[bugfix] qwen25-VL support lora

[SYChen123]

Motivation

LORA supports on Qwen25-VL

Modifications

add "should_apply_lora" function, same as other models.

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.
• Work with maintainers to merge your PR. See the PR Merge Process

[gemini-code-assist]

Summary of Changes

Hello @SYChen123, 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 enhances the Qwen2.5-VL model by integrating LORA (Low-Rank Adaptation) capabilities. The primary goal is to facilitate more efficient and resource-friendly fine-tuning of this large vision-language model. The changes involve adding a mechanism to correctly identify and target the appropriate model layers for LORA application, ensuring compatibility and proper functionality.

Highlights

• LORA Support for Qwen2.5-VL: This pull request introduces support for Low-Rank Adaptation (LORA) specifically for the Qwen2.5-VL model, enabling more efficient fine-tuning.
• Module Identification for LORA: A new should_apply_lora function has been added to programmatically identify which specific modules within the Qwen2.5-VL model are eligible for LORA application, consistent with how other models handle LORA.

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 adds LoRA support for the Qwen2.5-VL model by implementing the should_apply_lora method. This correctly restricts LoRA application to the text model's layers, preventing it from being applied to the vision encoder. The overall approach is sound. I have one suggestion to improve the precision of the regular expression used for matching module names.

[gemini-code-assist]

The current regular expression is slightly too broad. It allows for combinations of modules that do not exist in the model architecture, such as self_attn.down_proj. While this won't cause issues with the current model structure because named_modules() will only yield valid module names, making the regex more specific will improve its correctness and maintainability, especially for future model changes.

A more precise regex would explicitly group the allowed projections under their respective parent modules (self_attn or mlp).

Suggested change

	_lora_pattern = re.compile(
	r"^model\.layers\.(\d+)\.(?:self_attn|mlp)\.(?:qkv_proj|o_proj|down_proj|gate_up_proj)$"
	)
	_lora_pattern = re.compile(
	r"^model\.layers\.(\d+)\.(?:(?:self_attn\.(?:qkv_proj|o_proj))|(?:mlp\.(?:gate_up_proj|down_proj)))$"
	)