https://vitorpontual.com/tags/monitoring/ Recent content in Monitoring on Vitor Pontual | The VeePee Hub Hugo en-us Mon, 09 Feb 2026 00:00:00 +0000 https://vitorpontual.com/services/ollama-fleet-manager/ Mon, 09 Feb 2026 00:00:00 +0000 https://vitorpontual.com/services/ollama-fleet-manager/ <p>A dashboard and intelligent proxy for managing a fleet of Ollama GPU servers. Point any Ollama client at the proxy and it routes requests to the best available server automatically—no application changes needed.</p> <ul> <li><strong>Intelligent request routing</strong> — prioritizes servers with model already loaded, then model on disk, then most free VRAM</li> <li><strong>Real-time fleet monitoring</strong> — server status, loaded models, VRAM usage, CPU/GPU temperature, memory, disk, and uptime</li> <li><strong>Usage analytics</strong> — request volume, success rates, latency percentiles, and breakdowns by model, source, and server over 24h/7d/30d windows</li> <li><strong>Request aggregation</strong> — <code>/api/tags</code>, <code>/api/ps</code>, and <code>/v1/models</code> combine responses from all servers into a single unified list</li> <li><strong>Scheduled jobs</strong> — cron-based model scheduling with conflict detection across the fleet</li> <li><strong>Telegram alerts</strong> — server offline/online, overheating, low memory, and reboot notifications</li> <li><strong>Plugin system</strong> — extensible architecture for community plugins</li> <li><strong>OpenAI API compatible</strong> — supports <code>/v1/*</code> endpoints so OpenAI-compatible tools work out of the box</li> </ul>