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.

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

Can the video model be quantized? #53

Open
sdbds opened this issue Feb 26, 2025 · 4 comments
Open

Can the video model be quantized? #53

sdbds opened this issue Feb 26, 2025 · 4 comments

Comments

@sdbds
Copy link

sdbds commented Feb 26, 2025

Can the video model be quantized?

@Lyken17
Copy link
Member

Lyken17 commented Feb 28, 2025

Yes, it can. @ys-2020 can you share video quantized models and numbers?

@ys-2020
Copy link
Contributor

ys-2020 commented Feb 28, 2025

Add @synxlin for vis. Do we support video models right now?

@lmxyy
Copy link
Contributor

lmxyy commented Feb 28, 2025

Support for video diffusion models is in progress. Once completed, we will release the corresponding quantization scripts, instructions, and models at mit-han-lab/nunchaku and let you know. @sdbds

@sdbds
Copy link
Author

sdbds commented Mar 1, 2025

Support for video diffusion models is in progress. Once completed, we will release the corresponding quantization scripts, instructions, and models at mit-han-lab/nunchaku and let you know. @sdbds

Thank you for your information. I believe your work is obviously much better than GGUF convert, and SVD decomposition can also be applied to video.

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

No branches or pull requests

4 participants