Add sequence mask for grpo#420

Merged

pan-x-c merged 6 commits intomodelscope:mainfrom

garyzhang99:dev/scalable_grpo

Dec 5, 2025

Commits on Dec 2, 2025

add sequence mask for grpo
问昊
committed
udpate policy loss value test
问昊
committed

Commits on Dec 3, 2025

Merge branch 'main' into dev/scalable_grpo
garyzhang99
authored

Commits on Dec 4, 2025

fix pre commit after merge main
问昊
committed
not redundent compute
问昊
committed

Commits on Dec 5, 2025

clean code as suggested
问昊
committed