Skip to content

Pull requests: OpenRLHF/OpenRLHF

New pull request New
24 Open 433 Closed
24 Open 433 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

adding CFPO to OpenRLHF
#1184 opened Feb 9, 2026 by asparius Loading…
1
feat: add AgentTokenHandler with defensive token concatenation for agentic training (#1128)
#1181 opened Jan 30, 2026 by ichbinlucaskim Loading…
13
feat: Switch vLLM rollout sampling to oversampling.
#1179 opened Jan 20, 2026 by Freder-chen Loading…
6
feat: add the support of fsdp2 and remove deepspeed (new version of PR 1115)
#1176 opened Jan 16, 2026 by LYMDLUT Loading…
27
Default overlap_comm on for ZeRO-2+ RLHF runs
#1154 opened Nov 26, 2025 by MagellaX Loading…
4
Enhance PPO logging with entropy, reward stats, and grad norm insights
#1148 opened Nov 8, 2025 by MagellaX Loading…
7
Star Attention topology support with model integration and --attn_topology flag
#1122 opened Aug 26, 2025 by MagellaX Loading…
3
Add FSDP backend and --dist_backend flag across CLIs; introduce FSDPStrategy
#1115 opened Aug 23, 2025 by MagellaX Loading…
72
CLI support for top_k
#1104 opened Aug 13, 2025 by JoNeedsSleep Loading…
3
Update utils.py
#1101 opened Aug 6, 2025 by LiyuanLucasLiu Loading…
8
Enable logits extraction from vLLM for training
#1075 opened Jul 9, 2025 by MooMoo-Yang Loading…
12
Reward model outputting one reward per rollout.
#1037 opened May 28, 2025 by NotTheStallion Loading…
Merge lmm-r1 for Multimodal PPO
#989 opened Apr 23, 2025 by TideDra Loading…
2
Fix Tokenizer Behavior for Special Placeholder Token
#894 opened Mar 20, 2025 by YuchenFan48 Loading…
Support unbiased off-policy GRPO
#840 opened Mar 7, 2025 by LYMDLUT Loading…
1
added LoRA adapter disabling for computing KL divergence in single no…
#836 opened Mar 6, 2025 by wilkincr Loading…
1
Add support for max time per run
#711 opened Feb 5, 2025 by titu1994 Loading…
1
Support SFT and DPO training for Qwen2VL
#665 opened Jan 10, 2025 by LiuXTao Loading…
9
Integrate SGLang into OpenRLHF. Non-Hybrid Engine Only
#661 opened Jan 9, 2025 by zhaochenyang20 Loading…
12
Support rl logging board
#658 opened Jan 9, 2025 by HarderThenHarder Loading…
4
Ensure train datasets do not contain eval datasets
#594 opened Dec 17, 2024 by dingyuan-shi Loading…
Support broadcast vllm params by chunks
#593 opened Dec 17, 2024 by zhuzilin Loading…
2
Make sure there is always _some_ eval data
#582 opened Dec 13, 2024 by frrad Loading…
Support TRL's RLOO
#553 opened Dec 4, 2024 by songxxzp Loading…
4
ProTip! Mix and match filters to narrow down what you’re looking for.