第 5 章 Using NVIDIA GPU resources with serverless applications

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