Merge pull request pytorch#409 from gaurav-work/website_update

[Mobile] Landing page update for v1.6.0

Author: Jessica Lin

_layouts/mobile.html

@@ -12,7 +12,7 @@
       <div class="container">
         <h1>PyTorch Mobile</h1>
 
-        <p class="lead">End-to-end workflow from Python to deployment on iOS and Android</p>
+        <p class="lead">End-to-end workflow from Training to Deployment for iOS and Android mobile devices</p>
       </div>
     </div>
 

_mobile/home.md

@@ -11,17 +11,23 @@ redirect_from: "/mobile/"
 
 # PyTorch Mobile
 
-Running ML on edge devices is growing in importance as applications continue to demand lower latency. It is also a foundational element for privacy-preserving techniques such as federated learning. As of PyTorch 1.3, PyTorch supports an end-to-end workflow from Python to deployment on iOS and Android. 
+There is a growing need to execute ML models on edge devices to reduce latency, preserve privacy and enable new interactive use cases. In the past, engineers used to train models separately. They would then go through a multi-step, error prone and often complex process to transform the models for execution on a mobile device. The mobile runtime was often significantly different from the operations available during training leading to inconsistent developer and eventually user experience.
 
-This is an early, experimental release that we will be building on in several areas over the coming months:
+PyTorch Mobile removes these friction surfaces by allowing a seamless process to go from training to deployment by staying entirely within the PyTorch ecosystem. It provides an end-to-end workflow that simplifies the research to production environment for mobile devices. In addition, it paves the way for privacy-preserving features via Federated Learning techniques.
 
-- Provide APIs that cover common preprocessing and integration tasks needed for incorporating ML in mobile applications
-- Support for QNNPACK quantized kernel libraries and support for ARM CPUs
-- Build level optimization and selective compilation depending on the operators needed for user applications (i.e., you pay binary size for only the operators you need)
-- Further improvements to performance and coverage on mobile CPUs and GPUs
+PyTorch Mobile is in beta stage right now and in wide scale production use. It will soon be available as a stable release once the APIs are locked down.
 
-Learn more or get started on [Android]({{site.baseurl}}/mobile/android) or [iOS]({{site.baseurl}}/mobile/ios).
+Key features of PyTorch Mobile:
 
+* Available for [iOS]({{site.baseurl}}/mobile/ios), [Android]({{site.baseurl}}/mobile/android) and Linux
+* Provides APIs that cover common preprocessing and integration tasks needed for incorporating ML in mobile applications
+* Support for tracing and scripting via TorchScript IR
+* Support for XNNPACK floating point kernel libraries for Arm CPUs
+* Integration of QNNPACK for 8-bit quantized kernels. Includes support for per-channel quantization, dynamic quantization and more
+* Build level optimization and selective compilation depending on the operators needed for user applications, i.e., the final binary size of the app is determined by the actual operators the app needs
+* Support for hardware backends like GPU, DSP, NPU will be available soon
+
+A typical workflow from training to mobile deployment with the optional model optimization steps is outlined in the following figure.
 <div class="text-center">
   <img src="{{ site.baseurl }}/assets/images/pytorch-mobile.png" width="100%">
 </div>