sagemaker-inference 1.10.1

Open source toolkit for helping create serving containers to run on Amazon SageMaker.

SageMaker Inference Toolkit

Serve machine learning models within a Docker container using Amazon SageMaker.

:books: Background

Amazon SageMaker is a fully managed service for data science and machine learning (ML) workflows. You can use Amazon SageMaker to simplify the process of building, training, and deploying ML models.

Once you have a trained model, you can include it in a Docker container that runs your inference code. A container provides an effectively isolated environment, ensuring a consistent runtime regardless of where the container is deployed. Containerizing your model and code enables fast and reliable deployment of your model.

The SageMaker Inference Toolkit implements a model serving stack and can be easily added to any Docker container, making it deployable to SageMaker. This library's serving stack is built on Multi Model Server, and it can serve your own models or those you trained on SageMaker using machine learning frameworks with native SageMaker support. If you use a prebuilt SageMaker Docker image for inference, this library may already be included.

For more information, see the Amazon SageMaker Developer Guide sections on building your own container with Multi Model Server and using your own models.

:hammer_and_wrench: Installation

To install this library in your Docker image, add the following line to your Dockerfile:

RUN pip3 install multi-model-server sagemaker-inference

Here is an example of a Dockerfile that installs SageMaker Inference Toolkit.

:computer: Usage

Implementation Steps

To use the SageMaker Inference Toolkit, you need to do the following:

1. Implement an inference handler, which is responsible for loading the model and providing input, predict, and output functions. (Here is an example of an inference handler.)

   from sagemaker_inference import content_types, decoder, default_inference_handler, encoder, errors
   
   class DefaultPytorchInferenceHandler(default_inference_handler.DefaultInferenceHandler):
   
       def default_model_fn(self, model_dir, context=None):
           """Loads a model. For PyTorch, a default function to load a model cannot be provided.
           Users should provide customized model_fn() in script.
   
           Args:
               model_dir: a directory where model is saved.
               context (obj): the request context (default: None).
   
           Returns: A PyTorch model.
           """
           raise NotImplementedError(textwrap.dedent("""
           Please provide a model_fn implementation.
           See documentation for model_fn at https://github.com/aws/sagemaker-python-sdk
           """))
   
       def default_input_fn(self, input_data, content_type, context=None):
           """A default input_fn that can handle JSON, CSV and NPZ formats.
   
           Args:
               input_data: the request payload serialized in the content_type format
               content_type: the request content_type
               context (obj): the request context (default: None).
   
           Returns: input_data deserialized into torch.FloatTensor or torch.cuda.FloatTensor depending if cuda is available.
           """
           return decoder.decode(input_data, content_type)
   
       def default_predict_fn(self, data, model, context=None):
           """A default predict_fn for PyTorch. Calls a model on data deserialized in input_fn.
           Runs prediction on GPU if cuda is available.
   
           Args:
               data: input data (torch.Tensor) for prediction deserialized by input_fn
               model: PyTorch model loaded in memory by model_fn
               context (obj): the request context (default: None).
   
           Returns: a prediction
           """
           return model(input_data)
   
       def default_output_fn(self, prediction, accept, context=None):
           """A default output_fn for PyTorch. Serializes predictions from predict_fn to JSON, CSV or NPY format.
   
           Args:
               prediction: a prediction result from predict_fn
               accept: type which the output data needs to be serialized
               context (obj): the request context (default: None).
   
           Returns: output data serialized
           """
           return encoder.encode(prediction, accept)
   

   Note, passing context as an argument to the handler functions is optional. Customer can choose to omit context from the function declaration if it's not needed in the runtime. For example, the following handler function declarations will also work:

   def default_model_fn(self, model_dir)
   
   def default_input_fn(self, input_data, content_type)
   
   def default_predict_fn(self, data, model)
   
   def default_output_fn(self, prediction, accept)
   

2. Implement a handler service that is executed by the model server. (Here is an example of a handler service.) For more information on how to define your HANDLER_SERVICE file, see the MMS custom service documentation.

   from sagemaker_inference.default_handler_service import DefaultHandlerService
   from sagemaker_inference.transformer import Transformer
   from sagemaker_pytorch_serving_container.default_inference_handler import DefaultPytorchInferenceHandler
   
   
   class HandlerService(DefaultHandlerService):
       """Handler service that is executed by the model server.
       Determines specific default inference handlers to use based on model being used.
       This class extends ``DefaultHandlerService``, which define the following:
           - The ``handle`` method is invoked for all incoming inference requests to the model server.
           - The ``initialize`` method is invoked at model server start up.
       Based on: https://github.com/awslabs/multi-model-server/blob/master/docs/custom_service.md
       """
       def __init__(self):
           transformer = Transformer(default_inference_handler=DefaultPytorchInferenceHandler())
           super(HandlerService, self).__init__(transformer=transformer)
   

3. Implement a serving entrypoint, which starts the model server. (Here is an example of a serving entrypoint.)

   from sagemaker_inference import model_server
   
   model_server.start_model_server(handler_service=HANDLER_SERVICE)
   

4. Define the location of the entrypoint in your Dockerfile.

   ENTRYPOINT ["python", "/usr/local/bin/entrypoint.py"]
   

Complete Example

Here is a complete example demonstrating usage of the SageMaker Inference Toolkit in your own container for deployment to a multi-model endpoint.

:scroll: License

This library is licensed under the Apache 2.0 License. For more details, please take a look at the LICENSE file.

:handshake: Contributing

Contributions are welcome! Please read our contributing guidelines if you'd like to open an issue or submit a pull request.