Increased error rate when re-activating deactivated deployments and deploying over existing development deployment

Incident Report for Baseten

Resolved

This incident has been resolved.. All services are operating normally

Posted Jul 30, 2024 - 14:53 PDT

Monitoring

We have rolled out a fix and systems are recovering. Error rate related to activating and deploying models is decreasing. We are actively monitoring the systems.

Posted Jul 30, 2024 - 14:20 PDT

Update

We are continuing to work on a fix for this issue. Some new deployments in us-east can take longer that usual to reach a ready state.

Posted Jul 30, 2024 - 13:20 PDT

Update

We are continuing to work on a fix for this issue.

Posted Jul 30, 2024 - 12:33 PDT

Identified

The issue has been identified and a fix is being implemented.

Posted Jul 30, 2024 - 12:01 PDT

Update

Inference is *not* impacted.

Posted Jul 30, 2024 - 11:52 PDT

Investigating

We are currently investigating the issue.

Posted Jul 30, 2024 - 11:10 PDT

This incident affected: Model Management API.