Overview
Engine statusConnectingWaiting for the local service
Current modelNone loaded
Active requests—
Runtime
- Model state
- —
- Inference process
- —
- Time to first token
- —
- Last response tokens
- —
Effective inference settings
Model storage
—
Manage storageServer metrics
/metrics ↗- Running / waiting
- —
- Free KV blocks
- —
- Cache hits / misses
- —
- Avg. prefill / decode
- —
—
Activity
No activity.Models
DOWNLOAD
—
—
— recipes
Loading model catalog…
Local checkpoints
Scanning storage…
Chat
Load a model to start a conversation.
Settings
Model storage
Configuration:
Recipe catalogue
Developer settings
Local API
POST /v1/chat/completions
POST /v1/responses
POST /v1/messages