Skip to content

[https://nvbugs/6877539][fix] Fold GQA group into SDPA query axis in MiniMax-M3 decode attention - #20115

Closed
chenfeiz0326 wants to merge 2 commits into
NVIDIA:mainfrom
chenfeiz0326:nvbug6877539-m3-dense-decode-sdpa-main
Closed

chenfeiz0326 wants to merge 2 commits into
NVIDIA:mainfrom
chenfeiz0326:nvbug6877539-m3-dense-decode-sdpa-main

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

4394a4d
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs