Fix a typo in scaled_dot_product_attention_tutorial.py (#2549)

ganghe74 · Svetlana Karslioglu · web-flow · commit e28eace976aa · 2023-09-07T13:43:36.000-07:00
``CausaulSelfAttention`` to ``CausalSelfAttention``

Co-authored-by: Svetlana Karslioglu &lt;svekars@fb.com&gt;
diff --git a/intermediate_source/scaled_dot_product_attention_tutorial.py b/intermediate_source/scaled_dot_product_attention_tutorial.py
@@ -317,7 +317,7 @@ def generate_rand_batch(
 # on the same set of functions for both modules.
 # The reason for this here is that ``torch.compile`` is very good at removing the
 # framework overhead associated with PyTorch. If your model is launching
-# large, efficient CUDA kernels, which in this case ``CausaulSelfAttention``
+# large, efficient CUDA kernels, which in this case ``CausalSelfAttention``
 # is, then the overhead of PyTorch can be hidden.
 #
 # In reality, your module does not normally consist of a singular

Original file line number	Diff line number	Diff line change
`@@ -317,7 +317,7 @@ def generate_rand_batch(`
`317`	`317`	`# on the same set of functions for both modules.`
`318`	`318`	# The reason for this here is that ``torch.compile`` is very good at removing the
`319`	`319`	`# framework overhead associated with PyTorch. If your model is launching`
`320`		-# large, efficient CUDA kernels, which in this case ``CausaulSelfAttention``
	`320`	+# large, efficient CUDA kernels, which in this case ``CausalSelfAttention``
`321`	`321`	`# is, then the overhead of PyTorch can be hidden.`
`322`	`322`	`#`
`323`	`323`	`# In reality, your module does not normally consist of a singular`