PMLE Serving and Scaling Models Practice Test 6 — 15 Questions

Question 1

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)

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

Accepted Answer

Use a machine type from the n1-highmem series, such as n1-highmem-32 (208 GB) or higher.. The n1-highmem-32 machine type provides 208 GB of memory, which meets the requirement of over 200 GB. Vertex AI endpoints support this machine series, allowing you to deploy a custom PyTorch model with sufficient RAM for inference without modification.

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 2

A machine learning engineer wants to deploy a trained model to Vertex AI for online predictions. Which Vertex AI resource is required to serve the model and provide an endpoint URL?

Accepted Answer

Vertex AI Endpoint. Vertex AI Endpoint is the required resource to deploy a trained model for online predictions, as it provides a dedicated endpoint URL that accepts prediction requests and routes them to the model. Without an endpoint, the model cannot be accessed via HTTP/HTTPS for real-time inference, which is the core requirement for online serving.

Answer

Vertex AI Pipeline

Answer

Vertex AI Model Registry

Answer

Vertex AI Feature Store

Question 3

A company needs to serve a high-throughput prediction service with strict latency requirements. They want to minimize cold starts and ensure consistent performance. Which endpoint configuration is most appropriate?

Accepted Answer

Set min_replicas to an estimated baseline and max_replicas to a higher number. Setting min_replicas to an estimated baseline ensures that a minimum number of instances are always running, eliminating cold starts for baseline traffic. Setting max_replicas to a higher number allows the service to scale up to handle traffic spikes while maintaining consistent performance. This configuration balances cost and latency by avoiding the overhead of scaling from zero while still accommodating bursts.

Answer

Set min_replicas and max_replicas equal to a fixed number

Answer

Set min_replicas to 0 and max_replicas to a high number

Answer

Do not set min_replicas; let Vertex AI automatically determine

Question 4

A data scientist wants to perform A/B testing between two model versions deployed on the same Vertex AI endpoint. They need to route 10% of traffic to the challenger model. Which approach should they use?

Accepted Answer

Deploy both models to the same endpoint and set traffic_split to 90 for champion and 10 for challenger. Vertex AI endpoints support traffic splitting directly, allowing you to route a percentage of requests to different model versions deployed on the same endpoint. By setting `traffic_split` to 90 for the champion and 10 for the challenger, the data scientist can perform online A/B testing without additional infrastructure. This is the simplest and most cost-effective approach, as it avoids managing separate endpoints or load balancers.

Answer

Use Vertex AI Experiments to compare models offline, then deploy the winner

Answer

Deploy the challenger model to a separate endpoint and use a load balancer to split traffic

Answer

Update the champion model with a new version and use model version aliases

Question 5

A team is deploying a large PyTorch model for online inference. They want to use NVIDIA Triton Inference Server to optimize serving performance. How can they integrate Triton with Vertex AI?

Accepted Answer

Package the model with Triton in a custom container and deploy it to Vertex AI. Vertex AI supports custom containers; you can build a Docker image with Triton Inference Server and deploy it as a model on Vertex AI.

Answer

Vertex AI automatically uses Triton for all PyTorch models

Answer

Deploy the model to GKE and use Vertex AI as a frontend

Answer

Use a prebuilt Vertex AI PyTorch container that includes Triton

Question 6

A company needs to run batch predictions on 10 TB of data stored in Cloud Storage. The predictions should be written to BigQuery. Which approach should they use?

Accepted Answer

Create a Vertex AI Batch Prediction job with GCS input and BigQuery output. Vertex AI Batch Prediction natively supports reading input from Cloud Storage and writing predictions directly to BigQuery, making it the most efficient and fully managed solution for large-scale batch inference on 10 TB of data. This approach avoids the complexity of custom infrastructure or per-record model calls, leveraging Vertex AI's optimized batch processing pipeline.

Answer

Export the model to Cloud Functions and trigger on file upload

Answer

Use Vertex AI Online Prediction with a batch job

Answer

Use Dataflow to read from GCS and write to BigQuery, calling the model for each record

Question 7

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 8

A company uses Vertex AI Matching Engine for a product recommendation system. They need to update the index with new product embeddings every hour, but the index is used for online queries with low latency. Which index update strategy should they use?

Accepted Answer

Use streaming updates to insert new embeddings incrementally. Streaming updates in Vertex AI Matching Engine allow incremental insertion of new embeddings into an existing index without rebuilding it. This satisfies the requirement for hourly updates while maintaining low-latency online queries, as the index remains available and consistent during the update process.

Answer

Use a hybrid approach with batch for daily full rebuild and streaming for hourly

Answer

Use batch updates to replace the index every hour

Answer

Recreate the index from scratch each hour

Question 9

A team has deployed a model on Vertex AI and wants to cache frequent identical prediction requests to improve latency and reduce cost. Which Google Cloud service should they use?

Accepted Answer

Cloud Memorystore. Cloud Memorystore (Redis) can be used as a cache. The application hashes the request and checks the cache before calling the model.

Answer

Cloud Bigtable

Answer

Cloud CDN

Answer

Cloud SQL

Question 10

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

Question 11

A company wants to deploy a TensorFlow model on edge devices for real-time inference without internet connectivity. Which Vertex AI service should they use to manage the deployment?

Accepted Answer

Vertex AI Edge Manager. Vertex AI Edge Manager allows you to deploy models to edge devices and manage them centrally.

Answer

TensorFlow Lite Converter

Answer

Vertex AI Endpoint

Answer

AI Platform Prediction (legacy)

Question 12

Which machine type is most suitable for a Vertex AI endpoint serving a GPU-accelerated model?

Accepted Answer

n1-standard-4 with attached GPU. Vertex AI endpoints require a machine type that supports GPU acceleration, and the n1-standard-4 with an attached GPU provides the necessary CPU-to-GPU balance for inference workloads. The n1 series supports GPU attachments via the `accelerator` configuration, enabling CUDA-based model serving, while the e2 series and n1-highmem-8 without GPU cannot leverage GPU acceleration.

Answer

e2-standard-4

Answer

n1-highmem-8

Answer

n1-standard-4

Question 13

A company uses Vertex AI Vector Search for similarity search. They have a dataset of 10 million 512-dimensional vectors. Which index type should they choose for lowest latency at high recall?

Accepted Answer

Approximate nearest neighbor (ANN) index with Scann. For a dataset of 10 million 512-dimensional vectors, a brute-force (flat) index would be far too slow for low-latency queries. Approximate Nearest Neighbor (ANN) with ScaNN (Scalable Nearest Neighbors) is specifically designed by Google for high-dimensional vector search, offering sub-linear query time while maintaining high recall through techniques like anisotropic quantization and tree-based partitioning. This makes it the optimal choice for balancing latency and recall at this scale.

Answer

Brute-force (flat) index

Answer

Tree-based index

Answer

Hashing-based index

Question 14

A company needs to reduce inference latency for their online prediction service on Vertex AI. Which two actions would help? (Choose 2)

Accepted Answer

Deploy the model on a GPU-enabled machine. Deploying the model on a GPU-enabled machine significantly accelerates matrix operations and parallel computations inherent in deep learning inference, directly reducing per-request latency. Option C is correct because model quantization reduces the precision of model weights (e.g., from FP32 to INT8), which decreases memory footprint and speeds up computation, especially on compatible hardware like TPUs or GPUs.

Answer

Increase the maximum number of replicas

Answer

Use a smaller machine type with less memory

Answer

Enable autoscaling with a lower target CPU utilization

Question 15

A team wants to deploy a model on Vertex AI Edge Manager for offline inference on edge devices. Which three steps are required? (Choose 3)

Accepted Answer

Package the model and deploy using Vertex AI Edge Manager. The model must be in a format compatible with edge devices (TFLite/ONNX), and Edge Manager requires packaging and deploying the model to the device.

Answer

Enable Vertex AI Model Monitoring

Answer

Create a Vertex AI Endpoint with HTTP endpoint