ml-specialty video for a company currently has an Amazon SageMaker endpoint. The endpoint currently has 4 models running at evenly distributed weights such that
A company currently has an Amazon SageMaker endpoint. The endpoint currently has 4 models running at evenly distributed weights such that each model serves 25% of the traffic. The endpoint is based on a c6g.2xlarge instance. The company’s priority is to make sure the service reaches its users under all circumstances. In other words, the company wants the endpoint to be highly available. Which of the following solutions would help meet these requirements? (Select TWO.)