A machine learning engineer wants to deploy a model for real-time serving using MLflow Model Serving. For the model, the machine learning engineer currently has one model version in each of the stages in the MLflow Model Registry. The engineer wants to know which model versions can be queried once Model Serving is enabled for the model.
Which of the following lists all of the MLflow Model Registry stages whose model versions are automatically deployed with Model Serving?
In MLflow Model Serving, the model versions that are automatically deployed are those in the Staging and Production stages. The Staging stage is used for testing the latest changes in a controlled environment, while the Production stage is for serving predictions in a live environment. Model versions in the Archived stage are not automatically deployed. Therefore, the correct list of stages whose model versions are deployed with Model Serving includes only Staging and Production.
Correct answer is D. See https://www.databricks.com/blog/2020/06/25/announcing-mlflow-model-serving-on-databricks.html "Note the URL for each model: you can query either by the version number (1 or 2) or by the stage (Production or Staging)"
C. Correct
C. None, Staging, Production, Archived
E is correct
D. Staging, Production Model versions in the Staging and Production stages are automatically deployed with Model Serving. When Model Serving is enabled for a model, the latest version in the Staging stage is deployed for testing, and the latest version in the Production stage is deployed for serving predictions in production environments.
A is correct. Over the course of the model’s lifecycle, a model evolves—from development to staging to production. You can transition a registered model to one of the stages: Staging, Production or Archived. https://mlflow.org/docs/latest/model-registry.html#deprecated-using-model-stages
https://www.databricks.com/blog/2020/06/25/announcing-mlflow-model-serving-on-databricks.html