Question 260 of 990
mediumMultiple SelectObjective-mapped
Optimizing Cost and Performance for Large Model on Vertex AI
A data science team has trained a large deep learning model using Vertex AI Workbench. They want to deploy it to Vertex AI Prediction for online serving. The model is stored in a custom container with a Python-based web server. Which TWO actions should the team take to ensure optimal performance and cost?
Quick Answer
The answer is to enable autoscaling with a minimum number of replicas and to use GPU machine types for the deployment. This combination directly addresses cost performance optimization for Vertex AI prediction with large models because GPUs provide the parallel compute power needed to reduce inference latency, while autoscaling ensures you only pay for the resources you actually use during demand spikes, avoiding over-provisioning. On the Google Professional Machine Learning Engineer exam, this scenario tests your understanding of balancing serving efficiency with cost control—a common trap is choosing only one action, such as scaling without hardware acceleration, which fails to optimize performance. Remember the pairing: GPUs handle the heavy lifting, and autoscaling handles the wallet. A useful memory tip is “GPU for speed, scale for need.”
⚠ Common exam trap
Google Cloud often tests the misconception that health check endpoints should be the same as the prediction endpoint, but in practice, health checks must be lightweight and separate to avoid false positives and resource exhaustion.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Request GPU machine types for the prediction nodes.
B is correct because deep learning models, especially large ones, benefit significantly from GPU acceleration for online inference due to their parallel processing capabilities. Vertex AI Prediction supports GPU machine types, and using them reduces latency and improves throughput for compute-intensive model serving, which is critical for optimal performance.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Configure the model to use a larger batch size for inference.
Why it's wrong here
Batch size is a model-level optimization, not a deployment configuration on Vertex AI Prediction.
- ✓
Request GPU machine types for the prediction nodes.
Why this is correct
Deep learning models typically require GPUs for low-latency inference.
- ✗
Set the container's health check path to '/predict'.
Why it's wrong here
The health check path should be a lightweight endpoint like '/health', not the prediction endpoint.
- ✗
Use a global load balancer to distribute traffic across regions.
Why it's wrong here
A regional endpoint is preferred for lower latency; a global load balancer doesn't directly affect vCPU usage.
- ✓
Enable autoscaling with a minimum number of replicas.
Why this is correct
Autoscaling adjusts the number of replicas based on traffic, reducing cost during low demand.
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 →
Same concept, more angles
1 more way this is tested on PMLE
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. A data science team deploys a PyTorch model using Vertex AI Prediction. The model requires GPU for inference, but they notice high costs and underutilized GPUs during off-peak hours. What is the most cost-effective solution?
medium- A.Move the model to Cloud Functions
- B.Use a GPU instance with a fixed number of replicas
- ✓ C.Use a GPU instance with min replicas=0 and autoscaling
- D.Switch to a CPU-only machine type
Why C: Setting min replicas to 0 allows Vertex AI Prediction to scale down to zero instances during off-peak hours, eliminating GPU costs when no requests are being served. Combined with autoscaling, the deployment will spin up GPU-backed instances on demand only when traffic arrives, directly addressing the underutilization issue while maintaining low latency for inference requests.
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.