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

GPU memory for training/testing #14

Open
xiangxu007 opened this issue Nov 19, 2024 · 1 comment
Open

GPU memory for training/testing #14

xiangxu007 opened this issue Nov 19, 2024 · 1 comment

Comments

@xiangxu007
Copy link

Hello,
Could you tell me how much GPU memory is needed for training/testing, I only have 6G GPU memory, I'm guessing there isn't enough GPU memory for training/testing.
Best.
Xu.

@Lirui-Zhao
Copy link
Collaborator

Hello Xu,

Thank you for your interest in our Diffree.

For training with a batch size of 16, each GPU requires approximately 40 GB of memory. The GPU memory requirement is closely related to the batch size you choose. For inference, unfortunately, 6 GB of GPU memory is still insufficient. You would need around 16 GB of GPU memory to run inference smoothly.

Please let me know if you have any other questions.

Best regards,
Lirui

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

2 participants