Fleet Overview
Real-time monitoring of your AI inference cluster
Tokens Per Second
Total Power Draw (W)
VRAM Usage (%)
Job Completion Time (s)
nexus@fleet-control ~ activity-log
Server Fleet
Manage and monitor all connected servers
GPU Monitor
Real-time GPU utilization across the fleet
Model Deployments
Active model instances and their configurations
All Models
| Model Name | Quantization | Context Length | GPU Assignment | Tokens/sec | Status | Jobs |
|---|
Inference Queue
Track active, waiting, and completed inference jobs
All Jobs
Active
Waiting
Completed
Failed
Alerts & Notifications
Critical events requiring attention