the Mega MoE call convention (#56876)

2026-09-15 00:57:18 -07:00

deepselect.cmake

[Perf][Kernel] Integrate DeepSelect TopK for the DSA sparse indexer (#56464)

2026-09-13 00:44:37 -07:00

flashkda.cmake

[KDA] Update flashKDA to support bf16 checkpoint state (#56485)

2026-09-11 23:53:24 +00:00

flashmla.cmake

[Model][DSv4.1] Store the whole KV in MXFP8 (FlashMLA V4.1 record) (#56893)

2026-09-14 20:12:55 -07:00

fmha_sm100.cmake

[Attention][MiniMax-M3] Add MSA speculative decode verification (#50032)

2026-08-02 13:46:55 -07:00

qutlass.cmake

Add sm_107 for Rubin (#49387)

2026-07-24 11:59:49 -07:00

tml_fa4.cmake

[CI] Bump CUTLASS DSL to 4.7 (#54927)

2026-09-11 20:11:29 -07:00

triton_kernels.cmake

[CI/Build][AMD] Install triton_kernels via CMake (#50328)

2026-07-30 22:05:19 -05:00

vllm_flash_attn.cmake

[Attention] Sync FA with upstream (#54819)

2026-09-04 23:48:32 -04:00