Self Hosted installation over OpenShift - prerequisites¶

Before proceeding with this document, please review the installation types documentation to understand the difference between air-gapped and connected installations.

Run:ai components¶

As part of the installation process you will install:

• A control-plane managing cluster
• One or more clusters

Both the control plane and clusters require Kubernetes. Typically the control plane and first cluster are installed on the same Kubernetes cluster but this is not a must.

Installer machine¶

The machine running the installation script (typically the Kubernetes master) must have:

• At least 50GB of free space.
• Docker installed.

Helm¶

Run:ai requires Helm 3.14 or later. To install Helm, see Installing Helm. If you are installing an air-gapped version of Run:ai, The Run:ai tar file contains the helm binary.

Cluster hardware requirements¶

The Run:ai control plane services require the following resources:

If Run:ai cluster is planned to be installed on the same cluster as the Run:ai control plane: Ensure the control plane requirements are in addition to the Run:ai cluster hardware requirements.

Run:ai software requirements¶

Cluster Nodes¶

Nodes are required to be synchronized by time using NTP (Network Time Protocol) for proper system functionality.

OpenShift¶

Run:ai supports OpenShift. OpenShift Versions supported are detailed in Kubernetes distribution.

• OpenShift must be configured with a trusted certificate. Run:ai installation relies on OpenShift to create certificates for subdomains.
• OpenShift must have a configured identity provider (Idp).
• If your network is air-gapped, you will need to provide the Run:ai control-plane and cluster with information about the local certificate authority.

Install prerequisites¶

NVIDIA GPU Operator¶

See Run:ai Cluster prerequisites installing NVIDIA dependencies in OpenShift.

The Run:ai control plane, when installed without a Run:ai cluster, does not require the NVIDIA prerequisites.

Information on how to download the GPU Operator for air-gapped installation can be found in the NVIDIA GPU Operator pre-requisites.

Inference (optional)¶

See Run:ai Cluster prerequisites Inference requirements.

The Run:ai control plane, when installed without a Run:ai cluster, does not require the Inference prerequisites.

External PostgreSQL database (optional)¶

The Run:ai control plane installation includes a default PostgreSQL database. However, you may opt to use an existing PostgreSQL database if you have specific requirements or preferences. Please ensure that your PostgreSQL database is version 16 or higher.

Next steps¶

Continue to Preparing for a Run:ai OpenShift Installation .