Upgrading operators for services that require GPUs (Upgrading from Version 4.8 to Version 5.2)

If your environment includes services that require GPUs, you might need to upgrade the NVIDIA GPU Operator and the Node Feature Discovery Operator.

Upgrade phase

• Updating your cluster
• Updating your client workstation
• Collecting required information
• Preparing to run an upgrade in a restricted network
• Preparing to run an upgrade from a private container registry
• Installing and upgrading prerequisite software
• Updating the shared cluster components
• Preparing to upgrade an instance
• Upgrading an instance

Who needs to complete this task?

Cluster administrator A cluster administrator must complete this task.

When do you need to complete this task?

One-time setup Complete this task if one or more of the following services are installed or will be installed on the cluster:

Service	GPU operators
IBM Knowledge Catalog Premium	Required if you run the models on GPU. Not required if you run the models on: CPU A remote instance of watsonx.ai™
IBM Knowledge Catalog Standard	Required if you run the models on GPU. Not required if you run the models on: CPU A remote instance of watsonx.ai
Watson Machine Learning	Required only if you want to use deep learning or machine learning models that require GPU.
Watson Studio Runtimes	Required only if you want to use runtimes that require GPU.
watsonx.ai	Always required.
watsonx Assistant	Required only if you want to use features that require GPU.
watsonx™ BI	Always required.
watsonx Code Assistant™	Always required.
watsonx Code Assistant for Red Hat® Ansible® Lightspeed	Always required.
watsonx Code Assistant for Z	Always required.
watsonx Code Assistant for Z Agentic 5.2.1 and later	Always required.
watsonx Code Assistant for Z Code Explanation	Always required.
watsonx Code Assistant for Z Code Generation 5.2.1 and later	Always required.
watsonx.data™	Required only if you want to use Milvus indexes that require GPU.
watsonx.data Premium	Always required.
watsonx.data intelligence	Always required.
watsonx Orchestrate	Required if you run models locally. Not required if you use the AI gateway to access third-party models.