Repository navigation

[None][feat] Run GLM-5.3-Flash sparse attention on SM120 through FlashInfer - #20639

Merged

nvchenghaoz merged 2 commits into

NVIDIA:mainfrom

nvchenghaoz:glm53-flash-sm120

Nov 3, 2026

Merged

[None][feat] Run GLM-5.3-Flash sparse attention on SM120 through FlashInfer#20639
nvchenghaoz merged 2 commits into
NVIDIA:mainfrom
nvchenghaoz:glm53-flash-sm120

Commits on Nov 2, 2026
- [None][feat] Run GLM-5.3-Flash sparse attention on SM120 through FlashInfer
  
  nvchenghaoz
  authored and
  root
  committed
  d6c8f71
Commits on Nov 3, 2026
- [None][test] Add GLM-5.3-Flash NVFP4 GSM8K accuracy test on 4x RTX PRO 6000
  root
  committed
  897ac5e