Skip to content

Pull requests: huggingface/trl

New pull request New
138 Open 3,195 Closed
138 Open 3,195 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

Add explicit response_schema override for GRPO
#5833 opened May 25, 2026 by haimianxing Loading…
5 of 6 tasks
1
3
feat(grpo): tool response/observation training
#5832 opened May 25, 2026 by LeonEricsson Collaborator • Draft
1 of 8 tasks
1
[WIP] Add support for Audio
#5830 opened May 25, 2026 by qgallouedec Member Loading…
8 tasks
8
feat(sft): configurable chunked-NLL chunk size
#5829 opened May 24, 2026 by mrs83 Loading…
4 of 8 tasks
2
[feat] add Dapo prompt level avg
#5828 opened May 24, 2026 by DagaBhai Contributor Loading…
3 of 8 tasks
1
9
Fix NaN loss when completions are fully truncated
#5826 opened May 24, 2026 by matdou Contributor Loading…
4 of 8 tasks
1
3
Add Entropy Adaptive Fine Tuning
#5823 opened May 23, 2026 by electroglyph Loading…
3 of 6 tasks
1
3
Align KTO with DPO: Simplify metrics from sum/count to direct averages
#5820 opened May 22, 2026 by albertvillanova Member Loading…
6
Add SFT + reward-model recipe + diagnostics for PPO TL;DR example
#5813 opened May 22, 2026 by kohsheen1234 Loading…
5 of 6 tasks
1
10
Warn when GRPOTrainer use_liger_kernel masks LoRA adapters on lm_head
#5808 opened May 21, 2026 by adityasingh2400 Loading…
5 tasks done
1
MADPO
#5804 opened May 21, 2026 by qgallouedec Member • Draft
Make trl vllm-serve OpenAI-compatible (exploratory)
#5803 opened May 21, 2026 by qgallouedec Member Loading…
1
7
Add trust_remote_code to trainer configs
#5802 opened May 20, 2026 by qgallouedec Member Loading…
10
docs: document expandable_segments allocator config for memory tuning
#5794 opened May 20, 2026 by akshansh47 Loading…
4 of 8 tasks
[WIP] New parsing approach
#5791 opened May 19, 2026 by qgallouedec Member Loading…
8 tasks
7
Add compute_metrics support to GRPOTrainer
#5790 opened May 19, 2026 by JulesRoussel2001 Loading…
5 of 8 tasks
1
[GKD] Use vLLM for student generation
#5782 opened May 18, 2026 by roycho96 Contributor Loading…
4 of 8 tasks
3
Continuous Batching support for AsyncGRPO
#5781 opened May 16, 2026 by qgallouedec Member • Draft
8 tasks
3
use eager attn for test_train_vlm_multi_image as a WA
#5774 opened May 15, 2026 by kaixuanliu Contributor Loading…
5
cleanup xpu cahce memory after each test
#5771 opened May 15, 2026 by kaixuanliu Contributor Loading…
2
Memory-efficient PEFT/LoRA vLLM weight sync under DeepSpeed ZeRO-3
#5766 opened May 13, 2026 by rak96 Loading…
7 of 14 tasks
3
feat(grpo): replace deprecated use_transformers_paged with transformers continuous batching
#5765 opened May 13, 2026 by sergiopaniego Member Loading…
4 of 8 tasks
19
docs: set max_completion_length=1024 in GRPO quickstart examples
#5759 opened May 13, 2026 by dhruvnigam93 Loading…
5 of 8 tasks
1
Tighten old_per_token_logps recomputation check in GRPO
#5757 opened May 12, 2026 by wengeezhang Loading…
5 of 8 tasks
1
async_grpo don't return on queue.Empty
#5751 opened May 12, 2026 by AmineDiro Member Loading…
16
ProTip! Mix and match filters to narrow down what you’re looking for.