Merge branch 'main' into update_seq2seq_tutorial

Author: 4ydan

.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
@@ -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==1.1.0; platform_system == "Linux"
-fbgemm-gpu==1.1.0; platform_system == "Linux"
+fbgemm-gpu==1.2.0; platform_system == "Linux"

.jenkins/build.sh

@@ -22,13 +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
-sudo pip uninstall -y torch torchvision torchaudio torchtext torchdata torchrl tensordict
-pip3 install torch==2.7.0 torchvision torchaudio --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu126
-#sudo pip uninstall -y fbgemm-gpu
+# 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

@@ -51,14 +51,8 @@
     "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.
-    "intermediate_source/mario_rl_tutorial", # reenable after 3302 is fixed
-    "intermediate_source/reinforcement_ppo", # reenable after 3302 is fixed
-    "intermediate_source/pinmem_nonblock", # reenable after 3302 is fixed
-    "intermediate_source/dqn_with_rnn_tutorial", # reenable after 3302 is fixed
-    "advanced_source/pendulum", # reenable after 3302 is fixed
-    "advanced_source/coding_ddpg", # reenable after 3302 is fixed
-    "intermediate_source/torchrec_intro_tutorial", # reenable after 3302 is fixed
-    "recipes_source/recipes/reasoning_about_shapes" # reenable after 3326 is fixed
+    "intermediate_source/torchrec_intro_tutorial", # reenable after 3302 is fixe
+    "intermediate_source/memory_format_tutorial", # causes other tutorials like torch_logs fail. "state" issue, reseting dynamo didn't help
 ]
 
 def tutorial_source_dirs() -> List[Path]:

_templates/layout.html

@@ -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"/>
 
-<script>
-    //temporarily add a link to survey
-    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 %}

beginner_source/basics/optimization_tutorial.py

@@ -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.
 #

beginner_source/colab.rst

@@ -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.
 

conf.py

@@ -99,10 +99,16 @@
 
 def reset_seeds(gallery_conf, fname):
     torch.cuda.empty_cache()
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+    torch._dynamo.reset()
+    torch._inductor.config.force_disable_caches = True
     torch.manual_seed(42)
     torch.set_default_device(None)
     random.seed(10)
     numpy.random.seed(10)
+    torch.set_grad_enabled(True)
+
     gc.collect()
 
 sphinx_gallery_conf = {

en-wordlist.txt

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

index.rst

@@ -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
 

intermediate_source/torch_compile_tutorial.py

@@ -101,8 +101,11 @@ def forward(self, x):
         return torch.nn.functional.relu(self.lin(x))
 
 mod = MyModule()
-opt_mod = torch.compile(mod)
-print(opt_mod(t))
+mod.compile()
+print(mod(t))
+## or:
+# opt_mod = torch.compile(mod)
+# print(opt_mod(t))
 
 ######################################################################
 # torch.compile and Nested Calls
@@ -135,8 +138,8 @@ def forward(self, x):
         return torch.nn.functional.relu(self.outer_lin(x))
 
 outer_mod = OuterModule()
-opt_outer_mod = torch.compile(outer_mod)
-print(opt_outer_mod(t))
+outer_mod.compile()
+print(outer_mod(t))
 
 ######################################################################
 # We can also disable some functions from being compiled by using
@@ -197,6 +200,12 @@ def outer_function():
 # 4. **Compile Leaf Functions First:** In complex models with multiple nested
 # functions and modules, start by compiling the leaf functions or modules first.
 # For more information see `TorchDynamo APIs for fine-grained tracing <https://pytorch.org/docs/stable/torch.compiler_fine_grain_apis.html>`__.
+#
+# 5. **Prefer ``mod.compile()`` over ``torch.compile(mod)``:** Avoids ``_orig_`` prefix issues in ``state_dict``.
+#
+# 6. **Use ``fullgraph=True`` to catch graph breaks:** Helps ensure end-to-end compilation, maximizing speedup
+# and compatibility with ``torch.export``.
+
 
 ######################################################################
 # Demonstrating Speedups