replicate · 69d ago
Degraded scale-out due to failed setups pulling from huggingface
ResolvedYes — replicate had a problem on July 31, 2026, and replicate has since marked it resolved. replicate's latest word: “We're looking stable now, and with caching back on. Thanks again for your patience!”
Timeline
Started: 7/31/2026, 9:25:03 PM
Last update: 7/31/2026, 11:39:34 PM
Resolved: 7/31/2026, 11:39:34 PM
Updates
resolved
We're looking stable now, and with caching back on. Thanks again for your patience!
7/31/2026, 11:39:34 PM
monitoring
All affected hardware types have recovered and we are continuing to monitor and troubleshoot. Thanks for your patience!
7/31/2026, 10:27:50 PM
identified
We have confirmed that turning off our caching layer for huggingface downloads allows models to successfully set up, so we are making that change for all models while we continue to troubleshoot.
7/31/2026, 9:26:39 PM
identified
Models that pull from huggingface during setup have not been succeeding, which is resulting in scale-out delays and queue backups.
7/31/2026, 9:25:03 PM
More replicate incidents
- A100 hardware partial outage — resolved, 43d ago
- Delayed scaling due to node failure — resolved, 59d ago
- Significant degradation — resolved, 64d ago
- API degraded for A100s — resolved, 67d ago
- Hitting GPU Capacity for H100s creating large queue times for some models — resolved, 78d ago
- HuggingFace download issues — resolved, 84d ago