System Requirements

This section describes the infrastructure you must provide before installing NVIDIA Run:ai - hardware, Kubernetes distribution, networking, and storage - and the third-party services the installation deploys for you, whether you use the Guided Installation or Manual Helm path. It follows the shared responsibility model: NVIDIA provides the Run:ai software, while you prepare and manage the Kubernetes environment it runs on.

Note

Before reviewing the requirements, determine your deployment model, as it affects which infrastructure components must be provisioned once and which are required for each NVIDIA Run:ai cluster.

Complete each of the following before installing NVIDIA Run:ai:

Section	What to prepare
Deployment Model	Same-cluster vs multi-cluster connectivity, networking, DNS, and TLS requirements
Infrastructure Requirements	Hardware, OS, Kubernetes distribution, storage, and permissions
Networking Setup	Load balancer, ingress controller, DNS, FQDN, and TLS certificates
Third-Party Services	Services deployed as part of installation, their registries, and how to replace them with externally managed instances
External Access to Critical Services	Inbound/outbound firewall rules and registry domain allowlist

Next Steps

Once your environment is prepared, proceed to installation:

Guided Installation - Recommended for most installations.
Manual Helm - For organizations managing releases through their own tooling.