replicate · 91d ago
H100 GPU shortage resulting in high queue times
ResolvedYes — replicate had a problem on July 13, 2026, and replicate has since marked it resolved. replicate's latest word: “H100 capacity has returned to normal levels”
Timeline
Started: 7/13/2026, 4:26:41 PM
Last update: 7/14/2026, 5:27:56 PM
Resolved: 7/14/2026, 5:27:56 PM
Updates
resolved
H100 capacity has returned to normal levels
7/14/2026, 5:27:56 PM
monitoring
We pushed a fix and are monitoring
7/13/2026, 5:48:26 PM
investigating
Long queue times, especially on BFL models
7/13/2026, 4:26:41 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
- API degraded for A100s — resolved, 72d 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