Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Docker Image | vLLM | Support VLM Like Qwen-2-VLM #1242

Open
jordanparker6 opened this issue Nov 4, 2024 · 0 comments
Open

Docker Image | vLLM | Support VLM Like Qwen-2-VLM #1242

jordanparker6 opened this issue Nov 4, 2024 · 0 comments
Labels
enhancement

Comments

@jordanparker6
Copy link

What behavior of the library made you think about the improvement?

Would love to use the outlines docker image to host Qwen-2-vlm with structured output.

How would you like it to behave?

The current docker file doesn't support images as input. It would be great if this could be improved to support vLLM, outlines and VLMs for structured generations. This is great for OCR or knowledge extraction use cases. Qwen-2-VL is quite good at this.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@jordanparker6