P

Patra AI / Monitoring System

HOST UP LOAD connecting

Overview

GPU Utilisation

%

VRAM

%

CPU

%

Memory

%

Services

Inference Backend

GPU Detail

Storage

Network

Resilience

Last Health Check

Services

vLLM and Ollama are conflicting units — starting one stops the other.

ServiceStateBoot PortAnsweringRestartsControl

Bulk

Free the GPU stops vLLM and Ollama. Nothing else is touched.

System

the suite's own machinery — timers, boot-time tuning, firewall, driver

UnitStateBoot RestartsControl

Listening sockets

Docker containers

Install history

Configuration backups every changed file, per run

Models

what is on disk, and what is loaded

Add a model from HuggingFace download it, then hand it to vLLM

Currently serving

Pull an Ollama model

idle

HuggingFace cache

Ollama store

Metrics

telemetry recorded every minute — this is how you answer "what was it doing at 3am"

Modules

re-run any part of the installer — every module is idempotent

Installer modules

Output

select a module — preview shows what would change, apply makes the change

Configuration

every file that shapes how this machine behaves

Logs

journalctl, live

select a service

Health

runs ai-health with repairs disabled — looking never changes anything

Takes a few seconds. Pings, SMART and the GPU are all queried live.
not run yet

Playground

streaming chat against the running backend

Request

0.70
0.95
no messages yet
First token
Total
Tokens
Throughput

Benchmark

concurrent requests — this is what vLLM is for

Configuration

8

Continuous batching means N requests should finish in barely more wall-clock time than one. If total time scales linearly with N, batching is not happening — check ai-ctl logs vllm for KV-cache preemption.

Above 6, the browser is the bottleneck, not the server. Chrome opens at most six HTTP/1.1 connections per origin, so a run of 8 arrives as 6 + 2 and the wall clock roughly doubles. The aggregate figure stays honest; the per-request times do not. For a true concurrency sweep use the shell: ai-bench 32

Result

Wall clock
Completed
Total tokens
Aggregate
idle

Endpoints

reach anything on loopback and see what it says

Quick checks

Custom request

Status
Latency
no request sent