Address comments

Summary:

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:

Author: larryliu0820

docs/source/runtime-pybind-api-reference.rst renamed to docs/source/runtime-python-api-reference.rst

@@ -1,7 +1,6 @@
-Runtime Pybind API Reference
+ExecuTorch Runtime Python API Reference
 ----------------------------------
-Pybind APIs can load a serialized .pte file (see `Export to ExecuTorch Tutorial <tutorials/export-to-executorch-tutorial.html>`__ for how to get .pte file from a PyTorch `nn.Module`) and execute it using `torch.Tensor` as inputs, in a Python environment. The result also comes back as `torch.Tensor` so it can be used as a quick way to validate the correctness of the program.
-
+The Python ``executorch.runtime`` module wraps the C++ ExecuTorch runtime. It can load and execute serialized ``.pte`` program files: see the `Export to ExecuTorch Tutorial <tutorials/export-to-executorch-tutorial.html>`__ for how to convert a PyTorch ``nn.Module`` to an ExecuTorch ``.pte`` program file. Execution accepts and returns ``torch.Tensor`` values, making it a quick way to validate the correctness of the program.
 For detailed information on how APIs evolve and the deprecation process, please refer to the `ExecuTorch API Life Cycle and Deprecation Policy <api-life-cycle.html>`__.
 
 .. automodule:: executorch.runtime

runtime/__init__.py

@@ -7,6 +7,7 @@
 """Interface to the native C++ ExecuTorch runtime.
 
 Example usage:
+
 .. code-block:: text
 
     from pathlib import Path
@@ -28,6 +29,7 @@
     print(f"  outputs: {outputs}")
 
 Example output:
+
 .. code-block:: text
 
     Program methods: ('forward', 'forward2')