Google Professional Machine Learning Engineer

Get started today

Ultimate access to all questions.

Explanation:

The correct answer is C. Deploying the new model to the existing endpoint minimizes disruption to the application by avoiding any DNS changes. By setting the parentModel parameter, you maintain version lineage and can easily revert to a previous version if necessary. Additionally, Vertex AI allows for traffic control, so you can allocate 100% of the traffic to the new model, ensuring a smooth transition with minimal downtime.

Explanation:

Comments (0)

No comments yet.

Get started today

Ultimate access to all questions.

You are a machine learning engineer tasked with updating a machine learning model in a production environment using Vertex AI. Your current endpoint is live and serving traffic, and you need to deploy a new version of the model. The goal is to redirect all user traffic to the new model with minimal disruption to your application. How should you proceed?

Exam-Like

Last updated: February 24, 2026 at 14:03

Create a new endpoint
Create a new model. Set it as the default version. Upload the model to Vertex AI Model Registry
Deploy the new model to the new endpoint
Update Cloud DNS to point to the new endpoint

7.7%

Create a new endpoint
Create a new model. Set the parentModel parameter to the model ID of the currently deployed model and set it as the default version. Upload the model to Vertex AI Model Registry
Deploy the new model to the new endpoint, and set the new model to 100% of the traffic.

15.4%

Create a new model. Set the parentModel parameter to the model ID of the currently deployed model. Upload the model to Vertex AI Model Registry.
Deploy the new model to the existing endpoint, and set the new model to 100% of the traffic

62.5%

Create a new model. Set it as the default version. Upload the model to Vertex AI Model Registry
Deploy the new model to the existing endpoint

14.4%