What is the role of an autoscaling policy in model serving?

To automatically retrain the model when accuracy drops

To automatically adjust the number of serving instances based on load

To automatically update the model to the latest version

To automatically split traffic between model versions

What is the purpose of horizontal scaling for a model serving endpoint?

To increase the compute power of a single instance

To reduce the number of model versions

To change the hardware type of the endpoint

To add more instances to handle increased request volume

What is the purpose of graph optimization for a model?

To improve the model's accuracy on the test set

To add more training data to the model

To change the model's loss function

To simplify the computation graph to reduce inference time

What is the purpose of load testing a model serving endpoint?

To understand how the endpoint behaves under expected peak traffic conditions

To determine the model's accuracy on a test dataset

To automatically retrain the model with new data

Why is it important to keep previous model versions available in production?

To improve the accuracy of the new version

To allow for quick rollback if the new version performs poorly

To automatically retrain old versions

Google CloudProfessional Machine Learning Engineer

Domain 4Objective 2

Scaling Online Model Serving PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice Questions (Page 7)

Part of the Serving and scaling models domain, which accounts for ~20% of the PROFESSIONAL-MACHINE-LEARNING-ENGINEER exam.

37questions here

8free pages

14concepts

~20%of the exam

14 Concepts in This Objective

Feature Store fundamentals
Serving features from Feature Store
Feature Store configuration and monitoring
Public and private endpoints
Deploying models to endpoints
Endpoint security and access control
Hardware selection for serving
Hardware optimization and cost trade-offs
Scaling serving infrastructure
Containerized serving and inference platforms
Throughput and latency management
Model tuning for production
Serving-specific model optimization
Production model lifecycle management

Questions 31–35

31foundation · easy
What is the role of an autoscaling policy in model serving?
Select an answer first
32foundation · easy
What is the purpose of horizontal scaling for a model serving endpoint?
Select an answer first
33foundation · easy
What is the purpose of graph optimization for a model?
Select an answer first
34foundation · easy
What is the purpose of load testing a model serving endpoint?
Select an answer first
35foundation · easy
Why is it important to keep previous model versions available in production?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to PROFESSIONAL-MACHINE-LEARNING-ENGINEER

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 Google Cloud. “PROFESSIONAL-MACHINE-LEARNING-ENGINEER” is a trademark of its owner, used for identification only.