[feat](kt-kernel): support qwen3-vl weights convert

[mrhaoxx]

What does this PR do?

Before submitting

• [ ] Did you read the contributor guideline?
• [ ] Did you write any new necessary tests?

[gemini-code-assist[bot]]

Summary of Changes

Hello @mrhaoxx, I'm Gemini Code Assist[^1]! 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 significantly extends the weight conversion script to accommodate Qwen3-VL models. It addresses the unique structural differences of these models, particularly how their Mixture-of-Experts (MoE) layers are configured and stored. The changes ensure that the conversion process can correctly interpret and transform the weights of VL models, enabling their use with the kt-kernel framework.

Highlights

• Qwen3-VL Model Support: Introduced support for converting weights of Qwen3-VL models, which have a distinct configuration structure and fused MoE expert layouts.
• Dynamic Configuration Loading: Enhanced the configuration loading mechanism to detect and correctly parse text_config for VL models, distinguishing them from base models.
• Fused MoE Expert Handling: Implemented specialized logic within _find_expert_layers and _convert_layer_experts to correctly identify and process the fused gate, up, and down projection weights characteristic of VL models.
• Expanded Quantization Methods: Added moe_int4 and moe_int8 as supported quantization methods, allowing for more specific quantization strategies for Mixture-of-Experts models.
• Improved Error Handling and Logging: Added a warning for missing NUMA folders during layer loading and more informative print statements regarding model type and fused tensor shapes during conversion.

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 :thumbsup: and :thumbsdown: 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.

[^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.