Merge branch 'main' into dependabot/pip/dot-ci/docker/jinja2-3.1.4

Author: svekars

beginner_source/onnx/intro_onnx.py

@@ -39,13 +39,14 @@
 
   - `ONNX <https://onnx.ai>`_ standard library
   - `ONNX Script <https://onnxscript.ai>`_ library that enables developers to author ONNX operators,
-    functions and models using a subset of Python in an expressive, and yet simple fashion.
+    functions and models using a subset of Python in an expressive, and yet simple fashion
+  - `ONNX Runtime <https://onnxruntime.ai>`_ accelerated machine learning library.
 
 They can be installed through `pip <https://pypi.org/project/pip/>`_:
 
 .. code-block:: bash
 
-  pip install --upgrade onnx onnxscript
+  pip install --upgrade onnx onnxscript onnxruntime
 
 To validate the installation, run the following commands:
 

conf.py

@@ -67,6 +67,12 @@
 #
 # needs_sphinx = '1.0'
 
+html_meta = {
+    'description': 'Master PyTorch with our step-by-step tutorials for all skill levels. Start your journey to becoming a PyTorch expert today!',
+    'keywords': 'PyTorch, tutorials, Getting Started, deep learning, AI',
+    'author': 'PyTorch Contributors'
+}
+
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.

index.rst

@@ -3,6 +3,7 @@ Welcome to PyTorch Tutorials
 
 **What's new in PyTorch tutorials?**
 
+* `torch.export AOTInductor Tutorial for Python runtime (Beta) <https://pytorch.org/tutorials/recipes/torch_export_aoti_python.html>`__
 * `A guide on good usage of non_blocking and pin_memory() in PyTorch <https://pytorch.org/tutorials/intermediate/pinmem_nonblock.html>`__
 * `Introduction to Distributed Pipeline Parallelism <https://pytorch.org/tutorials/intermediate/pipelining_tutorial.html>`__
 * `Introduction to Libuv TCPStore Backend <https://pytorch.org/tutorials/intermediate/TCPStore_libuv_backend.html>`__ 

prototype_source/gpu_quantization_torchao_tutorial.py

@@ -35,14 +35,12 @@
 #
 # Segment Anything Model checkpoint setup:
 #
-# 1. Go to the `segment-anything repo <checkpoint https://github.com/facebookresearch/segment-anything/tree/main#model-checkpoints>`_ and download the ``vit_h`` checkpoint. Alternatively, you can just use ``wget``: `wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth --directory-prefix=<path>
+# 1. Go to the `segment-anything repo checkpoint <https://github.com/facebookresearch/segment-anything/tree/main#model-checkpoints>`_ and download the ``vit_h`` checkpoint. Alternatively, you can use ``wget`` (for example, ``wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth --directory-prefix=<path>``).
 # 2. Pass in that directory by editing the code below to say:
 #
-# .. code-block::
-#
-# {sam_checkpoint_base_path}=<path>
+# .. code-block:: bash
 #
-# This was run on an A100-PG509-200 power limited to 330.00 W
+#   {sam_checkpoint_base_path}=<path>
 #
 
 import torch
@@ -297,7 +295,7 @@ def get_sam_model(only_one_block=False, batchsize=1):
 # -----------------
 # In this tutorial, we have learned about the quantization and optimization techniques
 # on the example of the segment anything model.
-
+#
 # In the end, we achieved a full-model apples to apples quantization speedup
 # of about 7.7% on batch size 16 (677.28ms to 729.65ms). We can push this a
 # bit further by increasing the batch size and optimizing other parts of

recipes_source/torch_export_aoti_python.py

@@ -1,7 +1,11 @@
 # -*- coding: utf-8 -*-
 
 """
-(Beta) ``torch.export`` AOTInductor Tutorial for Python runtime
+.. meta::
+   :description: An end-to-end example of how to use AOTInductor for Python runtime.
+   :keywords: torch.export, AOTInductor, torch._inductor.aot_compile, torch._export.aot_load
+
+``torch.export`` AOTInductor Tutorial for Python runtime (Beta)
 ===============================================================
 **Author:** Ankith Gunapal, Bin Bao, Angela Yi
 """
@@ -18,7 +22,7 @@
 # a shared library that can be run in a non-Python environment.
 #
 #
-# In this tutorial, you will learn an end-to-end example of how to use AOTInductor for python runtime.
+# In this tutorial, you will learn an end-to-end example of how to use AOTInductor for Python runtime.
 # We will look at how  to use :func:`torch._inductor.aot_compile` along with :func:`torch.export.export` to generate a 
 # shared library. Additionally, we will examine how to execute the shared library in Python runtime using :func:`torch._export.aot_load`.
 # You will learn about the speed up seen in the first inference time using AOTInductor, especially when using