Update docs for Elastic Inference (#515)

Author: ChoiByungWook

README.rst

@@ -356,7 +356,9 @@ MXNet SageMaker Estimators
 
 By using MXNet SageMaker ``Estimators``, you can train and host MXNet models on Amazon SageMaker.
 
-Supported versions of MXNet: ``1.2.1``, ``1.1.0``, ``1.0.0``, ``0.12.1``.
+Supported versions of MXNet: ``1.3.0``, ``1.2.1``, ``1.1.0``, ``1.0.0``, ``0.12.1``.
+
+Supported versions of MXNet for Elastic Inference: ``1.3.0``
 
 We recommend that you use the latest supported version, because that's where we focus most of our development efforts.
 
@@ -372,6 +374,8 @@ By using TensorFlow SageMaker ``Estimators``, you can train and host TensorFlow
 
 Supported versions of TensorFlow: ``1.4.1``, ``1.5.0``, ``1.6.0``, ``1.7.0``, ``1.8.0``, ``1.9.0``, ``1.10.0``, ``1.11.0``.
 
+Supported versions of TensorFlow for Elastic Inference: ``1.11.0``.
+
 We recommend that you use the latest supported version, because that's where we focus most of our development efforts.
 
 For more information, see `TensorFlow SageMaker Estimators and Models`_.

src/sagemaker/mxnet/README.rst

@@ -6,6 +6,8 @@ With MXNet Estimators, you can train and host MXNet models on Amazon SageMaker.
 
 Supported versions of MXNet: ``1.3.0``, ``1.2.1``, ``1.1.0``, ``1.0.0``, ``0.12.1``.
 
+Supported versions of MXNet for Elastic Inference: ``1.3.0``.
+
 Training with MXNet
 ~~~~~~~~~~~~~~~~~~~
 
@@ -480,6 +482,14 @@ After calling ``fit``, you can call ``deploy`` on an ``MXNet`` Estimator to crea
 
 You use the SageMaker MXNet model server to host your MXNet model when you call ``deploy`` on an ``MXNet`` Estimator. The model server runs inside a SageMaker Endpoint, which your call to ``deploy`` creates. You can access the name of the Endpoint by the ``name`` property on the returned ``Predictor``.
 
+MXNet on SageMaker has support for `Elastic Inference <https://docs.aws.amazon.com/sagemaker/latest/dg/ei.html>`_, which allows for inference acceleration to a hosted endpoint for a fraction of the cost of using a full GPU instance. In order to attach an Elastic Inference accelerator to your endpoint provide the accelerator type to ``accelerator_type`` to your ``deploy`` call.
+
+.. code:: python
+
+  predictor = mxnet_estimator.deploy(instance_type='ml.m4.xlarge',
+                                     initial_instance_count=1,
+                                     accelerator_type='ml.eia1.medium')
+
 The SageMaker MXNet Model Server
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

src/sagemaker/tensorflow/README.rst

@@ -20,6 +20,8 @@ Documentation of the previous Legacy Mode versions: `1.4.1 <https://github.com/a
 | You can find the Legacy Mode README `here <https://github.com/aws/sagemaker-python-sdk/tree/v1.12.0/src/sagemaker/tensorflow#tensorflow-sagemaker-estimators-and-models>`_. |
 +-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
 
+Supported versions of TensorFlow for Elastic Inference: ``1.11.0``.
+
 Training with TensorFlow
 ~~~~~~~~~~~~~~~~~~~~~~~~
 

src/sagemaker/tensorflow/deploying_tensorflow_serving.rst

@@ -34,6 +34,15 @@ estimator object to create a SageMaker Endpoint:
 
 The code block above deploys a SageMaker Endpoint with one instance of the type 'ml.c5.xlarge'.
 
+TensorFlow serving on SageMaker has support for `Elastic Inference <https://docs.aws.amazon.com/sagemaker/latest/dg/ei.html>`_, which allows for inference acceleration to a hosted endpoint for a fraction of the cost of using a full GPU instance. In order to attach an Elastic Inference accelerator to your endpoint provide the accelerator type to ``accelerator_type`` to your ``deploy`` call.
+
+.. code:: python
+
+  predictor = estimator.deploy(initial_instance_count=1,
+                               instance_type='ml.c5.xlarge',
+                               accelerator_type='ml.eia1.medium'
+                               endpoint_type='tensorflow-serving-elastic-inference')
+
 What happens when deploy is called
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^