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

optimal GPU type #164

Closed
COMInterop opened this issue Aug 26, 2022 · 1 comment
Closed

optimal GPU type #164

COMInterop opened this issue Aug 26, 2022 · 1 comment

Comments

@COMInterop
Copy link

Hello,

I try to run PEPPER-Margin-DeepVariant on Amazon EC2 instance with the NVIDIA A10G Tensor Core GPU. It works but only uses a part of the GPU, about 12%:

Captura de Pantalla 2022-08-26 a la(s) 18 34 46

Is this expected? There is also one with the NVIDIA T4 Tensor Core GPU, or the NVIDIA Tesla M60 GPU. Can you say which is the best?

Also, is there a benefit to have TensorFlow, PyTorch, or MXNet? Or is CUDA sufficient?

Thank you!

@kishwarshafin
Copy link
Owner

@paracontias

This is a very difficult question to answer. You can increase the batch size etc. to see how to increase GPU usage. You can find them here: https://github.com/kishwarshafin/pepper/blob/r0.8/docs/usage/usage_and_parameters.md

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