Runware incident

Degraded worker autoscaling

Resolved after 1 hour 31 minutes, affecting Serverless (Inference), on November 17, 2026.

monitoring Nov 17, 2026, 05:16 PM UTC

Configuration changes have been deployed, we are seeing autoscaling return to normal. We continue to monitor the situation.

Started
Nov 17, 2026, 04:44 PM UTC
Resolved
Nov 17, 2026, 06:15 PM UTC
Duration
1h 31m
Detected by Pingoru
Nov 17, 2026, 04:44 PM UTC

Affected components

Serverless (Inference)

Update timeline

  1. investigating Nov 17, 2026, 04:44 PM UTC

    We have identified an issue which is preventing workers from scaling. This impacts apps that scale to zero, preventing them from starting as well as bursting new workers from the configured minimum workers. We are investigating the underlying causes.

  2. identified Nov 17, 2026, 04:54 PM UTC

    We have identified the root cause, and currently in the process of deploying configuration changes to restore automatic scaling.

  3. monitoring Nov 17, 2026, 05:16 PM UTC

    Configuration changes have been deployed, we are seeing autoscaling return to normal. We continue to monitor the situation.

  4. resolved Nov 17, 2026, 06:15 PM UTC

    Issue has been resolved. And the platform now is stable.

Your product runs on more than Runware

Add the vendors you depend on and get one message when any of them reports trouble. Free for 3 vendors, no card.

Add your stack →