Skip to content

Pull requests: huggingface/trl

New pull request New
82 Open 2,003 Closed
82 Open 2,003 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 docstring interlink to parent class for NashMDTrainer and XPOTrainer
#4179 opened Sep 30, 2025 by albertvillanova Loading…
1
Fix PEFT interlinks in docstrings
#4178 opened Sep 30, 2025 by albertvillanova Loading…
1
Fix CI ImportError: FlashAttention2
#4176 opened Sep 30, 2025 by albertvillanova Loading…
1
3
Fix CI ValueError: Unknown loss type: dapo
#4173 opened Sep 30, 2025 by albertvillanova Loading…
1
1
Fix handling of f_divergence_type in DPO
#4171 opened Sep 30, 2025 by albertvillanova Loading…
1
Fix FA loss
#4170 opened Sep 30, 2025 by qgallouedec Loading…
4
Have vLLM return processed (temperature scaled) log probs
#4163 opened Sep 29, 2025 by YonatanGideoni Loading…
Updated vLLM integration guide
#4162 opened Sep 29, 2025 by sergiopaniego Loading…
5 tasks
3
🖨️ Print rich table for messages
#4160 opened Sep 28, 2025 by qgallouedec Loading…
2
🧺 [5/N] Refactor _generate in GRPO/RLOO: Insert images in the prompt
#4155 opened Sep 26, 2025 by qgallouedec Loading…
5 tasks
1
🧺 [4/N] Refactor _generate in GRPO/RLOO: Move forward_kwargs outside generation method
#4154 opened Sep 26, 2025 by qgallouedec Loading…
5 tasks
1
🧺 [3/N] Refactor _generate in GRPO/RLOO: Rely on generator for prompt truncation
#4153 opened Sep 26, 2025 by qgallouedec Loading…
5 tasks
3
🧺 [2/N] Refactor _generate in GRPO/RLOO: Use prompt_ids from generation
#4152 opened Sep 26, 2025 by qgallouedec Loading…
5 tasks
1
[WIP] Tool call
#4151 opened Sep 26, 2025 by qgallouedec Loading…
5 tasks
1
🧺 [1/N] Refactor _generate in GRPO/RLOO: list of ints instead of tensors
#4146 opened Sep 26, 2025 by qgallouedec Loading…
19
[TODO] Fix GKD Liger memory spike
#4140 opened Sep 24, 2025 by qgallouedec Loading…
@kashif
🅰️ Remove apex
#4139 opened Sep 24, 2025 by qgallouedec Loading…
1
👾 Use our own require_bitsandbytes
#4137 opened Sep 24, 2025 by qgallouedec Loading…
Disable cache in compute_loss only when checkpointing is enabled
#4133 opened Sep 24, 2025 by cyyever Loading…
4
[WIP] Make the CI faster
#4127 opened Sep 23, 2025 by qgallouedec Loading…
1
update guided decoding param to structured outputs
#4117 opened Sep 22, 2025 by jiqing-feng Loading…
5
Multi-turn tool calling support
#4115 opened Sep 21, 2025 by qgallouedec • Draft
17
🎞️ Support sequence classification models in clone_chat_template
#4097 opened Sep 16, 2025 by qgallouedec Loading…
1
🎁 RewardTrainer refactor
#4093 opened Sep 15, 2025 by qgallouedec Loading…
14
feat:add support for 'image_grid_thw'(QwenVL) in DPOTrainer
#4091 opened Sep 15, 2025 by ycma8 Loading…
2 of 5 tasks
1
4
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.