Skip to content

Pull requests: huggingface/trl

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

Automatically label documentation and maintenance PRs 🔧 maintenance CI, tooling, tests, or repo upkeep
#7205 opened Sep 14, 2026 by albertvillanova Member Loading…
Reset the vLLM encoder cache after weight sync
#7200 opened Sep 13, 2026 by rmaguado Loading…
4 of 8 tasks
Reduce connection-pool warnings in the vLLM client
#7199 opened Sep 13, 2026 by vladbataev Loading…
5 of 7 tasks
[MFU] Use device peak flops instead of hardcoded H100's
#7197 opened Sep 13, 2026 by dwarez Loading…
4 of 8 tasks
Add selective activation checkpointing (SAC) to SFT
#7194 opened Sep 12, 2026 by kashif Collaborator Loading…
5 of 8 tasks
Bump the "github-actions-and-pre-commit" group with 2 updates across multiple ecosystems dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#7192 opened Sep 12, 2026 by dependabot Bot Loading…
docs: fix the clip explanation in the GRPO trainer page
#7190 opened Sep 12, 2026 by JiangLLM Loading…
4 of 8 tasks
fix: validate fractions in get_dataset to prevent ZeroDivisionError
#7164 opened Sep 10, 2026 by CJstate Loading…
5 of 6 tasks
Reject use_liger_kernel in GMPOTrainer
#7163 opened Sep 10, 2026 by YeonwooSung Contributor Loading…
5 of 8 tasks
Restore generation unwrap state if generate() raises
#7162 opened Sep 10, 2026 by YeonwooSung Contributor Loading…
4 of 8 tasks
Fail fast when GRPO combines Liger with the MoE auxiliary loss
#7161 opened Sep 10, 2026 by YeonwooSung Contributor Loading…
4 of 8 tasks
feat(grpo): add compute_metrics support to GRPOTrainer
#7144 opened Sep 9, 2026 by behroozazarkhalili Collaborator Loading…
4 of 5 tasks
feat: add activation_offloading to GRPOTrainer and RLOOTrainer
#7143 opened Sep 9, 2026 by behroozazarkhalili Collaborator Loading…
4 of 5 tasks
fix: validate dataset mixture fractions before loading
#7142 opened Sep 9, 2026 by behroozazarkhalili Collaborator Loading…
4 of 5 tasks
fix: score think_format_reward when <think> is prefilled in the prompt
#7141 opened Sep 9, 2026 by behroozazarkhalili Collaborator Loading…
4 of 5 tasks
Remove the experimental BCO trainer
#7136 opened Sep 9, 2026 by qgallouedec Member Loading…
Remove the experimental PRM trainer
#7133 opened Sep 9, 2026 by qgallouedec Member Loading…
[AsyncGRPO] Gather FSDP2 weights before NCCL send to vLLM
#7131 opened Sep 9, 2026 by sfc-gh-truwase Loading…
4 of 8 tasks
fix: validate ngram_size in get_repetition_penalty_reward
#7129 opened Sep 9, 2026 by CJstate Loading…
5 of 6 tasks
ProTip! What’s not been updated in a month: updated:<2026-08-14.