Understand deployments in MLOps

In H2O MLOps, deployments are created when model version(s) are served for scoring. Models can be deployed to Dev and/or Production environments. Model endpoint security, artifact type, runtime, and Kubernetes options can be configured when deploying a model.

note

Champion/Challenger deployments and A/B testing are available through the Wave app UI and the H2O MLOps Python client. For more information on creating these deployment types with the H2O MLOps Python client, see Champion/Challenger deployment and A/B testing.

To learn more about deployments in H2O MLOps, refer to the following pages:

• Create a deployment

• View deployments

• Shapley values support

---

Feedback

• Submit and view feedback for this page
• Send feedback about H2O MLOps to cloud-feedback@h2o.ai