—
healthy / total nodes
—
models
—
recent tasks
—
req / min
—
error rate
—
p50 latency
—
p95 latency
—
tokens/s out
—
cache hit rate
—
offloaded to remote
Tokens per Request estimated · sent vs received
no tasks yet
Latency per Request turnaround · failures in red
no tasks yet
Distributed Inference work served per machine
no node-served inference yet
Routing Breakdown by backend / mode
no data
Tool Calls
no tool calls yet
Infrastructure — nodes & default backend
| Node ID | Backend | Load | Status |
|---|---|---|---|
| loading… | |||
Providers & API keys
Configured: —
Cache
—
Entries
—
Hit Rate
—
Hits
—
Misses
Context sent to model — per user
no chats yet
Stress test load-test a node with random tokens
no run yet — caps: ≤1000 requests, ≤64 concurrency
Recent tasks click a row for composition
| Time | Prompt | Worker | Model | Duration | Status |
|---|---|---|---|---|---|
| loading… | |||||
Recent events
| ID | Kind | Model | Prompt | Duration |
|---|---|---|---|---|
| loading… | ||||