[Feature Request] Need to support Qwen2-VL model

[htlou]

Required prerequisites

• [X] I have searched the Issue Tracker and Discussions that this hasn't already been reported. (+1 or comment there if it has.)
• [ ] Consider asking first in a Discussion.

Motivation

Add the Qwen2-VL model, which represents a text_image_video_to_text model.

Solution

No response

Alternatives

No response

Additional context

No response