PMLE Serving and Scaling Models Practice Test 7 — 15 Questions

Question 1

An ML engineer needs to update a model deployed on a Vertex AI endpoint without downtime. They want to gradually shift traffic to the new version while monitoring for errors. What is the correct procedure?

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

Accepted Answer

Deploy the new model to the same endpoint with 0% traffic initially, then gradually increase traffic while monitoring.. Vertex AI supports deploying multiple models to the same endpoint and splitting traffic via a deployed model's traffic percentage. The correct canary procedure is to deploy the new model version to the existing endpoint with 0% traffic, then gradually increase its traffic share while monitoring error rates and latency. This avoids downtime and enables safe rollback by shifting traffic back to the old version.

Answer

Use a canary deployment by deploying to a separate endpoint and using a load balancer with weighted routing.

Answer

Deploy the new model to a new endpoint, then update DNS to point to the new endpoint.

Answer

Delete the old model and deploy the new one with the same endpoint.

Question 2

An organization is deploying a mission-critical model on Vertex AI Endpoints. They need to ensure high availability and meet a strict SLO of 99.9% uptime. Which THREE steps should they take? (Choose 3)

Accepted Answer

Set minReplicas to at least 2 to ensure redundancy within a region.. Option B is correct because setting minReplicas to at least 2 on a Vertex AI Endpoint ensures that multiple model server replicas run within the region, so a single replica failure or rolling update does not cause an outage and the 99.9% SLO can be maintained. Option D is correct because deploying the endpoint in multiple regions provides geographic redundancy, so a regional outage of Vertex AI or its underlying infrastructure does not take the mission-critical model offline. Option E is correct because configuring health checks (Vertex AI endpoint health checks/readiness probes) lets the service detect unhealthy replicas and route traffic away from or replace them, preserving availability. Option A is not appropriate because Cloud CDN caches HTTP responses at the edge and does not address the availability of the Vertex AI prediction backend or its SLO. Option C is not appropriate because using a single large instance creates a single point of failure and provides no redundancy, which works against high availability.

Answer

Use Cloud CDN to cache responses.

Answer

Use a single large instance instead of multiple small ones.

Question 3

Which TWO of the following can be used as input sources for Vertex AI batch prediction jobs? (Choose 2)

Accepted Answer

BigQuery. Option C (BigQuery) is correct because Vertex AI batch prediction jobs natively accept a BigQuery table as the input source, specified via the bigQuerySource field in the BatchPredictionJob, allowing you to run predictions directly against tabular data stored in BigQuery. Option E (Cloud Storage) is correct because Vertex AI batch prediction jobs also accept input files (such as JSONL, CSV, or TFRecord) stored in a Cloud Storage bucket, specified via the gcsSource field with a URI like gs://bucket/file.jsonl. Options A (Cloud Firestore), B (Cloud SQL), and D (Cloud Spanner) are not valid input sources for Vertex AI batch prediction; these are operational databases that are not directly supported as batch prediction inputs, so you would need to export their data to BigQuery or Cloud Storage first.

Answer

Cloud Firestore

Answer

Cloud SQL

Answer

Cloud Spanner

Question 4

You are deploying a model to a Vertex AI endpoint and need to minimize latency for online predictions. Which machine type should you choose?

Accepted Answer

n1-standard-2 with NVIDIA Tesla T4. For online predictions with minimal latency, a machine type with a GPU is essential because it accelerates model inference. The n1-standard-2 with NVIDIA Tesla T4 provides GPU acceleration, which significantly reduces latency compared to CPU-only instances. The other options lack GPUs and are not optimized for low-latency inference.

Answer

e2-standard-2

Answer

n1-standard-2

Answer

n1-highmem-2

Question 5

You need to perform batch predictions on 10 TB of data stored in BigQuery using Vertex AI. The model requires some preprocessing that cannot be expressed in SQL. What is the most scalable approach?

Accepted Answer

Use Dataflow to read from BigQuery, perform preprocessing, write results to GCS, then run Vertex AI batch prediction job with GCS source.. Dataflow (Apache Beam) provides a fully managed, auto-scaling, serverless execution environment that can read from BigQuery, apply arbitrary Python/Java preprocessing logic (e.g., feature engineering, normalization) that cannot be expressed in SQL, and write the preprocessed results to Cloud Storage (GCS). Vertex AI batch prediction can then read from GCS as input, making this the most scalable approach for 10 TB of data without requiring custom model container changes or manual data movement.

Answer

Use a Cloud Function to preprocess each row and write to a new BigQuery table, then run batch prediction.

Answer

Use Vertex AI batch prediction with BigQuery source and include preprocessing logic in the model container.

Answer

Export BigQuery data to CSV, run a local Python script for preprocessing, then upload to GCS and start a batch prediction job.

Question 6

You are using Vertex AI Vector Search for a product recommendation system. Your index is updated with new embeddings every hour. To minimize query latency while keeping the index fresh, what should you do?

Accepted Answer

Use streaming updates to insert new embeddings into the deployed index.. Vertex AI Vector Search supports streaming updates that let you insert, update, or delete datapoints in a deployed index without rebuilding it, so queries stay low-latency while the index remains fresh. This is the intended mechanism for near-real-time freshness with minimal disruption. Batch rebuilds and redeployments cause downtime and latency spikes, which the question explicitly asks to avoid.

Answer

Rebuild the entire index hourly as a batch job and redeploy it.

Answer

Create a new index each hour and use traffic splitting to gradually shift traffic.

Answer

Use a brute-force index instead of ANN to ensure accuracy after updates.

Question 7

You are A/B testing a new model version (challenger) against the current version (champion) on Vertex AI. You want to gradually shift traffic from champion to challenger while measuring business metrics. Which approach should you use?

Accepted Answer

Deploy both models to the same endpoint and use the traffic split feature to allocate percentages.. Vertex AI endpoints natively support traffic splitting between multiple deployed models on the same endpoint, allowing you to assign a percentage of prediction traffic to the champion and challenger. This is the built-in, supported mechanism for gradual rollouts and A/B experiments, and it integrates with Vertex AI's monitoring so you can measure business metrics per model version.

Answer

Deploy the challenger to a separate endpoint and use a load balancer to route a percentage of requests.

Answer

Use Cloud Armor to route traffic based on headers.

Answer

Create a new endpoint for the challenger and gradually shift DNS records.

Question 8

You need to serve multiple models on a single Vertex AI endpoint to reduce costs. How can you achieve this?

Accepted Answer

Use Vertex AI Prediction with multi-model serving by deploying multiple models to one endpoint with traffic splits.. Vertex AI Prediction supports multi-model serving, allowing you to deploy multiple models to a single endpoint and use traffic splits to route a percentage of requests to each model. This reduces costs by sharing underlying infrastructure (e.g., compute resources) across models, rather than provisioning separate endpoints or containers for each model.

Answer

Use Cloud Run to serve each model separately.

Answer

Package all models into a single container and deploy that container.

Answer

Deploy each model to its own endpoint and use a load balancer.

Question 9

You are deploying a PyTorch model on Vertex AI and want to use NVIDIA Triton Inference Server for optimal performance. You have built a custom container with Triton. Which serving configuration should you use?

Accepted Answer

Upload your Triton container to Container Registry and specify it as the prediction container in Vertex AI Model.. To deploy a custom Triton Inference Server container on Vertex AI, you upload your container to Artifact Registry (or Container Registry) and specify it as the prediction container when creating the Vertex AI Model resource. Vertex AI supports custom containers for prediction, allowing you to run Triton with your model artifacts. This is the standard approach for custom serving frameworks.

Answer

Deploy the model on GKE with Triton and expose via Istio.

Answer

Use the prebuilt Vertex AI PyTorch prediction container and set environment variables to enable Triton.

Answer

Use Vertex AI Model Optimization to automatically convert the model to TensorRT and deploy with built-in server.

Question 10

You are using Vertex AI batch prediction and your model requires preprocessing that involves joining two BigQuery tables. The preprocessing logic is complex and must be done before inference. How should you design the pipeline?

Accepted Answer

Use Dataflow to read from both BigQuery tables, perform the join and preprocessing, write the results to GCS, then run Vertex AI batch prediction with GCS source.. Dataflow (Apache Beam) is designed for complex, stateful data processing like joining two BigQuery tables and performing custom preprocessing. It can read from BigQuery, execute the join logic, and write the preprocessed results to Cloud Storage (GCS). Vertex AI batch prediction then reads the preprocessed data from GCS, which is the recommended pattern for non-trivial transformations before inference, as it decouples preprocessing from prediction and avoids resource contention.

Answer

Write a Cloud Composer workflow that runs the preprocessing and then triggers the batch prediction job.

Answer

Use Vertex AI batch prediction with a custom container that includes logic to read and join tables on the fly.

Answer

Use BigQuery to create a materialized view that joins the tables and directly use that as the batch prediction source.

Question 11

Your Vertex AI endpoint receives many identical prediction requests (same input features). You want to cache responses to reduce latency and cost. Which Google Cloud service should you use?

Accepted Answer

Cloud Memorystore for Redis. Cloud Memorystore for Redis is an in-memory data store that provides sub-millisecond latency, making it ideal for caching prediction responses. By caching identical prediction requests, you can reduce the number of calls to the Vertex AI endpoint, lowering latency and cost. Redis supports key-value storage with TTL, perfect for caching.

Answer

Cloud CDN

Answer

Bigtable

Answer

Cloud Storage with object versioning

Question 12

You are optimizing a model for deployment on Vertex AI using NVIDIA Triton Inference Server. Which TWO actions can you take to improve inference performance?

Accepted Answer

Use TensorRT to quantize the model to FP16 or INT8.. Option B is correct because TensorRT can quantize a model to FP16 or INT8, reducing precision and memory bandwidth requirements while leveraging NVIDIA GPU tensor cores, which directly lowers inference latency and increases throughput on Triton. Option D is correct because Triton's dynamic batching aggregates multiple incoming inference requests into a single batch at runtime, improving GPU utilization and throughput without requiring client-side batching. Option A is not appropriate because simply maxing out replicas can waste resources and does not guarantee better performance if the model is not compute-bound or if the machine lacks capacity. Option C is wrong because disabling model caching forces reloads and increases latency rather than improving inference performance. Option E is not ideal because adding vCPUs does not help GPU-bound inference and may not improve Triton throughput.

Answer

Increase the number of model replicas to the maximum.

Answer

Disable model caching to reduce memory usage.

Answer

Use a larger machine type with more vCPUs.

Question 13

You are designing a batch prediction pipeline using Vertex AI. The input data is 50 TB in CSV format on GCS. The model requires feature engineering that involves complex transformations (e.g., datetime parsing, one-hot encoding). Which TWO services or steps should you include in your pipeline?

Accepted Answer

Run Vertex AI batch prediction job with GCS source pointing to the processed TFRecord files.. Option D is correct because Dataflow is the managed, horizontally scalable Apache Beam service designed for large-scale ETL like 50 TB of CSV, and it can perform the required complex transformations (datetime parsing, one-hot encoding) before writing the engineered features to GCS in TFRecord format, which is an efficient binary format for ML training and prediction. Option C is correct because a Vertex AI batch prediction job can then consume those processed TFRecord files directly from GCS as its input source, letting the model run inference at scale without re-doing feature engineering. Option A is not appropriate because Cloud Functions is an event-driven, short-lived serverless compute service with limited memory and execution time, making it unsuitable for transforming 50 TB of data file-by-file. Option B is not appropriate because Cloud SQL is a relational OLTP database, not a scalable store for massive intermediate ML feature data. Option E is not appropriate because writing engineered features to BigQuery does not produce the TFRecord input that Vertex AI batch prediction expects, and BigQuery is not the target format for this pipeline's model input.

Answer

Use Cloud Functions to transform each file individually.

Answer

Use Cloud SQL to store intermediate results.

Answer

Use Dataflow to read CSV, perform feature engineering, and write to BigQuery.

Question 14

You deploy a new version of a model to a Vertex AI endpoint and want to gradually shift traffic from the old version to the new version over 24 hours. The endpoint currently serves 100% traffic to the old version. What should you do?

Accepted Answer

Update the endpoint to split traffic between the two model versions using the traffic split configuration.. Vertex AI endpoints support a built-in traffic split configuration that allows you to gradually shift traffic between model versions deployed to the same endpoint. By updating the endpoint's traffic split percentages (e.g., from 100% old / 0% new to 0% old / 100% new over 24 hours), you can achieve a smooth, controlled rollout without changing client code or managing multiple endpoints.

Answer

Use Vertex AI Experiments to run an A/B test between the two versions.

Answer

Deploy the new version to a separate endpoint and update your client to use the new endpoint for a percentage of requests.

Answer

Delete the old version and redeploy the new version with a different endpoint name, then update DNS.

Question 15

You are deploying a PyTorch model for online predictions on Vertex AI. The model expects input tensors and performs GPU-accelerated inference. You want to minimize prediction latency and maximize throughput. Which approach should you use?

Accepted Answer

Deploy using a prebuilt PyTorch serving container with NVIDIA Triton Inference Server.. NVIDIA Triton Inference Server provides advanced features like dynamic batching, concurrent model execution, and GPU scheduling that maximize throughput and minimize latency for GPU-accelerated inference. Vertex AI's prebuilt PyTorch serving container with Triton is specifically designed to handle online prediction workloads efficiently, outperforming a plain custom container without an inference server.

Answer

Package the model in a custom container without any inference server.

Answer

Use Vertex AI Model Optimization to quantize the model to FP16 and deploy using the optimized model.

Answer

Use batch prediction instead of online prediction to reduce latency.