Upgrading operators for services that require GPUs(Upgrading from Version 5.3 to Version 5.4)

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
  • You are not here. Updating your client workstation
  • You are not here. Collecting required information
  • You are not here. Preparing to run an upgrade in a restricted network
  • You are not here. Preparing to run an upgrade from a private container registry
  • You are here icon. Preparing the cluster
  • You are not here. Preparing to upgrade an instance
  • You are not here. Upgrading an instance
  • You are not here. Setting up IBM® Software Hub
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 Speech services

Required only if you want to enable enrichment.

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 Agentic

Always required.

watsonx Code Assistant for Z Understand

Always required.

watsonx.data™

Required only if you want to use Milvus indexes that require GPU.

watsonx.data Premium

Always required.

watsonx.data integration Required if you plan to enable the Unstructured Data Integration feature (enableUnstructuredDataIntegration: true).
watsonx.data intelligence

Required if one of the following statements are true:

  • You plan to run models for generative AI on local GPU
  • You plan to enable the Unstructured Data Integration feature (enableUnstructuredDataIntegration: true), which requires local GPU
watsonx Orchestrate
  • Required if you run models locally.
  • Not required if you use the AI gateway to access third-party models.

About this task

All of the services that require GPUs require the NVIDIA GPU Operator and the Node Feature Discovery Operator.

Review the following table to determine which operators you need to upgrade:
Operator Upgrade this operator if...
Node Feature Discovery Operator

You upgraded Red Hat OpenShift® Container Platform and the operator is installed with installPlanApproval: Manual.

NVIDIA GPU Operator

The version of the operator on your cluster has reached the end of support. For details, see NVIDIA GPU Operator Life Cycle in the

Procedure

  1. To upgrade the Node Feature Discovery Operator, follow the appropriate steps for your environment:
  2. To upgrade the NVIDIA GPU Operator, follow the appropriate steps for your environment:

What to do next

Now that you've upgraded the operators for services that require GPUs, you're ready to complete Upgrading Red Hat OpenShift AI (Upgrading from Version 5.3 to Version 5.4).