[model-gateway] add llava model image processor and tests

[slin1237]

1. add llava model image processor
2. add this to image processor to registry
3. add integration tests with generated results from python transformer

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 @slin1237, 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 integrates robust support for LLaVA model image preprocessing within the model-gateway. It provides dedicated processors for different LLaVA versions and modes, integrates them into a central registry for easy access, and establishes a rigorous testing framework using golden outputs from HuggingFace to guarantee accurate and consistent image transformations. This enhancement significantly expands the multimodal capabilities of the gateway.

Highlights

• LLaVA Image Processor: Implemented a new image processor for LLaVA models, supporting both LLaVA 1.5 (standard CLIP and pad modes) and LLaVA-NeXT (multi-crop anyres).
• Processor Registry Integration: The new LLaVA processors are integrated into the ImageProcessorRegistry with default configurations, allowing for dynamic selection based on model names.
• Golden Integration Tests: Added comprehensive golden tests that compare the Rust image processing outputs against reference outputs generated by HuggingFace transformers, ensuring pixel-perfect compatibility and correctness.

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 image processors for LLaVA models, including a Python script for generating golden test files and corresponding integration tests. The implementation is well-structured and the testing approach is robust. My review focuses on a few key areas for improvement. I've found a high-severity issue in the LlavaNextProcessor batch processing logic that could lead to performance degradation and stack overflows, and a correctness bug in an image centering function. Additionally, I've suggested a refactoring in the new test file to reduce code duplication and improve maintainability. After addressing these points, this will be an excellent addition.