Back to overview
Degraded

Degraded autoscaling performance

May 22 at 10:40am UTC
Affected services
Prediction serving

Status Report Update State Resolved
May 22 at 02:05pm UTC

Backlogs have been cleared and all models are now running smoothly.

Status Report Update State Updated
May 22 at 12:07pm UTC

The original issue has been resolved, but we will have elevated contention for a while as workloads that built up during the outage are processed.

Status Report Update State Updated
May 22 at 11:05am UTC

Models that run on A40 or A100 hardware are currently unable to boot up or scale out. Furthermore existing instances are suffering significant degradation and not all predictions are completing successfully in a timely manner.

We are actively monitoring the system and working with upstream providers to resolve the issue.

Status Report Update State Created
May 22 at 10:40am UTC

Models that run on A40 or A100 hardware are currently unable to boot up or scale out. Instances that are already running will continue to process predictions as normal.

We are actively monitoring the system and working with upstream providers to resolve the issue.