Support dynamic lora updating

[pan-x-c]

Description

As the title says

Checklist

Please check the following items before code is ready to be reviewed.

• Code has passed all tests
• Docstrings have been added/updated in Google Style
• Documentation has been updated
• Code is ready for review

[gemini-code-assist]

Summary of Changes

Hello @pan-x-c, 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 introduces support for dynamic LoRA updating, allowing LoRA adapters to be managed and updated at runtime. It achieves this by adding a new configuration flag to control the feature and linking it to the underlying VLLM library's capability for runtime LoRA management. This enhancement provides greater flexibility in adapting models without requiring a full restart.

Highlights

• New Configuration Option: Introduced a new boolean configuration field, enable_runtime_lora_updating, within InferenceModelConfig to explicitly control the dynamic LoRA updating feature.
• VLLM Integration: Integrated the new configuration option with VLLM by setting the VLLM_ALLOW_RUNTIME_LORA_UPDATING environment variable to '1' when enable_runtime_lora_updating is true, enabling VLLM's native support for dynamic LoRA updates.
• Test Configuration Update: Updated the test setup in vllm_test.py to enable both enable_lora and the new enable_runtime_lora_updating flags, ensuring test coverage for this new functionality.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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 introduces support for dynamic LoRA updating by adding a new configuration flag and setting the corresponding vLLM environment variable. The changes are logical, but I've found a couple of areas for improvement.

In the configuration file, the new flag could be confusing due to its placement, so I've suggested adding a clarifying comment.

More importantly, the test setup for this new feature appears to be incorrect. It manually enables LoRA, which bypasses the necessary automatic configuration steps and would likely cause the test to fail. I've provided a critical suggestion to fix the test setup to correctly enable and test the LoRA functionality.