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

Regarding GPU memory #23

Open
Red-Fairy opened this issue Sep 27, 2024 · 5 comments
Open

Regarding GPU memory #23

Red-Fairy opened this issue Sep 27, 2024 · 5 comments

Comments

@Red-Fairy
Copy link

Hi authors,

Thanks for your great work! May I know what gpu did you use for inference, as performing inference on the video you provided with 4090 (24GB) memory would encounter cuda OOM issue. I'm not sure if it's a bug or your model requires a gpu with larger memory.

Thanks.

@codecowboy
Copy link

The authors seem unresponsive but I have the same problem on a 3090 which has the same amount of VRAM. Please let me know if you manage to resolve this.

@heartInsert
Copy link

Can you run right now ?

@ALisstry
Copy link

There are frequent issues with the cuda OOM, and the L40 with 48GB of VRAM is not enough for inference.
经常会遇到cuda OOM的问题,使用48G显存的L40也不够进行推理。

@heartInsert
Copy link

@ALisstry 尬住了,本来想对老视频修复一下,没想到会这样,有12GB显卡能够运行的方案吗?

@Red-Fairy
Copy link
Author

Yeah I often encounter cuda OOM even on a 48GB A6000.

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