Is there a timeout for how long the code that sets up the worker (prior to runpod.serverless.start call) can run?
I have a case where this if fairly long, and it seems like the container is marked unhealthy and killed about 8 minutes in (out of ~10 it would take). I'm trying to figure out if something happens in the container, or is there an external timer. This is before jobs are even started. I know about the job timeout, that is set to 3600 seconds.
Continue the conversation
Join the Discord to ask follow-up questions and connect with the community
R
Runpod
We're a community of enthusiasts, engineers, and enterprises, all sharing insights on AI, Machine Learning and GPUs!