Skip to content

[https://nvbugs/6877539][fix] Fold GQA group into SDPA query axis in MiniMax-M3 decode attention - #20029

Merged
chenfeiz0326 merged 2 commits into
NVIDIA:release/1.3from
tensorrt-cicd:repair-bot-bug6877539-full-20261008T015514-f7aba38b-release-1.3-cb2b0e3d6f12
Oct 12, 2026
Merged

[https://nvbugs/6877539][fix] Fold GQA group into SDPA query axis in MiniMax-M3 decode attention#20029
chenfeiz0326 merged 2 commits into
NVIDIA:release/1.3from
tensorrt-cicd:repair-bot-bug6877539-full-20261008T015514-f7aba38b-release-1.3-cb2b0e3d6f12

[https://nvbugs/6877539][test] Add parity test for MiniMax-M3 dense S…

782c527
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs