[Bug]: Qwen2.5 VL inference in GPU gives output as !!!!!!!!!!

[nvsreerag]

OpenVINO Version

2025.2.0.dev20250505

Operating System

Windows System

Device used for inference

GPU

Framework

PyTorch

Model used

Qwen2.5 VL

Issue description

I have trying to do the inference of of Qwen2.5 VL model with OpenVINO and OpenVINO GenAI nightly and it is working in CPU. But When trying to do the inference of Qwen2.5 VL on GPU and the output is appearing as !!!!!!!!!! and not in a readable format.

Python package details are:

openvino                  2025.2.0.dev20250505
openvino-genai            2025.2.0.0.dev20250505

Do you have any suggestions or workarounds to resolve this?

Step-by-step reproduction

No response

Relevant log output

!!!!!!!!!!

Issue submission checklist

• I'm reporting an issue. It's not a question.
• I checked the problem with the documentation, FAQ, open issues, Stack Overflow, etc., and have not found a solution.
• There is reproducer code and related data files such as images, videos, models, etc.

[sshlyapn]

Hi @nvsreerag, could you let us know your GPU model and driver version? We will check the issue

[nvsreerag]

GPU model and version are:

GPU model : Intel(R) Arc(TM) 140V GPU (16GB)
Driver version:	32.0.101.6790