Answer-first summary for fast verification
Answer: Split incoming traffic to distribute prediction requests among the versions. Monitor the performance of each version using Vertex AI's built-in monitoring tools.
The question emphasizes using the 'simplest approach' for A/B testing multiple model versions in Vertex AI. Option A is optimal because Vertex AI provides built-in traffic splitting capabilities that allow direct distribution of prediction requests among different model versions, and it includes integrated monitoring tools specifically designed for model performance evaluation. This eliminates the need for additional infrastructure setup or external dashboard creation. Option B requires managing GKE clusters and Traffic Director, adding complexity. Option C requires building custom Looker Studio dashboards. Option D involves configuring separate Cloud Run instances, which is more complex than using Vertex AI's native capabilities. The community discussion shows equal support for A and D, but A aligns better with Vertex AI's integrated simplicity for model deployment and testing.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You have deployed multiple model versions from Vertex AI Model Registry and want to conduct A/B testing to determine the best performing model with the simplest approach. What should you do?
A
Split incoming traffic to distribute prediction requests among the versions. Monitor the performance of each version using Vertex AI's built-in monitoring tools.
B
Split incoming traffic among Google Kubernetes Engine (GKE) clusters, and use Traffic Director to distribute prediction requests to different versions. Monitor the performance of each version using Cloud Monitoring.
C
Split incoming traffic to distribute prediction requests among the versions. Monitor the performance of each version using Looker Studio dashboards that compare logged data for each version.
D
Split incoming traffic among separate Cloud Run instances of deployed models. Monitor the performance of each version using Cloud Monitoring.
No comments yet.