SageMaker Python SDK
The Python software development kit for Amazon SageMaker. It provides interfaces for model deployment, endpoint management, and inference invocation, and supports automating the deployment and evaluation workflow of JumpStart models through code.
Timeline (last 90 days)
Developers can deploy Muse Spark Open in their AWS account through SageMaker Studio or the Python SDK and issue inference requests.
The JumpStart model card specifies the image URI corresponding to that model, and the SDK automatically pulls the image onto the endpoint instance when deploy is called.
The typical path for deploying a JumpStart model with the SageMaker Python SDK is to first obtain the model object via the model ID, then call the deploy method specifying the instance type and instance count, and the SDK automatically handles container pulling, endpoint creation, and model loading.
A successful return from deploy only means the endpoint creation request was accepted; before the endpoint is truly available it goes through states such as Creating and InService, during which requests return 5xx or connection errors.
All Facts (4)
Developers can deploy Muse Spark Open in their AWS account through SageMaker Studio or the Python SDK and issue inference requests.
50%UnverifiedThe JumpStart model card specifies the image URI corresponding to that model, and the SDK automatically pulls the image onto the endpoint instance when deploy is called.
50%UnverifiedThe typical path for deploying a JumpStart model with the SageMaker Python SDK is to first obtain the model object via the model ID, then call the deploy method specifying the instance type and instance count, and the SDK automatically handles container pulling, endpoint creation, and model loading.
50%UnverifiedA successful return from deploy only means the endpoint creation request was accepted; before the endpoint is truly available it goes through states such as Creating and InService, during which requests return 5xx or connection errors.
50%