Scheduled maintenance: US South Central cache tier
resolved- Started
- Oct 11, 7:00 AM EDT
- Resolved
- Oct 11, 9:00 AM EDT
- Duration
- 2h
Cerebrium's updates (2)
- update · Oct 11, 7:00 AM EDT
On Sunday 11 October 2026, between 11:00 and 13:00 UTC, we will carry out scheduled maintenance on the distributed cache in US South Central. This cache speeds up reads of the model weights and files your apps load when a replica starts. The cache stays in service throughout, and no stored data is changing or at risk. While the cache rebuilds, during the window and for a few hours after, the first read of a given file may be slower than usual. Apps that load model weights or other files when a replica starts may see longer cold starts, mostly at the slow end rather than the typical start. Repeat reads return to normal speed. Running replicas, live request handling, builds, container image pulls, the dashboard, the REST API and metrics are not affected. All other regions remain fully operational. No customer action is required. If your app is latency-sensitive and loads files at startup, you can set min replicas to 1 or more before the window so it does not cold start during it.
- update · Oct 11, 9:00 AM EDT
Maintenance ended
What our checks recorded
We checked Cerebrium 24 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 157 ms, against 117 ms over the 24 hours before. Cerebrium posted the incident at Oct 11, 7:00 AM EDT.
Updates are Cerebrium's own words from its status page (status: resolved); we never add an inferred cause.