From bc10cdf22c9e4c9912bb397b030b13ed35735abb Mon Sep 17 00:00:00 2001
From: Svetlana Karslioglu <svekars@fb.com>
Date: Thu, 16 Mar 2023 09:51:50 -0700
Subject: [PATCH 1/6] Update what's new with 2.0 tutorials

---
 index.rst                                           | 13 +++++++++----
 .../scaled_dot_product_attention_tutorial.py        |  9 +++++----
 2 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/index.rst b/index.rst
index 71fcb717403..4fbc574b2f9 100644
--- a/index.rst
+++ b/index.rst
@@ -3,10 +3,15 @@ Welcome to PyTorch Tutorials
 
 What's new in PyTorch tutorials?
 
-* `PyTorch Distributed Series <https://pytorch.org/tutorials/beginner/ddp_series_intro.html?utm_source=whats_new_tutorials&utm_medium=ddp_series_intro>`__
-* `Fast Transformer Inference with Better Transformer <https://pytorch.org/tutorials/beginner/bettertransformer_tutorial.html?utm_source=whats_new_tutorials&utm_medium=bettertransformer>`__
-* `Advanced model training with Fully Sharded Data Parallel (FSDP) <https://pytorch.org/tutorials/intermediate/FSDP_adavnced_tutorial.html?utm_source=whats_new_tutorials&utm_medium=FSDP_advanced>`__
-* `Grokking PyTorch Intel CPU Performance from First Principles <https://pytorch.org/tutorials/intermediate/torchserve_with_ipex?utm_source=whats_new_tutorials&utm_medium=torchserve_ipex>`__
+* `Implementing High Performance Transformers with Scaled Dot Product Attention <https://pytorch.org/tutorials/intermediate/scaled_dot_product_attention_tutorial.html?utm_source=whats_new_tutorials&utm_medium=scaled_dot_product_attention_tutorial>`__
+* `torch.compile Tutorial <https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html?utm_source=whats_new_tutorials&utm_medium=torch_compile>`__
+* `Per Sample Gradients <https://pytorch.org/tutorials/intermediate/per_sample_grads.html?utm_source=whats_new_tutorials&utm_medium=per_sample_grads>`__
+* `Jacobians, Hessians, hvp, vhp, and more: composing function transforms <https://pytorch.org/tutorials/intermediate/jacobians_hessians.html?utm_source=whats_new_tutorials&utm_medium=jacobians_hessians>`__
+* `Model Ensembling <https://pytorch.org/tutorials/intermediate/ensembling.html?utm_source=whats_new_tutorials&utm_medium=ensembling>`__
+* `Neural Tangent Kernels <https://pytorch.org/tutorials/intermediate/neural_tangent_kernels.html?utm_source=whats_new_tutorials&utm_medium=neural_tangent_kernels>`__
+* `Reinforcement Learning (PPO) with TorchRL Tutorial <https://pytorch.org/tutorials/intermediate/reinforcement_ppo.html?utm_source=whats_new_tutorials&utm_medium=reinforcement_ppo>`__
+* `Changing Default Device <https://pytorch.org/tutorials/recipes/recipes/changing_default_device.html?utm_source=whats_new_tutorials&utm_medium=changing_default_device>`__
+
 
 .. raw:: html
 
diff --git a/intermediate_source/scaled_dot_product_attention_tutorial.py b/intermediate_source/scaled_dot_product_attention_tutorial.py
index c5f84308f42..80a7bcd2f04 100644
--- a/intermediate_source/scaled_dot_product_attention_tutorial.py
+++ b/intermediate_source/scaled_dot_product_attention_tutorial.py
@@ -1,9 +1,10 @@
 """
-Implementing High-Performance Transformers with SCALED DOT PRODUCT ATTENTION
-================================================================================
+(Beta) Implementing High-Performance Transformers with Scaled Dot Production Attention (SDPA)
+=============================================================================================
 
-"""
 
+**Author:** `Driss Guessous <https://github.com/drisspg>`_
+"""
 
 ######################################################################
 # Summary
@@ -334,4 +335,4 @@ def generate_rand_batch(
 # compilable. In the process we have shown how to the profiling tools can
 # be used to explore the performance characteristics of a user defined
 # module.
-#
\ No newline at end of file
+#

From 98d5ce1c97a40ee47608fff8942d86045ca4a676 Mon Sep 17 00:00:00 2001
From: Svetlana Karslioglu <svekars@fb.com>
Date: Thu, 16 Mar 2023 11:33:09 -0700
Subject: [PATCH 2/6] Add notes on running in colab to the SDPA tutorial

---
 intermediate_source/scaled_dot_product_attention_tutorial.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/intermediate_source/scaled_dot_product_attention_tutorial.py b/intermediate_source/scaled_dot_product_attention_tutorial.py
index 80a7bcd2f04..0c8b4b2518f 100644
--- a/intermediate_source/scaled_dot_product_attention_tutorial.py
+++ b/intermediate_source/scaled_dot_product_attention_tutorial.py
@@ -1,6 +1,6 @@
 """
-(Beta) Implementing High-Performance Transformers with Scaled Dot Production Attention (SDPA)
-=============================================================================================
+(Beta) Implementing High-Performance Transformers with Scaled Dot Product Attention (SDPA)
+==========================================================================================
 
 
 **Author:** `Driss Guessous <https://github.com/drisspg>`_
@@ -35,6 +35,7 @@
 # * `Memory-Efficient Attention <https://github.com/facebookresearch/xformers>`__
 # * A PyTorch implementation defined in C++
 #
+# .. include:: ../beginner_source/new-release-colab.rst
 
 import torch
 import torch.nn as nn

From bdb8b78fbeacc06c1014cc4c5507019954fdd775 Mon Sep 17 00:00:00 2001
From: Svetlana Karslioglu <svekars@fb.com>
Date: Thu, 16 Mar 2023 12:43:08 -0700
Subject: [PATCH 3/6] Change to literalinclude

---
 intermediate_source/scaled_dot_product_attention_tutorial.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/intermediate_source/scaled_dot_product_attention_tutorial.py b/intermediate_source/scaled_dot_product_attention_tutorial.py
index 0c8b4b2518f..61ee1c94b25 100644
--- a/intermediate_source/scaled_dot_product_attention_tutorial.py
+++ b/intermediate_source/scaled_dot_product_attention_tutorial.py
@@ -35,7 +35,7 @@
 # * `Memory-Efficient Attention <https://github.com/facebookresearch/xformers>`__
 # * A PyTorch implementation defined in C++
 #
-# .. include:: ../beginner_source/new-release-colab.rst
+# .. literalinclude:: ../beginner_source/new-release-colab.rst
 
 import torch
 import torch.nn as nn

From a3746b99dc731d5188c2bcd3469e5ba11c35f265 Mon Sep 17 00:00:00 2001
From: Svetlana Karslioglu <svekars@fb.com>
Date: Thu, 16 Mar 2023 12:57:33 -0700
Subject: [PATCH 4/6] Fix

---
 intermediate_source/scaled_dot_product_attention_tutorial.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/intermediate_source/scaled_dot_product_attention_tutorial.py b/intermediate_source/scaled_dot_product_attention_tutorial.py
index 61ee1c94b25..260ff6d9dee 100644
--- a/intermediate_source/scaled_dot_product_attention_tutorial.py
+++ b/intermediate_source/scaled_dot_product_attention_tutorial.py
@@ -35,7 +35,10 @@
 # * `Memory-Efficient Attention <https://github.com/facebookresearch/xformers>`__
 # * A PyTorch implementation defined in C++
 #
-# .. literalinclude:: ../beginner_source/new-release-colab.rst
+"""
+.. literalinclude:: ../beginner_source/new-release-colab.rst
+   :language: rst
+"""
 
 import torch
 import torch.nn as nn

From 25a360ecf61842600253bab130084e88d6e6c8c9 Mon Sep 17 00:00:00 2001
From: Svetlana Karslioglu <svekars@fb.com>
Date: Thu, 16 Mar 2023 13:39:13 -0700
Subject: [PATCH 5/6] Fix

---
 .../scaled_dot_product_attention_tutorial.py                | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/intermediate_source/scaled_dot_product_attention_tutorial.py b/intermediate_source/scaled_dot_product_attention_tutorial.py
index 260ff6d9dee..ed2186fdc67 100644
--- a/intermediate_source/scaled_dot_product_attention_tutorial.py
+++ b/intermediate_source/scaled_dot_product_attention_tutorial.py
@@ -35,10 +35,8 @@
 # * `Memory-Efficient Attention <https://github.com/facebookresearch/xformers>`__
 # * A PyTorch implementation defined in C++
 #
-"""
-.. literalinclude:: ../beginner_source/new-release-colab.rst
-   :language: rst
-"""
+#.. literalinclude:: ../beginner_source/new-release-colab.rst
+#   :language: rst
 
 import torch
 import torch.nn as nn

From 5136c7afdb94feb3bd0ece8d8bd3f26cf8f14d68 Mon Sep 17 00:00:00 2001
From: Svetlana Karslioglu <svekars@fb.com>
Date: Thu, 16 Mar 2023 14:11:39 -0700
Subject: [PATCH 6/6] Fix

---
 intermediate_source/scaled_dot_product_attention_tutorial.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/intermediate_source/scaled_dot_product_attention_tutorial.py b/intermediate_source/scaled_dot_product_attention_tutorial.py
index ed2186fdc67..8161f318ec5 100644
--- a/intermediate_source/scaled_dot_product_attention_tutorial.py
+++ b/intermediate_source/scaled_dot_product_attention_tutorial.py
@@ -35,8 +35,8 @@
 # * `Memory-Efficient Attention <https://github.com/facebookresearch/xformers>`__
 # * A PyTorch implementation defined in C++
 #
-#.. literalinclude:: ../beginner_source/new-release-colab.rst
-#   :language: rst
+# .. literalinclude:: ../beginner_source/new-release-colab.rst
+#    :language: rst
 
 import torch
 import torch.nn as nn