Skip to content

Pull requests: huggingface/trl

New pull request New
92 Open 2,723 Closed
92 Open 2,723 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

feat(grpo_trainer.py): Variational Sequence-Level Soft Policy Optimization (VESPO)
#5199 opened Feb 27, 2026 by casinca • Draft
5 tasks
1
fix logprobs handling 🩹 for patch
#5198 opened Feb 27, 2026 by winglian Loading…
5 tasks
7
Misc packing improvements
#5189 opened Feb 26, 2026 by mariosasko Loading…
1 of 5 tasks
1
vLLM Server Sync via LoRA Adapter Reload (avoid merge + full weight sync) for GRPO
#5188 opened Feb 26, 2026 by lfranceschetti Loading…
2
Fix title consistency from "Transformers Reinforcement Learning" to "Transformer Reinforcement Learning"
#5183 opened Feb 26, 2026 by qgallouedec Loading…
5 tasks
2
Simplify NeMo Gym user experience
#5156 opened Feb 24, 2026 by cmunley1 Loading…
3
Fix GRPO tool mask alignment after tool-call retokenization
#5145 opened Feb 21, 2026 by MichalMraz Loading…
1
5
DPO padding-free
#5141 opened Feb 21, 2026 by qgallouedec • Draft
5 tasks
6
[GKD] Buffer Implementation for Distillation Trainer
#5137 opened Feb 20, 2026 by cmpatino • Draft
5 tasks
MGPO feature addition
#5126 opened Feb 19, 2026 by damoonsh Loading…
2 of 5 tasks
wip(neuron): add neuron integration for SFT
#5125 opened Feb 18, 2026 by michaelbenayoun • Draft
Decouple rollout dispatch from vLLM backend in GRPO _generate_single_turn
#5122 opened Feb 18, 2026 by albertvillanova Loading…
1
7
feat(experimental): Divergence Proximal Policy Optimization
#5117 opened Feb 17, 2026 by LeonEricsson Loading…
5 tasks
30
Add prefix-preserving training chat template for GPT-OSS
#5109 opened Feb 17, 2026 by qgallouedec Loading…
6
Add support for DGPO (ICLR 2026) to GRPO
#5102 opened Feb 15, 2026 by YanqiDai Loading…
5 tasks done
22
Cast multimodal forward_kwargs to compute dtype for bf16/fp16 training
#5073 opened Feb 11, 2026 by akshan-main Loading…
4 of 5 tasks
5
Add support for DPPO [WIP]
#5065 opened Feb 10, 2026 by catherinelee274 • Draft
5 tasks
1
2
Fix GRPO VLM prompt handling for string prompts
#5064 opened Feb 10, 2026 by akshan-main Loading…
5 tasks done
3
5
Add CFPO objective to GRPO trainer
#5027 opened Feb 9, 2026 by asparius Loading…
1
Add support for MaxRL
#5026 opened Feb 9, 2026 by catherinelee274 Loading…
4 of 5 tasks
1
21
Feature/ HICRA implementation
#4997 opened Feb 6, 2026 by w601sxs Loading…
2 of 5 tasks
1
Add OpenEnv's Rubrics support
#4994 opened Feb 6, 2026 by sergiopaniego • Draft
5 tasks
fix: add gradient checkpointing to PolicyAndValueWrapper
#4955 opened Feb 3, 2026 by lvhungdev Loading…
3 of 5 tasks
1
OpenEnv clients async support update
#4949 opened Feb 2, 2026 by sergiopaniego Loading…
5 tasks
16
[Experimental] Add SDFT trainer, config, docs, and tests
#4941 opened Jan 31, 2026 by Shekswess Loading…
4 of 5 tasks
1
8
ProTip! Filter pull requests by the default branch with base:main.