System Online — 14d 07h 23m
6
Total Servers
18
Active GPUs
9
Running Models
7
Queued Jobs
2,847
Tokens/sec Total
3.2 kW
Power Draw
Tokens/sec — Last 60s
VRAM Usage — Last 60s
Power Draw — Last 60s
Job Completion Time — Last 20
fleet-control — activity log

Servers

GPU Monitors

Model Deployments

Model Name ↕Quantization ↕Context ↕GPU Assignment ↕Status ↕Tokens/sec ↕VRAM Used ↕Jobs ↕

Inference Queue

Alerts & Notifications