replicate · 72d ago
API degraded for A100s
ResolvedYes — replicate had a problem on August 2, 2026, and replicate has since marked it resolved. replicate's latest word: “We have restarted the affected component and service should be back to normal. Thank you for your patience”
Timeline
Started: 8/2/2026, 4:09:45 PM
Last update: 8/2/2026, 4:18:43 PM
Resolved: 8/2/2026, 4:18:43 PM
Updates
resolved
We have restarted the affected component and service should be back to normal. Thank you for your patience
8/2/2026, 4:18:43 PM
identified
The API for creating predictions for A100s is currently degraded as a piece of backing infrastructure failed. We are working on getting it back online
8/2/2026, 4:09:45 PM
More replicate incidents
- A100 hardware partial outage — resolved, 48d ago
- Delayed scaling due to node failure — resolved, 64d ago
- Significant degradation — resolved, 69d ago
- Degraded scale-out due to failed setups pulling from huggingface — resolved, 74d ago
- Hitting GPU Capacity for H100s creating large queue times for some models — resolved, 83d ago
- HuggingFace download issues — resolved, 89d ago