Skip to content

Pull requests: huggingface/trl

New pull request New
173 Open 3,606 Closed
173 Open 3,606 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

Fix OpenEnv docker-image example bootstrap
#6329 opened Jul 8, 2026 by sergiopaniego Member Loading…
3 tasks done
1
[GOLD] Tool calling support for GOLDTrainer
#6328 opened Jul 8, 2026 by Strongich Contributor • Draft
3 of 6 tasks
pip install -e ".[dev]" fails on macOS: liger-kernel requires triton
#6327 opened Jul 8, 2026 by clementtisseau Loading…
2 of 8 tasks
1
Support DatasetDict and IterableDatasetDict as eval_dataset in evaluate
#6326 opened Jul 8, 2026 by albertvillanova Member Loading…
4
Fix KTO evaluate crash on streaming datasets with unpaired-preference data
#6325 opened Jul 8, 2026 by albertvillanova Member • Draft
1
Fix error type for IterableDataset in GRPO and RLOO
#6324 opened Jul 8, 2026 by albertvillanova Member Loading…
2
Document that max_steps is required for iterable train datasets
#6323 opened Jul 8, 2026 by albertvillanova Member Loading…
1
Support DatasetDict and IterableDatasetDict as eval_dataset in trainers
#6322 opened Jul 8, 2026 by albertvillanova Member Loading…
2
Drop examples with no completion left after truncation in DPO and KTO
#6321 opened Jul 7, 2026 by qgallouedec Member Loading…
4
Drop fully-masked examples after truncation in SFT
#6320 opened Jul 7, 2026 by qgallouedec Member Loading…
1
1
chunked_nll GPU and Neuron
#6314 opened Jul 6, 2026 by michaelbenayoun Member Loading…
2
Fix crash when reward function is a functools.partial or callable instance
#6313 opened Jul 6, 2026 by qgallouedec Member Loading…
1
1
Raise on quantization_config + already-instantiated model in DPOTrainer
#6312 opened Jul 6, 2026 by qgallouedec Member Loading…
3
Fix GRPOTrainer vLLM prompt token expansion bug with VLMs (#6294)
#6300 opened Jul 6, 2026 by Saurav-Gupta-9741 Loading…
5 of 8 tasks
1
3
fix(grpo): handle NaN/None vLLM logprobs in importance-sampling correction
#6297 opened Jul 5, 2026 by shadowmodder Loading…
2 tasks done
3
Respect use_cpu in create_model_from_path device_map default
#6295 opened Jul 5, 2026 by Strongich Contributor Loading…
2 of 8 tasks
2
Fix GRPO tool loop handling for image-returning tools
#6290 opened Jul 5, 2026 by vieveks Loading…
4 of 8 tasks
1
1
Fix multimodal field handling in GRPO tool call loop
#6286 opened Jul 4, 2026 by HariomJangra Loading…
4 of 8 tasks
1
Fix multimodal tool call slicing in GRPO tool loop
#6284 opened Jul 4, 2026 by Shankar-v27 Loading…
4 of 8 tasks
1
Cosmetic alignements
#6282 opened Jul 4, 2026 by qgallouedec Member • Draft
8 tasks
Clarify stream-only dedupe check
#6280 opened Jul 3, 2026 by kashif Collaborator Loading…
4
Align KTO with DPO: quantization_config trainer argument
#6276 opened Jul 3, 2026 by qgallouedec Member Loading…
6
Async grpo vllm client
#6269 opened Jul 3, 2026 by AmineDiro Member Loading…
5
Add idefics2 training chat template
#6267 opened Jul 3, 2026 by nathon-lee Loading…
5 of 8 tasks
3
Change default max_completion_length from 256 to 512
#6264 opened Jul 3, 2026 by dhruvnigam93 Loading…
4 of 8 tasks
1
ProTip! Follow long discussions with comments:>50.