[Bugfix] kv aware routing for lmcache 0.3.5

[zerofishnoodles]

Fix kvaware routing for lmcache 0.3.5

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE

---

• 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].

Detailed Checklist (Click to Expand)

Thank you for your contribution to production-stack! Before submitting the pull request, please ensure the PR meets the following criteria. This helps us maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Please try to classify PRs for easy understanding of the type of changes. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

• [Bugfix] for bug fixes.
• [CI/Build] for build or continuous integration improvements.
• [Doc] for documentation fixes and improvements.
• [Feat] for new features in the cluster (e.g., autoscaling, disaggregated prefill, etc.).
• [Router] for changes to the vllm_router (e.g., routing algorithm, router observability, etc.).
• [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

• Pass all linter checks. Please use pre-commit to format your code. See README.md for installation.
• The code need to be well-documented to ensure future contributors can easily understand the code.
• Please include sufficient tests to ensure the change is stay correct and robust. This includes both unit tests and integration tests.

DCO and Signed-off-by

When contributing changes to this project, you must agree to the DCO. Commits must include a Signed-off-by: header which certifies agreement with the terms of the DCO.

Using -s with git commit will automatically add this header.

What to Expect for the Reviews

We aim to address all PRs in a timely manner. If no one reviews your PR within 5 days, please @-mention one of YuhanLiu11
, Shaoting-Feng or ApostaC.

[gemini-code-assist]

Summary of Changes

Hello @zerofishnoodles, 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 provides a critical bugfix for KV-aware routing, specifically targeting compatibility with lmcache 0.3.5. The changes primarily focus on enhancing the robustness and stability of the vllm-router by implementing comprehensive graceful shutdown mechanisms for various routing logic instances and service discovery components. Additionally, it refines the Docker build process by adopting uv for dependency management and introduces a fixed PYTHONHASHSEED for improved determinism, alongside an adjustment to the router's startup probe delay.

Highlights

• Graceful Shutdown for Routers: Implemented close() methods and a cleanup_routing_logic function to ensure all router instances, especially KvawareRouter, gracefully shut down their background tasks during application termination or reconfiguration.
• Service Discovery Shutdown: Added a close() method to the ServiceDiscovery class to properly terminate health check tasks and associated event loops, preventing resource leaks.
• Dependency Management Update: Switched the Docker build process from pip to uv for installing dependencies within a virtual environment, improving build speed and consistency.
• Deterministic Hashing: Introduced PYTHONHASHSEED=123 environment variable in Helm deployments for both router and vLLM multi-engine, aiming for more consistent hashing behavior.
• Router Startup Probe Adjustment: Increased the initialDelaySeconds for the router's startup probe in Helm from 5 to 30 seconds, allowing more time for initialization.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 introduces several improvements, primarily focused on fixing KV-aware routing for lmcache 0.3.5 and ensuring graceful shutdown of various components. Key changes include switching to uv for faster dependency installation in the Dockerfile, adding PYTHONHASHSEED for deterministic hashing, and implementing close() methods for KvawareRouter and StaticServiceDiscovery to properly clean up background tasks and threads. The application lifecycle is updated to call the new cleanup logic on shutdown.

My review focuses on a couple of areas for improvement. In the Dockerfile, I've suggested combining RUN commands to optimize the image size. More importantly, in routing_logic.py, I've identified a potential resource leak in the reconfigure_routing_logic function and suggested a refactoring to fix it and reduce code duplication. The rest of the changes for graceful shutdown are well-implemented.