Installing the NVIDIA operator
The NVIDIA GPU Operator uses the operator framework within Kubernetes to automate the management of all NVIDIA software components that are needed to provision the GPU.
Before you begin
For more information about the NVIDIA GPU Operator, see the following information on the NVIDIA website: GPU Operator on OpenShift® Overview.
Complete the following tasks, dependent on your software needs:
- For AWS, see: Adding a GPU worker node to a Red Hat OpenShift cluster on AWS.
-
Note: For AWS clusters, check if entitlements are necessary in instances that the client is on Red Hat® OpenShift 4.9.8 or previous versions.
- For on-premises, see: Enabling GPU passthrough.
Procedure
Install the NVIDIA operator by using the Red Hat OpenShift Container Platform web console and
complete the following steps on the NVIDIA site: Installing the NVIDIA GPU Operator.
Tip: This task can also be done by using the following Ansible® role: nvidia_gpu. For more information about the Ansible
role, see IBM Maximo Application Suite installation with Ansible collection.