Yongye ZhuandClaude Opus 5.5 7566d83bd3 [Attention][MiniMax-M3] NVFP4 KV cache on the MSA sparse attention path (#59300) ...

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-01 14:39:55 -07:00

..

deepgemm.cmake

[Build] Fix DeepGEMM CUDA 12.9 release builds (#57554)

2026-09-20 20:14:00 -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

[Kernel] Bump FlashKDA to keep the recurrent state in fp32 (#58846)

2026-09-26 22:20:44 +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] NVFP4 KV cache on the MSA sparse attention path (#59300)

2026-10-01 14:39:55 -07:00

qutlass.cmake

[Compilation] Fix QuTLASS compilation with PyTorch 2.13 (#58173)

2026-09-22 20:43:28 -07:00

tml_fa4.cmake

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

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

triton_kernels.cmake

[ROCm] Bump torch 2.13, triton 3.8, torchaudio, torchvision (#50605)

2026-09-25 14:55:52 -05:00

vllm_flash_attn.cmake

[perf] wire FA and FlashMLA for sm90 GLM5Next NoPE SparseMLA (#55385)

2026-09-22 02:03:59 -07:00