Add Quantization Support for Qwen2.5-VL Model

[kurosakiharachan]

The https://github.com/NVIDIA/TensorRT-Model-Optimizer/tree/main/examples/vlm_ptq page indicates that TensorRT-Model-Optimizer currently only supports quantization for three multimodal models: Llava, VILA, and Phi-3-vision. It would be beneficial to add support for quantizing the Qwen2.5-VL model as well.

[cjluo-nv]

Thanks for the request and we are working on it. CC @i-riyad

[i-riyad]

Qwen2.5-VL is supported now. Please give it a try and reopen the issue if the example instructions don’t work.