PMLE Serving and Scaling Models Practice Test 2 — 15 Questions

Question 1

An ML engineer is optimizing a large model for deployment on Vertex AI with GPU acceleration. They want to reduce model size and improve inference latency without significant accuracy loss. Which tool should they use?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Use Vertex AI Model Optimization with TensorRT.. Vertex AI Model Optimization with TensorRT is specifically designed to reduce model size and improve inference latency on NVIDIA GPUs by applying techniques like quantization, pruning, and graph optimizations. TensorRT optimizes the model for the target GPU architecture, enabling faster inference with minimal accuracy loss, which directly addresses the engineer's goals.

Answer

Use gcloud CLI to prune the model.

Answer

Use Cloud TPU for faster inference.

Answer

Use TensorFlow.js converter to optimize the model for web.

Question 2

A company is deploying multiple models on a single Vertex AI endpoint to reduce costs. Each model has different traffic patterns. Which configuration should they use?

Accepted Answer

Use a single endpoint with multiple deployed models and traffic allocation.. Vertex AI endpoints support deploying multiple models behind a single endpoint with traffic splitting, allowing you to route different percentages of requests to each model based on their traffic patterns. This reduces infrastructure costs compared to separate endpoints, as the endpoint's underlying compute resources are shared. Traffic allocation can be adjusted dynamically to match changing model usage without redeploying.

Answer

Use Cloud Run to serve each model as a separate service.

Answer

Deploy each model to separate endpoints and use a load balancer.

Answer

Use Vertex AI Matching Engine to serve models.

Question 3

A company wants to use Vertex AI Vector Search for real-time product recommendations based on user embeddings. They need to update the index frequently with new product embeddings without significant downtime. Which TWO options should they consider? (Choose 2)

Accepted Answer

Maintain two separate indexes: one for building and one for serving, and swap them after building.. Option A is correct because Vertex AI Vector Search supports a blue/green-style pattern where you build a new index while the current index continues serving, then swap the deployed index to the new one, minimizing downtime during frequent updates. Option B is correct because streaming updates let you add or modify embeddings incrementally in near real time without rebuilding the whole index, which suits frequently changing product embeddings. Option C is not ideal because daily full rebuilds cause stale data and require index rebuild/swap cycles rather than continuous freshness. Option D is wrong because increasing replicas improves query throughput and availability, not index update frequency. Option E is wrong because GPU endpoints accelerate serving/query performance, not the indexing update mechanism.

Answer

Use batch updates to rebuild the entire index daily.

Answer

Increase the number of replicas on the deployed index.

Answer

Use a GPU-powered endpoint for faster indexing.

Question 4

You have a Vertex AI endpoint serving a model with min replicas=2 and max replicas=10. You notice that during low traffic hours, the endpoint still runs 2 replicas, incurring costs. You want to reduce costs to zero when there is no traffic. What should you do?

Accepted Answer

Change min replicas to 0 and max replicas to 10.. Setting min replicas to 0 allows Vertex AI to scale down to zero instances when there is no traffic, eliminating costs during idle periods. The endpoint will automatically scale up from 0 to handle incoming requests, while max replicas=10 ensures it can handle peak load. This is the standard approach for cost optimization in Vertex AI endpoints.

Answer

Use a custom metric to trigger scaling down to zero.

Answer

Delete the endpoint when not in use and recreate it on demand.

Answer

Set max replicas to 0.

Question 5

You have a Vertex AI endpoint with autoscaling enabled. You notice that during traffic spikes, the endpoint takes a long time to scale up, causing prediction errors. What is the most effective solution?

Accepted Answer

Increase the minimum number of replicas to maintain a larger buffer.. Increasing the minimum number of replicas ensures that a baseline capacity is always running, so when traffic spikes occur, the endpoint already has enough replicas to handle the initial surge without waiting for autoscaling to add more. Autoscaling in Vertex AI adds replicas based on metrics like CPU utilization, but there is inherent latency in detecting the spike, provisioning new replicas, and warming them up. By maintaining a larger buffer of minimum replicas, you reduce the reliance on rapid scale-up during spikes, thereby minimizing prediction errors. This is the most effective solution because it directly addresses the cold-start delay of autoscaling.

Answer

Use a larger machine type to handle more requests per replica.

Answer

Reduce the target CPU utilization to trigger scaling earlier.

Answer

Increase the maximum number of replicas.

Question 6

You need to deploy a TensorFlow model to edge devices for real-time inference with minimal latency. The model is currently trained on Vertex AI. Which approach should you use?

Accepted Answer

Convert the model to TensorFlow Lite using the TF Lite converter, then deploy to edge devices via Vertex AI Edge Manager.. TensorFlow Lite is specifically designed for on-device inference on edge devices, offering reduced model size and optimized performance for low-latency, real-time scenarios. Vertex AI Edge Manager provides a managed service to deploy, monitor, and update models on edge devices, making it the ideal combination for this use case.

Answer

Export the model as a SavedModel and deploy it to Vertex AI Edge Manager using the Edge Manager API.

Answer

Deploy the model to Vertex AI endpoint and use Cloud IoT Core to stream data to the cloud for inference.

Answer

Use Vertex AI Model Optimization to quantize the model to INT8 and then deploy as a web service on a Raspberry Pi.

Question 7

You are using Vertex AI Vector Search to find nearest neighbors for a recommendation system. Your index is built on 10M embeddings and you need low-latency queries. You want to ensure that adding new embeddings does not require a full index rebuild. Which index type should you use?

Accepted Answer

ANN index with the 'streaming' update mode. The ANN index with 'streaming' update mode is correct because it supports real-time insertion of new embeddings without requiring a full index rebuild, which is essential for low-latency recommendation systems. This mode uses a separate unsearched buffer for new vectors and periodically merges them into the main index, enabling continuous updates while maintaining query performance.

Answer

Brute-force index (exact neighbor search)

Answer

ANN index with the 'batch' update mode

Answer

Tree-AH index

Question 8

You are deploying a model on Vertex AI and need to ensure high availability and low latency. Which THREE configurations should you implement?

Accepted Answer

Choose a machine type with GPUs for compute-intensive models.. Option A is correct because selecting a machine type with GPUs (e.g., NVIDIA T4, V100, or A100) provides the accelerated compute needed for compute-intensive models, directly reducing inference latency on Vertex AI. Option B is correct because enabling logging and monitoring on the Vertex AI endpoint (via Cloud Logging and Cloud Monitoring) lets you track latency, error rates, and resource utilization so you can detect and respond to availability issues. Option D is correct because deploying with min_replicas=2 and max_replicas=10 across multiple zones provides horizontal scaling and zonal redundancy, which is the core mechanism for high availability and consistent low latency under load. Option C is not required because a static IP on a custom endpoint does not improve availability or latency, and Vertex AI endpoints already provide managed DNS. Option E is incorrect because deploying to a single zone creates a single point of failure and does not guarantee lower network latency for a globally distributed user base.

Answer

Use a custom endpoint with a static IP address.

Answer

Deploy to a single zone to reduce network latency.

Question 9

A data science team has trained a custom TensorFlow model for real-time fraud detection. They need to deploy it on Vertex AI with minimal latency and support for multiple concurrent requests. The model requires a GPU for inference. Which machine type should they choose for the Vertex AI endpoint?

Accepted Answer

n1-standard-4 with NVIDIA T4. The n1-standard-4 with NVIDIA T4 provides the GPU acceleration required for real-time inference, while the n1 machine family supports GPU attachments on Vertex AI. The T4 GPU is optimized for low-latency inference workloads, and the n1-standard-4 offers sufficient CPU and memory for serving a custom TensorFlow model with multiple concurrent requests.

Answer

n2-standard-8

Answer

e2-standard-4

Answer

n1-highmem-4

Question 10

You have a Vertex AI endpoint serving a model for real-time predictions. The endpoint is configured with minReplicaCount=2 and maxReplicaCount=10. Over the past week, you notice that the actual number of replicas rarely exceeds 2, but the average CPU utilization is around 85%. You want to reduce costs without impacting performance. What should you do?

Accepted Answer

Decrease minReplicaCount to 1.. Decreasing minReplicaCount to 1 allows the endpoint to scale down to a single replica when traffic is low, reducing compute costs. Since the actual replica count rarely exceeds 2, the current minReplicaCount=2 forces at least two replicas to run continuously, even when one would suffice. With average CPU utilization at 85%, the model is already efficiently handling load, so scaling down to one replica will not impact performance while saving costs.

Answer

Increase minReplicaCount to 5.

Answer

Increase maxReplicaCount to 20.

Answer

Decrease the CPU utilization target to 50%

Question 11

You are using Vertex AI Matching Engine (Vector Search) to serve similarity search for an e-commerce product recommendation system. The index is updated daily with new product embeddings via a batch job. However, you notice that some new products are not appearing in the search results for up to 24 hours. You need to ensure that new products are discoverable within 1 hour of ingestion. What should you do?

Accepted Answer

Switch to a streaming update configuration for the index.. Vertex AI Matching Engine supports streaming updates to the index, which allows new embeddings to be added in near real-time (typically within minutes) without requiring a full batch rebuild. By switching to a streaming update configuration, new product embeddings become searchable within the 1-hour requirement, as the index is updated incrementally as data arrives.

Answer

Deploy multiple index endpoints and use traffic splitting.

Answer

Increase the frequency of the batch update job to run every 30 minutes.

Answer

Use a brute-force index instead of an ANN index.

Question 12

You need to deploy a model to a Vertex AI endpoint that can scale down to zero when there are no requests to minimize costs. Which feature should you enable?

Accepted Answer

Enable autoscaling with minReplicaCount=0. Vertex AI endpoints support autoscaling with a `minReplicaCount` of 0, which allows the endpoint to scale down to zero instances when there are no incoming requests, thereby minimizing costs. This feature is specifically designed for serverless model serving, where the endpoint automatically scales up from zero when traffic arrives and scales down to zero during idle periods.

Answer

Deploy the model to a Compute Engine instance and use instance groups.

Answer

Use a custom metric for autoscaling

Answer

Set maxReplicaCount to 0

Question 13

You need to deploy a model that requires a large amount of memory (over 200 GB) for inference. The model is a custom PyTorch model. Vertex AI endpoints have machine type limitations. Which TWO actions can you take to handle this memory requirement? (Choose 2 correct answers)

Accepted Answer

Use a machine type from the n1-highmem series, such as n1-highmem-32 (208 GB) or higher.. Option A is correct because Vertex AI prediction supports the n1-highmem machine series, and n1-highmem-32 provides 208 GB of RAM, which exceeds the 200 GB requirement for hosting this custom PyTorch model on an endpoint. Option C is correct because deploying the model in a custom container lets you control the runtime environment and apply memory optimizations (for example, loading weights in lower precision, using quantization, or efficient inference libraries) so the model fits within the available memory. Option B is not appropriate because Vertex AI does not automatically shard a single model across multiple replicas; replicas each load a full copy of the model, so splitting the model across them is not a supported mechanism. Option D does not solve the problem because batch prediction still requires a machine with enough memory to load and run the model, and it changes the serving pattern rather than addressing the memory constraint. Option E is incorrect because Cloud Run's maximum memory (32 GB) is far below the 200 GB requirement and it is not designed for large-model GPU/CPU inference at this scale.

Answer

Use multiple replicas and split the model across them.

Answer

Use batch prediction instead of online prediction.

Answer

Deploy the model on Cloud Run with 32 GB memory.

Question 14

What is the primary purpose of Vertex AI Model Optimization (formerly Model Garden)?

Accepted Answer

To optimize models for deployment by quantizing and compiling them. Vertex AI Model Optimization automatically quantizes and compiles models to reduce latency and memory footprint for serving.

Answer

To monitor model performance in production

Answer

To search for optimal hyperparameters

Answer

To train models faster using distributed training

Question 15

An engineer needs to deploy multiple models on a single Vertex AI endpoint with separate traffic allocations. What is the maximum number of deployed models that can be assigned traffic on one endpoint?

Accepted Answer

5. Vertex AI endpoints allow up to 5 deployed models to receive traffic simultaneously, with each model assigned a traffic percentage that sums to 100%. This limit ensures predictable routing and resource management, preventing overcommitment of the endpoint's underlying infrastructure.

Answer

2

Answer

Unlimited

Answer

10