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

Tomesd is not reducing the total memory consumption. #51

Open
ghost opened this issue Aug 16, 2023 · 2 comments
Open

Tomesd is not reducing the total memory consumption. #51

ghost opened this issue Aug 16, 2023 · 2 comments

Comments

@ghost
Copy link

ghost commented Aug 16, 2023

When i use Diffusors without tomesd the total memory usage in nvidia-smi is 3966MiB.
But when i use it with tomesd ( using the example in the readme ) , the usage on nvidia-smi is still the same.

Any idea whats happening?

@reynoldscem
Copy link

Yes I experience this too

@dbolya
Copy link
Owner

dbolya commented Oct 31, 2023

I believe someone looked into this before and found that diffusers was already using memory efficient attention, which saves most of the memory that ToMe would have saved anyway. The numbers in the paper are for the original implementation of stable diffusion.

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