Demo Cluster Setup on Minikube#
Get started with creating a single-node minikube cluster and installing the NeMo microservices as a platform.
This minikube cluster demo setup is to help cluster administrators, data scientists, and AI application developers deploy the NeMo microservices as an end-to-end platform on a minikube cluster.
After you complete setting up the minikube cluster, you can proceed to the Beginner Tutorials.
Note
This minikube demo cluster setup tutorial is designed for the Beginner Tutorials that run small workloads of fine-tuning, evaluating, and running inference on smaller LLMs such as llama-3.1-8b-instruct and meta-llama/llama-3.2-1b-instruct. If you want to run AI workloads at a larger scale, set up the NeMo microservices platform on a larger Kubernetes cluster. For more information, refer to About Admin Setup.
Before You Begin#
Check the following requirements before you begin.
Check the system and software requirements to set up a minikube cluster and the NeMo microservices platform for the beginner tutorials.
To Install the NeMo Microservices Platform#
You can set up a minikube cluster with the NeMo microservices platform using the installation scripts provided by NVIDIA or manually. Choose one of the following options.
Deploy the NeMo microservices platform using automated deployment scripts with no manual steps.
Practice manually setting up the minikube cluster and the NeMo microservices with more control.