Is this page helpful?

Day 2 Operations

Deploying NVIDIA NIMs on Kubernetes

NIMs are intended to be run on a system with NVIDIA GPUs, with the type and number of GPUs depending on the model. To use helm, you must have a Kubernetes cluster with appropriate GPU nodes and the GPU Operator installed.

Using the NIM will require an NVIDIA AI Enterprise license and an accompanying NGC API Key which may be added to your cluster as a Secret. This enables pulling the containers, and optimized models from NGC. For more information on deploying NIMs, please check the official documentation: Deploying with Helm - NVIDIA Docs