What is the purpose of scale-out configuration for a model endpoint?

To define the input schema for the model's predictions

To control the number of instances that serve traffic to handle varying load

To specify the programming language used to write the model code

To set the logging level for endpoint monitoring

A team has a custom model that uses a custom Python module that is not available on PyPI. They have the module as a .py file. They want to deploy the model to an endpoint. What should they do?

Package the .py file as a wheel and install it via the conda environment.

Include the .py file in the MLflow model artifacts and reference it in the model code.

Use a custom Docker image that includes the .py file.

Upload the .py file to DBFS and add it to the Python path in the conda environment.

A team wants to deploy a model endpoint that can handle a predictable baseline load with occasional spikes. They want to minimize cost while ensuring availability. What should they configure?

Disable auto-scaling and manually adjust the instance count based on expected load.

Use a single instance and rely on the endpoint's built-in queuing to handle spikes.

Set a fixed number of instances high enough to handle the maximum expected load.

Set a minimum number of instances for the baseline and enable auto-scaling to handle spikes.

DatabricksCertified Machine Learning Associate

Domain 4Objective 2

Deploy a Custom Model to a Model Endpoint MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 5)

Part of the Section 4: Model Deployment domain, which makes up ~30% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~11–18 in this domain), expect 2–3 from this objective — we provide 27 practice questions to prepare you well beyond it. (estimate)

27questions here

6free pages

7concepts

Questions 21–25

21foundation · easy
What is the purpose of scale-out configuration for a model endpoint?
Select an answer first
22expert · hard
A team has a custom model that uses a custom Python module that is not available on PyPI. They have the module as a .py file. They want to deploy the model to an endpoint. What should they do?
Select an answer first
23foundation · easy
Which interface can be used to create a model endpoint in Databricks?
Select an answer first
24application · medium
A team wants to deploy a model endpoint that can handle a predictable baseline load with occasional spikes. They want to minimize cost while ensuring availability. What should they configure?
Select an answer first
25foundation · easy
Which Databricks tool can be used to invoke a model endpoint programmatically?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to MACHINE-LEARNING-ASSOCIATE

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Databricks. “MACHINE-LEARNING-ASSOCIATE” is a trademark of its owner, used for identification only.

Deploy a Custom Model to a Model Endpoint MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 5)

Questions 21–25

What is the purpose of scale-out configuration for a model endpoint?

A team has a custom model that uses a custom Python module that is not available on PyPI. They have the module as a .py file. They want to deploy the model to an endpoint. What should they do?

Which interface can be used to create a model endpoint in Databricks?

A team wants to deploy a model endpoint that can handle a predictable baseline load with occasional spikes. They want to minimize cost while ensuring availability. What should they configure?

Which Databricks tool can be used to invoke a model endpoint programmatically?

Keep studying — Section 4: Model Deployment