Add rst entry for nn.MultiheadAttention (#19346)

Summary:
Fix #19259 by adding the missing `autoclass` entry for `nn.MultiheadAttention` from [here](https://github.com/pytorch/pytorch/blob/master/torch/nn/modules/activation.py#L676)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/19346

Differential Revision: D14971426

Pulled By: soumith

fbshipit-source-id: ceaaa8ea4618c38fa2bff139e7fa0d6c9ea193ea

diff --git a/docs/source/nn.rst b/docs/source/nn.rst
index 08b3358..1d4bc3e 100644 (file)
--- a/docs/source/nn.rst
+++ b/docs/source/nn.rst
@@ -308,6 +308,11 @@ Non-linear activations (weighted sum, nonlinearity)
 .. autoclass:: LogSigmoid
     :members:
 
+:hidden:`MultiheadAttention`
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+.. autoclass:: MultiheadAttention
+    :members:
+
 :hidden:`PReLU`
 ~~~~~~~~~~~~~~~