forked from THUDM/slime
-
Notifications
You must be signed in to change notification settings - Fork 1
Pull requests: puyuan1996/slime
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feature(pu): add init version of off-policy grpo/ppo enhancement with list and http buffer
#4
opened Dec 17, 2025 by
puyuan1996
Loading…
feature(pu): add init version of off-policy grpo/ppo enhancement with list and http buffer
#3
opened Dec 11, 2025 by
puyuan1996
Loading…
feature(pu): add init version of off-policy grpo/ppo
enhancement
New feature or request
#1
opened Dec 9, 2025 by
puyuan1996
Loading…
ProTip!
Adding no:label will show everything without a label.