Cannot run dedicated server for interface endpoint

Inference Endpoints on the Hub
1

I am trying to run a dedicated endpoint, I tried several models, different instance size, CPU based, GPU based, tried to run it on AWS/Azure/GCP, it fails every single time with the same error:
Workload evicted, storage limit exceeded (8G)

What am I doing wrong or what do I need to do to be able to run a dedicated interface endpoint because right now it’s unusable.

Thanks to anyone that helps.

1 Like
2

Quick update, I got it to run, so it seems like the recommended setup is not even remotely close to be able to run the model…

1 Like