Merge branch '2.4-RC-TEST' into rzou/2.4_custom_ops

Author: svekars

.jenkins/build.sh

@@ -21,9 +21,9 @@ 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 2.2 for testing - uncomment to install nightly binaries (update the version as needed).
-# pip uninstall -y torch torchvision torchaudio torchtext torchdata
-# pip3 install torch==2.3.0 torchvision torchaudio --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu121 
+# Install 2.4 for testing - uncomment to install nightly binaries (update the version as needed).
+pip uninstall -y torch torchvision torchaudio torchtext torchdata
+pip3 install torch==2.4.0 torchvision torchaudio --no-cache-dir --index-url https://download.pytorch.org/whl/test/cu124
 
 # Install two language tokenizers for Translation with TorchText tutorial
 python -m spacy download en_core_web_sm
@@ -36,7 +36,6 @@ awsv2 configure set default.s3.multipart_threshold 5120MB
 if [[ "${JOB_TYPE}" == "worker" ]]; then
   # Step 1: Remove runnable code from tutorials that are not supposed to be run
   python $DIR/remove_runnable_code.py beginner_source/aws_distributed_training_tutorial.py beginner_source/aws_distributed_training_tutorial.py || true
-  # python $DIR/remove_runnable_code.py advanced_source/ddp_pipeline_tutorial.py advanced_source/ddp_pipeline_tutorial.py || true
   # Temp remove for mnist download issue. (Re-enabled for 1.8.1)
   # python $DIR/remove_runnable_code.py beginner_source/fgsm_tutorial.py beginner_source/fgsm_tutorial.py || true
   # python $DIR/remove_runnable_code.py intermediate_source/spatial_transformer_tutorial.py intermediate_source/spatial_transformer_tutorial.py || true

.jenkins/validate_tutorials_built.py

@@ -29,7 +29,6 @@
     "intermediate_source/fx_conv_bn_fuser",
     "intermediate_source/_torch_export_nightly_tutorial",  # does not work on release
     "advanced_source/super_resolution_with_onnxruntime",
-    "advanced_source/ddp_pipeline",  # requires 4 gpus
     "advanced_source/usb_semisup_learn", # fails with CUDA OOM error, should try on a different worker
     "prototype_source/fx_graph_mode_ptq_dynamic",
     "prototype_source/vmap_recipe",
@@ -53,7 +52,10 @@
     "recipes_source/recipes/Captum_Recipe",
     "intermediate_source/flask_rest_api_tutorial",
     "intermediate_source/text_to_speech_with_torchaudio",
-    "intermediate_source/tensorboard_profiler_tutorial" # reenable after 2.0 release.
+    "intermediate_source/tensorboard_profiler_tutorial", # reenable after 2.0 release.
+    "intermediate_source/inductor_debug_cpu", # reenable after 2942 
+    "beginner_source/onnx/onnx_registry_tutorial", # reenable after 2941 is fixed.
+    "intermediate_source/torch_export_tutorial" # reenable after 2940 is fixed.
 ]
 
 def tutorial_source_dirs() -> List[Path]:

_static/css/custom.css

@@ -71,3 +71,23 @@
 .sd-card:hover:after {
     transform: scaleX(1);
 }
+
+.card-prerequisites:hover {
+    transition: none;
+    border: none;
+}
+
+.card-prerequisites:hover:after {
+    transition: none;
+    transform: none;
+}
+
+.card-prerequisites:after {
+    display: block;
+    content: '';
+    border-bottom: none;
+    background-color: #fff;
+    transform: none;
+    transition: none;
+    transform-origin: none;
+}

advanced_source/cpp_custom_ops.rst

@@ -8,14 +8,16 @@ Custom C++ and CUDA Operators
 .. grid:: 2
 
     .. grid-item-card:: :octicon:`mortar-board;1em;` What you will learn
+       :class-card: card-prerequisites
 
-      * How to integrate custom operators written in C++/CUDA with PyTorch
-      * How to test custom operators using ``torch.library.opcheck``
+       * How to integrate custom operators written in C++/CUDA with PyTorch
+       * How to test custom operators using ``torch.library.opcheck``
 
     .. grid-item-card:: :octicon:`list-unordered;1em;` Prerequisites
+       :class-card: card-prerequisites
 
-      * PyTorch 2.4 or later
-      * Basic understanding of C++ and CUDA programming
+       * PyTorch 2.4 or later
+       * Basic understanding of C++ and CUDA programming
 
 PyTorch offers a large library of operators that work on Tensors (e.g. torch.add, torch.sum, etc).
 However, you may wish to bring a new custom operator to PyTorch. This tutorial demonstrates the