System Requirements | NVIDIA Run:ai Documentation

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

Complete each of the following before installing NVIDIA Run:ai multi-tenant:

Section	What to prepare
Deployment Model	Control plane and tenant 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
Metrics Store Requirements	External metrics backend required to aggregate metrics across tenants
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 deployments.
Manual Helm - For organizations managing deployments through their own tooling.