A100 hardware partial outage

Resolved

Yes — replicate had a problem on August 26, 2026, and replicate has since marked it resolved. replicate's latest word: “We've been below capacity for A100 hardware for the past 30 minutes and all queues have been drained. Thanks for your patience 💖”

See replicate's live status →

Timeline

Started: 8/26/2026, 9:17:34 PM

Last update: 8/27/2026, 12:25:21 AM

Resolved: 8/27/2026, 12:25:21 AM

Updates

resolved
We've been below capacity for A100 hardware for the past 30 minutes and all queues have been drained. Thanks for your patience 💖
8/27/2026, 12:25:21 AM
monitoring
We are seeing pods start up again now and they are working through the backlog.
8/26/2026, 11:07:40 PM
investigating
We're seeing most A100 hardware automatically cordoned due to possible hardware failure.
8/26/2026, 9:17:34 PM

More replicate incidents

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
HuggingFace download issues — resolved, 89d ago

Is replicate down right now?All outage history →