Apply suggestions from code review

agunapal · svekars · web-flow · commit 67bc08075551 · 2024-08-21T13:23:42.000-07:00
Co-authored-by: Svetlana Karslioglu &lt;svekars@meta.com&gt;
diff --git a/recipes_source/torch_export_aoti_python.py b/recipes_source/torch_export_aoti_python.py
@@ -51,7 +51,7 @@
 # We will use the TorchVision pretrained `ResNet18` model and TorchInductor on the 
 # exported PyTorch program using :func:`torch._inductor.aot_compile`.
 #
-#  .. note::
+# .. note::
 #
 #       This API also supports :func:`torch.compile` options like ``mode``
 #       This means that if used on a CUDA enabled device, you can, for example, set ``"max_autotune": True``
@@ -107,7 +107,7 @@
 # we added a new API called :func:`torch._export.aot_load` to load the shared library in the Python runtime.
 # The API follows a structure similar to the :func:`torch.jit.load` API . You need to specify the path 
 # of the shared library and the device where it should be loaded.
-#  .. note::
+# .. note::
 #
 #      In the example above, we specified ``batch_size=1`` for inference and  it still functions correctly even though we specified ``min=2`` in 
 #      :func:`torch.export.export`.

Original file line number	Diff line number	Diff line change
`@@ -51,7 +51,7 @@`
`51`	`51`	# We will use the TorchVision pretrained `ResNet18` model and TorchInductor on the
`52`	`52`	# exported PyTorch program using :func:`torch._inductor.aot_compile`.
`53`	`53`	`#`
`54`		`-# .. note::`
	`54`	`+# .. note::`
`55`	`55`	`#`
`56`	`56`	# This API also supports :func:`torch.compile` options like ``mode``
`57`	`57`	# This means that if used on a CUDA enabled device, you can, for example, set ``"max_autotune": True``
`@@ -107,7 +107,7 @@`
`107`	`107`	# we added a new API called :func:`torch._export.aot_load` to load the shared library in the Python runtime.
`108`	`108`	# The API follows a structure similar to the :func:`torch.jit.load` API . You need to specify the path
`109`	`109`	`# of the shared library and the device where it should be loaded.`
`110`		`-# .. note::`
	`110`	`+# .. note::`
`111`	`111`	`#`
`112`	`112`	# In the example above, we specified ``batch_size=1`` for inference and it still functions correctly even though we specified ``min=2`` in
`113`	`113`	# :func:`torch.export.export`.