QuestionQ86
VerifiedDeployment and Orchestration of ML WorkflowsAn airline deploys ML models to one dozen Amazon SageMaker AI inference endpoints. The endpoints must handle different workload types cost-effectively.
Choose the correct inference option for each workload. Select every inference option one time.
Select
Provide flight departure, arrival, and delay information, and provide updates for low-latency workloads.
Advertise holiday travel promotional deals to millions of users in multiple markets before holiday seasons for spiky workloads.
Generate quarterly and annual flight reports and insights for trend analysis of large datasets.
Generate online image and audio stories for passengers to watch or listen to while waiting at an airport.
Community Discussion