Upstream outage: us-central1
resolved- Started
- Aug 19, 7:19 AM EDT
- Resolved
- Aug 19, 12:26 PM EDT
- Duration
- 5h 7m
Cerebrium's updates (4)
- update · Aug 19, 7:19 AM EDT
We are currently investigating an upstream issue with our Nebius provider in us-central1. We will provide regular updates as more information becomes available
- update · Aug 19, 7:37 AM EDT
The root cause has been identified as hardware related degradation. GPU performance in the region is impacted and inference to containers in the Nebius us-central1 region currently suffers from intermittent failure.
- update · Aug 19, 8:59 AM EDT
The issue has been resolved upstream and services should resume shortly
- resolved · Aug 19, 12:26 PM EDT
Upstream provider has resolved the issue.
What our checks recorded
We checked Cerebrium 62 times from Cerebrium's start time to its resolution, once every five minutes. Every one of them reached Cerebrium's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 149 ms, against 179 ms over the 24 hours before. Cerebrium posted the incident at Aug 19, 7:19 AM EDT.
Updates are Cerebrium's own words from its status page (status: resolved); we never add an inferred cause.