Skip to content

Pull requests: huggingface/trl

New pull request New
Clear current search query, filters, and sorts
75 Open 2,166 Closed
75 Open 2,166 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

🚀 Enhance GRPO VLLM server from sync to async and accelerate training
#3182 opened Mar 30, 2025 by binary-husky Loading…
5
Fixing GRPO reward_func being a model with DeepSpeed ZeRO-3
#2984 opened Feb 28, 2025 by jamesbraza Loading…
4
Add a raw generate API to the vLLM server
#3227 opened Apr 3, 2025 by wilrop Loading…
5 tasks
4
[WIP] Iterative training scripts for SPIN and SPPO
#3011 opened Mar 5, 2025 by jkx19 • Draft
3 of 5 tasks
Add special token to PRM vocabulary if not present
#2646 opened Jan 24, 2025 by plaguss • Draft
5 tasks
5
Add the metrics completion_length_max and completion_length_min
#2930 opened Feb 22, 2025 by dignfei Loading…
4 tasks
4
[WIP] vllm-server-spec-dec-support
#3643 opened Jun 24, 2025 by shirinyamani Loading…
5 tasks
1
dynamic temperature
#3844 opened Aug 4, 2025 by shirinyamani • Draft
5 tasks
1
Allow for saving the PPOTrainer value model (critic model)
#3308 opened Apr 16, 2025 by AMindToThink Loading…
Add config_init_kwargs option in GRPOConfig
#4069 opened Sep 12, 2025 by hokuyama0106 Loading…
2 of 5 tasks
6
ClearML logging of visualization in RewardTrainer evaluation
#3602 opened Jun 16, 2025 by ioverho Loading…
2 of 5 tasks
1
Add basic support for FSDP/Lora when using TRL/VLLM
#3735 opened Jul 14, 2025 by ojh31 Loading…
5 tasks
4
Support dLLM in GRPO reference model creation
#3743 opened Jul 18, 2025 by xijia-tao Loading…
1
4
Implement DPOP
#3864 opened Aug 7, 2025 by 1485840691 Loading…
5
Reintroduce generate method for PPOTrainer
#3374 opened Apr 27, 2025 by CloseChoice Loading…
4 tasks done
5
Allow an user to train from a local dataset
#3470 opened May 19, 2025 by gogo2464 Loading…
1 of 5 tasks
30
Test in distributed setting
#3902 opened Aug 15, 2025 by qgallouedec Loading…
5 tasks
1
Remove attention mask when position ids is returned
#3997 opened Sep 2, 2025 by qgallouedec • Draft
[GSPO]: Refactor _compute_loss
#3835 opened Aug 1, 2025 by pramodith Loading…
2 of 5 tasks
1
3
Reintroducing step method in ppo_trainer
#3410 opened May 3, 2025 by jskaf34 Loading…
2 of 5 tasks
1
@shirinyamani
5
Online-dpo-ben
#4252 opened Oct 10, 2025 by burtenshaw • Draft
5 tasks
Update max_length explanation for VLM trainers
#4220 opened Oct 7, 2025 by sergiopaniego Loading…
5 tasks
3
add vllm support for token ids as input
#3280 opened Apr 11, 2025 by wybryan Loading…
4
[Draft] Add configurable dataset column logging to GRPOTrainer W&B tables
#4045 opened Sep 9, 2025 by davanstrien • Draft
3
[#3647] Fix: Assign default values in the GKDTrainer's constructor only when …
#3851 opened Aug 5, 2025 by seungduk-yanolja Loading…
2 of 5 tasks
1
2
ProTip! Follow long discussions with comments:>50.