# AI Platform Monitoring

![NVIDIA](https://datalab.tuwien.ac.at/infrastructure/ai-platform-monitoring/assets/nvidia.png)

## Dashboards

### NVIDIA DCGM Dashboard
[GPU Metrics Dashboard](https://monitoring.ai.datalab.tuwien.ac.at/d/nvidia-dcgm-dashboard/better-nvidia-dcgm-dashboard?orgId=1&from=now-30m&to=now&timezone=browser&var-datasource=prometheus&var-host=$__all&var-gpu=$__all&refresh=5s)

Monitors GPU utilization, temperature, power consumption, memory usage, and overall GPU health across all nodes in the AI platform.

### VLLM Dashboard
[VLLM Server Dashboard](https://monitoring.ai.datalab.tuwien.ac.at/d/750918278/vllm-dashboard?orgId=1&from=now-1h&to=now&timezone=browser&refresh=auto)

Tracks VLLM server performance including request throughput, latency metrics, model-specific load, and server resource utilization.