Previous incidents

There is an ongoing outage with cloudflare that are degrading or blocking Runpod products.

https://www.cloudflarestatus.com/

The network issue has been resolved and machines have been returned to service.

The network issue has been resolved and machines have been returned to service.

We’ve added more CPU resources, and so far both CPU serverless and public endpoints are scaling up normally again.

We are tracking an ongoing incident with CPU pod, serverles, github integration and public endpoints.

we are spinning up emergency reservers of CPU server capacity in multiple datacenters and tracking current usage to pinpoint exact issues

Our GPU utilization is back to normal, and most clients’ serverless queue items have been processed. AWS still hasn’t updated their status page, but we’ll continue monitoring the situation.

Issue has been resolved and network is operating normally.

Issue has been resolved and network is operating normally.

Changes have been made to improve the connectivity to proxy. Issue has been resolved and is operating normally.

Network connectivity between AWS and EU-RO-1 has been restored. Network is operating normally.

This has been resolved and the service is operating normally.

Issue has been resolved and network is operating normally.

Issue has been resolved. We've been monitoring the situation and it is operating normally.

Issue has been resolved and network is operating normally.

Services have returned to normal and we are continuing to monitor the situation