LLM-as-a-Judge (LLMaJ) evaluation execution in Langfuse's EU region was degraded for approximately 1.3 hours due to a slow tenant/model workload overwhelming evaluation throughput, compounded by lock-expiry retries multiplying the work queue and a concurrent worker rollout prolonging recovery. Autoscaling eventually responded and began draining the backlog. The incident was classified as minor and resolved as the system self-corrected.
Trusted by 1,000+ teams
Stop finding out about outages from your users. Monitor 6,320+ cloud services and get alerted the second something breaks.
our autoscaling responded slower than expected, but responded nonetheless. the backlog is draining
evaluation throughput was overwhelmed by a slow tenant/model workload, with lock-expiry retries multiplying work; the concurrent worker rollout prolonged the incident.
Eval execution in EU region is taking longer than usual
With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.
Start free trialNo credit card required · Cancel anytime · 6320 services available
Integrations with