Quick Answer
The answer is to increase the number of max replicas. This configuration change directly reduces AutoML Vision inference latency during peak hours by enabling the Vertex AI Prediction endpoint to scale horizontally, distributing the inference load across additional compute instances and preventing request queuing or resource contention. On the Google Professional Machine Learning Engineer exam, this tests your understanding of autoscaling behavior for deployed models—specifically that increasing the max replica count allows the service to spin up more nodes under high throughput, while the min replica count only affects baseline capacity. A common trap is confusing min replicas (which reduce cold-start latency) with max replicas (which handle burst traffic). Remember the memory tip: “Max for the load, min for the cold.”
This PMLE practice question tests your understanding of architecting low-code ml solutions. This is a configuration task: choose the command set that satisfies every stated requirement. Small differences — like 'secret' vs 'password' or 'transport input ssh' vs 'all' — change whether the answer is correct. 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 deploys an AutoML Vision model for real-time defect detection. They notice high inference latency during peak hours. Which configuration change can help?
Reduce the model's input resolution
Why wrong: Wrong: May reduce latency but also accuracy; not best practice.
Use batch prediction
Why wrong: Wrong: Not real-time; would not solve online latency.
Enable model compression
Why wrong: Wrong: Helpful but not as direct as scaling replicas.
Increase the number of max replicas
Correct: Handles increased load with more parallelism.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Increase the number of max replicas
Increasing the number of max replicas allows the AutoML Vision endpoint to scale horizontally during peak hours, distributing the inference load across more compute instances. This directly reduces per-request latency by preventing queuing and resource contention, as the Vertex AI Prediction service can spin up additional replicas up to the configured maximum to handle higher throughput.
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.
Reduce the model's input resolution
Why it's wrong here
Wrong: May reduce latency but also accuracy; not best practice.
Use batch prediction
Why it's wrong here
Wrong: Not real-time; would not solve online latency.
Enable model compression
Why it's wrong here
Wrong: Helpful but not as direct as scaling replicas.
Increase the number of max replicas
Why this is correct
Correct: Handles increased load with more parallelism.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
Google Cloud often tests the misconception that reducing input resolution or enabling compression is a safe latency fix, but the PMLE exam expects you to recognize that AutoML Vision models are black-box optimized and that horizontal scaling via max replicas is the proper architectural response to real-time latency spikes.
Detailed technical explanation
Vertex AI Prediction uses a managed autoscaling mechanism based on CPU utilization or request count; increasing max replicas raises the ceiling for scaling, but the actual scaling decision is governed by the target utilization level (default 60%). Under the hood, each replica runs a container with the exported SavedModel, and the load balancer distributes requests across replicas using gRPC or HTTP, so adding replicas reduces the probability of any single instance being overloaded. In practice, for defect detection with high-resolution images, the bottleneck is often the model's forward pass on the GPU, so ensuring enough replicas (with GPU accelerators) is critical.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
An e-commerce site experiences heavy traffic on Black Friday and near-zero traffic during off-peak weeks. Rather than provisioning permanent large VMs, the team uses auto-scaling groups that add capacity automatically under load and reduce it overnight. Questions like this test whether you understand elasticity, availability zones, and cloud compute scaling patterns.
What to study next
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Architecting low-code ML solutions — study guide chapter
Learn the concepts, then practise the questions
Architecting low-code ML solutions practice questions
Targeted practice on this topic area only
All PMLE questions
506 questions across all exam domains
Google Professional Machine Learning Engineer study guide
Full concept coverage aligned to exam objectives
PMLE 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 PMLE questions linked to Scaling prototypes into ML models.
Practise PMLE questions linked to Automating and orchestrating ML pipelines.
Practise PMLE questions linked to Collaborating within and across teams to manage data and models.
Practise PMLE questions linked to Architecting low-code ML solutions.
Practise PMLE questions linked to Collaborating to manage data and models.
Practise PMLE questions linked to Serving and scaling models.
Practise PMLE questions linked to Monitoring ML solutions.
Practise PMLE questions linked to Solving business challenges with ML.
Practise PMLE questions linked to PMLE fundamentals.
Practise PMLE questions linked to PMLE scenario.
Practise PMLE questions linked to PMLE troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Architecting low-code ML solutions — This question tests Architecting low-code ML solutions — Read the scenario before looking for a memorised answer..
The correct answer is: Increase the number of max replicas — Increasing the number of max replicas allows the AutoML Vision endpoint to scale horizontally during peak hours, distributing the inference load across more compute instances. This directly reduces per-request latency by preventing queuing and resource contention, as the Vertex AI Prediction service can spin up additional replicas up to the configured maximum to handle higher throughput.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
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 PMLE 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 PMLE 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.