LLM engines
reading engines…
window
Engines answering
n/a
Active sessions
n/a
Queued
n/a
No engines configured
Set GUFO_BASE_URL (llama.cpp / gufo) and/or VLLM_BASE_URL.
Either half appears only when its variable is set — a server you do not run
should not have a red panel on your dashboard.
Prompt / prefill throughput
tok/sKV / prefix cache pressure
% in useSessions & queue
running vs waitinggufo slots
one row per parallel slot| Slot | State | Tokens | N prompt | N gen | Cache | Speed |
|---|
No /slots rows.
Events
engine up / down- loading…