Jump to contentJump to page navigation: previous page [access key p]/next page [access key n]
documentation.suse.com / Introduction to SUSE AI deployment

Introduction to SUSE AI deployment

Publication Date: 01 Oct 2024
WHAT?

Basic information about SUSE AI deployment workflow.

WHY?

To better understand the SUSE AI deployment process.

EFFORT

Less than 15 minutes of reading and a basic knowledge of Linux deployment.

1 Deployment overview

This topic outlines the complete workflow to deploy the SUSE AI product. It aims to clarify the deployment process to get good understanding of its complexity, find minimum hardware requirements, and steps to take after the deployment.

1.1 Requirements

Before deploying SUSE AI, the following must be fulfilled:

Hardware requirements

1.2 Cluster preparation

  1. Install and register SUSE Linux Micro 6.0 or later on each RKE2 cluster node. Refer to https://documentation.suse.com/sle-micro/6.0/ for details.

  2. (Optional) If you plan to utilize the computing power of NVIDIA GPUs, install the NVIDIA GPU driver on cluster nodes with GPUs. Refer to https://documentation.suse.com/suse-ai/1.0/html/NVIDIA-GPU-driver-on-SL-Micro/index.html for details.

  3. (Optional) Install the NVIDIAcontainer toolkit on GPU enabled systems. Refer to https://documentation.suse.com/suse-ai/1.0/html/NVIDIA-GPU-driver-on-SL-Micro/index.html#nvidia-gpu-validation for details.

  4. Install RKE2 Kubernetes distribution on the cluster nodes. Refer to https://docs.rke2.io/ for details.

  5. Connect the RKE2 cluster to Rancher Manager.

  6. Configure the GPU enabled nodes so that the SUSE AI containers are assigned to Pods that run on nodes equipped with NVIDIA GPU hardware. Find more details assigning Pods to nodes in https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/.

  7. (Optional) If you previously installed the NVIDIA GPU driver on hosts with GPU hardware, install NVIDIA GPU Operator with the additional option --set driver.enabled=false. Refer to https://documentation.suse.com/suse-ai/1.0/html/NVIDIA-Operator-installation/index.html.

  8. (Optional) Configure SUSE Security to scan the nodes that will be used for SUSE AI. Although this step is not required, we strongly encourage it to ensure the security in production environment.

  9. Configure SUSE Observability to observe the nodes with the SUSE AI application.