Skip to content

feat(grpo): support message penalties in single controller - #3734

Merged
yuki-97 merged 4 commits into
mainfrom
amahishi/malformed_thinking_sc
Aug 31, 2026
Merged

feat(grpo): support message penalties in single controller#3734
yuki-97 merged 4 commits into
mainfrom
amahishi/malformed_thinking_sc

fix(sc): update checkpoint converter stub

9cd5e2e
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Aug 31, 2026 in 1s

DCO

All commits are signed off!