Merge branch 'main' into main

Author: ahoblitz

advanced_source/static_quantization_tutorial.rst

@@ -59,7 +59,7 @@ to enable quantization:
 - Replace ReLU6 with ReLU 
 
 Note: this code is taken from 
-`here <https://github.com/pytorch/vision/blob/master/torchvision/models/mobilenet.py>`_.  
+`here <https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv2.py>`_.
 
 .. code:: python
 

intermediate_source/FSDP_adavnced_tutorial.rst

@@ -74,8 +74,8 @@ summarization using WikiHow dataset.  The main focus of this tutorial is to
 highlight different available features in FSDP that are helpful for training
 large scale model above 3B parameters. Also, we cover specific features for
 Transformer based models. The code for this tutorial is available in  `Pytorch
-Examples
-<https://github.com/HamidShojanazeri/examples/tree/FSDP_example/distributed/FSDP/>`__.
+examples
+<https://github.com/pytorch/examples/tree/main/distributed/FSDP/>`__.
 
 
 *Setup*
@@ -97,13 +97,13 @@ Please create a `data` folder, download the WikiHow dataset from `wikihowAll.csv
 `wikihowSep.cs <https://ucsb.app.box.com/s/7yq601ijl1lzvlfu4rjdbbxforzd2oag>`__,
 and place them in the `data` folder.  We will use the wikihow dataset from
 `summarization_dataset
-<https://github.com/HamidShojanazeri/examples/blob/FSDP_example/distributed/FSDP/summarization_dataset.py>`__.
+<https://github.com/pytorch/examples/blob/main/distributed/FSDP/summarization_dataset.py>`__.
 
 Next, we add the following code snippets to a Python script “T5_training.py”.
 
 .. note::
    The full source code for this tutorial is available in `PyTorch examples
-   <https://github.com/HamidShojanazeri/examples/tree/FSDP_example/distributed/FSDP>`__.
+   <https://github.com/pytorch/examples/tree/main/distributed/FSDP/>`__.
 
 1.3  Import necessary packages:
 

intermediate_source/mario_rl_tutorial.py

@@ -32,6 +32,9 @@
 #
 #      %%bash
 #      pip install gym-super-mario-bros==7.4.0
+#      pip install tensordict==0.2.0
+#      pip install torchrl==0.2.0
+#
 
 import torch
 from torch import nn

intermediate_source/parametrizations.py

@@ -227,7 +227,7 @@ def __init__(self, n):
 
     def forward(self, X):
         # (I + X)(I - X)^{-1}
-        return torch.solve(self.Id + X, self.Id - X).solution
+        return torch.linalg.solve(self.Id - X, self.Id + X)
 
 layer = nn.Linear(3, 3)
 parametrize.register_parametrization(layer, "weight", Skew())
@@ -301,13 +301,13 @@ def __init__(self, n):
     def forward(self, X):
         # Assume X skew-symmetric
         # (I + X)(I - X)^{-1}
-        return torch.solve(self.Id + X, self.Id - X).solution
+        return torch.linalg.solve(self.Id - X, self.Id + X)
 
     def right_inverse(self, A):
         # Assume A orthogonal
         # See https://en.wikipedia.org/wiki/Cayley_transform#Matrix_map
         # (X - I)(X + I)^{-1}
-        return torch.solve(X - self.Id, self.Id + X).solution
+        return torch.linalg.solve(X + self.Id, self.Id - X)
 
 layer_orthogonal = nn.Linear(3, 3)
 parametrize.register_parametrization(layer_orthogonal, "weight", Skew())

intermediate_source/pruning_tutorial.py

@@ -44,9 +44,9 @@
 class LeNet(nn.Module):
     def __init__(self):
         super(LeNet, self).__init__()
-        # 1 input image channel, 6 output channels, 3x3 square conv kernel
-        self.conv1 = nn.Conv2d(1, 6, 3)
-        self.conv2 = nn.Conv2d(6, 16, 3)
+        # 1 input image channel, 6 output channels, 5x5 square conv kernel
+        self.conv1 = nn.Conv2d(1, 6, 5)
+        self.conv2 = nn.Conv2d(6, 16, 5)
         self.fc1 = nn.Linear(16 * 5 * 5, 120)  # 5x5 image dimension
         self.fc2 = nn.Linear(120, 84)
         self.fc3 = nn.Linear(84, 10)

recipes_source/recipes/tuning_guide.py

@@ -193,15 +193,12 @@ def fused_gelu(x):
 #
 #    numactl --cpunodebind=N --membind=N python <pytorch_script>
 
-###############################################################################
-# More detailed descriptions can be found `here <https://software.intel.com/content/www/us/en/develop/articles/how-to-get-better-performance-on-pytorchcaffe2-with-intel-acceleration.html>`_.
-
 ###############################################################################
 # Utilize OpenMP
 # ~~~~~~~~~~~~~~
 # OpenMP is utilized to bring better performance for parallel computation tasks.
 # ``OMP_NUM_THREADS`` is the easiest switch that can be used to accelerate computations. It determines number of threads used for OpenMP computations.
-# CPU affinity setting controls how workloads are distributed over multiple cores. It affects communication overhead, cache line invalidation overhead, or page thrashing, thus proper setting of CPU affinity brings performance benefits. ``GOMP_CPU_AFFINITY`` or ``KMP_AFFINITY`` determines how to bind OpenMP* threads to physical processing units. Detailed information can be found `here <https://software.intel.com/content/www/us/en/develop/articles/how-to-get-better-performance-on-pytorchcaffe2-with-intel-acceleration.html>`_.
+# CPU affinity setting controls how workloads are distributed over multiple cores. It affects communication overhead, cache line invalidation overhead, or page thrashing, thus proper setting of CPU affinity brings performance benefits. ``GOMP_CPU_AFFINITY`` or ``KMP_AFFINITY`` determines how to bind OpenMP* threads to physical processing units.
 
 ###############################################################################
 # With the following command, PyTorch run the task on N OpenMP threads.