Skip to content

Pull requests: huggingface/trl

New pull request New
185 Open 3,956 Closed
185 Open 3,956 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

Device agnostic
#6770 opened Aug 17, 2026 by kaixuanliu Contributor Loading…
Do not quantize the teacher by default in the distillation scripts
#6769 opened Aug 16, 2026 by behroozazarkhalili Collaborator Loading…
1
1
Require liger-kernel 0.8.2 and drop the SAPO warning filter
#6768 opened Aug 15, 2026 by albertvillanova Member • Draft
2
@albertvillanova
Add DeepSeek-R1-Distill chat template
#6766 opened Aug 15, 2026 by qgallouedec Member Loading…
1
Use vLLM's own server instead of TRL's
#6765 opened Aug 15, 2026 by qgallouedec Member Loading…
21
Add Qwen3.8 support and testing
#6764 opened Aug 14, 2026 by qgallouedec Member Loading…
1
Test one Python version on PRs, matrix nightly
#6763 opened Aug 14, 2026 by qgallouedec Member Loading…
1
Scan the pushed commits in the secret scanning workflow
#6759 opened Aug 14, 2026 by albertvillanova Member • 3/3 Loading…
4
Fail the secret scanning job when the scan errors out
#6758 opened Aug 14, 2026 by albertvillanova Member • 2/3 Loading…
3
Restrict token access in the secret scanning workflow
#6757 opened Aug 14, 2026 by albertvillanova Member • 1/3 Loading…
2
Declare the test report dependencies in the test extra
#6756 opened Aug 14, 2026 by albertvillanova Member • 3/3 Loading…
3
Report slow tests results to Slack based on the job status
#6754 opened Aug 14, 2026 by albertvillanova Member • 2/3 Loading…
7
Fix misaligned headers in the failed tests report table
#6753 opened Aug 14, 2026 by albertvillanova Member • 1/3 Loading…
1
Pass the pytest report log flag from the workflow instead of the Makefile
#6750 opened Aug 14, 2026 by albertvillanova Member • 2/2 Loading…
1
Use built-in GITHUB_ACTIONS variable instead of custom IS_GITHUB_CI
#6749 opened Aug 14, 2026 by albertvillanova Member • 1/2 Loading…
1
Add Weighted Instruction Tuning loss to SFTTrainer
#6747 opened Aug 14, 2026 by C-anwoy Loading…
5 of 8 tasks
1
3
Make the installed TRL skill discoverable
#6745 opened Aug 14, 2026 by DaoyuanLi2816 Contributor Loading…
5 of 8 tasks
1
Align the chunked-loss config access between SFT and Distillation
#6744 opened Aug 13, 2026 by qgallouedec Member • 3/3 Loading…
1
Move GPU CI from T4 to L40S
#6741 opened Aug 13, 2026 by qgallouedec Member • 1/2 Loading…
7
Add Muse Glimmer chat template
#6739 opened Aug 13, 2026 by qgallouedec Member • 2/3 Loading…
1
Add Muse Glimmer support and testing
#6738 opened Aug 13, 2026 by qgallouedec Member • 1/3 Loading…
3
Add LFM2.5-VL support and testing
#6737 opened Aug 13, 2026 by qgallouedec Member Loading…
5
Add Nemotron 3.5 Lightning support and testing
#6736 opened Aug 13, 2026 by qgallouedec Member Loading…
1
fix(data): fix _pack_wrapped corrupting data on sliced input tables
#6733 opened Aug 13, 2026 by AuthRan Loading…
4 tasks done
1
fix(trainer): make compute_flops_per_token invariant to embedding tying
#6731 opened Aug 13, 2026 by AuthRan Loading…
3 tasks done
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.