2023/11/29 - 2 updated api methods
Changes This release adds following support 1/ Improved SDK tooling for model deployment. 2/ New Inference Component based features to lower inference costs and latency 3/ SageMaker HyperPod management. 4/ Additional parameters for FM Fine Tuning in Autopilot
2023/08/31 - 1 new api methods
Changes This release adds a new InvokeEndpointWithResponseStream API to support streaming of model responses.
2023/04/04 - 1 updated api methods
Changes Amazon SageMaker Asynchronous Inference now allows customer's to receive failure model responses in S3 and receive success/failure model responses in SNS notifications.
2023/01/27 - 1 updated api methods
Changes This release supports running SageMaker Training jobs with container images that are in a private Docker registry.
2022/09/30 - 1 updated api methods
Changes A new parameter called ExplainerConfig is added to CreateEndpointConfig API to enable SageMaker Clarify online explainability feature.
2021/08/18 - 1 new api methods
Changes Amazon SageMaker now supports Asynchronous Inference endpoints. Adds PlatformIdentifier field that allows Notebook Instance creation with different platform selections. Increases the maximum number of containers in multi-container endpoints to 15. Adds more instance types to InstanceType field.
2021/02/22 - 1 updated api methods
Changes Amazon SageMaker now supports core dump for SageMaker Endpoints and direct invocation of a single container in a SageMaker Endpoint that hosts multiple containers.
2020/12/08 - 1 updated api methods
Changes This feature helps you monitor model performance characteristics such as accuracy, identify undesired bias in your ML models, and explain model decisions better with explainability drift detection.
2020/06/05 - 1 updated api methods
Changes You can now specify the production variant to send the inference request to, when invoking a SageMaker Endpoint that is running two or more variants.
2019/11/18 - 1 updated api methods
Changes Amazon SageMaker now supports multi-model endpoints to host multiple models on an endpoint using a single inference container.
2018/08/29 - 1 updated api methods
Changes SageMaker Runtime supports CustomAttributes header which allows customers provide additional information in a request for an inference submitted to a model or in the response about the inference returned by a model hosted at an Amazon SageMaker endpoint.
2017/11/29 - 1 new api methods
Changes Amazon SageMaker is a fully-managed service that enables data scientists and developers to quickly and easily build, train, and deploy machine learning models, at scale.