Skip to content

Conversation

@Arcs-ur
Copy link
Contributor

@Arcs-ur Arcs-ur commented Aug 15, 2025

Qwen2.5-VL-3B-Instruct Deployment Guide (ComfyUI + Intel GPU + Linux)
Qwen2.5-VL-7B-Instruct Multimodal Deployment Guide (Intel GPU/Docker/Gradio)

@Arcs-ur Arcs-ur changed the title feat(webui): ComfyUI feat(webui): ComfyUI&Gradio Aug 15, 2025
@glorysdj glorysdj requested a review from gc-fu August 15, 2025 06:12
@glorysdj
Copy link
Contributor

also need a section in overall readme https://github.com/intel/llm-scaler/tree/main/vllm
2.8 multi-modal webui

Copy link
Contributor

@lalalapotter lalalapotter left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Others LGTM.

Access the web interface at: `http://localhost:8188`

## Post-Installation Configuration
1. Replace the final component node with `Preview Any` in your workflow
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe we can just provide a workflow json file for users.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

@Arcs-ur
Copy link
Contributor Author

Arcs-ur commented Aug 15, 2025

also need a section in overall readme https://github.com/intel/llm-scaler/tree/main/vllm 2.8 multi-modal webui

done

vllm/README.md Outdated
--max-model-len 114432
```

### 2.8 Multi-modal Webui
Copy link
Contributor

@glorysdj glorysdj Aug 15, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Multi-modal -> Multi-Modal

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

also change multimodal_gradio to multi-modal-gradio, and multimodal_comfyui to multi-modal-comfyui

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

### 3. Launch Gradio Interface on Host
```bash
conda create -n qwen_gradio python=3.11
conda activate qwen_gradio
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we need to install gradio here?

Also, I think we can directly install the gradio with pip

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

Copy link
Contributor

@gc-fu gc-fu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@gc-fu gc-fu merged commit bfff48f into intel:main Aug 15, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants