Answer-first summary for fast verification
Answer: Configure the model deployment settings to use an n1-standard-4 machine type. Set the minReplicaCount value to 1 and the maxReplicaCount value to 8.
Option B is the optimal choice because it balances cost efficiency with performance requirements for an AutoML tabular classification model. The n1-standard-4 machine type provides sufficient compute power without overprovisioning, avoiding unnecessary costs from larger instances like n1-standard-32 (Option A). The autoscaling configuration (minReplicaCount=1, maxReplicaCount=8) dynamically adjusts to fluctuating traffic patterns, maintaining low latency during peak hours (nights/weekends) while minimizing costs during low-traffic periods. Options C and D are less suitable as they include GPU accelerators, which are unnecessary for tabular models and would increase costs without significant performance benefits, as confirmed by community consensus highlighting that GPUs are typically reserved for deep learning models with complex architectures.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are deploying an AutoML tabular classification model to a new Vertex AI endpoint to identify high-value customers from your website application. The endpoint must be configured to handle higher traffic during nights and weekends while minimizing latency and cost. What should you do?
A
Configure the model deployment settings to use an n1-standard-32 machine type.
B
Configure the model deployment settings to use an n1-standard-4 machine type. Set the minReplicaCount value to 1 and the maxReplicaCount value to 8.
C
Configure the model deployment settings to use an n1-standard-4 machine type and a GPU accelerator. Set the minReplicaCount value to 1 and the maxReplicaCount value to 4.
D
Configure the model deployment settings to use an n1-standard-8 machine type and a GPU accelerator.
No comments yet.