Changes / Baseten / Elevated errors for dedicated inference in a subset of clusters

Baseten: Major incident: Elevated errors for dedicated inference in a subset of clusters

Summary

Baseten reported a major incident causing elevated errors for Dedicated Inference in a subset of clusters, starting at 2026-06-26 22:00 UTC and resolved at 2026-06-26 22:15 UTC (computed duration: 14 min). A fix was being implemented, and nearly all clusters had recovered by 22:03 UTC; no cause was stated.

Machine-written from the diff below (Sol; type: incident outage). Check the diff before relying on it.

Major incidentLabel: outage (model (Jev), 92%)Changed Detected Source: stspg.io (opens in new tab)

What changed

AddedTitle#1
Before: not present
After: Elevated errors for dedicated inference in a subset of clusters
AddedImpact#2
Before: not present
After: major
AddedStatus#3
Before: not present
After: resolved
AddedStart time#4
Before: not present
After: 2026-06-26 22:00 UTC
AddedResolved time#5
Before: not present
After: 2026-06-26 22:15 UTC
AddedAffected components#6
Before: not present
After: Dedicated Inference
AddedUpdateinvestigating#7
Before: not present
After: We are currently investigating this issue.
AddedUpdateidentified#8
Before: not present
After: The issue has been identified and a fix is being implemented.
AddedUpdateidentified#9
Before: not present
After: Nearly all clusters have recovered.
AddedUpdateidentified#10
Before: not present
After: We are continuing to work on a fix for this issue.
AddedUpdateresolved#11
Before: not present
After: This incident has been resolved.

First version of this incident archived by Rewindex. View the live incident (opens in new tab).

History of this incident

When (UTC)ChangeKind
Major incident: Elevated errors for dedicated inference in a subset of clusters (this change)
Baseten reported a major incident causing elevated errors for Dedicated Inference in a subset of clusters, starting at 2026-06-26 22:00 UTC and resolved at 2026-06-26 22:15 UTC (computed duration: 14 min). A fix was being implemented, and nearly all clusters had recovered by 22:03 UTC; no cause was stated.
Major incident

All Baseten changes → · Baseten profile · Markdown · JSON