vllm lora_dir rename and make embedding padding optional

[danielhanchen]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @danielhanchen, 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 minor but impactful refinements to the VLLM LoRA integration. It standardizes a parameter name for LoRA directory paths, enhancing code readability, and increases flexibility in the initialization process by making the embedding_padding_modules argument optional. These changes contribute to a more robust and user-friendly LoRA management system.

Highlights

• LoRA Parameter Renaming: The lora_path keyword argument has been renamed to lora_dir when loading LoRA models from local checkpoints in the _load_adapter function for improved clarity and consistency.
• Optional Embedding Padding: The embedding_padding_modules parameter in the new_init function has been made optional, now defaulting to an empty list if not explicitly provided.

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 the vllm_lora_worker_manager by renaming a parameter to align with vLLM and making another parameter optional. My review identifies a potential issue with the use of a mutable default argument, which is a common anti-pattern in Python, and I've provided a recommendation to improve the code's robustness.

[gemini-code-assist]

Using a mutable default argument like [] is a common pitfall in Python. If this list were to be modified, it would be mutated for all subsequent calls to this function that rely on the default value. It is safer to use None as the default value and create a new list within the function body.

Recommendation:

def new_init(
    # ... other arguments
    embedding_padding_modules: Optional[list[str]] = None,
    # ... other arguments
):
    if embedding_padding_modules is None:
        embedding_padding_modules = []

    old_init(
        # ...
        embedding_padding_modules=embedding_padding_modules,
        # ...
    )