You create an MLflow model. You must deploy the model to Azure Machine Learning for batch inference. You need to create the batch deployment. Which two components should you use? Each correct answer…

The correct answer is B. Model files E. Compute target. To create a batch deployment in Azure Machine Learning for an MLflow model, you need two core components: (B) Model files-the registered MLflow model that will be used for inference, and (E) Compute target-the compute cluster or compute instance on which the batch scoring job…

Train and deploy models

Question

You create an MLflow model. You must deploy the model to Azure Machine Learning for batch inference. You need to create the batch deployment. Which two components should you use? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point.

Options

AEnvironment
BModel files
COnline endpoint
DKubernetes online endpoint
ECompute target

How the community answered

(57 responses)

A
7% (4)
B
86% (49)
C
2% (1)
D
5% (3)

Explanation

To create a batch deployment in Azure Machine Learning for an MLflow model, you need two core components: (B) Model files-the registered MLflow model that will be used for inference, and (E) Compute target-the compute cluster or compute instance on which the batch scoring job will execute, since batch inference jobs require dedicated compute to process large datasets asynchronously. MLflow models in Azure ML batch deployments benefit from auto-generated environments (so a separate Environment definition is not strictly required), but model files and compute are always mandatory. Online endpoints (C) and Kubernetes online endpoints (D) are used for real-time, synchronous inference, not batch inference, which uses batch endpoints instead.

Topics

#Azure Machine Learning#MLflow#Batch Inference#Model Deployment

Community Discussion

No community discussion yet for this question.

Full DP-100 Practice