H100 GPU shortage resulting in high queue times

lowReplicateJul 15, 2026 03:35

capacity

Capacity Issue

Summary

H100 capacity has returned to normal levels

Impact

minor

Timeline

Jul 13, 2026 16:26

[investigating] Long queue times, especially on BFL models

via statuspage

+1h 22m

Jul 13, 2026 17:48

[monitoring] We pushed a fix and are monitoring

via statuspage

+23h 40m

Jul 14, 2026 17:27

[resolved] H100 capacity has returned to normal levels

via statuspage

Lessons Learned

⚠Replicate has experienced 37 incidents in the past year. This frequency suggests systemic reliability challenges that may warrant additional monitoring.

📊Incidents related to capacity have occurred 58 times across all providers in the past year. This is one of the most common failure categories in cloud infrastructure.

💡This incident is categorized as: Capacity Issue. Consider implementing preventive measures specific to this failure category.