Add mod: fix-mistral-reasoning-effort#119
Open
ChuckChambers wants to merge 1 commit intoeugr:mainfrom
Open
Conversation
vLLM 0.17.2rc1 unconditionally passes reasoning_effort to apply_chat_template, but mistral_common <1.11 doesn't support it, causing a 400 on every request. This mod guards the reasoning_effort kwarg with a null check and a try/except import of REASONING_EFFORTS from mistral_common, skipping gracefully if the installed version doesn't support it. Workaround until PR #37081 lands in a vLLM release. Usage: ./launch-cluster.sh --apply-mod mods/fix-mistral-reasoning-effort ...
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
vLLM 0.17.2rc1 unconditionally passes
reasoning_efforttoapply_chat_template, butmistral_common<1.11 does not support it, causing a 400 error on every request when using Mistral models.Fix
This mod guards the
reasoning_effortkwarg with a null check and atry/exceptimport ofREASONING_EFFORTSfrommistral_common, skipping gracefully if the installed version does not support it.Uses
patchcommand as recommended — safe to apply on any vLLM version, skips automatically if already applied or not applicable.Usage
Workaround until PR vllm-project/vllm#37081 lands in a vLLM release.