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.
 #