Skip to content

Pull requests: huggingface/trl

New pull request New
133 Open 2,967 Closed
133 Open 2,967 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

Drop vLLM 0.11 support
#5549 opened Apr 14, 2026 by qgallouedec Member Loading…
3
Update vLLM version support to 0.18.0
#5547 opened Apr 14, 2026 by qgallouedec Member Loading…
3
Differentiate Phi-3 and Phi-3.5 in tests
#5546 opened Apr 14, 2026 by qgallouedec Member Loading…
1
[docs] Add LLaMA 3 / Qwen 2.5 entries to chat_templates/README
#5545 opened Apr 14, 2026 by qgallouedec Member Loading…
1
Deprecate use_transformers_paged
#5544 opened Apr 14, 2026 by qgallouedec Member Loading…
1
Don't load ref_model when precompute_ref_log_probs in DPO/KTO
#5542 opened Apr 14, 2026 by albertvillanova Member Loading…
16
fix: Pass AsyncGRPOTrainer's processing_class to AsyncRolloutWorker
#5538 opened Apr 14, 2026 by xuanduy04 Contributor Loading…
2 of 8 tasks
1
3
Add additional model parameters to TestSupportsToolCalling for improved coverage
#5537 opened Apr 13, 2026 by qgallouedec Member Loading…
3
feat: add Phi-3 training chat template with generation markers
#5526 opened Apr 12, 2026 by RudrenduPaul Contributor Loading…
2 of 4 tasks
4
feat: add Gemma/Gemma2 training chat templates with generation markers
#5523 opened Apr 11, 2026 by ps-abhi Loading…
5 of 8 tasks
Fix add_response_schema for VLM processors
#5520 opened Apr 11, 2026 by qgallouedec Member Loading…
8
feat(glm-4-moe): Add {% generation %} markers for training chat template
#5519 opened Apr 10, 2026 by casinca Contributor Loading…
5 of 8 tasks
10
Add LLaMA 3.1 and 3.2 tool calling support
#5518 opened Apr 10, 2026 by qgallouedec Member Loading…
6
[WIP] Fix OnlineDPO vLLM server completion handling
#5516 opened Apr 10, 2026 by JohnGiorgi Contributor • Draft
5 of 8 tasks
1
Expose trainer dataset type metadata
#5512 opened Apr 10, 2026 by JohnGiorgi Contributor Loading…
5 of 8 tasks
1
2
[TPO] experimental TPO trainer
#5506 opened Apr 10, 2026 by kashif Collaborator Loading…
8 tasks
10
Set _tokenizer as trainer attribute
#5489 opened Apr 9, 2026 by albertvillanova Member Loading…
18
Deprecate eos_token config parameter
#5481 opened Apr 9, 2026 by albertvillanova Member Loading…
2
Fix is_liger_kernel_available compatibility with liger-kernel-nightly
#5478 opened Apr 8, 2026 by flofiz Loading…
3 of 6 tasks
1
Support messages with images in prepare_multimodal_messages
#5474 opened Apr 8, 2026 by albertvillanova Member Loading…
12
Fix the tests related to Flash Attention 2
#5473 opened Apr 8, 2026 by YangKai0616 Contributor Loading…
2 tasks
@kashif
7
[docs] Add hardware requirements note to quickstart
#5472 opened Apr 7, 2026 by pqbas Loading…
5 of 8 tasks
1
1
GOLDTrainer VLM support
#5461 opened Apr 6, 2026 by Strongich Loading…
4 of 8 tasks
24
[docs] Clarify dtype defaults between trf v5 and TRL
#5457 opened Apr 4, 2026 by casinca Contributor Loading…
2 of 4 tasks
1
[AsyncGRPO] Support async tool calls in AsyncRolloutWorker
#5446 opened Apr 3, 2026 by PoilZero Loading…
5 of 8 tasks
6
ProTip! no:milestone will show everything without a milestone.