Amazon SageMaker AI Announces New observability capability For Inference Endpoints

Summary

• Adds native observability for SageMaker inference endpoints, exposing token latency, GPU health, scaling events, and other performance metrics in real time.
• Publishes OpenTelemetry metrics automatically to CloudWatch and a PromQL endpoint for Grafana, with a pre‑built dashboard, requiring no manual instrumentation.
• Provides the feature across multiple AWS regions, with documentation and a ready‑to‑use SageMaker AI Insights dashboard.