How to migrate serverless endpoint to a pod?
I have a strange use case in which I have a functional serverless endpoint that must run on AMD hardware (for none technical reasons)
Everything is setup and working currently running on NVIDIA hardware.
AMD hardware is not yet available for serverless, can I recreate the serverless behaviour using a pod?
I understand the two services are very different, I just need an API that generates an output using AMD hardware.
3 Replies
hmm sadly not..
just for testing yes,but it wont scale and handle multiple jobs as normal serverless does
Test locally | RunPod Documentation
Learn how to test your Handler Function locally using custom inputs and a local test server, simulating deployment scenarios without the need for cloud resources.
using that mode