Output throughput
—tokens / secondNetwork overview
Operations
Last 60 minutes · 1 minute resolution
Requests
—selected windowActive now
—in flightAvg latency
—millisecondsSuccess rate
—— errorsRoutable nodes
—— registeredGPUs online
—available devicesWarm models
—routable replicasThroughput
Generated tokens / second
Waiting for traffic data
Traffic
Requests / minute
Waiting for request data
Infrastructure
Live fabric
Routable Disconnected Offline