
Ultimate access to all questions.
You work for a textile manufacturing company with hundreds of machines, each equipped with multiple sensors. Your team has built hundreds of machine learning models using this sensor data to detect machine anomalies. These models are retrained daily and need to be deployed in a cost-effective manner. The deployment must support 24/7 operation with no downtime and provide sub-millisecond prediction latency. What should you do?
A
Deploy a Dataflow batch pipeline and a Vertex AI Prediction endpoint.
B
Deploy a Dataflow batch pipeline with the Runlnference API, and use model refresh.
C
Deploy a Dataflow streaming pipeline and a Vertex AI Prediction endpoint with autoscaling.
D
Deploy a Dataflow streaming pipeline with the Runlnference API, and use automatic model refresh.