[Build][Router] Update vllm to v0.13.0

[shernshiou]

The latest lmcache/lmstack-router docker image (lmcache/lmstack-router:0.1.9.dev4-ge1447afd3.d20251215) contains several CVEs including CVEs belonging to vllm v0.11.0 and also older version of starlette. Updating vllm to v0.12.0 reduces the CVEs and also update the starlette to the version without CVE.

---

• Make sure the code changes pass the pre-commit checks.
• Sign-off your commit by using -s when doing git commit
• Try to classify PRs for easy understanding of the type of changes, such as [Bugfix], [Feat], and [CI].:

[gemini-code-assist]

Summary of Changes

Hello @shernshiou, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request focuses on a critical build update for the router component, primarily by upgrading several key Python dependencies. The main objective is to address and reduce existing Common Vulnerabilities and Exposures (CVEs) found in the current lmcache/lmstack-router docker image, ensuring a more secure and robust application environment.

Highlights

• Dependency Updates: Updated vllm from 0.11.0 to 0.12.0, fastapi from 0.115.8 to 0.124.4, and lmcache from 0.3.9post2 to 0.3.11 across pyproject.toml and src/vllm_router/requirements.txt.
• Security Enhancements: These dependency updates are crucial for mitigating known CVEs, particularly those associated with older versions of vllm and starlette (a dependency of fastapi), thereby enhancing the security posture of the lmcache/lmstack-router docker image.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates several dependencies, including vllm, lmcache, and fastapi, to address security vulnerabilities as described. The changes are correct and consistently applied across the relevant files. I have one suggestion to improve dependency management consistency between pyproject.toml and requirements.txt, which I've detailed in a review comment.

[zerofishnoodles]

Hi Can you revert the change to the uv lock since there are too many change line in that.

[shernshiou]

Hi Can you revert the change to the uv lock since there are too many change line in that.

Hi @zerofishnoodles
Yes, I can but can you help me understand why? Shouldn't uv.lock be consistent with pyproject.toml?

[shernshiou]

@zerofishnoodles I have reset the uv.lock

[bcdonadio]

I believe a production-stack release should follow this update as well, right?

[zerofishnoodles]

Hi Can you revert the change to the uv lock since there are too many change line in that.

Hi @zerofishnoodles Yes, I can but can you help me understand why? Shouldn't uv.lock be consistent with pyproject.toml?

Yes it should be. It is just that we don't want too many changes in one PR. Also since pyproject itself should be enough for the venv.

[zerofishnoodles]

I believe a production-stack release should follow this update as well, right?

Yes it should be