GPU usage limiter during machine learning #20047
Closed
ronzino83
started this conversation in
Feature Request
Replies: 1 comment
-
You can already tune this with the env vars you linked (in particular the threads/workers ones), as well as by limiting the jobs concurrency on the immich-server side. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I have searched the existing feature requests, both open and closed, to make sure this is not a duplicate request.
The feature
During ML process, GPU utilization hits 100% and stay at this value during the whole process.
The whole system and other apps that need GPU will struggle in this scenario.
It would be good to have sort of limiter (like the other ones for CPU https://immich.app/docs/install/environment-variables#machine-learning ) for the GPU
Platform
Beta Was this translation helpful? Give feedback.
All reactions