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

specify gpu number to use #25

Open
Xieeeee opened this issue May 4, 2023 · 1 comment
Open

specify gpu number to use #25

Xieeeee opened this issue May 4, 2023 · 1 comment

Comments

@Xieeeee
Copy link

Xieeeee commented May 4, 2023

Hi Xiaotao,
Thanks for this wonderful tool. I am currently running EagleC on a machine with 4 Quadro RTX 5000 (I hope this would be faster than running on cpu only...) But with one of the gpu largely occupied by another job. However when initiating EagleC run it encounter an error:
could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR
I assume this could be caused by the low memory in that occupied gpu. I there a way like specifying threads, in specifying number (or which) gpu to use?

Best,
Yang

@XiaoTaoWang
Copy link
Owner

Hi Yang, sorry for the delayed response. Just wanted to let you know that while EagleC used GPU for training, it does not currently support GPU for prediction.

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