Quick Answer
The answer is to use a Vertex AI Endpoint with GPU and configure autoscaling to zero when idle. This strategy is correct because Vertex AI Endpoints support GPU-accelerated inference with native autoscaling, including the ability to scale down to zero replicas when there is no traffic, which directly achieves the goal of vertex ai gpu autoscaling to zero cost. On the Google Professional Data Engineer exam, this tests your understanding of cost optimization for ML workloads, often appearing as a scenario where a candidate must choose between always-on GPU instances, batch prediction, or serverless endpoints—the trap being that many assume GPUs cannot scale to zero. A key memory tip: think “GPU idle = zero replicas, zero cost,” and remember that Vertex AI’s managed endpoints handle the scaling policy automatically, so you only pay for active inference.
This PDE practice question tests your understanding of operationalizing machine learning models. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A company uses Vertex AI to serve a model that requires GPU for inference. They want to minimize cost while handling variable traffic. Which strategy should they use?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue: "minimum / minimize"
Why it matters: Asks for the least resource use — fewest addresses, smallest subnet, lowest overhead. Eliminate over-provisioned options even if they would technically work.
Deploy the model to Cloud Functions with GPU
Why wrong: Cloud Functions does not support GPU.
Use a Vertex AI Endpoint with GPU and configure auto-scaling to zero when idle
Scales to zero reduces cost.
Use Vertex AI Batch Prediction with GPU
Why wrong: Not real-time.
Use a Vertex AI Endpoint with GPU with a fixed number of replicas
Why wrong: Fixed replicas waste resources when idle.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Use a Vertex AI Endpoint with GPU and configure auto-scaling to zero when idle
Option B is correct because Vertex AI Endpoints support GPU-accelerated inference with autoscaling, including the ability to scale down to zero replicas when there is no traffic. This minimizes cost by only incurring GPU charges during active inference, while still handling variable traffic through dynamic scaling.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
Deploy the model to Cloud Functions with GPU
Why it's wrong here
Cloud Functions does not support GPU.
Use a Vertex AI Endpoint with GPU and configure auto-scaling to zero when idle
Why this is correct
Scales to zero reduces cost.
Clue confirmation
The clue word "minimum / minimize" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
Use Vertex AI Batch Prediction with GPU
Why it's wrong here
Not real-time.
Use a Vertex AI Endpoint with GPU with a fixed number of replicas
Why it's wrong here
Fixed replicas waste resources when idle.
Common exam traps
Google Cloud often tests the misconception that serverless services like Cloud Functions can support GPU acceleration, when in reality GPU compute requires dedicated infrastructure like Vertex AI Endpoints or GKE.
Detailed technical explanation
Vertex AI Endpoints use the same underlying infrastructure as Google Kubernetes Engine (GKE) with GPU nodes, but managed by Vertex AI. Autoscaling to zero is achieved by setting the minReplicaCount to 0 in the endpoint deployment configuration, which triggers the release of GPU resources when no requests are received, and cold starts are mitigated by setting a suitable maxReplicaCount and using traffic splitting for gradual ramp-up.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
A startup's cloud architect reviews their monthly bill and notices costs are higher than expected for a long-running batch job. Switching from on-demand instances to Reserved Instances — or using Spot/Preemptible VMs — can reduce compute costs by up to 72 %. Questions like this test whether you understand the tradeoffs between commitment, flexibility, and cost across cloud pricing models.
What to study next
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Operationalizing machine learning models — study guide chapter
Learn the concepts, then practise the questions
Operationalizing machine learning models practice questions
Targeted practice on this topic area only
All PDE questions
499 questions across all exam domains
Google Professional Data Engineer study guide
Full concept coverage aligned to exam objectives
PDE practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Practise PDE questions linked to Designing data processing systems.
Practise PDE questions linked to Building and operationalizing data processing systems.
Practise PDE questions linked to Operationalizing machine learning models.
Practise PDE questions linked to Ensuring solution quality.
Practise PDE questions linked to PDE fundamentals.
Practise PDE questions linked to PDE scenario.
Practise PDE questions linked to PDE troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Operationalizing machine learning models — This question tests Operationalizing machine learning models — Read the scenario before looking for a memorised answer..
The correct answer is: Use a Vertex AI Endpoint with GPU and configure auto-scaling to zero when idle — Option B is correct because Vertex AI Endpoints support GPU-accelerated inference with autoscaling, including the ability to scale down to zero replicas when there is no traffic. This minimizes cost by only incurring GPU charges during active inference, while still handling variable traffic through dynamic scaling.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Yes — watch for: "minimum / minimize". Asks for the least resource use — fewest addresses, smallest subnet, lowest overhead. Eliminate over-provisioned options even if they would technically work.
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Last reviewed: Jun 30, 2026
This PDE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PDE exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.