This is a cache of https://docs.openshift.com/serverless/1.28/integrations/gpu-resources.html. It is a snapshot of the page at 2024-11-26T17:15:04.182+0000.
Using NVIDIA GPU resources with serverless applications | Integrations | Red Hat OpenShift Serverless 1.28
    OpenShift docs are moving and will soon only be available at docs.redhat.com, the home of all Red Hat product documentation. Explore the new docs experience today.
  1. Documentation
    2. history
×

Using NVIDIA GPU resources with serverless applications

NVIDIA supports using GPU resources on OpenShift Container Platform. See GPU Operator on OpenShift for more information about setting up GPU resources on OpenShift Container Platform.

Specifying GPU requirements for a service

After GPU resources are enabled for your OpenShift Container Platform cluster, you can specify GPU requirements for a Knative service using the Knative (kn) CLI.

Prerequisites

  • The OpenShift Serverless Operator, Knative Serving and Knative Eventing are installed on the cluster.

  • You have installed the Knative (kn) CLI.

  • GPU resources are enabled for your OpenShift Container Platform cluster.

  • You have created a project or have access to a project with the appropriate roles and permissions to create applications and other workloads in OpenShift Container Platform.

Using NVIDIA GPU resources is not supported for IBM zSystems and IBM Power on OpenShift Container Platform or OpenShift Dedicated.
Procedure

  1. Create a Knative service and set the GPU resource requirement limit to 1 by using the --limit nvidia.com/gpu=1 flag:

    $ kn service create hello --image <service-image> --limit nvidia.com/gpu=1

    A GPU resource requirement limit of 1 means that the service has 1 GPU resource dedicated. services do not share GPU resources. Any other services that require GPU resources must wait until the GPU resource is no longer in use.

    A limit of 1 GPU also means that applications exceeding usage of 1 GPU resource are restricted. If a service requests more than 1 GPU resource, it is deployed on a node where the GPU resource requirements can be met.

  2. Optional. For an existing service, you can change the GPU resource requirement limit to 3 by using the --limit nvidia.com/gpu=3 flag:

    $ kn service update hello --limit nvidia.com/gpu=3

Additional resources for OpenShift Container Platform