Skip to content

Pull requests: huggingface/trl

New pull request New
100 Open 2,772 Closed
100 Open 2,772 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

Update TRL banner to support light/dark mode
#5270 opened Mar 10, 2026 by qgallouedec Loading…
5
Centralize AI agent templates in .ai
#5268 opened Mar 10, 2026 by qgallouedec Loading…
5
Introduce backend rollout-completions interface and decouple OpenEnv helper from vLLM internals
#5256 opened Mar 10, 2026 by rycerzes Loading…
1
2
Change default vllm_mode to "colocate" and add v0→v1 migration guide
#5255 opened Mar 10, 2026 by qgallouedec Loading…
10
async streaming grpo w prefetch
#5250 opened Mar 9, 2026 by winglian Loading…
5 tasks
6
batch params together in weight sync and async update the weights
#5249 opened Mar 9, 2026 by winglian Loading…
5 tasks
5
Introduce minimal generation backend interface for GRPO and RLOO trainers
#5244 opened Mar 8, 2026 by rycerzes Loading…
1
6
feat: log raw importance ratios and fraction of truncation/masking in vLLM importance sampling correction
#5243 opened Mar 8, 2026 by muupan Loading…
1 of 5 tasks
1
3
[GRPO] Fix re-tokenization bug in tool-calling loop by concatenating token IDs
#5242 opened Mar 7, 2026 by qgallouedec Loading…
22
Fix error message in OnlineDPO
#5237 opened Mar 7, 2026 by qgallouedec Loading…
7
Update openenv examples to use environment_factory
#5235 opened Mar 6, 2026 by sergiopaniego • Draft
8 tasks
Allow reward functions to log extra columns and scalar metrics
#5233 opened Mar 6, 2026 by manueldeprada Loading…
14
fix(vllm): handle `logprobs=None´ and align logprob docs
#5203 opened Mar 2, 2026 by LeonEricsson Loading…
feat(grpo_trainer.py): Variational Sequence-Level Soft Policy Optimization (VESPO)
#5199 opened Feb 27, 2026 by casinca Loading…
4 of 5 tasks
1
2
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
11
vLLM Server Sync via LoRA Adapter Reload (avoid merge + full weight sync) for GRPO
#5188 opened Feb 26, 2026 by lfranceschetti Loading…
2
1
Fix title consistency from "Transformer Reinforcement Learning" to "Transformers Reinforcement Learning"
#5183 opened Feb 26, 2026 by qgallouedec Loading…
5 tasks
7
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
7
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 Loading…
3 tasks done
17
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
feat(experimental): Divergence Proximal Policy Optimization
#5117 opened Feb 17, 2026 by LeonEricsson Loading…
5 tasks
33
ProTip! Mix and match filters to narrow down what you’re looking for.