System status

Live status of this instance's components. Last checked: 2026-07-09 21:42 UTC.

Model registry 99.98% uptime (30 d) ● Operational
Artifact storage 99.99% uptime (30 d) ● Operational
Fine-tune queue 99.95% uptime (30 d) ● Operational
Image workers 99.91% uptime (30 d) ● Operational
Artifact CDN 99.97% uptime (30 d) ● Operational
API 99.99% uptime (30 d) ● Operational
Auth service 99.98% uptime (30 d) ● Operational

Incident history

2026-06-11

Elevated API latency — Image workers Resolved

P99 latency on /events/* endpoints rose to 4.2 s for ~35 minutes due to a container scheduling anomaly. No jobs were lost. Resolved by rebalancing the worker pool at 14:22 UTC.

2026-04-29

Fine-tune queue backlog Resolved

A batch of 18 large GGUF jobs saturated the queue for ~2 hours. Jobs completed with a delay; no data loss. Queue now has a per-job size guard to prevent recurrence.