Amazon SageMaker
Developer Guide

The AWS Documentation website is getting a new look!
Try it now and let us know what you think. Switch to the new look >>

You can return to the original look by selecting English in the language selector above.

Deploy a Model Compiled with Neo (Amazon SageMaker SDK)

The object handle for the compiled model supplies the deploy function, which allows you to create an endpoint to serve inference requests. The function lets you set the number and type of instances that are used for the endpoint. You must choose an instance for which you have compiled your model. For example, in the job compiled in Compile a Model (Amazon SageMaker SDK) section, this is ml_c5. The Neo API uses a special runtime, the Neo runtime, to run Neo-optimized models.

predictor = compiled_model.deploy(initial_instance_count = 1, instance_type = 'ml.c5.4xlarge')

After the command is done, the name of the newly created endpoint is printed in the jupyter notebook.