TRL Updated version of VLM GRPO update along with GSPO #3132

Merged

danielhanchen merged 39 commits intounslothai:mainfrom

pluesclues:vlm_grpo_update

Sep 16, 2025

Commits on Jun 24, 2025

Update rl.py, made sure tokenized_output on eval step was on same device
pluesclues
authored
Update rl.py, corrected tokenized_outputs to inputs
pluesclues
authored

Commits on Jun 25, 2025

Update rl.py, removed sagemaker stuff
pluesclues
authored

Commits on Jul 2, 2025

Update llama.py, figures out if there is right padding automatically
pluesclues
authored
Update llama.py, changed conditional statement for right padding slightlyt
pluesclues
authored

Commits on Jul 12, 2025

Merge branch 'main' into main
pluesclues
authored

Commits on Aug 3, 2025

Merge branch 'main' into main
pluesclues
authored

Commits on Aug 8, 2025

Commits on Aug 11, 2025

Commits on Aug 12, 2025

Commits on Aug 13, 2025

Merge branch 'unslothai:main' into vlm_grpo_update
pluesclues
authored

Commits on Aug 18, 2025

Merge branch 'unslothai:main' into vlm_grpo_update
pluesclues
authored

Commits on Aug 20, 2025

Merge branch 'unslothai:main' into vlm_grpo_update
pluesclues
authored

Commits on Aug 22, 2025

Commits on Sep 4, 2025

Merge branch 'unslothai:main' into vlm_grpo_update
pluesclues
authored

Commits on Sep 8, 2025

Merge branch 'unslothai:main' into vlm_grpo_update
pluesclues
authored

Commits on Sep 9, 2025

Commits on Sep 10, 2025

Commits on Sep 16, 2025