Skip to content

Pull requests: huggingface/trl

New pull request New
161 Open 3,300 Closed
161 Open 3,300 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(profiling): log ProfilingContext metrics to Trackio backend
#5979 opened Jun 8, 2026 by Anai-Guo Loading…
3 of 6 tasks
1
Raise when use_liger_kernel is combined with a PEFT adapter on lm_head
#5977 opened Jun 8, 2026 by akshansh47 Loading…
4 of 6 tasks
1
5
Fix broken code examples in docs (RLOO syntax, SFTConfig max_length)
#5970 opened Jun 7, 2026 by DaoyuanLi2816 Contributor Loading…
3 of 8 tasks
[GOLD] VLM support for GOLDTrainer
#5969 opened Jun 7, 2026 by Strongich Loading…
4 of 8 tasks
@kashif
6
Secure trl vllm-serve server defaults
#5965 opened Jun 7, 2026 by LaPhilosophie Loading…
4 of 8 tasks
7
Fix reward function name fallback for callable objects
#5955 opened Jun 6, 2026 by msdsm Loading…
5 of 8 tasks
1
fix: Add warning for unsupported int4 quantization with device_map auto
#5953 opened Jun 5, 2026 by NIK-TIGER-BILL Loading…
6 of 8 tasks
1
2
feat(sft): add loss_type='weighted_nll' for per-sample loss scaling
#5952 opened Jun 5, 2026 by Sumu004 Loading…
5 of 8 tasks
1
12
Align KTO with DPO: Support VLM
#5939 opened Jun 4, 2026 by albertvillanova Member Loading…
16
Delta weight sync for AsyncGRPO (sparse patches over HF Bucket)
#5937 opened Jun 4, 2026 by AmineDiro Member Loading…
1 task done
19
chore: update pr_style_bot.yml
#5921 opened Jun 2, 2026 by hf-security-analysis Bot Loading…
3
Add AMD/ROCm CI
#5918 opened Jun 2, 2026 by kashif Collaborator Loading…
12
Fix prepare_deepspeed crash with cpu offload optimizer
#5916 opened Jun 2, 2026 by roycho96 Contributor Loading…
2 of 8 tasks
@kashif
3
Fix AsyncGRPO checkpoint resume triggering unnecessary vLLM inference
#5911 opened Jun 2, 2026 by AmmarHassona Loading…
4 of 8 tasks
1
@AmineDiro
12
Fix: update merged probability computation to follow Bayes' rule
#5905 opened Jun 1, 2026 by vman049 Loading…
4 of 8 tasks
1
@kashif @cmpatino
5
AsyncGRPOTrainer: add PEFT/LoRA support
#5896 opened May 31, 2026 by rycerzes Contributor Loading…
5 of 8 tasks
10
AsyncGRPOTrainer: add ProcessorMixin handling
#5895 opened May 31, 2026 by rycerzes Contributor Loading…
5 of 8 tasks
7
AsyncGRPOTrainer: add sampling parameters (top_p, top_k, min_p, repetition_penalty)
#5894 opened May 31, 2026 by rycerzes Contributor Loading…
5 of 8 tasks
AsyncGRPOTrainer: add model_init_kwargs support
#5893 opened May 31, 2026 by rycerzes Contributor Loading…
5 of 8 tasks
async grpo native weight sync with vllm>=0.22.0
#5892 opened May 30, 2026 by AmineDiro Member Loading…
6
[GRPO] Match the Liger dapo/cispo/vespo normalizer to the non-Liger path
#5890 opened May 30, 2026 by kashif Collaborator • Draft
3
fix(grpo,rloo): apply generation_config override in use_transformers_paged path
#5888 opened May 30, 2026 by Sumu004 Loading…
4 of 8 tasks
1
DPOTrainer: eagerly delete intermediate logits tensors to reduce peak memory
#5882 opened May 29, 2026 by flutist Contributor Loading…
4
[DPOTrainer] Drop images when max_length truncation causes token/feature mismatch
#5881 opened May 29, 2026 by flutist Contributor Loading…
5
Simplify reference model handling in GRPO/RLOO
#5877 opened May 29, 2026 by albertvillanova Member Loading…
3
ProTip! Filter pull requests by the default branch with base:main.