Explore our recent post Deep Dive into nvidia-smi: Monitoring Your NVIDIA GPU with Real Examples from the Kubernetes Current blog. Read our thoughts on all things Kubernetes and stay current on the latest news from Rafay.

Rafay

nvidia-smi is a command-line utility for monitoring NVIDIA GPU performance, health, and processes in real-time. The tool provides essential information including GPU temperature, memory usage, power consumption, and running processes. Using a real NVIDIA T1000 8GB GPU example, the guide demonstrates practical commands for live monitoring, process management, and advanced configuration options like persistence mode and compute access restrictions. The utility supports scripting for automated monitoring and works without requiring the full CUDA toolkit installation.