[Perceiver] Skip multi-gpu tests for now (#14813)

* [Perceiver] Skip multi-gpu tests for now

* Update tests/test_modeling_perceiver.py

* up

* up

docs/source/model_doc/perceiver.mdx

@@ -86,6 +86,10 @@ is implemented in the library. Note that the models available in the library onl
 with the Perceiver. There are many more use cases, including question answering, named-entity recognition, object detection, 
 audio classification, video classification, etc. 
 
+**Note**:
+
+- Perceiver does **not** work with `torch.nn.DataParallel` due to a bug in PyTorch, see [issue #36035](https://github.com/pytorch/pytorch/issues/36035)
+
 ## Perceiver specific outputs
 
 [[autodoc]] models.perceiver.modeling_perceiver.PerceiverModelOutput
@@ -208,4 +212,4 @@ audio classification, video classification, etc.
 ## PerceiverForMultimodalAutoencoding
 
 [[autodoc]] PerceiverForMultimodalAutoencoding
-    - forward
+    - forward

docs/source/model_doc/reformer.rst

@@ -35,6 +35,11 @@ while being much more memory-efficient and much faster on long sequences.*
 This model was contributed by `patrickvonplaten <https://huggingface.co/patrickvonplaten>`__. The Authors' code can be
 found `here <https://github.com/google/trax/tree/master/trax/models/reformer>`__.
 
+**Note**:
+
+- Reformer does **not** work with `torch.nn.DataParallel` due to a bug in PyTorch, see `issue #36035
+  <https://github.com/pytorch/pytorch/issues/36035>`__
+
 Axial Positional Encodings
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

docs/source/model_doc/transformerxl.rst

@@ -44,6 +44,11 @@ Tips:
 This model was contributed by `thomwolf <https://huggingface.co/thomwolf>`__. The original code can be found `here
 <https://github.com/kimiyoung/transformer-xl>`__.
 
+**Note**:
+
+- TransformerXL does **not** work with `torch.nn.DataParallel` due to a bug in PyTorch, see `issue #36035
+  <https://github.com/pytorch/pytorch/issues/36035>`__
+
 
 TransfoXLConfig
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~