Skip to content

Conversation

@rzbhatti
Copy link

Description

This PR adds kv_cache_specs for mistral modals

Related Issues

Fixes #567

@github-actions
Copy link

👋 Hi! Thank you for contributing to vLLM support on Spyre.
Just a reminder: Make sure that your code passes all the linting checks, otherwise your PR won't be able to be merged. To do so, first install the linting requirements, then run format.sh and commit the changes. This can be done with uv directly:

uv sync --frozen --group lint --active --inexact

Or this can be done with pip:

uv pip compile --group lint > requirements-lint.txt
pip install -r requirements-lint.txt
bash format.sh

Now you are good to go 🚀

@tjohnson31415 tjohnson31415 changed the title Added kv_cache_specs for mistral modals Add kv_cache_specs for mistral models Nov 19, 2025
Copy link
Collaborator

@tjohnson31415 tjohnson31415 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The code is checking for attributes from the FMS config, but the model.config here is the Transformers config class.

Also, we should avoid hard-coded numbers for defaults here if we can.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

KV Cache support for Mistral Model

2 participants