You are deploying a custom ML model on Vertex AI for online prediction and need to optimize it for high throughput and low latency using the simplest solution. What should you do?

Exam-Like

Deploy the model to a Vertex AI endpoint resource to automatically scale the serving backend based on the throughput. Configure the endpoint's autoscaling settings to minimize latency.

33.7%

Implement a containerized serving solution using Cloud Run. Configure the concurrency settings to handle multiple requests simultaneously.

40.8%

Apply simplification techniques such as model pruning and quantization to reduce the model's size and complexity. Retrain the model using Vertex AI to improve its performance, latency, memory, and throughput.

16.3%

Enable request-response logging for the model hosted in Vertex AI. Use Looker Studio to analyze the logs, identify bottlenecks, and optimize the model accordingly.

9.2%

Google Professional Machine Learning Engineer

Get started today

Comments

You are deploying a custom ML model on Vertex AI for online prediction and need to optimize it for high throughput and low latency using the simplest solution. What should you do?