[
CF
//
ORCH
]
coordinator
⚙ settings
5
s
Dashboard
Analytics
History
Services
GPU Nodes
System
Service Instances
Service
Node
GPU
State
Model
URL
Active Leases
Service
Node / GPU
VRAM
Priority
TTL / Expires
Allocation Queue
ID
Service
Node / GPU
VRAM
Priority
Waiting
Warm Models
Service
Node
Model
Warm Since
Service Monitors
Device
Model
Temp
SMART Status
Security
Window:
1h
24h
7d
All
Alerts
By Service
By Caller
Recent Events
All events
allocated
released
failed
expired
All services
Time
Event
Service
Caller
Node / GPU
Hold
Reason / Model
Window:
1h
6h
12h
All
Filter:
All callers
All pipelines
VRAM Utilisation
Accumulating data — first sample in ~30 s
Throughput & Queue
Accumulating data — first sample in ~30 s
Capacity Breakdown
⚙ Settings
✕