cuOpt

NVIDIA cuOpt™ is optionally provided as a RESTful microservice that builds upon the core functionality of cuOpt and can be easily deployed via helm chart.

Setup

The Nvidia cuOpt microservice container is packaged as a Kubernetes (aka k8s) deployment using a Helm chart. There are multiple options to create your own local K8s cluster. One such option is minikube.

Create Namespace for Nvidia cuOpt Server

Create a namespace and an environment variable for the namespace to organize the k8s cluster deployed to logically separate Nvidia cuOpt deployments from other projects using the following command:

kubectl create namespace <some name>
export NAMESPACE="<some name>"

Fetch helm chart

Fetch the helm chart using Fetch Command provided above, by default this command shows the latest version, if other versions are available they will be listed in File Browser Tab.

Install cuOpt

Run cuOpt as Server

• On ClusterIP

helm install --namespace $NAMESPACE --set ngc.apiKey=<YOUR API KEY> nvidia-cuopt-chart cuopt --values cuopt/values.yaml

It might take some time for downloading the container which can bee seen in the status as ContainerCreating, else it would be Running.
Use following commands to verify,

kubectl -n $NAMESPACE get all
NAME                                          READY   STATUS    RESTARTS   AGE
pod/cuopt-cuopt-deployment-595656b9d6-dbqcb   1/1     Running   0          21s

NAME                                           TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)             AGE
service/cuopt-cuopt-deployment-cuopt-service   ClusterIP   X.X.X.X	        <none>        5000/TCP,8888/TCP   21s

NAME                                     READY   UP-TO-DATE   AVAILABLE   AGE
deployment.apps/cuopt-cuopt-deployment   1/1     1            1           21s

NAME                                                DESIRED   CURRENT   READY   AGE
replicaset.apps/cuopt-cuopt-deployment-595656b9d6   1         1         1       21s

• On nodePort
  • Enable node port using param enable_nodeport, default node port for server is 30000 and can be changed to other using param node_port_server,

helm install --namespace $NAMESPACE --set ngc.apiKey=<YOUR API KEY> nvidia-cuopt-chart cuopt --set enable_nodeport=true --set node_port_server=30011 --values cuopt/values.yaml

Note: Notebook can also be run with option enable_notebook_server along with cuOpt server.

Run Jupyter Notebook

Note: Using values_notebook.yaml to set-up notebook related set-ups

• On ClusterIP

helm install --namespace $NAMESPACE --set ngc.apiKey=<YOUR API KEY> nvidia-cuopt-chart cuopt --values cuopt/values_notebook.yaml

• On nodePort
  • Enable node port using param enable_nodeport, default node port for server is 30001 and can be changed to other using param node_port_notebook,

helm install --namespace $NAMESPACE --set ngc.apiKey=<YOUR API KEY> nvidia-cuopt-chart cuopt --set enable_nodeport=true --set node_port_notebook=30021 --values cuopt/values_notebook.yaml

Note: cuOpt server can also be run with option enable_server along with notebook.

Uninstalling Nvidia cuOpt Server

helm uninstall -n $NAMESPACE nvidia-cuopt-chart

Documentation

• NVIDIA cuOpt Docs
• NVIDIA cuOpt Service Docs
• NVIDIA Container Toolkit

Examples and Resources

• Example notebooks
• Cloud scripts

By pulling and using the containers or Helm charts, you accept the terms and conditions of this End User License Agreement.