-
-
Notifications
You must be signed in to change notification settings - Fork 2k
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
Cuda is not working on A100 GPU #184
Comments
This looks like a docker error log, I suggest you try |
I tried this but did not work. I also tried using this command "lama-cleaner --model=lama --device=cuda" but it taken 9 minutes to load the model. When i upload the image to test the lama model. So I waited 3 minutes but still working and did not give any response. Device name is "GRID A100d-1-10C MIG 1g.10gb". Is lama-cleaner compatible for this device? |
You are actually using a virtual GPU (MIG), a slice of the whole A100. In theory it should work fine, but you are getting 1/7 of the whole card's resources, so it might be a bit slower. |
I found an issue on the Nvidia-docker GitHub repository, which might be helpful could not select device driver "" with capabilities: [[gpu]]. #1034 |
I also tried using docker. But it's showing this error.
docker: Error response from daemon: could not select device driver "" with capabilities: [[gpu]].
The text was updated successfully, but these errors were encountered: