Register models in SageMaker Model Registry and deploy endpoints

Steps

1. Create a model package group if one does not exist: sm_client.create_model_package_group(ModelPackageGroupName='my-model-group', ModelPackageGroupDescription='...')
2. Register a model version: response = sm_client.create_model_package(ModelPackageGroupName='my-model-group', ModelApprovalStatus='PendingManualApproval', InferenceSpecification={...}) — InferenceSpecification specifies container image and supported instance types
3. Approve the model package to enable deployment: sm_client.update_model_package(ModelPackageArn=model_package_arn, ModelApprovalStatus='Approved')
4. Create a deployable Model object from the approved package using the SageMaker Python SDK: model = ModelPackage(role=role, model_package_arn=model_package_arn)
5. Deploy to a real-time endpoint: predictor = model.deploy(initial_instance_count=1, instance_type='ml.m5.large', endpoint_name='my-endpoint')
6. Invoke the endpoint for inference: predictor.predict(data) or use sm_runtime_client.invoke_endpoint() for raw Boto3 calls