Changes Online store feature groups supports Standard and InMemory tier storage types for low latency storage for real-time data retrieval. The InMemory tier supports collection types List, Set, and Vector.
Changes Introducing TTL for online store records in feature groups.
Changes In this release, you can now chose between soft delete and hard delete when calling the DeleteRecord API, so you have more flexibility when it comes to managing online store data.
Changes For online + offline Feature Groups, added ability to target PutRecord and DeleteRecord actions to only online store, or only offline store. If target store parameter is not specified, actions will apply to both stores.
Changes Using SageMaker Edge Manager with AWS IoT Greengrass v2 simplifies accessing, maintaining, and deploying models to your devices. You can now create deployable IoT Greengrass components during edge packaging jobs. You can choose to create a device fleet with or without creating an AWS IoT role alias.
Changes Amazon SageMaker Pipelines for ML workflows. Amazon SageMaker Feature Store, a fully managed repository for ML features.