I’m using GPU accelerated ML for Immich. It is great. However the ML model needs to be reloaded if I have not done a search for a while. Waiting 10sec for search is not a big problem, but is there a way to keep the model loaded?
I’m using GPU accelerated ML for Immich. It is great. However the ML model needs to be reloaded if I have not done a search for a while. Waiting 10sec for search is not a big problem, but is there a way to keep the model loaded?