Fix vLLM error for tools usage not supported when running GRPO training #4663
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ng with vLLM-powered generation in server mode
Member
|
thanks! good catch! |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Contributor
Author
Happy to help. The failing tests are not related (I think) with the change, let me know if there is something else required to merge the fix. |
qgallouedec
approved these changes
Dec 11, 2025
qgallouedec
changed the title
qgallouedec
added a commit
that referenced
this pull request
Dec 12, 2025
…ng (#4663) Co-authored-by: a.palmas <a.palmas@AP-T-054.local> Co-authored-by: Quentin Gallouédec <gallouedec.quentin@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
When using GRPO training with vLLM powered generation in server mode, even if tools are not specified (i.e. equal to
Noneat GRPO init) the processing at linetrl/trl/trainer/grpo_trainer.py
Line 415 in ad02d98
causes a vLLM-side failure on line
trl/trl/trainer/grpo_trainer.py
Line 1291 in ad02d98
because
toolsparameter is notNone.Before submitting
Pull Request section?
to it if that's the case.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.