The answer is quantizing the model from FP32 to INT8 and using a GPU accelerator, as these two actions directly reduce prediction latency on Vertex AI without altering the model architecture. Quantization shrinks the model’s numerical precision, cutting memory footprint and speeding up matrix operations, while a GPU accelerator parallelizes computation for faster inference, especially for deep learning models. On the Google Professional Machine Learning Engineer exam, this question tests your understanding of latency optimization trade-offs—a common trap is confusing network latency (solved by multiregion deployment) with prediction latency, which is the time the model itself takes to compute. Remember that increasing batch size or downsizing the machine type can actually increase per-request latency, so focus on hardware acceleration and precision reduction. A handy memory tip: “GPU and INT8—faster inference, no architecture rewrite.”
PMLE Serving and scaling models Practice Question
This PMLE practice question tests your understanding of serving and scaling 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.
Which TWO actions can help reduce prediction latency for a model deployed on Vertex AI Endpoint without changing the model architecture?
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Attach a GPU accelerator to the endpoint's machine type.
Options A and D are correct. Option A (GPU accelerator) can significantly speed up inference for deep learning models. Option D (model quantization) reduces model size and inference time. Option B (increasing batch size) increases latency per request. Option C (multiregion deployment) reduces network latency but not prediction latency. Option E (smaller machine type) may increase latency.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Increase the batch size of prediction requests.
Why it's wrong here
Larger batches increase latency due to processing time.
✓
Attach a GPU accelerator to the endpoint's machine type.
Why this is correct
GPU reduces computation time for neural networks.
Related concept
Read the scenario before looking for a memorised answer.
✓
Quantize the model from FP32 to INT8.
Why this is correct
Quantization reduces model size and speeds up inference.
Related concept
Read the scenario before looking for a memorised answer.
✗
Deploy the model in multiple regions and use global load balancing.
Why it's wrong here
Reduces network latency, not model inference latency.
✗
Use a smaller machine type to reduce complexity.
Why it's wrong here
Smaller machines have less CPU/memory, increasing latency.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Many certification questions include familiar terms but test a specific constraint. Read the exact wording before choosing an answer that is generally true but wrong for this case.
Detailed technical explanation
How to think about this question
This question should be treated as a scenario, not a definition check. Identify the problem, the constraint and the best action. Then compare each option against those facts.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
Use explanations to understand the rule behind the answer.
TExam Day Tips
→Underline the problem statement mentally.
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A healthcare organisation deploys an application with a public-facing web tier and a private database tier. The database subnet has no public IP and only accepts connections from the web tier's security group. Questions like this test whether you can design cloud network isolation using VNets/VPCs, subnets, and security group rules.
What to study next
Got this wrong? Here's your next step.
Identify which PMLE exam domain this question belongs to, then review the specific concept being tested. Practise related questions in that domain and focus on understanding why each wrong answer is tempting — not just why the correct answer is right.
Serving and scaling models — This question tests Serving and scaling models — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Attach a GPU accelerator to the endpoint's machine type. — Options A and D are correct. Option A (GPU accelerator) can significantly speed up inference for deep learning models. Option D (model quantization) reduces model size and inference time. Option B (increasing batch size) increases latency per request. Option C (multiregion deployment) reduces network latency but not prediction latency. Option E (smaller machine type) may increase latency.
What should I do if I get this PMLE question wrong?
Identify which PMLE exam domain this question belongs to, then review the specific concept being tested. Practise related questions in that domain and focus on understanding why each wrong answer is tempting — not just why the correct answer is right.
What is the key concept behind this question?
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 →
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. Which TWO actions can help reduce the latency of online prediction requests for a deep learning model served on Vertex AI?
easy
A.Increase the number of CPU vCPUs per machine.
B.Set min_replica_count to 0 to avoid idle instances.
✓ C.Use a GPU accelerator for the deployed model.
D.Decrease the number of replicas to reduce resource contention.
✓ E.Enable request batching to process multiple inputs together.
Why C: Using a GPU accelerator speeds up inference, and batching requests reduces overhead per request. Minimizing replicas doesn't help latency; increasing CPU doesn't always help if GPU is better.
Variation 2. You deploy a PyTorch model to Vertex AI Online Prediction. After deployment, you observe that inference latency is approximately 300ms per request, but the desired SLA is under 100ms. The model uses a custom container with CPU only. Which action is most likely to reduce latency to the target?
medium
✓ A.Deploy the model on a machine with a GPU accelerator.
B.Switch from online prediction to batch prediction.
C.Increase the min_replica_count to ensure more instances are always available.
D.Use a smaller machine type with less CPU to reduce overhead.
Why A: Enabling GPU acceleration can significantly speed up inference for deep learning models. Adding more CPU instances may help with throughput but not per-request latency. Switching to batch prediction changes the use case, and using a smaller instance type might reduce latency if the model is small, but GPU is more impactful.
Last reviewed: Jun 24, 2026
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.
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.