Skip to content

Pull requests: huggingface/trl

New pull request New
63 Open 1,874 Closed
63 Open 1,874 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 self.current_gradient_accumulation_steps in GRPOTrainer
#3984 opened Aug 31, 2025 by ahatamiz Loading…
5 tasks done
1
🎯 Add Trackio integration documentation and update TOC
#3971 opened Aug 28, 2025 by qgallouedec Loading…
5 tasks
2
👷 Added Kernels on the Hub x TRL guide
#3969 opened Aug 28, 2025 by sergiopaniego Loading…
2 of 8 tasks
1
[GRPO] Adds an option to sleep vllm when running in colocated mode
#3968 opened Aug 28, 2025 by edbeeching Loading…
13
[GRPO]: Fix Multi-GPU training for Entropy based masking of tokens.
#3964 opened Aug 27, 2025 by pramodith Loading…
2 of 5 tasks
12
Dft
#3960 opened Aug 27, 2025 by 1485840691 Loading…
5 tasks
1
3
fix bug when using dataset streaming by accelerate
#3950 opened Aug 25, 2025 by kaixuanliu Loading…
5
Docker update
#3931 opened Aug 20, 2025 by qgallouedec Loading…
5 tasks
1
[SFTTrainer]: Check for assistant mask up to max_length
#3930 opened Aug 20, 2025 by pramodith Loading…
3 of 5 tasks
14
[DRAFT] Refactor DPO
#3906 opened Aug 15, 2025 by qgallouedec • Draft
5 tasks
Test in distributed setting
#3902 opened Aug 15, 2025 by qgallouedec Loading…
5 tasks
1
BEMA for ref model
#3898 opened Aug 14, 2025 by qgallouedec Loading…
5 tasks
1
GRPOTrainer : fix prompt truncation for multimodal inputs with multiple image tokens
#3879 opened Aug 11, 2025 by artem-spector Loading…
4 tasks
7
[GRPO] Truncated Importance Sampling to address rollout-training mismatch
#3867 opened Aug 7, 2025 by LeonEricsson • Draft
5 tasks
18
Implement DPOP
#3864 opened Aug 7, 2025 by 1485840691 Loading…
5
[#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
Update profiling.py: fix scoping problems for wandb and mlflow
#3845 opened Aug 4, 2025 by markshinyounglee Loading…
5 tasks done
2
dynamic temperature
#3844 opened Aug 4, 2025 by shirinyamani • Draft
5 tasks
1
[GSPO]: Refactor _compute_loss
#3835 opened Aug 1, 2025 by pramodith Loading…
2 of 5 tasks
1
3
support GSPO-token
#3820 opened Jul 31, 2025 by hjh0119 Loading…
15
Add vLLM server mode and VLM support to OnlineDPOTrainer
#3783 opened Jul 27, 2025 by vaelev Loading…
6 tasks done
1
11
change doc for num_iterations and steps_per_generation to hopefully make them more clear and differentiate between them more clearly
#3761 opened Jul 23, 2025 by avishaiElmakies Loading…
2 of 5 tasks
1
3
Dynamic sampling option in GRPO trainer based on DAPO paper
#3758 opened Jul 23, 2025 by almeidava93 Loading…
2 of 5 tasks
1
12
Support dLLM in GRPO reference model creation
#3743 opened Jul 18, 2025 by xijia-tao Loading…
1
4
Add basic support for FSDP/Lora when using TRL/VLLM
#3735 opened Jul 14, 2025 by ojh31 Loading…
5 tasks
4
ProTip! no:milestone will show everything without a milestone.