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

RWKV only show lower GPU memory occupancy when inference? #250

Open
thucz opened this issue Jul 21, 2024 · 3 comments
Open

RWKV only show lower GPU memory occupancy when inference? #250

thucz opened this issue Jul 21, 2024 · 3 comments

Comments

@thucz
Copy link

thucz commented Jul 21, 2024

I tried to use RWKV(e.g., Vision-RWKV) in CV tasks. But I found RWKV shows similar GPU memory occupancy to full-attention Transformer (like ViT) when training. I found both RWKV and Vision-RWKV only present their inference memory occupancy in the paper.

The high memory consume is not friendly for my tasks. Do you have any advice?

@BlinkDL
Copy link
Owner

BlinkDL commented Jul 21, 2024

Hi may I know your ctxlen

@thucz
Copy link
Author

thucz commented Jul 21, 2024

ctx_len is 8192

@BlinkDL
Copy link
Owner

BlinkDL commented Sep 8, 2024

Please check whether attention/rwkv is your bottleneck

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