Do I need to base my serverless worker image from the official base image?
I have my own Dockerfile already optimized with only the things I need to perform the inference. Runpod docs says that we should start by forking the worker-template, but basing from it I end up with a HUGE image.
Is there anything special in the runpod/base image or can I just use my own and simply make sure I'm installing runpod in Python and exposing a handler function with CMD at the end?
3 Replies
You can use most any base image you want, as long as it has all the modules your code needs. I have some very small serverless workers based off of python:3.10-slim.
check the dockerfile it may download additional package or deps
And maybe from your layers in docker image
Thank you, I got it working.