A model serving endpoint is configured with autoscaling from 1 to 10 instances. The team notices that during a sudden spike, the endpoint returns errors for the first few seconds before scaling up. They want to eliminate these errors. What is the most effective configuration change?

Increase the maximum number of instances to 20.

Enable provisioned throughput mode.

Set the minimum number of instances to 5.

Increase the autoscaling threshold to scale out sooner.

A team has a model that is a scikit-learn pipeline. They have logged it with MLflow and want to deploy it for realtime inference. What is the correct way to create the serving endpoint?

Upload the model's pickle file to DBFS and reference the path.

Use the MLflow model's registered name and version in the endpoint configuration.

Use the Databricks CLI to deploy the model directly from the experiment.

Create a notebook that loads the model and run it as a job.

DatabricksCertified Machine Learning Associate

Domain 4Objective 5

Deploy and Query a Model for Realtime Inference MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 2)

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 18 practice questions to prepare you well beyond it. (estimate)

18questions here

4free pages

4concepts

Questions 6–10

6expert · hard
A model serving endpoint is configured with autoscaling from 1 to 10 instances. The team notices that during a sudden spike, the endpoint returns errors for the first few seconds before scaling up. They want to eliminate these errors. What is the most effective configuration change?
Select an answer first
7foundation · easy
Which Databricks Model Serving mode is designed for development and testing, where traffic is low and variable?
Select an answer first
8foundation · easy
A team needs to serve a model with predictable, high-volume traffic and requires consistent low latency. Which Databricks Model Serving mode is most appropriate?
Select an answer first
9foundation · easy
Which HTTP method is used to send a prediction request to a Databricks Model Serving endpoint?
Select an answer first
10application · medium
A team has a model that is a scikit-learn pipeline. They have logged it with MLflow and want to deploy it for realtime inference. What is the correct way to create the serving endpoint?
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 and Query a Model for Realtime Inference MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 2)

Questions 6–10

A model serving endpoint is configured with autoscaling from 1 to 10 instances. The team notices that during a sudden spike, the endpoint returns errors for the first few seconds before scaling up. They want to eliminate these errors. What is the most effective configuration change?

Which Databricks Model Serving mode is designed for development and testing, where traffic is low and variable?

A team needs to serve a model with predictable, high-volume traffic and requires consistent low latency. Which Databricks Model Serving mode is most appropriate?

Which HTTP method is used to send a prediction request to a Databricks Model Serving endpoint?

A team has a model that is a scikit-learn pipeline. They have logged it with MLflow and want to deploy it for realtime inference. What is the correct way to create the serving endpoint?

Keep studying — Section 4: Model Deployment