[Model] Support quantization of Qwen2VisionTransformer for Qwen2-VL

[mgoin]

Relies on #9812

Allows us to support quantization of the vision encoder for Qwen2-VL, where before we could only quantize the language model

Tested with

• nm-testing/Qwen2-VL-7B-Instruct-FP8-dynamic (only Qwen2Model quantized)
• nm-testing/Qwen2-VL-7B-Instruct-FP8-dynamic-all (Qwen2Model and Qwen2VisionTransformer quantized, just not lm_head)

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can do one of these:

• Add ready label to the PR
• Enable auto-merge.

🚀

[ywang96]

Thanks for adding support for quantization for this model!