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

361: Feature cuda skip install #319

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

Ravencrest-01
Copy link

This pull request enhances the CUDA extension to skip the installation step if CUDA is already present on the system. It adds a check to detect whether CUDA is installed using the nvidia-smi command, ensuring that redundant installations are avoided.

Key Changes

  1. Added function is_cuda_installed() to check if CUDA is already installed.
  2. Modified get_snippet() method to: Skip generating the Dockerfile if CUDA is detected.

@Ravencrest-01 Ravencrest-01 requested a review from tfoote as a code owner February 8, 2025 10:43
@Ravencrest-01
Copy link
Author

Hi @tfoote,

I’ve implemented the enhancement to the CUDA extension to skip the installation if CUDA is already present on the system. This change introduces a check using the nvidia-smi command and ensures that redundant installations are avoided, improving efficiency.

I’ve tested the feature under the following conditions:

  • With CUDA installed: The system correctly skips installation and logs the message: "CUDA is already installed. Skipping installation."
  • Without CUDA installed: The extension proceeds with the installation as expected.

Looking forward to your feedback! Please let me know if there’s anything else I can improve.

Best regards,
Ritik kumar

Copy link
Collaborator

@tfoote tfoote left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for looking at this, however this won't do what is needed. This is checking the host, not the container or the presence of cuda.

@tfoote
Copy link
Collaborator

tfoote commented Feb 14, 2025

This needs major changes before it will be ready so I'm going to push this back to draft status. It can be rereviewed when the additional functionality has been implemented.

@tfoote tfoote marked this pull request as draft February 14, 2025 20:19
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

Successfully merging this pull request may close these issues.

2 participants