CloudWatch Metrics for Multi-Model Endpoint Deployments - Amazon SageMaker

CloudWatch Metrics for Multi-Model Endpoint Deployments

Amazon SageMaker provides metrics for endpoints so you can monitor the cache hit rate, the number of models loaded, and the model wait times for loading, downloading, and uploading at a multi-model endpoint. For information, see Multi-Model Endpoint Model Loading Metrics and Multi-Model Endpoint Model Instance Metrics in Monitor Amazon SageMaker with Amazon CloudWatch. Per-model metrics aren't supported.