Answer-first summary for fast verification
Answer: scoring script
The correct answer is A (scoring script) because when customizing inference logic for an MLflow model deployment to a batch endpoint, the scoring script must be created first. This script contains the init() function for loading the model and the run() function for processing inference requests. The community discussion shows 67% support for option A, with references to Microsoft documentation confirming that scoring scripts are used to customize model deployment. While deployment definition (D) is mentioned by some users, the scoring script is the foundational component that defines the custom inference logic before deployment configuration.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are managing an Azure Machine Learning workspace. An MLflow model is already registered, and you plan to customize the inference logic for the deployment.
To deploy this MLflow model to a batch endpoint for batch inferencing, what is the first component you must create?
A
scoring script
B
deployment
C
environment
D
deployment definition
No comments yet.