[model-gateway] add qwen3_vl model image processor#14377
Conversation
Summary of ChangesHello @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 the Highlights
Using Gemini Code AssistThe 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
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 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
|
There was a problem hiding this comment.
Code Review
This pull request adds support for the qwen3_vl model image processor. The changes include a new Rust implementation for the processor, updates to the processor registry, a Python script for generating golden test files, and new golden tests. The implementation for Qwen3VLProcessor is well-tested and seems correct. However, it introduces significant code duplication from the existing Qwen2VLProcessor, which could be a maintenance concern. I've left a few suggestions to address this and other minor points.
| // Load golden values | ||
| let golden_grid_thw = load_golden_grid_thw(&npz_path); | ||
| let golden_num_tokens = load_golden_num_tokens(&npz_path); | ||
| let (golden_pixels, golden_shape) = load_golden_qwen2_vl_pixels(&npz_path); |
There was a problem hiding this comment.
The function name load_golden_qwen2_vl_pixels is a bit confusing here, as it's being used for qwen3_vl tests. While it works because the data format is the same, consider renaming it to something more generic like load_golden_patched_pixels in a future refactoring to improve maintainability and avoid confusion.
Checklist