Fix: Correct limit_mm_per_prompt parameter format for vLLM#1075
Open
Teeeio wants to merge 1 commit intoflagos-ai:mainfrom
Open
Fix: Correct limit_mm_per_prompt parameter format for vLLM#1075Teeeio wants to merge 1 commit intoflagos-ai:mainfrom
Teeeio wants to merge 1 commit intoflagos-ai:mainfrom
Conversation
The vLLM --limit-mm-per-prompt argument uses type=json.loads for
parsing, which requires valid JSON string format. Original config
used incorrect format causing JSON parse error.
Changes:
- Fixed format in 6 serve configuration files
- Changed from: limit_mm_per_prompt: image=X
- Changed to: limit_mm_per_prompt: '{image: X}'
Tested with vLLM 0.13.0, service starts successfully.
tengqm
approved these changes
Jan 21, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR Category
Serve
PR Types
Bug Fixes
PR Description
The --limit-mm-per-prompt argument in vLLM uses json.loads for parsing, which requires a valid JSON string format. The original configuration files used an invalid format (image=X), causing a JSON parse error during service startup.
This PR fixes the issue by updating the format to valid JSON string syntax in 6 serve configuration files:
Before: limit_mm_per_prompt: image=X
After: limit_mm_per_prompt: '{image: X}'
✅ Verified with vLLM v0.13.0 — the service now starts successfully without parsing errors.