machine learning keeps crashing
Hello! I'm running
immich
in kubernetes. Today the machine learning pod keeps crashlooping. The log doesn't say much either
The pod restarted around this point so I don't know what I should look for. The memory limit to the pod is 4Gi and the usage tops at 850Mi before crashing so I think this is not OOMKilled.7 Replies
I managed to fix this by increasing the startupprobe to a very long time (10 minutes).
This is the way indeed, at startup it downloads the ml models which can take a while
Do you have a cache volume configured for it?
no, maybe I should?
where is the cache mounted?
Whatever path
TRANSFORMERS_CACHE
is set to, which by default is /cache
thanks!
how did you do that?
I am wondering this too