Merge branch 'readme' into 'release/1.0'

doc: Update installation instructions based on ABI and platforms

See merge request adlsa/TRTorch!22

Author: narendasan

README.md

@@ -56,7 +56,7 @@ import torch_tensorrt
 
 ...
 
-trt_ts_module = torch_tensorrt.compile(torch_script_module, 
+trt_ts_module = torch_tensorrt.compile(torch_script_module,
     inputs = [example_tensor, # Provide example tensor for input shape or...
         torch_tensorrt.Input( # Specify input object with shape and dtype
             min_shape=[1, 3, 224, 224],
@@ -204,9 +204,10 @@ bazel build //:libtorchtrt --compilation_mode=dbg
 ```
 
 ### Native compilation on NVIDIA Jetson AGX
+We performed end to end testing on Jetson platform using Jetpack SDK 4.6. 
 
 ``` shell
-bazel build //:libtorchtrt --distdir third_party/dist_dir/aarch64-linux-gnu
+bazel build //:libtorchtrt --platforms //toolchains:jetpack_4.6
 ```
 
 > Note: Please refer [installation](docs/tutorials/installation.html) instructions for Pre-requisites

docsrc/tutorials/creating_torchscript_module_in_python.rst

@@ -2,8 +2,7 @@
 
 Creating a TorchScript Module
 ------------------------------
-
-Once you have a trained model you want to compile with Torch-TensorRT, you need to start by converting that model from Python code to TorchScript code.
+TorchScript is a way to create serializable and optimizable models from PyTorch code.
 PyTorch has detailed documentation on how to do this https://pytorch.org/tutorials/beginner/Intro_to_TorchScript_tutorial.html but briefly here is the
 here is key background information and the process:
 
@@ -65,7 +64,7 @@ To trace an instance of our LeNet module, we can call ``torch.jit.trace`` with a
 
 .. code-block:: python
 
-    import torch.jit
+    import torch
 
     model = LeNet()
     input_data = torch.empty([1,1,32,32])
@@ -77,7 +76,7 @@ include these components. We can run the script compiler on our LeNet module by
 
 .. code-block:: python
 
-    import torch.jit
+    import torch
 
     model = LeNet()
     script_model = torch.jit.script(model)
@@ -131,7 +130,7 @@ For either traced or scripted modules, you can save the module to disk with the
 
 .. code-block:: python
 
-    import torch.jit
+    import torch
 
     model = LeNet()
     script_model = torch.jit.script(model)

py/README.md

@@ -31,9 +31,16 @@ results = compiled_trt_model(data.half())
 
 ## Installation
 
-```
-python3 setup.py install
-```
+| ABI / Platform                          | Installation command                                         |
+| --------------------------------------- | ------------------------------------------------------------ |
+| Pre CXX11 ABI (Linux x86_64)            | python3 setup.py install --release                           |
+| CXX ABI  (Linux x86_64)                 | python3 setup.py install --use-cxx11-abi --release           |
+| Pre CXX11 ABI (Jetson platform aarch64) | python3 setup.py install --release --jetpack-version 4.6     |
+| CXX11 ABI (Jetson platform aarch64)     | python3 setup.py install --release --jetpack-version 4.6 --use-cxx11-abi |
+
+For Linux x86_64 platform, Pytorch libraries default to pre cxx11 abi. So, please use `python3 setup.py install --release`.
+
+On Jetson platforms, NVIDIA hosts <a href="https://forums.developer.nvidia.com/t/pytorch-for-jetson-version-1-10-now-available/72048">pre-built Pytorch wheel files</a>. These wheel files are built with CXX11 ABI. So on jetson platforms, please use `python3 setup.py install --release --jetpack-version 4.6`   
 
 ## Under the Hood