Add support for mistral3 (no vision encoding)#627
Draft
alex-jw-brooks wants to merge 1 commit intovllm-project:mainfrom
Draft
Add support for mistral3 (no vision encoding)#627alex-jw-brooks wants to merge 1 commit intovllm-project:mainfrom
alex-jw-brooks wants to merge 1 commit intovllm-project:mainfrom
Conversation
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
|
👋 Hi! Thank you for contributing to vLLM support on Spyre. We also recommend installing prek and configuring it to check your code before every local commit. |
gkumbhat
reviewed
Jan 21, 2026
gkumbhat
reviewed
Jan 21, 2026
alex-jw-brooks
changed the title
gkumbhat
reviewed
Jan 21, 2026
| # TODO (Alex) move this to utils after granite vision | ||
| # is merged. | ||
| if hasattr(cfg, "text_config"): | ||
| return cfg.text_config.src_vocab_size |
Collaborator
There was a problem hiding this comment.
nit: next line can be modified to be cfg.src_vocab_size
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Supports running only the text part of multimodal mistral3 models through vLLM Spyre; I haven't been able to validate on AIU quite yet, but have at least ensured I can run it with the eager backend.
This PR is dependent on the following PR in FMS: foundation-model-stack/foundation-model-stack#501
I will follow up in both FMS and here (after the granite vision PR is merged) to add support for pixtral in separate PRs & implement the multimodal utils.