Replicate incident

We're seeing long setup times and high contention for models on some L40S and H200 clusters.

Name: Replicate — We're seeing long setup times and high contention for models on some L40S and H200 clusters.
Start: 2026-06-03T17:59:32Z
End: 2026-06-03T19:06:24Z

Major Resolved

Started

June 3, 2026 at 05:59 PM UTC

Duration

1h 6m

Resolved

June 3, 2026 at 07:06 PM UTC

Updates timeline

Investigating Jun 3, 05:59 PM UTC

We're seeing long setup times and high contention for models on some L40S and H200 clusters.
Investigating Jun 3, 07:06 PM UTC

System is back to operating normally
Resolved Jun 3, 07:06 PM UTC

System is back to operating normally

Live Replicate status

Current indicator + 24h latency

All incidents

Cross-service timeline

Subscribe via RSS

Atom feed for any reader