Merge branch 'main' into patch-2

Author: svekars

beginner_source/basics/optimization_tutorial.py

@@ -76,7 +76,7 @@ def forward(self, x):
 # (`read more <https://pytorch.org/tutorials/beginner/hyperparameter_tuning_tutorial.html>`__ about hyperparameter tuning)
 #
 # We define the following hyperparameters for training:
-#  - **Number of Epochs** - the number times to iterate over the dataset
+#  - **Number of Epochs** - the number of times to iterate over the dataset
 #  - **Batch Size** - the number of data samples propagated through the network before the parameters are updated
 #  - **Learning Rate** - how much to update models parameters at each batch/epoch. Smaller values yield slow learning speed, while large values may result in unpredictable behavior during training.
 #

intermediate_source/torch_compile_tutorial.py

@@ -101,8 +101,11 @@ def forward(self, x):
         return torch.nn.functional.relu(self.lin(x))
 
 mod = MyModule()
-opt_mod = torch.compile(mod)
-print(opt_mod(t))
+mod.compile()
+print(mod(t))
+## or:
+# opt_mod = torch.compile(mod)
+# print(opt_mod(t))
 
 ######################################################################
 # torch.compile and Nested Calls
@@ -135,8 +138,8 @@ def forward(self, x):
         return torch.nn.functional.relu(self.outer_lin(x))
 
 outer_mod = OuterModule()
-opt_outer_mod = torch.compile(outer_mod)
-print(opt_outer_mod(t))
+outer_mod.compile()
+print(outer_mod(t))
 
 ######################################################################
 # We can also disable some functions from being compiled by using
@@ -197,6 +200,12 @@ def outer_function():
 # 4. **Compile Leaf Functions First:** In complex models with multiple nested
 # functions and modules, start by compiling the leaf functions or modules first.
 # For more information see `TorchDynamo APIs for fine-grained tracing <https://pytorch.org/docs/stable/torch.compiler_fine_grain_apis.html>`__.
+#
+# 5. **Prefer ``mod.compile()`` over ``torch.compile(mod)``:** Avoids ``_orig_`` prefix issues in ``state_dict``.
+#
+# 6. **Use ``fullgraph=True`` to catch graph breaks:** Helps ensure end-to-end compilation, maximizing speedup
+# and compatibility with ``torch.export``.
+
 
 ######################################################################
 # Demonstrating Speedups

prototype_source/inductor_windows.rst

@@ -22,10 +22,9 @@ Install a Compiler
 
 C++ compiler is required for TorchInductor optimization, let's take Microsoft Visual C++ (MSVC) as an example.
 
-1. Download and install `MSVC <https://visualstudio.microsoft.com/downloads/>`_.
+#. Download and install `MSVC <https://visualstudio.microsoft.com/downloads/>`_.
 
-1. During Installation, select **Workloads** and then **Desktop & Mobile**.
-1. Select a checkmark on **Desktop Development with C++** and install.
+#. During Installation, select **Workloads** and then **Desktop & Mobile**. Select a checkmark on **Desktop Development with C++** and install.
 
 .. image:: ../_static/img/install_msvc.png