AI-Monitoring
v1.8.10
‹
🏠 Overview
🖥️ GPU/CPU
🌐 Network
⚙️ Settings
☰
Overview
◀
15m
1h
24h
30d
12mo
MTD
▶
● Live
live
connecting…
🌙
connecting…
LLM usage & cost
rolling window · via LiteLLM
details →
Host
ⓘ
GPU
Uptime
24h
no backend history yet
Containers
sampling…
Top 10 apps · CPU
sampling…
Top 10 apps · RAM
sampling…
Top-CPU apps over time —
1h
Top-RAM apps over time —
1h
Metrics over time —
1h
⬇ CSV
LiteLLM
Ollama
loaded-model memory — request throughput is on the LiteLLM page
llama.cpp