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.

Sign up for GitHub

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

Jump to bottom

[FEATURE] GPU memory control #660

Open
ylwu-amzn opened this issue Jan 5, 2023 · 0 comments
Open

[FEATURE] GPU memory control #660

ylwu-amzn opened this issue Jan 5, 2023 · 0 comments
Labels
enhancement New feature or request

Comments

@ylwu-amzn
Copy link
Collaborator

GPU acceleration is important for improving model inference performance. GPU has its own memory and the DL framework like libtorch has its own memory management mechanism. Loading too many models on GPU will cause OOM issue. We should control memory usage to ensure high availability.
@ylwu-amzn ylwu-amzn added the enhancement New feature or request label Jan 5, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@ylwu-amzn