DocumentationSelf-Managed Deployment

About Platform Setup

View as Markdown

This section describes how to deploy NeMo Platform to a Kubernetes cluster using the NeMo Platform Helm chart. The chart is the supported path for self-managed clusters such as minikube, kind, EKS, AKS, GKE, OKE, OpenShift, and on-prem Kubernetes.

This Platform Setup chapter is for the following personas.

  • Cloud administrators: Manage Kubernetes clusters and compute/storage resources. Deploy NeMo Platform to the Kubernetes clusters on premises or cloud.

NeMo Platform Helm Chart

The NeMo Platform Helm chart is published in the nvidia/nemo-platform NGC org. The chart deploys the platform API, controllers, storage integration, and dependencies required for a full self-managed deployment.

Customize the installation by updating a pinned values.yaml file for your target cluster. For chart assets and additional details, see the NeMo Platform artifacts in NGC.

The install guide uses NMP_HELM_CHART_VERSION so every install and upgrade is tied to a specific chart version.

Deploy the NeMo Platform with Helm

The following sections provide detailed instructions on how to deploy the NeMo Platform using the NeMo Platform Helm Chart.

Install

Install NeMo Platform with Helm on a Kubernetes cluster.

cluster-admin

Other Configurations

Review and manage other cluster settings.

OpenTelemetry

Review and configure how NeMo Platform uses OpenTelemetry for observability.

Milvus

Review and configure how NeMo Platform uses Milvus for vector database storage.