- 590 Views
- 1 replies
- 0 kudos
Model Serving Endpoints Scaling From Zero Forever
Hello,When deploying agents via a Serving Endpoint with "Scale To Zero" enabled, we are encountering that at seemingly random times, when we hit the endpoint to wake it up, it will begin to "Scale From Zero", but will never become fully available. Th...
- 590 Views
- 1 replies
- 0 kudos
- 0 kudos
Hi @jAAmes_bentley, There are multiple possible root causes, so let me walk through them so you can diagnose which applies to your situation. WHAT HAPPENS DURING SCALE-FROM-ZERO When an endpoint scales from zero, Databricks must: 1. Acquire comp...
- 0 kudos
- 755 Views
- 1 replies
- 1 kudos
Inference table not working for Gemma 3 12b
Hi, I have a problem regarding the inference table for Gemma 3 12b. If I create a serving endpoint for the model (from system.ai.gemma-3-12b-it) with an inference table, the inference table is being created, but it always stays empty. No matter how m...
- 755 Views
- 1 replies
- 1 kudos
- 1 kudos
The endpoint is working since you’re receiving responses, but the inference table isn’t capturing any records. This points to a logging/compatibility issue rather than request handling. Please confirm inference logging is enabled, verify permissions,...
- 1 kudos