AI Server Fleet Control Panel
Overview
Servers
GPUs
Models
Jobs
Alerts
Total Servers
12
6 Active, 6 Inactive
Active GPUs
24
184.5 TFLOPS Total
Running Models
18
204.3B Params Total
Queued Jobs
24
1,245 tokens/sec
Power Usage
8.7 kW
Average 3.2°C GPU Temp
Tokens Per Second (Last 24 Hours)
Recent Server Activity
Status:
All
Active
Inactive
Search:
GPU Utilization
Status:
All
Running
Pending
Stopped
Sort:
Speed (Tokens/sec)
Name
GPU Assignment
Model Name
Quantization
Context Length
GPU Assignment
Status
Current Jobs
Actions
Inference Queue
Job ID
Model
Status
Progress
Created
Actions
Active Alerts
VRAM Usage Over Time
Activity Log