Merge branch 'main' into fix-typos

Author: IvanBarbosaFilho

.ci/docker/requirements.txt

@@ -14,7 +14,7 @@ tqdm==4.66.1
 numpy==1.24.4
 matplotlib
 librosa
-torch==2.6
+torch==2.7
 torchvision
 torchdata
 networkx
@@ -36,7 +36,7 @@ datasets
 transformers
 torchmultimodal-nightly # needs to be updated to stable as soon as it's avaialable
 onnx
-onnxscript
+onnxscript>=0.2.2
 onnxruntime
 evaluate
 accelerate>=0.20.1
@@ -67,7 +67,7 @@ iopath
 pygame==2.6.0
 pycocotools
 semilearn==0.3.2
-torchao==0.5.0
+torchao==0.10.0
 segment_anything==1.0
-torchrec==1.0.0; platform_system == "Linux"
-fbgemm-gpu==1.1.0; platform_system == "Linux"
+torchrec==1.1.0; platform_system == "Linux"
+fbgemm-gpu==1.2.0; platform_system == "Linux"

.github/workflows/build-tutorials.yml

@@ -22,15 +22,15 @@ jobs:
           - { shard: 4, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
           - { shard: 5, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
           - { shard: 6, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
-          - { shard: 7, num_shards: 15, runner: "linux.4xlarge.nvidia.gpu" }
-          - { shard: 8, num_shards: 15, runner: "linux.4xlarge.nvidia.gpu" }
-          - { shard: 9, num_shards: 15, runner: "linux.4xlarge.nvidia.gpu" }
-          - { shard: 10, num_shards: 15, runner: "linux.4xlarge.nvidia.gpu" }
-          - { shard: 11, num_shards: 15, runner: "linux.4xlarge.nvidia.gpu" }
-          - { shard: 12, num_shards: 15, runner: "linux.4xlarge.nvidia.gpu" }
-          - { shard: 13, num_shards: 15, runner: "linux.4xlarge.nvidia.gpu" }
-          - { shard: 14, num_shards: 15, runner: "linux.4xlarge.nvidia.gpu" }
-          - { shard: 15, num_shards: 15, runner: "linux.4xlarge.nvidia.gpu" }
+          - { shard: 7, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
+          - { shard: 8, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
+          - { shard: 9, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
+          - { shard: 10, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
+          - { shard: 11, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
+          - { shard: 12, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
+          - { shard: 13, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
+          - { shard: 14, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
+          - { shard: 15, num_shards: 15, runner: "linux.g5.4xlarge.nvidia.gpu" }
       fail-fast: false
     runs-on: ${{ matrix.runner }}
     steps:

.jenkins/build.sh

@@ -22,11 +22,10 @@ sudo apt-get install -y pandoc
 #Install PyTorch Nightly for test.
 # Nightly - pip install --pre torch torchvision torchaudio -f https://download.pytorch.org/whl/nightly/cu102/torch_nightly.html
 # Install 2.5 to merge all 2.4 PRs - uncomment to install nightly binaries (update the version as needed).
-# sudo pip uninstall -y torch torchvision torchaudio torchtext torchdata
-# sudo pip3 install torch==2.6.0 torchvision --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu124
 # sudo pip uninstall -y fbgemm-gpu torchrec
+# sudo pip uninstall -y torch torchvision torchaudio torchtext torchdata torchrl tensordict
 # sudo pip3 install fbgemm-gpu==1.1.0 torchrec==1.0.0 --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu124
-
+# pip3 install torch==2.7.0 torchvision torchaudio --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu126
 # Install two language tokenizers for Translation with TorchText tutorial
 python -m spacy download en_core_web_sm
 python -m spacy download de_core_news_sm

.jenkins/validate_tutorials_built.py

@@ -31,6 +31,7 @@
     "prototype_source/vmap_recipe",
     "prototype_source/torchscript_freezing",
     "prototype_source/nestedtensor",
+    "prototype_source/gpu_direct_storage", # requires specific filesystem + GPUDirect Storage to be set up
     "recipes_source/recipes/saving_and_loading_models_for_inference",
     "recipes_source/recipes/saving_multiple_models_in_one_file",
     "recipes_source/recipes/tensorboard_with_pytorch",
@@ -50,7 +51,8 @@
     "intermediate_source/flask_rest_api_tutorial",
     "intermediate_source/text_to_speech_with_torchaudio",
     "intermediate_source/tensorboard_profiler_tutorial", # reenable after 2.0 release.
-    "advanced_source/semi_structured_sparse" # reenable after 3303 is fixed.
+    "advanced_source/semi_structured_sparse", # reenable after 3303 is fixed.
+    "intermediate_source/torchrec_intro_tutorial", # reenable after 3302 is fixe
 ]
 
 def tutorial_source_dirs() -> List[Path]:

_static/img/distributed/fsdp_implicit.png

@@ -211,14 +211,5 @@
 
 <img height="1" width="1" style="border-style:none;" alt="" src="https://www.googleadservices.com/pagead/conversion/795629140/?label=txkmCPmdtosBENSssfsC&amp;guid=ON&amp;script=0"/>
 
-//temporarily add a link to survey
-<script>
-    var survey = '<div class="survey-banner"><p><i class="fas fa-poll" aria-hidden="true">&nbsp </i> Take the <a href="https://forms.gle/KZ4xGL65VRMYNbbG6">PyTorch Docs/Tutorials survey</a>.</p></div>'
-    if ($(".pytorch-call-to-action-links").length) {
-        $(".pytorch-call-to-action-links").before(survey);
-    } else {
-        $("#pytorch-article").prepend(survey);
-    }
-</script>
 
 {% endblock %}

_static/img/install_msvc.png

@@ -13,7 +13,7 @@ Learn the Basics
     Tensors
     https://pytorch.org/tutorials/beginner/basics/tensor_tutorial.html
 
-4. dataquickstart_tutorial.py
+4. data_tutorial.py
     Datasets & DataLoaders
     https://pytorch.org/tutorials/beginner/basics/data_tutorial.html
 

_static/img/pt2e_quant_xpu_inductor.png

@@ -76,7 +76,7 @@ def forward(self, x):
 # (`read more <https://pytorch.org/tutorials/beginner/hyperparameter_tuning_tutorial.html>`__ about hyperparameter tuning)
 #
 # We define the following hyperparameters for training:
-#  - **Number of Epochs** - the number times to iterate over the dataset
+#  - **Number of Epochs** - the number of times to iterate over the dataset
 #  - **Batch Size** - the number of data samples propagated through the network before the parameters are updated
 #  - **Learning Rate** - how much to update models parameters at each batch/epoch. Smaller values yield slow learning speed, while large values may result in unpredictable behavior during training.
 #

_templates/layout.html

@@ -11,7 +11,7 @@ PyTorch Version in Google Colab
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Wen you are running a tutorial that requires a version of PyTorch that has
-jst been released, that version might not be yet available in Google Colab.
+just been released, that version might not be yet available in Google Colab.
 To check that you have the required ``torch`` and compatible domain libraries
 installed, run ``!pip list``.
 
@@ -27,7 +27,7 @@ Using Tutorial Data from Google Drive in Colab
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 We've added a new feature to tutorials that allows users to open the
-ntebook associated with a tutorial in Google Colab. You may need to
+notebook associated with a tutorial in Google Colab. You may need to
 copy data to your Google drive account to get the more complex tutorials
 to work.
 

beginner_source/basics/README.txt

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 PyTorch: Tensors and autograd
 -------------------------------

beginner_source/basics/optimization_tutorial.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 PyTorch: Defining New autograd Functions
 ----------------------------------------

beginner_source/colab.rst

@@ -33,8 +33,6 @@
 sys.path.insert(0, os.path.abspath('./.jenkins'))
 import pytorch_sphinx_theme
 import torch
-import numpy
-import gc
 import glob
 import random
 import shutil
@@ -49,6 +47,46 @@
 pio.renderers.default = 'sphinx_gallery'
 
 
+import sphinx_gallery.gen_rst
+import multiprocessing
+
+# Monkey patch sphinx gallery to run each example in an isolated process so that
+# we don't need to worry about examples changing global state.
+#
+# Alt option 1: Parallelism was added to sphinx gallery (a later version that we
+# are not using yet) using joblib, but it seems to result in errors for us, and
+# it has no effect if you set parallel = 1 (it will not put each file run into
+# its own process and run singly) so you need parallel >= 2, and there may be
+# tutorials that cannot be run in parallel.
+#
+# Alt option 2: Run sphinx gallery once per file (similar to how we shard in CI
+# but with shard sizes of 1), but running sphinx gallery for each file has a
+# ~5min overhead, resulting in the entire suite taking ~2x time
+def call_fn(func, args, kwargs, result_queue):
+    try:
+        result = func(*args, **kwargs)
+        result_queue.put((True, result))
+    except Exception as e:
+        result_queue.put((False, str(e)))
+
+def call_in_subprocess(func):
+    def wrapper(*args, **kwargs):
+        result_queue = multiprocessing.Queue()
+        p = multiprocessing.Process(
+            target=call_fn,
+            args=(func, args, kwargs, result_queue)
+        )
+        p.start()
+        p.join()
+        success, result = result_queue.get()
+        if success:
+            return result
+        else:
+            raise RuntimeError(f"Error in subprocess: {result}")
+    return wrapper
+
+sphinx_gallery.gen_rst.generate_file_rst = call_in_subprocess(sphinx_gallery.gen_rst.generate_file_rst)
+
 try:
     import torchvision
 except ImportError:
@@ -97,14 +135,6 @@
 
 # -- Sphinx-gallery configuration --------------------------------------------
 
-def reset_seeds(gallery_conf, fname):
-    torch.cuda.empty_cache()
-    torch.manual_seed(42)
-    torch.set_default_device(None)
-    random.seed(10)
-    numpy.random.seed(10)
-    gc.collect()
-
 sphinx_gallery_conf = {
     'examples_dirs': ['beginner_source', 'intermediate_source',
                       'advanced_source', 'recipes_source', 'prototype_source'],
@@ -115,7 +145,6 @@ def reset_seeds(gallery_conf, fname):
     'first_notebook_cell': ("# For tips on running notebooks in Google Colab, see\n"
                             "# https://pytorch.org/tutorials/beginner/colab\n"
                             "%matplotlib inline"),
-    'reset_modules': (reset_seeds),
     'ignore_pattern': r'_torch_export_nightly_tutorial.py',
     'pypandoc': {'extra_args': ['--mathjax', '--toc'],
                  'filters': ['.jenkins/custom_pandoc_filter.py'],

beginner_source/examples_autograd/polynomial_autograd.py

@@ -698,3 +698,14 @@ TorchServe
 Inductor’s
 onwards
 recompilations
+BiasCorrection
+ELU
+GELU
+NNCF
+OpenVINO
+OpenVINOQuantizer
+PReLU
+Quantizer
+SmoothQuant
+quantizer
+quantizers

beginner_source/examples_autograd/polynomial_custom_function.py

@@ -3,13 +3,11 @@ Welcome to PyTorch Tutorials
 
 **What's new in PyTorch tutorials?**
 
-* `Dynamic Compilation Control with torch.compiler.set_stance <https://pytorch.org/tutorials/recipes/torch_compiler_set_stance_tutorial.html>`__
-* `Accelerating PyTorch Transformers by replacing nn.Transformer with Nested Tensors and torch.compile() <https://pytorch.org/tutorials/intermediate/transformer_building_blocks.html>`__
-* `Understanding the torch.export Flow and Solutions to Common Challenges <https://pytorch.org/tutorials/recipes/torch_export_challenges_solutions.html>`__
-* Updated `torch.export Tutorial <https://pytorch.org/tutorials/intermediate/torch_export_tutorial.html#constraints-dynamic-shapes>`__ with automatic dynamic shapes ``Dim.AUTO``
-* Updated `torch.export AOTInductor Tutorial for Python runtime <https://pytorch.org/tutorials/recipes/torch_export_aoti_python.html>`__
-* Updated `Using User-Defined Triton Kernels with torch.compile <https://pytorch.org/tutorials/recipes/torch_compile_user_defined_triton_kernel_tutorial.html#composability>`__ with new ``torch.library.triton_op``
-* Updated `Compile Time Caching in torch.compile <https://pytorch.org/tutorials/recipes/torch_compile_caching_tutorial.html>`__ with new ``Mega-Cache``
+* `Utilizing Torch Function modes with torch.compile <https://pytorch.org/tutorials/recipes/torch_compile_torch_function_modes.html>`__
+* `Context Parallel Tutorial <https://pytorch.org/tutorials/prototype/context_parallel.html>`__
+* `PyTorch 2 Export Quantization with Intel GPU Backend through Inductor <https://pytorch.org/tutorials/prototype/pt2e_quant_xpu_inductor.html>`__
+* `(beta) Explicit horizontal fusion with foreach_map and torch.compile <https://pytorch.org/tutorials/recipes/foreach_map.html>`__
+* Updated `Inductor Windows CPU Tutorial <https://pytorch.org/tutorials/prototype/inductor_windows.html>`__
 
 .. raw:: html
 
@@ -768,14 +766,14 @@ Welcome to PyTorch Tutorials
    :tags: Parallel-and-Distributed-Training
 
 .. customcarditem::
-   :header: Getting Started with Fully Sharded Data Parallel(FSDP)
-   :card_description: Learn how to train models with Fully Sharded Data Parallel package.
+   :header: Getting Started with Fully Sharded Data Parallel (FSDP2)
+   :card_description: Learn how to train models with Fully Sharded Data Parallel (fully_shard) package.
    :image: _static/img/thumbnails/cropped/Getting-Started-with-FSDP.png
    :link: intermediate/FSDP_tutorial.html
    :tags: Parallel-and-Distributed-Training
 
 .. customcarditem::
-   :header: Advanced Model Training with Fully Sharded Data Parallel (FSDP)
+   :header: Advanced Model Training with Fully Sharded Data Parallel (FSDP1)
    :card_description: Explore advanced model training with Fully Sharded Data Parallel package.
    :image: _static/img/thumbnails/cropped/Getting-Started-with-FSDP.png
    :link: intermediate/FSDP_advanced_tutorial.html