Update (base update)

[ghstack-poisoned]

.ci/docker/build.sh

@@ -236,7 +236,7 @@ case "$image" in
     TRITON=yes
     ;;
   pytorch-linux-focal-py3-clang10-onnx)
-    ANACONDA_PYTHON_VERSION=3.8
+    ANACONDA_PYTHON_VERSION=3.9
     CLANG_VERSION=10
     PROTOBUF=yes
     DB=yes
@@ -245,7 +245,7 @@ case "$image" in
     ONNX=yes
     ;;
   pytorch-linux-focal-py3-clang9-android-ndk-r21e)
-    ANACONDA_PYTHON_VERSION=3.8
+    ANACONDA_PYTHON_VERSION=3.9
     CLANG_VERSION=9
     LLVMDEV=yes
     PROTOBUF=yes
@@ -254,8 +254,8 @@ case "$image" in
     GRADLE_VERSION=6.8.3
     NINJA_VERSION=1.9.0
     ;;
-  pytorch-linux-focal-py3.8-clang10)
-    ANACONDA_PYTHON_VERSION=3.8
+  pytorch-linux-focal-py3.9-clang10)
+    ANACONDA_PYTHON_VERSION=3.9
     CLANG_VERSION=10
     PROTOBUF=yes
     DB=yes
@@ -276,8 +276,8 @@ case "$image" in
     CONDA_CMAKE=yes
     TRITON=yes
     ;;
-  pytorch-linux-focal-py3.8-gcc9)
-    ANACONDA_PYTHON_VERSION=3.8
+  pytorch-linux-focal-py3.9-gcc9)
+    ANACONDA_PYTHON_VERSION=3.9
     GCC_VERSION=9
     PROTOBUF=yes
     DB=yes
@@ -318,8 +318,8 @@ case "$image" in
     CONDA_CMAKE=yes
     TRITON=yes
     ;;
-    pytorch-linux-jammy-py3.8-gcc11-inductor-benchmarks)
-    ANACONDA_PYTHON_VERSION=3.8
+    pytorch-linux-jammy-py3.9-gcc11-inductor-benchmarks)
+    ANACONDA_PYTHON_VERSION=3.9
     GCC_VERSION=11
     PROTOBUF=yes
     DB=yes
@@ -330,8 +330,8 @@ case "$image" in
     DOCS=yes
     INDUCTOR_BENCHMARKS=yes
     ;;
-  pytorch-linux-jammy-cuda11.8-cudnn9-py3.8-clang12)
-    ANACONDA_PYTHON_VERSION=3.8
+  pytorch-linux-jammy-cuda11.8-cudnn9-py3.9-clang12)
+    ANACONDA_PYTHON_VERSION=3.9
     CUDA_VERSION=11.8
     CUDNN_VERSION=9
     CLANG_VERSION=12
@@ -355,8 +355,8 @@ case "$image" in
     CONDA_CMAKE=yes
     VISION=yes
     ;;
-  pytorch-linux-jammy-py3.8-gcc11)
-    ANACONDA_PYTHON_VERSION=3.8
+  pytorch-linux-jammy-py3.9-gcc11)
+    ANACONDA_PYTHON_VERSION=3.9
     GCC_VERSION=11
     PROTOBUF=yes
     DB=yes

.ci/docker/centos-rocm/Dockerfile

@@ -108,10 +108,10 @@ ENV CMAKE_C_COMPILER cc
 ENV CMAKE_CXX_COMPILER c++
 COPY ./common/install_triton.sh install_triton.sh
 COPY ./common/common_utils.sh common_utils.sh
-COPY ci_commit_pins/triton-rocm.txt triton-rocm.txt
+COPY ci_commit_pins/triton.txt triton.txt
 COPY triton_version.txt triton_version.txt
 RUN if [ -n "${TRITON}" ]; then bash ./install_triton.sh; fi
-RUN rm install_triton.sh common_utils.sh triton-rocm.txt triton_version.txt
+RUN rm install_triton.sh common_utils.sh triton.txt triton_version.txt
 
 # Install AOTriton (Early fail)
 COPY ./aotriton_version.txt aotriton_version.txt

.ci/docker/ci_commit_pins/executorch.txt

@@ -1 +1 @@
-5e9bab8c5956249e75a0f187bf8075df97ca2555
+cd1c833b079adb324871dcbbe75b43d42ffc0ade

.ci/docker/ci_commit_pins/halide.txt

@@ -1 +1 @@
-340136fec6d3ebc73e7a19eba1663e9b0ba8ab2d
+461c12871f336fe6f57b55d6a297f13ef209161b

.ci/docker/ci_commit_pins/triton-rocm.txt

@@ -1 +0,0 @@
-21eae954efa5bf584da70324b640288c3ee7aede

.ci/docker/ci_commit_pins/triton-xpu.txt

@@ -1 +1 @@
-1b2f15840e0d70eec50d84c7a0575cb835524def
+cc981feba10a3f4c2e46f3fe368e8fcf5f5643df

.ci/docker/ci_commit_pins/triton.txt

@@ -1 +1 @@
-dedb7bdf339a3546896d4820366ca562c586bfa0
+757b6a61e7df814ba806f498f8bb3160f84b120c

.ci/docker/common/install_conda.sh

@@ -5,32 +5,22 @@ set -ex
 # Optionally install conda
 if [ -n "$ANACONDA_PYTHON_VERSION" ]; then
   BASE_URL="https://repo.anaconda.com/miniconda"
+  CONDA_FILE="Miniconda3-latest-Linux-x86_64.sh"
+  if [[ $(uname -m) == "aarch64" ]] || [[ "$BUILD_ENVIRONMENT" == *xpu* ]]; then
+    BASE_URL="https://github.com/conda-forge/miniforge/releases/latest/download"
+    CONDA_FILE="Miniforge3-Linux-$(uname -m).sh"
+  fi
 
   MAJOR_PYTHON_VERSION=$(echo "$ANACONDA_PYTHON_VERSION" | cut -d . -f 1)
   MINOR_PYTHON_VERSION=$(echo "$ANACONDA_PYTHON_VERSION" | cut -d . -f 2)
 
-if [[ $(uname -m) == "aarch64" ]]; then
-  BASE_URL="https://github.com/conda-forge/miniforge/releases/latest/download"
   case "$MAJOR_PYTHON_VERSION" in
-    3)
-      CONDA_FILE="Miniforge3-Linux-aarch64.sh"
-    ;;
+    3);;
     *)
       echo "Unsupported ANACONDA_PYTHON_VERSION: $ANACONDA_PYTHON_VERSION"
       exit 1
       ;;
   esac
-else
-  case "$MAJOR_PYTHON_VERSION" in
-    3)
-      CONDA_FILE="Miniconda3-latest-Linux-x86_64.sh"
-    ;;
-    *)
-      echo "Unsupported ANACONDA_PYTHON_VERSION: $ANACONDA_PYTHON_VERSION"
-      exit 1
-      ;;
-  esac
-fi
 
   mkdir -p /opt/conda
   chown jenkins:jenkins /opt/conda

.ci/docker/common/install_cpython.sh

@@ -58,7 +58,8 @@ function do_cpython_build {
     if [ -e ${prefix}/bin/pip3 ] && [ ! -e ${prefix}/bin/pip ]; then
         ln -s pip3 ${prefix}/bin/pip
     fi
-    ${prefix}/bin/pip install wheel==0.34.2
+    # install setuptools since python 3.12 is required to use distutils
+    ${prefix}/bin/pip install wheel==0.34.2 setuptools==68.2.2
     local abi_tag=$(${prefix}/bin/python -c "from wheel.pep425tags import get_abbr_impl, get_impl_ver, get_abi_tag; print('{0}{1}-{2}'.format(get_abbr_impl(), get_impl_ver(), get_abi_tag()))")
     ln -s ${prefix} /opt/python/${abi_tag}
 }

.ci/docker/common/install_onnx.sh

@@ -15,7 +15,7 @@ pip_install \
   flatbuffers==2.0 \
   mock==5.0.1 \
   ninja==1.10.2 \
-  networkx==2.0 \
+  networkx==2.5 \
   numpy==1.24.2
 
 # ONNXRuntime should be installed before installing
@@ -30,10 +30,9 @@ pip_install \
 
 pip_install coloredlogs packaging
 
-pip_install onnxruntime==1.18
-pip_install onnx==1.16.0
-# pip_install "onnxscript@git+https://github.com/microsoft/onnxscript@3e869ef8ccf19b5ebd21c10d3e9c267c9a9fa729" --no-deps
-pip_install onnxscript==0.1.0.dev20240613 --no-deps
+pip_install onnxruntime==1.18.1
+pip_install onnx==1.16.2
+pip_install onnxscript==0.1.0.dev20240831 --no-deps
 # required by onnxscript
 pip_install ml_dtypes
 

.ci/docker/common/install_triton.sh

@@ -12,10 +12,7 @@ conda_reinstall() {
   as_jenkins conda install -q -n py_$ANACONDA_PYTHON_VERSION -y --force-reinstall $*
 }
 
-if [ -n "${ROCM_VERSION}" ]; then
-  TRITON_REPO="https://github.com/openai/triton"
-  TRITON_TEXT_FILE="triton-rocm"
-elif [ -n "${XPU_VERSION}" ]; then
+if [ -n "${XPU_VERSION}" ]; then
   TRITON_REPO="https://github.com/intel/intel-xpu-backend-for-triton"
   TRITON_TEXT_FILE="triton-xpu"
 else

.ci/docker/requirements-ci.txt

@@ -30,9 +30,14 @@ dill==0.3.7
 #Pinned versions: 0.3.7
 #test that import: dynamo/test_replay_record.py test_dataloader.py test_datapipe.py test_serialization.py
 
-expecttest==0.1.6
+expecttest==0.2.1
 #Description: method for writing tests where test framework auto populates
 # the expected output based on previous runs
+#Pinned versions: 0.2.1
+#test that import:
+
+fbscribelogger==0.1.6
+#Description: write to scribe from authenticated jobs on CI
 #Pinned versions: 0.1.6
 #test that import:
 
@@ -104,7 +109,7 @@ networkx==2.8.8
 #test that import: run_test.py, test_cpp_extensions_aot.py,test_determination.py
 
 numba==0.49.0 ; python_version < "3.9"
-numba==0.54.1 ; python_version == "3.9"
+numba==0.55.2 ; python_version == "3.9"
 numba==0.55.2 ; python_version == "3.10"
 #Description: Just-In-Time Compiler for Numerical Functions
 #Pinned versions: 0.54.1, 0.49.0, <=0.49.1

.ci/docker/ubuntu-rocm/Dockerfile

@@ -100,10 +100,10 @@ ARG TRITON
 # try to reach out to S3, which docker build runners don't have access
 COPY ./common/install_triton.sh install_triton.sh
 COPY ./common/common_utils.sh common_utils.sh
-COPY ci_commit_pins/triton-rocm.txt triton-rocm.txt
+COPY ci_commit_pins/triton.txt triton.txt
 COPY triton_version.txt triton_version.txt
 RUN if [ -n "${TRITON}" ]; then bash ./install_triton.sh; fi
-RUN rm install_triton.sh common_utils.sh triton-rocm.txt triton_version.txt
+RUN rm install_triton.sh common_utils.sh triton.txt triton_version.txt
 
 # Install AOTriton
 COPY ./aotriton_version.txt aotriton_version.txt

.ci/docker/ubuntu-xpu/Dockerfile

@@ -30,6 +30,7 @@ RUN bash ./install_docs_reqs.sh && rm install_docs_reqs.sh
 ARG ANACONDA_PYTHON_VERSION
 ARG CONDA_CMAKE
 ARG DOCS
+ARG BUILD_ENVIRONMENT
 ENV ANACONDA_PYTHON_VERSION=$ANACONDA_PYTHON_VERSION
 ENV PATH /opt/conda/envs/py_$ANACONDA_PYTHON_VERSION/bin:/opt/conda/bin:$PATH
 ENV DOCS=$DOCS

.ci/pytorch/build.sh

@@ -285,9 +285,8 @@ else
     if [[ "$BUILD_ENVIRONMENT" != *rocm*  &&
           "$BUILD_ENVIRONMENT" != *xla* ]]; then
       if [[ "$BUILD_ENVIRONMENT" != *py3.8* ]]; then
-        # Install numpy-2.0 release candidate for builds
-        # Which should be backward compatible with Numpy-1.X
-        python -mpip install --pre numpy==2.0.0rc1
+        # Install numpy-2.0.2 for builds which are backward compatible with 1.X
+        python -mpip install --pre numpy==2.0.2
       fi
 
       WERROR=1 python setup.py clean

.ci/pytorch/test.sh

@@ -575,10 +575,10 @@ test_single_dynamo_benchmark() {
     fi
 
     if [[ "${TEST_CONFIG}" == *_avx2* ]]; then
-      TEST_CONFIG=${TEST_CONFIG::-5}
+      TEST_CONFIG=${TEST_CONFIG//_avx2/}
     fi
     if [[ "${TEST_CONFIG}" == *_avx512* ]]; then
-      TEST_CONFIG=${TEST_CONFIG::-7}
+      TEST_CONFIG=${TEST_CONFIG//_avx512/}
     fi
     python "benchmarks/dynamo/$suite.py" \
       --ci --accuracy --timing --explain \
@@ -596,6 +596,9 @@ test_single_dynamo_benchmark() {
 
 test_inductor_micro_benchmark() {
   TEST_REPORTS_DIR=$(pwd)/test/test-reports
+  if [[ "${TEST_CONFIG}" == *cpu* ]]; then
+    test_inductor_set_cpu_affinity
+  fi
   python benchmarks/gpt_fast/benchmark.py --output "${TEST_REPORTS_DIR}/gpt_fast_benchmark.csv"
 }
 
@@ -1479,9 +1482,7 @@ elif [[ "${TEST_CONFIG}" == *inductor* ]]; then
   install_torchvision
   test_inductor_shard "${SHARD_NUMBER}"
   if [[ "${SHARD_NUMBER}" == 1 ]]; then
-    if [[ "${BUILD_ENVIRONMENT}" != linux-jammy-py3.8-gcc11-build ]]; then
-      # Temporarily skip test_inductor_aoti due to https://github.com/pytorch/pytorch/issues/130311
-      test_inductor_aoti
+    if [[ "${BUILD_ENVIRONMENT}" != linux-jammy-py3.9-gcc11-build ]]; then
       test_inductor_distributed
     fi
   fi

.ci/pytorch/win-test-helpers/build_pytorch.bat

@@ -24,6 +24,12 @@ call %INSTALLER_DIR%\install_sccache.bat
 if errorlevel 1 goto fail
 if not errorlevel 0 goto fail
 
+if "%USE_XPU%"=="1" (
+  :: Install xpu support packages
+  call %INSTALLER_DIR%\install_xpu.bat
+  if errorlevel 1 exit /b 1
+)
+
 :: Miniconda has been installed as part of the Windows AMI with all the dependencies.
 :: We just need to activate it here
 call %INSTALLER_DIR%\activate_miniconda3.bat
@@ -43,6 +49,16 @@ if "%VC_VERSION%" == "" (
 )
 if errorlevel 1 goto fail
 if not errorlevel 0 goto fail
+
+if "%USE_XPU%"=="1" (
+  :: Activate xpu environment - VS env is required for xpu
+  call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat"
+  if errorlevel 1 exit /b 1
+  :: Reduce build time. Only have MTL self-hosted runner now
+  SET TORCH_XPU_ARCH_LIST=xe-lpg
+  SET USE_KINETO=0
+)
+
 @echo on
 popd
 

.ci/pytorch/win-test-helpers/installation-helpers/install_xpu.bat

@@ -0,0 +1,91 @@
+@echo on
+REM Description: Install Intel Support Packages on Windows
+REM BKM reference: https://www.intel.com/content/www/us/en/developer/articles/tool/pytorch-prerequisites-for-intel-gpu/2-5.html
+
+set XPU_INSTALL_MODE=%~1
+if "%XPU_INSTALL_MODE%"=="" goto xpu_bundle_install_start
+if "%XPU_INSTALL_MODE%"=="bundle" goto xpu_bundle_install_start
+if "%XPU_INSTALL_MODE%"=="driver" goto xpu_driver_install_start
+if "%XPU_INSTALL_MODE%"=="all" goto xpu_driver_install_start
+
+:arg_error
+
+echo Illegal XPU installation mode. The value can be "bundle"/"driver"/"all"
+echo If keep the value as space, will use default "bundle" mode
+exit /b 1
+
+:xpu_driver_install_start
+:: TODO Need more testing for driver installation
+set XPU_DRIVER_LINK=https://downloadmirror.intel.com/830975/gfx_win_101.5972.exe
+curl -o xpu_driver.exe --retry 3 --retry-all-errors -k %XPU_DRIVER_LINK%
+echo "XPU Driver installing..."
+start /wait "Intel XPU Driver Installer" "xpu_driver.exe"
+if errorlevel 1 exit /b 1
+del xpu_driver.exe
+if "%XPU_INSTALL_MODE%"=="driver" goto xpu_install_end
+
+:xpu_bundle_install_start
+
+set XPU_BUNDLE_PARENT_DIR=C:\Program Files (x86)\Intel\oneAPI
+set XPU_BUNDLE_URL=https://registrationcenter-download.intel.com/akdlm/IRC_NAS/9d1a91e2-e8b8-40a5-8c7f-5db768a6a60c/w_intel-for-pytorch-gpu-dev_p_0.5.3.37_offline.exe
+set XPU_PTI_URL=https://registrationcenter-download.intel.com/akdlm/IRC_NAS/9d1a91e2-e8b8-40a5-8c7f-5db768a6a60c/w_intel-pti-dev_p_0.9.0.37_offline.exe
+set XPU_BUNDLE_VERSION=0.5.3+31
+set XPU_PTI_VERSION=0.9.0+36
+set XPU_BUNDLE_PRODUCT_NAME=intel.oneapi.win.intel-for-pytorch-gpu-dev.product
+set XPU_PTI_PRODUCT_NAME=intel.oneapi.win.intel-pti-dev.product
+set XPU_BUNDLE_INSTALLED=0
+set XPU_PTI_INSTALLED=0
+set XPU_BUNDLE_UNINSTALL=0
+set XPU_PTI_UNINSTALL=0
+
+:: Check if XPU bundle is target version or already installed
+if exist "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" goto xpu_bundle_ver_check
+goto xpu_bundle_install
+
+:xpu_bundle_ver_check
+
+"%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" --list-products > xpu_bundle_installed_ver.log
+
+for /f "tokens=1,2" %%a in (xpu_bundle_installed_ver.log) do (
+    if "%%a"=="%XPU_BUNDLE_PRODUCT_NAME%" (
+        echo %%a Installed Version: %%b
+        set XPU_BUNDLE_INSTALLED=1
+        if not "%XPU_BUNDLE_VERSION%"=="%%b" (
+            start /wait "Installer Title" "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" --action=remove --eula=accept --silent --product-id %XPU_BUNDLE_PRODUCT_NAME% --product-ver %%b --log-dir uninstall_bundle
+            set XPU_BUNDLE_UNINSTALL=1
+        )
+    )
+    if "%%a"=="%XPU_PTI_PRODUCT_NAME%" (
+        echo %%a Installed Version: %%b
+        set XPU_PTI_INSTALLED=1
+        if not "%XPU_PTI_VERSION%"=="%%b" (
+            start /wait "Installer Title" "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" --action=remove --eula=accept --silent --product-id %XPU_PTI_PRODUCT_NAME% --product-ver %%b --log-dir uninstall_bundle
+            set XPU_PTI_UNINSTALL=1
+        )
+    )
+)
+if errorlevel 1 exit /b 1
+if exist xpu_bundle_installed_ver.log del xpu_bundle_installed_ver.log
+if "%XPU_BUNDLE_INSTALLED%"=="0" goto xpu_bundle_install
+if "%XPU_BUNDLE_UNINSTALL%"=="1" goto xpu_bundle_install
+if "%XPU_PTI_INSTALLED%"=="0" goto xpu_pti_install
+if "%XPU_PTI_UNINSTALL%"=="1" goto xpu_pti_install
+goto xpu_install_end
+
+:xpu_bundle_install
+
+curl -o xpu_bundle.exe --retry 3 --retry-all-errors -k %XPU_BUNDLE_URL%
+echo "XPU Bundle installing..."
+start /wait "Intel Pytorch Bundle Installer" "xpu_bundle.exe" --action=install --eula=accept --silent --log-dir install_bundle
+if errorlevel 1 exit /b 1
+del xpu_bundle.exe
+
+:xpu_pti_install
+
+curl -o xpu_pti.exe --retry 3 --retry-all-errors -k %XPU_PTI_URL%
+echo "XPU PTI installing..."
+start /wait "Intel PTI Installer" "xpu_pti.exe" --action=install --eula=accept --silent --log-dir install_bundle
+if errorlevel 1 exit /b 1
+del xpu_pti.exe
+
+:xpu_install_end

.ci/pytorch/win-test.sh

@@ -40,6 +40,9 @@ python -m pip install pytest-rerunfailures==10.3 pytest-cpp==2.3.0 tensorboard==
 # Install Z3 optional dependency for Windows builds.
 python -m pip install z3-solver==4.12.2.0
 
+# Install tlparse for test\dynamo\test_structured_trace.py UTs.
+python -m pip install tlparse==0.3.25
+
 run_tests() {
     # Run nvidia-smi if available
     for path in '/c/Program Files/NVIDIA Corporation/NVSMI/nvidia-smi.exe' /c/Windows/System32/nvidia-smi.exe; do

.circleci/scripts/binary_linux_test.sh

@@ -116,12 +116,6 @@ if [[ "$PACKAGE_TYPE" == libtorch ]]; then
   cd /tmp/libtorch
 fi
 
-if [[ "$GPU_ARCH_TYPE" == xpu ]]; then
-  # Refer https://www.intel.com/content/www/us/en/developer/articles/tool/pytorch-prerequisites-for-intel-gpu/2-5.html
-  source /opt/intel/oneapi/pytorch-gpu-dev-0.5/oneapi-vars.sh
-  source /opt/intel/oneapi/pti/latest/env/vars.sh
-fi
-
 # Test the package
 /builder/check_binary.sh
 

.circleci/scripts/binary_populate_env.sh

@@ -90,7 +90,7 @@ fi
 if [[ "$PACKAGE_TYPE" =~ .*wheel.* && -n "$PYTORCH_BUILD_VERSION" && "$PYTORCH_BUILD_VERSION" =~ .*rocm.* && $(uname) == "Linux" ]]; then
     TRITON_REQUIREMENT="pytorch-triton-rocm==${TRITON_VERSION}; ${TRITON_CONSTRAINT}"
     if [[ -n "$PYTORCH_BUILD_VERSION" && "$PYTORCH_BUILD_VERSION" =~ .*dev.* ]]; then
-        TRITON_SHORTHASH=$(cut -c1-10 $PYTORCH_ROOT/.ci/docker/ci_commit_pins/triton-rocm.txt)
+        TRITON_SHORTHASH=$(cut -c1-10 $PYTORCH_ROOT/.ci/docker/ci_commit_pins/triton.txt)
         TRITON_REQUIREMENT="pytorch-triton-rocm==${TRITON_VERSION}+${TRITON_SHORTHASH}; ${TRITON_CONSTRAINT}"
     fi
     if [[ -z "${PYTORCH_EXTRA_INSTALL_REQUIREMENTS:-}" ]]; then

.circleci/scripts/binary_windows_build.sh

@@ -10,6 +10,11 @@ export SCCACHE_BUCKET=ossci-compiler-cache
 export SCCACHE_IGNORE_SERVER_IO_ERROR=1
 export VC_YEAR=2019
 
+if [[ "$DESIRED_CUDA" == 'xpu' ]]; then
+    export VC_YEAR=2022
+    export USE_SCCACHE=0
+fi
+
 echo "Free space on filesystem before build:"
 df -h
 

.circleci/scripts/binary_windows_test.sh

@@ -6,6 +6,10 @@ source "${BINARY_ENV_FILE:-/c/w/env}"
 export CUDA_VERSION="${DESIRED_CUDA/cu/}"
 export VC_YEAR=2019
 
+if [[ "$DESIRED_CUDA" == 'xpu' ]]; then
+    export VC_YEAR=2022
+fi
+
 pushd "$BUILDER_ROOT"
 
 ./windows/internal/smoke_test.bat

.flake8

@@ -57,7 +57,7 @@ per-file-ignores =
     torch/distributed/_tensor/_collective_utils.py: TOR901
     # This is a full package that happen to live within the test
     # folder, so ok to skip
-    test/cpp_extensions/open_registration_extension/pytorch_openreg/__init__.py: TOR901
+    test/cpp_extensions/open_registration_extension/pytorch_openreg/_aten_impl.py: TOR901
 optional-ascii-coding = True
 exclude =
     ./.git,

.github/actionlint.yaml

@@ -3,8 +3,6 @@ self-hosted-runner:
     # GitHub hosted x86 Linux runners
     - linux.20_04.4x
     - linux.20_04.16x
-    # Repo-specific LF hosted ARC runners
-    - linux.large.arc
     # Organization-wide AWS Linux Runners
     - linux.large
     - linux.2xlarge
@@ -16,7 +14,9 @@ self-hosted-runner:
     - linux.24xlarge
     - linux.24xlarge.ephemeral
     - linux.arm64.2xlarge
+    - linux.arm64.2xlarge.ephemeral
     - linux.arm64.m7g.4xlarge
+    - linux.arm64.m7g.4xlarge.ephemeral
     - linux.4xlarge.nvidia.gpu
     - linux.8xlarge.nvidia.gpu
     - linux.16xlarge.nvidia.gpu
@@ -40,6 +40,7 @@ self-hosted-runner:
     - amz2023.linux.24xlarge
     - amz2023.linux.arm64.2xlarge
     - amz2023.linux.arm64.m7g.4xlarge
+    - amz2023.linux.arm64.m7g.4xlarge.ephemeral
     - amz2023.linux.4xlarge.nvidia.gpu
     - amz2023.linux.8xlarge.nvidia.gpu
     - amz2023.linux.16xlarge.nvidia.gpu
@@ -60,6 +61,7 @@ self-hosted-runner:
     # Organization wide AWS Windows runners
     - windows.g4dn.xlarge
     - windows.g4dn.xlarge.nonephemeral
+    - windows.4xlarge
     - windows.4xlarge.nonephemeral
     - windows.8xlarge.nvidia.gpu
     - windows.8xlarge.nvidia.gpu.nonephemeral

.github/ci_commit_pins/audio.txt

@@ -1 +1 @@
-b3f6f511f2a1082bd56b13a3f6794e7fc3ba4862
+97ed7b36b7a741253d4e41e4da3c901d83294503

.github/label_to_label.yml

@@ -1,13 +1,50 @@
 # Use this to auto apply labels based on other labels.  Applies to both PRs and
 # issues. Currently only supports any and all
 - any:
-  - "module: custom operators"
+  - "module: opcheck"
+  then:
+  - "module: custom-operators"
+- any:
+  - "module: custom-operators"
+  - "module: functionalization"
   - "module: aotdispatch"
+  - "module: higher order operators"
+  - "module: fakeTensor"
+  - "module: ProxyTensor"
+  - "module: library"
+  - "module: reinplacing"
   then:
   - "module: pt2-dispatcher"
+- any:
+  - "module: vmap"
+  then:
+  - "module: functorch"
+- any:
+  - "module: reinplacing"
+  then:
+  - "module: inductor"
+- any:
+  - "module: pt2 optimizer"
+  then:
+  - "module: dynamo"
+- any:
+  - "module: flex attention"
+  then:
+  - "module: higher order operators"
+- any:
+  - "module: aotinductor"
+  then:
+  - "oncall: export"
 - any:
   - "module: dynamo"
   - "module: pt2-dispatcher"
   - "module: inductor"
+  - "module: aotinductor"
+  - "module: cudagraphs"
+  - "oncall: export"
+  - "module: startup-tracing-compile"
+  - "module: compiled autograd"
+  - "module: flex attention"
+  - "module: dynamic shapes"
   then:
   - "oncall: pt2"

.github/lf-canary-scale-config.yml

@@ -289,6 +289,30 @@ runner_types:
         ami: al2023-ami-2023.5.20240701.0-kernel-6.1-arm64
       am2:
         ami: amzn2-ami-hvm-2.0.20240306.2-arm64-gp2
+  lf.c.linux.arm64.2xlarge.ephemeral:
+    disk_size: 256
+    instance_type: t4g.2xlarge
+    is_ephemeral: true
+    max_available: 200
+    os: linux
+    ami: al2023-ami-2023.5.20240701.0-kernel-6.1-arm64
+    variants:
+      amz2023:
+        ami: al2023-ami-2023.5.20240701.0-kernel-6.1-arm64
+      am2:
+        ami: amzn2-ami-hvm-2.0.20240306.2-arm64-gp2
+  lf.c.linux.arm64.m7g.4xlarge.ephemeral:
+    disk_size: 256
+    instance_type: m7g.4xlarge
+    is_ephemeral: true
+    max_available: 200
+    os: linux
+    ami: al2023-ami-2023.5.20240701.0-kernel-6.1-arm64
+    variants:
+      amz2023:
+        ami: al2023-ami-2023.5.20240701.0-kernel-6.1-arm64
+      am2:
+        ami: amzn2-ami-hvm-2.0.20240306.2-arm64-gp2
   lf.c.linux.arm64.m7g.metal:
     disk_size: 256
     instance_type: m7g.metal

.github/lf-scale-config.yml

@@ -289,6 +289,30 @@ runner_types:
         ami: al2023-ami-2023.5.20240701.0-kernel-6.1-arm64
       am2:
         ami: amzn2-ami-hvm-2.0.20240306.2-arm64-gp2
+  lf.linux.arm64.2xlarge.ephemeral:
+    disk_size: 256
+    instance_type: t4g.2xlarge
+    is_ephemeral: true
+    max_available: 200
+    os: linux
+    ami: al2023-ami-2023.5.20240701.0-kernel-6.1-arm64
+    variants:
+      amz2023:
+        ami: al2023-ami-2023.5.20240701.0-kernel-6.1-arm64
+      am2:
+        ami: amzn2-ami-hvm-2.0.20240306.2-arm64-gp2
+  lf.linux.arm64.m7g.4xlarge.ephemeral:
+    disk_size: 256
+    instance_type: m7g.4xlarge
+    is_ephemeral: true
+    max_available: 200
+    os: linux
+    ami: al2023-ami-2023.5.20240701.0-kernel-6.1-arm64
+    variants:
+      amz2023:
+        ami: al2023-ami-2023.5.20240701.0-kernel-6.1-arm64
+      am2:
+        ami: amzn2-ami-hvm-2.0.20240306.2-arm64-gp2
   lf.linux.arm64.m7g.metal:
     disk_size: 256
     instance_type: m7g.metal

.github/merge_rules.yaml

@@ -107,8 +107,8 @@
   mandatory_checks_name:
   - EasyCLA
   - Lint
-  - pull / linux-focal-py3_8-clang9-xla / build
-  - pull / linux-focal-py3_8-clang9-xla / test (xla, 1, 1, linux.12xlarge)
+  - pull / linux-focal-py3_9-clang9-xla / build
+  - pull / linux-focal-py3_9-clang9-xla / test (xla, 1, 1, linux.12xlarge)
 
 - name: Documentation
   patterns:

.github/pytorch-probot.yml

@@ -9,6 +9,7 @@ ciflow_push_tags:
 - ciflow/inductor-rocm
 - ciflow/inductor-perf-compare
 - ciflow/inductor-micro-benchmark
+- ciflow/inductor-micro-benchmark-cpu-x86
 - ciflow/inductor-cu124
 - ciflow/linux-aarch64
 - ciflow/mps

.github/requirements/pip-requirements-macOS.txt

@@ -1,6 +1,7 @@
 boto3==1.19.12
 hypothesis==6.56.4
-expecttest==0.1.6
+expecttest==0.2.1
+fbscribelogger==0.1.6
 librosa>=0.6.2
 mpmath==1.3.0
 networkx==2.8.7

.github/scripts/build_triton_wheel.py

@@ -15,9 +15,7 @@ REPO_DIR = SCRIPT_DIR.parent.parent
 
 def read_triton_pin(device: str = "cuda") -> str:
     triton_file = "triton.txt"
-    if device == "rocm":
-        triton_file = "triton-rocm.txt"
-    elif device == "xpu":
+    if device == "xpu":
         triton_file = "triton-xpu.txt"
     with open(REPO_DIR / ".ci" / "docker" / "ci_commit_pins" / triton_file) as f:
         return f.read().strip()

.github/scripts/check_labels.py

@@ -27,6 +27,12 @@ def parse_args() -> Any:
 
     parser = ArgumentParser("Check PR labels")
     parser.add_argument("pr_num", type=int)
+    # add a flag to return a non-zero exit code if the PR does not have the required labels
+    parser.add_argument(
+        "--exit-non-zero",
+        action="store_true",
+        help="Return a non-zero exit code if the PR does not have the required labels",
+    )
 
     return parser.parse_args()
 
@@ -41,10 +47,13 @@ def main() -> None:
         if not has_required_labels(pr):
             print(LABEL_ERR_MSG)
             add_label_err_comment(pr)
+            if args.exit_non_zero:
+                sys.exit(1)
         else:
             delete_all_label_err_comments(pr)
     except Exception as e:
-        pass
+        if args.exit_non_zero:
+            sys.exit(1)
 
     sys.exit(0)
 

.github/scripts/generate_binary_build_matrix.py

@@ -340,7 +340,7 @@ def generate_wheels_matrix(
         if os == "linux":
             arches += CPU_CXX11_ABI_ARCH + CUDA_ARCHES + ROCM_ARCHES + XPU_ARCHES
         elif os == "windows":
-            arches += CUDA_ARCHES
+            arches += CUDA_ARCHES + XPU_ARCHES
         elif os == "linux-aarch64":
             # Only want the one arch as the CPU type is different and
             # uses different build/test scripts
@@ -462,7 +462,7 @@ def generate_wheels_matrix(
                         ),
                         "pytorch_extra_install_requirements": (
                             PYTORCH_EXTRA_INSTALL_REQUIREMENTS["12.1"]  # fmt: skip
-                            if os != "linux"
+                            if os != "linux" and gpu_arch_type != "xpu"
                             else ""
                         ),
                     }

.github/scripts/github_utils.py

@@ -46,16 +46,24 @@ def gh_fetch_url_and_headers(
         with urlopen(Request(url, headers=headers, data=data_, method=method)) as conn:
             return conn.headers, reader(conn)
     except HTTPError as err:
-        if err.code == 403 and all(
-            key in err.headers for key in ["X-RateLimit-Limit", "X-RateLimit-Used"]
+        if (
+            err.code == 403
+            and all(
+                key in err.headers
+                for key in ["X-RateLimit-Limit", "X-RateLimit-Remaining"]
+            )
+            and int(err.headers["X-RateLimit-Remaining"]) == 0
         ):
             print(
-                f"""Rate limit exceeded:
+                f"""{url}
+                Rate limit exceeded:
                 Used: {err.headers['X-RateLimit-Used']}
                 Limit: {err.headers['X-RateLimit-Limit']}
                 Remaining: {err.headers['X-RateLimit-Remaining']}
                 Resets at: {err.headers['x-RateLimit-Reset']}"""
             )
+        else:
+            print(f"Error fetching {url} {err}")
         raise
 
 

.github/scripts/runner_determinator.py

@@ -137,11 +137,14 @@ def get_issue(gh: Github, repo: str, issue_num: int) -> Issue:
 
 
 def get_potential_pr_author(
-    gh: Github, repo: str, username: str, ref_type: str, ref_name: str
+    github_token: str, repo: str, username: str, ref_type: str, ref_name: str
 ) -> str:
     # If the trigger was a new tag added by a bot, this is a ciflow case
     # Fetch the actual username from the original PR. The PR number is
     # embedded in the tag name: ciflow/<name>/<pr-number>
+
+    gh = get_gh_client(github_token)
+
     if username == "pytorch-bot[bot]" and ref_type == "tag":
         split_tag = ref_name.split("/")
         if (
@@ -163,23 +166,32 @@ def get_potential_pr_author(
 
 
 def is_exception_branch(branch: str) -> bool:
+    """
+    Branches that get opted out of all experiments and should always use Meta runners
+    """
     return branch.split("/")[0] in {"main", "nightly", "release", "landchecks"}
 
 
-def get_workflow_type(issue: Issue, workflow_requestors: Iterable[str]) -> str:
-    try:
-        first_comment = issue.get_comments()[0].body.strip("\n\t ")
+def get_fleet(rollout_state: str, workflow_requestors: Iterable[str]) -> str:
+    """
+    Determines if the job should run on the LF fleet or the Meta fleet
 
-        if first_comment[0] == "!":
+    Returns:
+        The appropriate label prefix for the runner, corresponding to the fleet to use.
+        This gets prefixed to the very start of the runner label.
+    """
+
+    try:
+        if rollout_state[0] == "!":
             log.info("LF Workflows are disabled for everyone. Using meta runners.")
             return WORKFLOW_LABEL_META
-        elif first_comment[0] == "*":
+        elif rollout_state[0] == "*":
             log.info("LF Workflows are enabled for everyone. Using LF runners.")
             return WORKFLOW_LABEL_LF
         else:
             all_opted_in_users = {
                 usr_raw.strip("\n\t@ ").split(",")[0]
-                for usr_raw in first_comment.split()
+                for usr_raw in rollout_state.split()
             }
             opted_in_requestors = {
                 usr for usr in workflow_requestors if usr in all_opted_in_users
@@ -203,11 +215,17 @@ def get_workflow_type(issue: Issue, workflow_requestors: Iterable[str]) -> str:
 
 
 def get_optin_feature(
-    issue: Issue, workflow_requestors: Iterable[str], feature: str, fallback: str
+    rollout_state: str, workflow_requestors: Iterable[str], feature: str, fallback: str
 ) -> str:
+    """
+    Used to dynamically opt in jobs to specific runner-type variants.
+
+    Returns:
+        The runner-type's variant name if the user has opted in to the feature, otherwise returns an empty string.
+        This variant name is prefixed to the runner-type in the label.
+    """
     try:
-        first_comment = issue.get_comments()[0].body.strip("\n\t ")
-        userlist = {u.lstrip("#").strip("\n\t@ ") for u in first_comment.split()}
+        userlist = {u.lstrip("#").strip("\n\t@ ") for u in rollout_state.split()}
         all_opted_in_users = set()
         for user in userlist:
             for i in user.split(","):
@@ -235,6 +253,17 @@ def get_optin_feature(
         return fallback
 
 
+def get_rollout_state_from_issue(github_token: str, repo: str, issue_num: int) -> str:
+    """
+    Gets the first comment of the issue, which contains the desired rollout state.
+
+    The default issue we use - https://github.com/pytorch/test-infra/issues/5132
+    """
+    gh = get_gh_client(github_token)
+    issue = get_issue(gh, repo, issue_num)
+    return str(issue.get_comments()[0].body.strip("\n\t "))
+
+
 def main() -> None:
     args = parse_args()
 
@@ -244,25 +273,27 @@ def main() -> None:
         runner_ami = RUNNER_AMI_LEGACY
     else:
         try:
-            gh = get_gh_client(args.github_token)
-            # The default issue we use - https://github.com/pytorch/test-infra/issues/5132
-            issue = get_issue(gh, args.github_issue_repo, args.github_issue)
+            rollout_state = get_rollout_state_from_issue(
+                args.github_token, args.github_issue_repo, args.github_issue
+            )
+
             username = get_potential_pr_author(
-                gh,
+                args.github_token,
                 args.github_repo,
                 args.github_actor,
                 args.github_ref_type,
                 args.github_branch,
             )
-            label_type = get_workflow_type(
-                issue,
+
+            label_type = get_fleet(
+                rollout_state,
                 (
                     args.github_issue_owner,
                     username,
                 ),
             )
             runner_ami = get_optin_feature(
-                issue=issue,
+                rollout_state=rollout_state,
                 workflow_requestors=(
                     args.github_issue_owner,
                     username,

.github/scripts/s390x-ci/README.md

@@ -3,7 +3,7 @@
 ## Install prerequisites.
 
 ```
-$ sudo dnf install docker
+$ sudo dnf install podman podman-docker jq
 ```
 
 ## Add services.
@@ -27,23 +27,48 @@ $ sudo systemctl enable --now qemu-user-static
 
 ## Rebuild the image
 
-In order to build or update the `iiilinuxibmcom/actions-runner` image, e.g. to get the
-latest OS security fixes, use the following commands:
+First build s390x builder image `docker.io/pytorch/manylinuxs390x-builder`,
+using following commands:
+
+```
+$ cd ~
+$ git clone https://github.com/pytorch/pytorch
+$ cd pytorch
+$ git submodule update --init --recursive
+$ GPU_ARCH_TYPE=cpu-s390x "$(pwd)/.ci/docker/manywheel/build.sh" manylinuxs390x-builder
+$ docker image tag localhost/pytorch/manylinuxs390x-builder docker.io/pytorch/manylinuxs390x-builder:cpu-s390x
+$ docker image save -o ~/manywheel-s390x.tar docker.io/pytorch/manylinuxs390x-builder:cpu-s390x
+```
+
+Next step is to build `actions-runner` image using:
 
 ```
 $ cd self-hosted-builder
 $ sudo docker build \
-      --build-arg repo=<owner>/<name> \
-      --build-arg token=<***> \
       --pull \
       -f actions-runner.Dockerfile \
-      -t iiilinuxibmcom/actions-runner \
+      -t iiilinuxibmcom/actions-runner.<name> \
       .
 ```
 
-If it fails, ensure that selinux doesn't prevent it from working.
+If there are failures, ensure that selinux doesn't prevent it from working.
 In worst case, selinux can be disabled with `setenforce 0`.
 
+Now prepare all necessary files for runner registration:
+
+```
+$ sudo mkdir -p /etc/actions-runner/<name>
+$ sudo chmod 700 /etc/actions-runner/<name>
+$ sudo /bin/cp <github_app_private_key_file> /etc/actions-runner/<name>/key_private.pem
+$ sudo echo <github_app_id> | sudo tee /etc/actions-runner/<name>/appid.env
+$ sudo echo <github_app_install_id> | sudo tee /etc/actions-runner/<name>/installid.env
+$ sudo echo NAME=<worker_name> | sudo tee    /etc/actions-runner/<name>/env
+$ sudo echo ORG=<github_org>   | sudo tee -a /etc/actions-runner/<name>/env
+$ cd self-hosted-builder
+$ sudo /bin/cp helpers/*.sh /usr/local/bin/
+$ sudo chmod 755 /usr/local/bin/app_token.sh /usr/local/bin/gh_token_generator.sh
+```
+
 ## Autostart the runner.
 
 ```

.github/scripts/s390x-ci/self-hosted-builder/actions-runner.Dockerfile

@@ -1,12 +1,12 @@
 # Self-Hosted IBM Z Github Actions Runner.
 
 # Temporary image: amd64 dependencies.
-FROM docker.io/amd64/ubuntu:22.04 as ld-prefix
+FROM docker.io/amd64/ubuntu:23.10 as ld-prefix
 ENV DEBIAN_FRONTEND=noninteractive
-RUN apt-get update && apt-get -y install ca-certificates libicu70 libssl3
+RUN apt-get update && apt-get -y install ca-certificates libicu72 libssl3
 
 # Main image.
-FROM docker.io/s390x/ubuntu:22.04
+FROM docker.io/s390x/ubuntu:23.10
 
 # Packages for pytorch building and testing.
 ENV DEBIAN_FRONTEND=noninteractive
@@ -16,6 +16,7 @@ RUN apt-get update && apt-get -y install \
         gcc \
         git \
         jq \
+        zip \
         libxml2-dev \
         libxslt-dev \
         ninja-build \
@@ -43,24 +44,28 @@ COPY fs/ /
 
 RUN chmod +x /usr/bin/actions-runner /usr/bin/entrypoint
 
+# install podman
+RUN apt -y install podman podman-docker
+
 # amd64 Github Actions Runner.
 RUN useradd -m actions-runner
 USER actions-runner
 WORKDIR /home/actions-runner
-RUN curl -L https://github.com/actions/runner/releases/download/v2.309.0/actions-runner-linux-x64-2.309.0.tar.gz | tar -xz
 
-# repository
-ARG repo
+# set up python virtual environment which is later used by runner.
+# build workflows use "python -m pip install ...",
+# and it doesn't work for non-root user
+RUN virtualenv --system-site-packages venv
 
-# repository token
-ARG token
+# copy prebuilt manywheel docker image for builds and tests
+# build command is:
+# GPU_ARCH_TYPE=cpu-s390x "$(pwd)/manywheel/build_docker.sh"
+# and save command is:
+# docker image save -o manywheel-s390x.tar pytorch/manylinuxs390x-builder:cpu-s390x
+#
+COPY --chown=actions-runner:actions-runner manywheel-s390x.tar /home/actions-runner/manywheel-s390x.tar
 
-RUN ./config.sh \
-        --unattended \
-        --url "https://github.com/${repo}" \
-        --token "${token}" \
-        --no-default-labels \
-        --labels self-hosted,linux.s390x
+RUN curl -L https://github.com/actions/runner/releases/download/v2.317.0/actions-runner-linux-x64-2.317.0.tar.gz | tar -xz
 
 ENTRYPOINT ["/usr/bin/entrypoint"]
 CMD ["/usr/bin/actions-runner"]

.github/scripts/s390x-ci/self-hosted-builder/actions-runner@.service

@@ -8,12 +8,16 @@ StartLimitIntervalSec=0
 Type=simple
 Restart=always
 ExecStartPre=-/usr/bin/docker rm --force actions-runner.%i
+ExecStartPre=-/usr/local/bin/gh_token_generator.sh /etc/actions-runner/%i/appid.env /etc/actions-runner/%i/installid.env /etc/actions-runner/%i/key_private.pem /etc/actions-runner/%i/ghtoken.env
 ExecStart=/usr/bin/docker run \
+              --env-file=/etc/actions-runner/%i/env \
+              --env-file=/etc/actions-runner/%i/ghtoken.env \
               --init \
               --interactive \
               --name=actions-runner.%i \
               --rm \
-              iiilinuxibmcom/actions-runner
+              --privileged \
+              iiilinuxibmcom/actions-runner.%i
 ExecStop=/bin/sh -c "docker exec actions-runner.%i kill -INT -- -1"
 ExecStop=/bin/sh -c "docker wait actions-runner.%i"
 ExecStop=/bin/sh -c "docker rm actions-runner.%i"

.github/scripts/s390x-ci/self-hosted-builder/fs/usr/bin/actions-runner

@@ -2,5 +2,45 @@
 
 set -e -u
 
+# first import docker image
+if [ -f ./manywheel-s390x.tar ] ; then
+        docker image load --input manywheel-s390x.tar
+        docker image tag docker.io/pytorch/manylinuxs390x-builder:cpu-s390x docker.io/pytorch/manylinuxs390x-builder:cpu-s390x-main
+        rm -f manywheel-s390x.tar
+fi
+
+token_file=registration-token.json
+
+# Generate registration token
+curl \
+        -X POST \
+        -H "Accept: application/vnd.github.v3+json" \
+        -H "Authorization: Bearer ${ACCESS_TOKEN}" \
+        "https://api.github.com/orgs/${ORG}/actions/runners/registration-token" \
+        -o "$token_file"
+
+unset ACCESS_TOKEN
+
+# register runner as ephemeral runner
+# it does one job, stops and unregisters
+registration_token=$(jq --raw-output .token "$token_file")
+
+./config.sh \
+        --unattended \
+        --ephemeral \
+        --url "https://github.com/${ORG}" \
+        --token "${registration_token}" \
+        --name "${NAME}" \
+        --no-default-labels \
+        --labels self-hosted,linux.s390x
+
+unset registration_token
+rm -f "$token_file"
+
+# enter into python virtual environment.
+# build workflows use "python -m pip install ...",
+# and it doesn't work for non-root user
+source venv/bin/activate
+
 # Run one job.
-./run.sh --once
+./run.sh

.github/scripts/s390x-ci/self-hosted-builder/helpers/app_token.sh

@@ -0,0 +1,84 @@
+#!/usr/bin/env bash
+#
+# Request an ACCESS_TOKEN to be used by a GitHub APP
+# Environment variable that need to be set up:
+# * APP_ID, the GitHub's app ID
+# * INSTALL_ID, the Github's app's installation ID
+# * APP_PRIVATE_KEY, the content of GitHub app's private key in PEM format.
+#
+# https://github.com/orgs/community/discussions/24743#discussioncomment-3245300
+#
+
+set -o pipefail
+
+_GITHUB_HOST=${GITHUB_HOST:="github.com"}
+
+# If URL is not github.com then use the enterprise api endpoint
+if [[ ${GITHUB_HOST} = "github.com" ]]; then
+  URI="https://api.${_GITHUB_HOST}"
+else
+  URI="https://${_GITHUB_HOST}/api/v3"
+fi
+
+API_VERSION=v3
+API_HEADER="Accept: application/vnd.github.${API_VERSION}+json"
+CONTENT_LENGTH_HEADER="Content-Length: 0"
+APP_INSTALLATIONS_URI="${URI}/app/installations"
+
+
+# JWT parameters based off
+# https://docs.github.com/en/developers/apps/building-github-apps/authenticating-with-github-apps#authenticating-as-a-github-app
+#
+# JWT token issuance and expiration parameters
+JWT_IAT_DRIFT=60
+JWT_EXP_DELTA=600
+
+JWT_JOSE_HEADER='{
+    "alg": "RS256",
+    "typ": "JWT"
+}'
+
+
+build_jwt_payload() {
+    now=$(date +%s)
+    iat=$((now - JWT_IAT_DRIFT))
+    jq -c \
+        --arg iat_str "${iat}" \
+        --arg exp_delta_str "${JWT_EXP_DELTA}" \
+        --arg app_id_str "${APP_ID}" \
+    '
+        ($iat_str | tonumber) as $iat
+        | ($exp_delta_str | tonumber) as $exp_delta
+        | ($app_id_str | tonumber) as $app_id
+        | .iat = $iat
+        | .exp = ($iat + $exp_delta)
+        | .iss = $app_id
+    ' <<< "{}" | tr -d '\n'
+}
+
+base64url() {
+    base64 | tr '+/' '-_' | tr -d '=\n'
+}
+
+rs256_sign() {
+    openssl dgst -binary -sha256 -sign <(echo "$1")
+}
+
+request_access_token() {
+    jwt_payload=$(build_jwt_payload)
+    encoded_jwt_parts=$(base64url <<<"${JWT_JOSE_HEADER}").$(base64url <<<"${jwt_payload}")
+    encoded_mac=$(echo -n "$encoded_jwt_parts" | rs256_sign "${APP_PRIVATE_KEY}" | base64url)
+    generated_jwt="${encoded_jwt_parts}.${encoded_mac}"
+
+    auth_header="Authorization: Bearer ${generated_jwt}"
+
+    app_installations_response=$(curl -sX POST \
+        -H "${auth_header}" \
+        -H "${API_HEADER}" \
+        --header "X-GitHub-Api-Version: 2022-11-28" \
+        --url "https://api.github.com/app/installations/${INSTALL_ID}/access_tokens" \
+    )
+    echo "$app_installations_response" | jq --raw-output '.token'
+}
+
+request_access_token

.github/scripts/s390x-ci/self-hosted-builder/helpers/gh_token_generator.sh

@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+
+SCRIPT_DIR=$(dirname "$0")
+APP_ID=$1
+INSTALL_ID=$2
+APP_PRIVATE_KEY=$3
+DST_FILE="$4"
+
+ACCESS_TOKEN="$(APP_ID="$(<"${APP_ID}")" INSTALL_ID="$(<"${INSTALL_ID}")" APP_PRIVATE_KEY="$(<"${APP_PRIVATE_KEY}")" "${SCRIPT_DIR}/app_token.sh")"
+echo "ACCESS_TOKEN=${ACCESS_TOKEN}" > "${DST_FILE}"

.github/scripts/test_check_labels.py

@@ -18,6 +18,7 @@ def mock_parse_args() -> object:
     class Object:
         def __init__(self) -> None:
             self.pr_num = 76123
+            self.exit_non_zero = False
 
     return Object()
 

.github/templates/common.yml.j2

@@ -1,7 +1,7 @@
 {%- set upload_artifact_s3_action = "seemethere/upload-artifact-s3@v5" -%}
 {%- set download_artifact_s3_action = "seemethere/download-artifact-s3@v4" -%}
-{%- set upload_artifact_action = "actions/upload-artifact@v3" -%}
-{%- set download_artifact_action = "actions/download-artifact@v3" -%}
+{%- set upload_artifact_action = "actions/upload-artifact@v4.4.0" -%}
+{%- set download_artifact_action = "actions/download-artifact@v4.1.7" -%}
 
 {%- set timeout_minutes = 240 -%}
 

.github/templates/linux_binary_build_workflow.yml.j2

@@ -68,17 +68,16 @@ jobs:
     needs: get-label-type
     with:!{{ upload.binary_env_as_input(config) }}
       {%- if "aarch64" in build_environment %}
-      runner_prefix: amz2023.
-      runs_on: linux.arm64.m7g.4xlarge
+      runs_on: linux.arm64.m7g.4xlarge.ephemeral
       ALPINE_IMAGE: "arm64v8/alpine"
       {%- elif "s390x" in build_environment %}
       runs_on: linux.s390x
       ALPINE_IMAGE: "docker.io/s390x/alpine"
       {%- elif "conda" in build_environment and config["gpu_arch_type"] == "cuda" %}
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       {%- else %}
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       {%- endif %}
       build_name: !{{ config["build_name"] }}
       build_environment: !{{ build_environment }}
@@ -103,7 +102,6 @@ jobs:
       build_name: !{{ config["build_name"] }}
       build_environment: !{{ build_environment }}
       {%- if "aarch64" in build_environment %}
-      runner_prefix: amz2023.
       runs_on: linux.arm64.2xlarge
       ALPINE_IMAGE: "arm64v8/alpine"
       {%- elif "s390x" in build_environment %}
@@ -112,10 +110,10 @@ jobs:
       {%- elif config["gpu_arch_type"] == "rocm" %}
       runs_on: linux.rocm.gpu
       {%- elif config["gpu_arch_type"] == "cuda" %}
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
       {%- else %}
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
       {%- endif %}
     secrets:

.github/templates/macos_binary_build_workflow.yml.j2

@@ -101,7 +101,7 @@ jobs:
           # shellcheck disable=SC1091
           source "${RUNNER_TEMP}/anaconda/bin/activate"
           "${PYTORCH_ROOT}/.circleci/scripts/binary_macos_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: !{{ config["build_name"] }}

.github/templates/upload.yml.j2

@@ -45,7 +45,7 @@
   {%- if is_windows %}
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
   {%- endif %}
 
 {%- else %}

.github/templates/windows_binary_build_workflow.yml.j2

@@ -53,10 +53,24 @@ env:
 !{{ common.concurrency(build_environment) }}
 
 jobs:
+  get-label-type:
+    name: get-label-type
+    uses: ./.github/workflows/_runner-determinator.yml
+    with:
+      triggering_actor: ${{ github.triggering_actor }}
+      issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
+      curr_branch: ${{ github.head_ref || github.ref_name }}
+      curr_ref_type: ${{ github.ref_type }}
+
 {%- for config in build_configs %}
   !{{ config["build_name"] }}-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    {%- if branches == "nightly" %}
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
+    {%- else %}
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
+    {%- endif %}
     timeout-minutes: !{{ common.timeout_minutes }}
     !{{ upload.binary_env(config, True) }}
     {%- if config.pytorch_extra_install_requirements is defined and config.pytorch_extra_install_requirements|d('')|length > 0  %}
@@ -85,15 +99,17 @@ jobs:
       !{{ common.wait_and_kill_ssh_windows('pytorch') }}
   !{{ config["build_name"] }}-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: !{{ config["build_name"] }}-build
+    needs:
+      - !{{ config["build_name"] }}-build
+      - get-label-type
 {%- if config["gpu_arch_type"] == "cuda" %}
 {%- if branches == "nightly" %}
-    runs-on: windows.8xlarge.nvidia.gpu
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
 {%- else %}
-    runs-on: windows.8xlarge.nvidia.gpu.nonephemeral
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge.nonephemeral"
 {%- endif %}
 {%- else %}
-    runs-on: windows.4xlarge.nonephemeral
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
 {%- endif %}
     timeout-minutes: !{{ common.timeout_minutes }}
     !{{ upload.binary_env(config, True) }}

.github/workflows/_binary-build-linux.yml

@@ -283,7 +283,7 @@ jobs:
           # Ensure the working directory gets chowned back to the current user
           docker run --rm -v "${RUNNER_TEMP}/artifacts:/v" -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
 
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: ${{ steps.filter.outputs.is-test-matrix-empty == 'False' }}
         with:
           name: ${{ inputs.build_name }}

.github/workflows/_binary-test-linux.yml

@@ -210,7 +210,7 @@ jobs:
 
       - name: Download Build Artifacts
         if: ${{ steps.filter.outputs.is-test-matrix-empty == 'False' }}
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4.1.7
         with:
           name: ${{ inputs.build_name }}
           path: "${{ runner.temp }}/artifacts/"

.github/workflows/_binary-upload.yml

@@ -126,7 +126,7 @@ jobs:
         # NB: When the previous build job is skipped, there won't be any artifacts and
         # this step will fail. Binary build jobs can only be skipped on CI, not nightly
         continue-on-error: true
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4.1.7
         with:
           name: ${{ inputs.build_name }}
           path: "${{ runner.temp }}/artifacts/"

.github/workflows/_ios-build-test.yml

@@ -292,7 +292,7 @@ jobs:
           bundler-cache: true
 
       - name: Download arm64 artifacts
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4.1.7
         with:
           name: pytorch-ios-build-artifacts-arm64
 

.github/workflows/_runner-determinator.yml

@@ -196,11 +196,14 @@ jobs:
 
 
           def get_potential_pr_author(
-              gh: Github, repo: str, username: str, ref_type: str, ref_name: str
+              github_token: str, repo: str, username: str, ref_type: str, ref_name: str
           ) -> str:
               # If the trigger was a new tag added by a bot, this is a ciflow case
               # Fetch the actual username from the original PR. The PR number is
               # embedded in the tag name: ciflow/<name>/<pr-number>
+
+              gh = get_gh_client(github_token)
+
               if username == "pytorch-bot[bot]" and ref_type == "tag":
                   split_tag = ref_name.split("/")
                   if (
@@ -222,23 +225,32 @@ jobs:
 
 
           def is_exception_branch(branch: str) -> bool:
+              """
+              Branches that get opted out of all experiments and should always use Meta runners
+              """
               return branch.split("/")[0] in {"main", "nightly", "release", "landchecks"}
 
 
-          def get_workflow_type(issue: Issue, workflow_requestors: Iterable[str]) -> str:
-              try:
-                  first_comment = issue.get_comments()[0].body.strip("\n\t ")
+          def get_fleet(rollout_state: str, workflow_requestors: Iterable[str]) -> str:
+              """
+              Determines if the job should run on the LF fleet or the Meta fleet
 
-                  if first_comment[0] == "!":
+              Returns:
+                  The appropriate label prefix for the runner, corresponding to the fleet to use.
+                  This gets prefixed to the very start of the runner label.
+              """
+
+              try:
+                  if rollout_state[0] == "!":
                       log.info("LF Workflows are disabled for everyone. Using meta runners.")
                       return WORKFLOW_LABEL_META
-                  elif first_comment[0] == "*":
+                  elif rollout_state[0] == "*":
                       log.info("LF Workflows are enabled for everyone. Using LF runners.")
                       return WORKFLOW_LABEL_LF
                   else:
                       all_opted_in_users = {
                           usr_raw.strip("\n\t@ ").split(",")[0]
-                          for usr_raw in first_comment.split()
+                          for usr_raw in rollout_state.split()
                       }
                       opted_in_requestors = {
                           usr for usr in workflow_requestors if usr in all_opted_in_users
@@ -262,11 +274,17 @@ jobs:
 
 
           def get_optin_feature(
-              issue: Issue, workflow_requestors: Iterable[str], feature: str, fallback: str
+              rollout_state: str, workflow_requestors: Iterable[str], feature: str, fallback: str
           ) -> str:
+              """
+              Used to dynamically opt in jobs to specific runner-type variants.
+
+              Returns:
+                  The runner-type's variant name if the user has opted in to the feature, otherwise returns an empty string.
+                  This variant name is prefixed to the runner-type in the label.
+              """
               try:
-                  first_comment = issue.get_comments()[0].body.strip("\n\t ")
-                  userlist = {u.lstrip("#").strip("\n\t@ ") for u in first_comment.split()}
+                  userlist = {u.lstrip("#").strip("\n\t@ ") for u in rollout_state.split()}
                   all_opted_in_users = set()
                   for user in userlist:
                       for i in user.split(","):
@@ -294,6 +312,17 @@ jobs:
                   return fallback
 
 
+          def get_rollout_state_from_issue(github_token: str, repo: str, issue_num: int) -> str:
+              """
+              Gets the first comment of the issue, which contains the desired rollout state.
+
+              The default issue we use - https://github.com/pytorch/test-infra/issues/5132
+              """
+              gh = get_gh_client(github_token)
+              issue = get_issue(gh, repo, issue_num)
+              return str(issue.get_comments()[0].body.strip("\n\t "))
+
+
           def main() -> None:
               args = parse_args()
 
@@ -303,25 +332,27 @@ jobs:
                   runner_ami = RUNNER_AMI_LEGACY
               else:
                   try:
-                      gh = get_gh_client(args.github_token)
-                      # The default issue we use - https://github.com/pytorch/test-infra/issues/5132
-                      issue = get_issue(gh, args.github_issue_repo, args.github_issue)
+                      rollout_state = get_rollout_state_from_issue(
+                          args.github_token, args.github_issue_repo, args.github_issue
+                      )
+
                       username = get_potential_pr_author(
-                          gh,
+                          args.github_token,
                           args.github_repo,
                           args.github_actor,
                           args.github_ref_type,
                           args.github_branch,
                       )
-                      label_type = get_workflow_type(
-                          issue,
+
+                      label_type = get_fleet(
+                          rollout_state,
                           (
                               args.github_issue_owner,
                               username,
                           ),
                       )
                       runner_ami = get_optin_feature(
-                          issue=issue,
+                          rollout_state=rollout_state,
                           workflow_requestors=(
                               args.github_issue_owner,
                               username,
@@ -346,6 +377,7 @@ jobs:
 
           if __name__ == "__main__":
               main()
+
           EOF
 
           cat runner_determinator.py

.github/workflows/_win-build.yml

@@ -11,6 +11,16 @@ on:
         required: true
         type: string
         description: What CUDA version to build with, "cpu" for none.
+      use-xpu:
+        required: false
+        type: boolean
+        default: false
+        description: If set, build with XPU support.
+      vc-year:
+        required: false
+        type: string
+        default: "2019"
+        description: The Visual Studio year to use for building.
       build-with-debug:
         required: false
         type: boolean
@@ -141,7 +151,7 @@ jobs:
           SCCACHE_REGION: us-east-1
           VC_PRODUCT: "BuildTools"
           VC_VERSION: ""
-          VC_YEAR: "2019"
+          VC_YEAR: "${{ inputs.vc-year }}"
           ALPINE_IMAGE: "308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine"
           AWS_DEFAULT_REGION: us-east-1
           PR_NUMBER: ${{ github.event.pull_request.number }}
@@ -149,6 +159,7 @@ jobs:
           DEBUG: ${{ inputs.build-with-debug && '1' || '0' }}
           TORCH_CUDA_ARCH_LIST: "8.6"
           USE_CUDA: ${{ inputs.cuda-version != 'cpu' && '1' || '0' }}
+          USE_XPU: ${{ inputs.use-xpu == true && '1' || '0' }}
           OUR_GITHUB_JOB_ID: ${{ steps.get-job-id.outputs.job-id }}
         run: |
           .ci/pytorch/win-build.sh

.github/workflows/build-manywheel-images.yml

@@ -12,11 +12,13 @@ on:
       - v[0-9]+.[0-9]+.[0-9]+-rc[0-9]+
     paths:
       - '.ci/docker/manywheel/*'
+      - '.ci/docker/manywheel/build_scripts/*'
       - '.ci/docker/common/*'
       - .github/workflows/build-manywheel-images.yml
   pull_request:
     paths:
       - '.ci/docker/manywheel/*'
+      - '.ci/docker/manywheel/build_scripts/*'
       - '.ci/docker/common/*'
       - .github/workflows/build-manywheel-images.yml
 
@@ -108,7 +110,7 @@ jobs:
           .ci/docker/manywheel/build.sh manylinux2_28-builder:cuda${{matrix.cuda_version}}
   build-docker-cuda-aarch64:
     environment: ${{ (github.ref == 'refs/heads/main' || startsWith(github.event.ref, 'refs/tags/v')) && 'docker-build' || '' }}
-    runs-on: linux.arm64.2xlarge
+    runs-on: linux.arm64.2xlarge.ephemeral
     strategy:
       matrix:
         cuda_version: ["12.4"]
@@ -236,7 +238,7 @@ jobs:
           .ci/docker/manywheel/build.sh manylinux2_28-builder:cpu
   build-docker-cpu-aarch64:
     environment: ${{ (github.ref == 'refs/heads/main' || startsWith(github.event.ref, 'refs/tags/v')) && 'docker-build' || '' }}
-    runs-on: linux.arm64.2xlarge
+    runs-on: linux.arm64.2xlarge.ephemeral
     env:
       GPU_ARCH_TYPE: cpu-aarch64
     steps:
@@ -267,7 +269,7 @@ jobs:
           .ci/docker/manywheel/build.sh manylinuxaarch64-builder:cpu-aarch64
   build-docker-cpu-aarch64-2_28:
     environment: ${{ (github.ref == 'refs/heads/main' || startsWith(github.event.ref, 'refs/tags/v')) && 'docker-build' || '' }}
-    runs-on: linux.arm64.2xlarge
+    runs-on: linux.arm64.2xlarge.ephemeral
     env:
       GPU_ARCH_TYPE: cpu-aarch64-2_28
     steps:

.github/workflows/build-triton-wheel.yml

@@ -13,7 +13,6 @@ on:
       - .github/scripts/build_triton_wheel.py
       - .github/ci_commit_pins/triton.txt
       - .ci/docker/ci_commit_pins/triton.txt
-      - .ci/docker/ci_commit_pins/triton-rocm.txt
       - .ci/docker/ci_commit_pins/triton-xpu.txt
   pull_request:
     paths:
@@ -21,7 +20,6 @@ on:
       - .github/scripts/build_triton_wheel.py
       - .github/ci_commit_pins/triton.txt
       - .ci/docker/ci_commit_pins/triton.txt
-      - .ci/docker/ci_commit_pins/triton-rocm.txt
       - .ci/docker/ci_commit_pins/triton-xpu.txt
 
 concurrency:
@@ -31,7 +29,7 @@ concurrency:
 jobs:
   build-wheel:
     name: "Build Triton Wheel"
-    runs-on: [self-hosted, linux.2xlarge]
+    runs-on: [self-hosted, linux.4xlarge]
     strategy:
       fail-fast: false
       matrix:
@@ -120,7 +118,7 @@ jobs:
           fi
           docker exec -t "${container_name}" chown -R 1000.1000 /artifacts
 
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         with:
           name: pytorch-triton-wheel-${{ matrix.py_vers }}-${{ matrix.device }}
           if-no-files-found: error
@@ -157,7 +155,7 @@ jobs:
           aws-region: us-east-1
 
       - name: Download Build Artifacts
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4.1.7
         with:
           # Download all available artifacts
           path: ${{ runner.temp }}/artifacts-all
@@ -253,7 +251,7 @@ jobs:
           docker exec -t "${container_name}" python /pytorch/.github/scripts/build_triton_wheel.py --build-conda --py-version="${PY_VERS}" $RELEASE
           docker exec -t "${container_name}" chown -R 1000.1000 /artifacts
 
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         with:
           name: pytorch-triton-conda-${{ matrix.py_vers }}
           if-no-files-found: error
@@ -273,7 +271,7 @@ jobs:
       - uses: actions/checkout@v3
 
       - name: Download Build Artifacts
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4.1.7
         with:
           # Download all available artifacts
           path: ${{ runner.temp }}/artifacts-all

.github/workflows/check-labels.yml

@@ -19,6 +19,10 @@ on:
     branches: [gh/**/base]
 
   workflow_dispatch:
+    inputs:
+      pr_number:
+        description: 'PR number to check labels for'
+        required: true
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }}
@@ -54,7 +58,7 @@ jobs:
       - name: Check labels
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          PR_NUM: ${{ github.event.number }}
+          PR_NUM: ${{ github.event.number || github.event.inputs.pr_number }}
         run: |
           set -ex
-          python3 .github/scripts/check_labels.py "${PR_NUM}"
+          python3 .github/scripts/check_labels.py --exit-non-zero "${PR_NUM}"

.github/workflows/create_release.yml

@@ -80,7 +80,7 @@ jobs:
       id-token: write
     needs: release
     steps:
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v4.1.7
         with:
           name: ${{ needs.release.outputs.pt_release_name }}
       - name: Configure AWS credentials(PyTorch account)

.github/workflows/docker-builds.yml

@@ -45,15 +45,15 @@ jobs:
           pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9-inductor-benchmarks,
           pytorch-linux-focal-cuda12.1-cudnn9-py3.12-gcc9-inductor-benchmarks,
           pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9,
-          pytorch-linux-focal-py3.8-clang10,
+          pytorch-linux-focal-py3.9-clang10,
           pytorch-linux-focal-py3.11-clang10,
           pytorch-linux-focal-py3.12-clang10,
           pytorch-linux-focal-rocm-n-1-py3,
           pytorch-linux-focal-rocm-n-py3,
-          pytorch-linux-jammy-cuda11.8-cudnn9-py3.8-clang12,
+          pytorch-linux-jammy-cuda11.8-cudnn9-py3.9-clang12,
           pytorch-linux-focal-py3-clang9-android-ndk-r21e,
-          pytorch-linux-jammy-py3.8-gcc11,
-          pytorch-linux-jammy-py3.8-gcc11-inductor-benchmarks,
+          pytorch-linux-jammy-py3.9-gcc11,
+          pytorch-linux-jammy-py3.9-gcc11-inductor-benchmarks,
           pytorch-linux-jammy-py3.12-halide,
           pytorch-linux-jammy-xpu-2024.0-py3,
           pytorch-linux-jammy-py3-clang15-asan,

.github/workflows/generated-linux-aarch64-binary-manywheel-nightly.yml

@@ -59,8 +59,7 @@ jobs:
       GPU_ARCH_TYPE: cpu-aarch64
       DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: amz2023.
-      runs_on: linux.arm64.m7g.4xlarge
+      runs_on: linux.arm64.m7g.4xlarge.ephemeral
       ALPINE_IMAGE: "arm64v8/alpine"
       build_name: manywheel-py3_9-cpu-aarch64
       build_environment: linux-aarch64-binary-manywheel
@@ -85,7 +84,6 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cpu-aarch64
       build_environment: linux-aarch64-binary-manywheel
-      runner_prefix: amz2023.
       runs_on: linux.arm64.2xlarge
       ALPINE_IMAGE: "arm64v8/alpine"
     secrets:
@@ -128,8 +126,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
       DESIRED_DEVTOOLSET: cxx11-abi
       DESIRED_PYTHON: "3.9"
-      runner_prefix: amz2023.
-      runs_on: linux.arm64.m7g.4xlarge
+      runs_on: linux.arm64.m7g.4xlarge.ephemeral
       ALPINE_IMAGE: "arm64v8/alpine"
       build_name: manywheel-py3_9-cuda-aarch64
       build_environment: linux-aarch64-binary-manywheel
@@ -174,8 +171,7 @@ jobs:
       GPU_ARCH_TYPE: cpu-aarch64
       DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: amz2023.
-      runs_on: linux.arm64.m7g.4xlarge
+      runs_on: linux.arm64.m7g.4xlarge.ephemeral
       ALPINE_IMAGE: "arm64v8/alpine"
       build_name: manywheel-py3_10-cpu-aarch64
       build_environment: linux-aarch64-binary-manywheel
@@ -200,7 +196,6 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cpu-aarch64
       build_environment: linux-aarch64-binary-manywheel
-      runner_prefix: amz2023.
       runs_on: linux.arm64.2xlarge
       ALPINE_IMAGE: "arm64v8/alpine"
     secrets:
@@ -243,8 +238,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
       DESIRED_DEVTOOLSET: cxx11-abi
       DESIRED_PYTHON: "3.10"
-      runner_prefix: amz2023.
-      runs_on: linux.arm64.m7g.4xlarge
+      runs_on: linux.arm64.m7g.4xlarge.ephemeral
       ALPINE_IMAGE: "arm64v8/alpine"
       build_name: manywheel-py3_10-cuda-aarch64
       build_environment: linux-aarch64-binary-manywheel
@@ -289,8 +283,7 @@ jobs:
       GPU_ARCH_TYPE: cpu-aarch64
       DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: amz2023.
-      runs_on: linux.arm64.m7g.4xlarge
+      runs_on: linux.arm64.m7g.4xlarge.ephemeral
       ALPINE_IMAGE: "arm64v8/alpine"
       build_name: manywheel-py3_11-cpu-aarch64
       build_environment: linux-aarch64-binary-manywheel
@@ -315,7 +308,6 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cpu-aarch64
       build_environment: linux-aarch64-binary-manywheel
-      runner_prefix: amz2023.
       runs_on: linux.arm64.2xlarge
       ALPINE_IMAGE: "arm64v8/alpine"
     secrets:
@@ -358,8 +350,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
       DESIRED_DEVTOOLSET: cxx11-abi
       DESIRED_PYTHON: "3.11"
-      runner_prefix: amz2023.
-      runs_on: linux.arm64.m7g.4xlarge
+      runs_on: linux.arm64.m7g.4xlarge.ephemeral
       ALPINE_IMAGE: "arm64v8/alpine"
       build_name: manywheel-py3_11-cuda-aarch64
       build_environment: linux-aarch64-binary-manywheel
@@ -404,8 +395,7 @@ jobs:
       GPU_ARCH_TYPE: cpu-aarch64
       DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cpu-aarch64-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: amz2023.
-      runs_on: linux.arm64.m7g.4xlarge
+      runs_on: linux.arm64.m7g.4xlarge.ephemeral
       ALPINE_IMAGE: "arm64v8/alpine"
       build_name: manywheel-py3_12-cpu-aarch64
       build_environment: linux-aarch64-binary-manywheel
@@ -430,7 +420,6 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cpu-aarch64
       build_environment: linux-aarch64-binary-manywheel
-      runner_prefix: amz2023.
       runs_on: linux.arm64.2xlarge
       ALPINE_IMAGE: "arm64v8/alpine"
     secrets:
@@ -473,8 +462,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinuxaarch64-builder:cuda12.4-main
       DESIRED_DEVTOOLSET: cxx11-abi
       DESIRED_PYTHON: "3.12"
-      runner_prefix: amz2023.
-      runs_on: linux.arm64.m7g.4xlarge
+      runs_on: linux.arm64.m7g.4xlarge.ephemeral
       ALPINE_IMAGE: "arm64v8/alpine"
       build_name: manywheel-py3_12-cuda-aarch64
       build_environment: linux-aarch64-binary-manywheel

.github/workflows/generated-linux-binary-conda-nightly.yml

@@ -59,7 +59,7 @@ jobs:
       GPU_ARCH_TYPE: cpu
       DOCKER_IMAGE: pytorch/conda-builder:cpu-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: conda-py3_9-cpu
       build_environment: linux-binary-conda
     secrets:
@@ -82,7 +82,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cpu
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -124,7 +124,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_9-cuda11_8
       build_environment: linux-binary-conda
@@ -149,7 +149,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cuda11_8
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -192,7 +192,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_9-cuda12_1
       build_environment: linux-binary-conda
@@ -217,7 +217,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cuda12_1
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -260,7 +260,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_9-cuda12_4
       build_environment: linux-binary-conda
@@ -285,7 +285,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: conda-py3_9-cuda12_4
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -327,7 +327,7 @@ jobs:
       GPU_ARCH_TYPE: cpu
       DOCKER_IMAGE: pytorch/conda-builder:cpu-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: conda-py3_10-cpu
       build_environment: linux-binary-conda
     secrets:
@@ -350,7 +350,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cpu
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -392,7 +392,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_10-cuda11_8
       build_environment: linux-binary-conda
@@ -417,7 +417,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cuda11_8
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -460,7 +460,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_10-cuda12_1
       build_environment: linux-binary-conda
@@ -485,7 +485,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cuda12_1
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -528,7 +528,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_10-cuda12_4
       build_environment: linux-binary-conda
@@ -553,7 +553,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: conda-py3_10-cuda12_4
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -595,7 +595,7 @@ jobs:
       GPU_ARCH_TYPE: cpu
       DOCKER_IMAGE: pytorch/conda-builder:cpu-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: conda-py3_11-cpu
       build_environment: linux-binary-conda
     secrets:
@@ -618,7 +618,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cpu
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -660,7 +660,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_11-cuda11_8
       build_environment: linux-binary-conda
@@ -685,7 +685,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cuda11_8
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -728,7 +728,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_11-cuda12_1
       build_environment: linux-binary-conda
@@ -753,7 +753,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cuda12_1
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -796,7 +796,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_11-cuda12_4
       build_environment: linux-binary-conda
@@ -821,7 +821,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: conda-py3_11-cuda12_4
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -863,7 +863,7 @@ jobs:
       GPU_ARCH_TYPE: cpu
       DOCKER_IMAGE: pytorch/conda-builder:cpu-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: conda-py3_12-cpu
       build_environment: linux-binary-conda
     secrets:
@@ -886,7 +886,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cpu
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -928,7 +928,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda11.8-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_12-cuda11_8
       build_environment: linux-binary-conda
@@ -953,7 +953,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cuda11_8
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -996,7 +996,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda12.1-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_12-cuda12_1
       build_environment: linux-binary-conda
@@ -1021,7 +1021,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cuda12_1
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -1064,7 +1064,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/conda-builder:cuda12.4-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.24xlarge.ephemeral
       build_name: conda-py3_12-cuda12_4
       build_environment: linux-binary-conda
@@ -1089,7 +1089,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: conda-py3_12-cuda12_4
       build_environment: linux-binary-conda
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/generated-linux-binary-libtorch-cxx11-abi-main.yml

@@ -55,7 +55,7 @@ jobs:
       DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-cpu-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
     secrets:
@@ -79,7 +79,7 @@ jobs:
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cpu-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/generated-linux-binary-libtorch-cxx11-abi-nightly.yml

@@ -60,7 +60,7 @@ jobs:
       DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cpu-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-cpu-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
     secrets:
@@ -84,7 +84,7 @@ jobs:
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cpu-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -128,7 +128,7 @@ jobs:
       DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda11.8-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-cuda11_8-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
     secrets:
@@ -153,7 +153,7 @@ jobs:
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cuda11_8-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -198,7 +198,7 @@ jobs:
       DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.1-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-cuda12_1-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
     secrets:
@@ -223,7 +223,7 @@ jobs:
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cuda12_1-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -268,7 +268,7 @@ jobs:
       DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:cuda12.4-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-cuda12_4-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
     secrets:
@@ -293,7 +293,7 @@ jobs:
       DESIRED_DEVTOOLSET: cxx11-abi
       build_name: libtorch-cuda12_4-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -338,7 +338,7 @@ jobs:
       DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.1-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-rocm6_1-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
     secrets:
@@ -366,7 +366,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-rocm6_1-shared-with-deps-cxx11-abi
@@ -448,7 +448,7 @@ jobs:
       DOCKER_IMAGE: pytorch/libtorch-cxx11-builder:rocm6.2-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: cxx11-abi
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-rocm6_2-shared-with-deps-cxx11-abi
       build_environment: linux-binary-libtorch-cxx11-abi
     secrets:
@@ -476,7 +476,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-rocm6_2-shared-with-deps-cxx11-abi

.github/workflows/generated-linux-binary-libtorch-pre-cxx11-main.yml

@@ -55,7 +55,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-cpu-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
     secrets:
@@ -79,7 +79,7 @@ jobs:
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cpu-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/generated-linux-binary-libtorch-pre-cxx11-nightly.yml

@@ -60,7 +60,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-cpu-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
     secrets:
@@ -84,7 +84,7 @@ jobs:
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cpu-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -128,7 +128,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-cuda11_8-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
     secrets:
@@ -153,7 +153,7 @@ jobs:
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cuda11_8-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -198,7 +198,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-cuda12_1-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
     secrets:
@@ -223,7 +223,7 @@ jobs:
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cuda12_1-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -268,7 +268,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-cuda12_4-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
     secrets:
@@ -293,7 +293,7 @@ jobs:
       DESIRED_DEVTOOLSET: pre-cxx11
       build_name: libtorch-cuda12_4-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -338,7 +338,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-rocm6_1-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
     secrets:
@@ -366,7 +366,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-rocm6_1-shared-with-deps-pre-cxx11
@@ -448,7 +448,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-main
       LIBTORCH_VARIANT: shared-with-deps
       DESIRED_DEVTOOLSET: pre-cxx11
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: libtorch-rocm6_2-shared-with-deps-pre-cxx11
       build_environment: linux-binary-libtorch-pre-cxx11
     secrets:
@@ -476,7 +476,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-rocm6_2-shared-with-deps-pre-cxx11

.github/workflows/generated-linux-binary-manywheel-main.yml

@@ -55,7 +55,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda11_8
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -80,7 +80,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda11_8
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -101,7 +101,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       use_split_build: True
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda11_8-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -127,7 +127,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda11_8-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -147,7 +147,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda12_1
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -172,7 +172,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_1
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -193,7 +193,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       use_split_build: True
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda12_1-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -219,7 +219,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_1-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -239,7 +239,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda12_4
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -264,7 +264,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_4
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -285,7 +285,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       use_split_build: True
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda12_4-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -311,7 +311,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_4-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/generated-linux-binary-manywheel-nightly.yml

@@ -59,7 +59,7 @@ jobs:
       GPU_ARCH_TYPE: cpu
       DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cpu
       build_environment: linux-binary-manywheel
     secrets:
@@ -82,7 +82,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cpu
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -124,7 +124,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinuxcxx11-abi-builder:cpu-cxx11-abi-main
       DESIRED_DEVTOOLSET: cxx11-abi
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cpu-cxx11-abi
       build_environment: linux-binary-manywheel
     secrets:
@@ -148,7 +148,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cpu-cxx11-abi
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -191,7 +191,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda11_8
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -216,7 +216,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda11_8
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -260,7 +260,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       use_split_build: True
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda11_8-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -286,7 +286,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda11_8-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -330,7 +330,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda12_1
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -355,7 +355,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_1
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -399,7 +399,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       use_split_build: True
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda12_1-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -425,7 +425,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_1-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -469,7 +469,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda12_4
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -494,7 +494,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_4
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -538,7 +538,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       use_split_build: True
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-cuda12_4-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -564,7 +564,7 @@ jobs:
       DESIRED_PYTHON: "3.9"
       build_name: manywheel-py3_9-cuda12_4-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -608,7 +608,7 @@ jobs:
       GPU_ARCH_TYPE: rocm
       DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-rocm6_1
       build_environment: linux-binary-manywheel
     secrets:
@@ -635,7 +635,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_9-rocm6_1
@@ -715,7 +715,7 @@ jobs:
       GPU_ARCH_TYPE: rocm
       DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-rocm6_2
       build_environment: linux-binary-manywheel
     secrets:
@@ -742,7 +742,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_9-rocm6_2
@@ -821,7 +821,7 @@ jobs:
       GPU_ARCH_TYPE: xpu
       DOCKER_IMAGE: pytorch/manylinux2_28-builder:xpu-main
       DESIRED_PYTHON: "3.9"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_9-xpu
       build_environment: linux-binary-manywheel
     secrets:
@@ -859,7 +859,7 @@ jobs:
       - name: Login to Amazon ECR
         id: login-ecr
         uses: aws-actions/amazon-ecr-login@v2
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_9-xpu
@@ -934,7 +934,7 @@ jobs:
       GPU_ARCH_TYPE: cpu
       DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-cpu
       build_environment: linux-binary-manywheel
     secrets:
@@ -957,7 +957,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cpu
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -999,7 +999,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinuxcxx11-abi-builder:cpu-cxx11-abi-main
       DESIRED_DEVTOOLSET: cxx11-abi
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-cpu-cxx11-abi
       build_environment: linux-binary-manywheel
     secrets:
@@ -1023,7 +1023,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cpu-cxx11-abi
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -1066,7 +1066,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-cuda11_8
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -1091,7 +1091,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda11_8
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -1135,7 +1135,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       use_split_build: True
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-cuda11_8-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -1161,7 +1161,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda11_8-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -1205,7 +1205,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-cuda12_1
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -1230,7 +1230,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_1
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -1274,7 +1274,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       use_split_build: True
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-cuda12_1-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -1300,7 +1300,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_1-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -1345,7 +1345,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       use_split_build: False
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-cuda12_1-full
       build_environment: linux-binary-manywheel
     secrets:
@@ -1370,7 +1370,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_1-full
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -1414,7 +1414,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-cuda12_4
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -1439,7 +1439,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_4
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -1483,7 +1483,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       use_split_build: True
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-cuda12_4-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -1509,7 +1509,7 @@ jobs:
       DESIRED_PYTHON: "3.10"
       build_name: manywheel-py3_10-cuda12_4-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -1553,7 +1553,7 @@ jobs:
       GPU_ARCH_TYPE: rocm
       DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-rocm6_1
       build_environment: linux-binary-manywheel
     secrets:
@@ -1580,7 +1580,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_10-rocm6_1
@@ -1660,7 +1660,7 @@ jobs:
       GPU_ARCH_TYPE: rocm
       DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-rocm6_2
       build_environment: linux-binary-manywheel
     secrets:
@@ -1687,7 +1687,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_10-rocm6_2
@@ -1766,7 +1766,7 @@ jobs:
       GPU_ARCH_TYPE: xpu
       DOCKER_IMAGE: pytorch/manylinux2_28-builder:xpu-main
       DESIRED_PYTHON: "3.10"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_10-xpu
       build_environment: linux-binary-manywheel
     secrets:
@@ -1804,7 +1804,7 @@ jobs:
       - name: Login to Amazon ECR
         id: login-ecr
         uses: aws-actions/amazon-ecr-login@v2
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_10-xpu
@@ -1879,7 +1879,7 @@ jobs:
       GPU_ARCH_TYPE: cpu
       DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-cpu
       build_environment: linux-binary-manywheel
     secrets:
@@ -1902,7 +1902,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cpu
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -1944,7 +1944,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinuxcxx11-abi-builder:cpu-cxx11-abi-main
       DESIRED_DEVTOOLSET: cxx11-abi
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-cpu-cxx11-abi
       build_environment: linux-binary-manywheel
     secrets:
@@ -1968,7 +1968,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cpu-cxx11-abi
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -2011,7 +2011,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-cuda11_8
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -2036,7 +2036,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda11_8
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -2080,7 +2080,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       use_split_build: True
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-cuda11_8-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -2106,7 +2106,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda11_8-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -2150,7 +2150,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-cuda12_1
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -2175,7 +2175,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda12_1
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -2219,7 +2219,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       use_split_build: True
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-cuda12_1-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -2245,7 +2245,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda12_1-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -2289,7 +2289,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-cuda12_4
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -2314,7 +2314,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda12_4
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -2358,7 +2358,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       use_split_build: True
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-cuda12_4-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -2384,7 +2384,7 @@ jobs:
       DESIRED_PYTHON: "3.11"
       build_name: manywheel-py3_11-cuda12_4-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -2428,7 +2428,7 @@ jobs:
       GPU_ARCH_TYPE: rocm
       DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-rocm6_1
       build_environment: linux-binary-manywheel
     secrets:
@@ -2455,7 +2455,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_11-rocm6_1
@@ -2535,7 +2535,7 @@ jobs:
       GPU_ARCH_TYPE: rocm
       DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-rocm6_2
       build_environment: linux-binary-manywheel
     secrets:
@@ -2562,7 +2562,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_11-rocm6_2
@@ -2641,7 +2641,7 @@ jobs:
       GPU_ARCH_TYPE: xpu
       DOCKER_IMAGE: pytorch/manylinux2_28-builder:xpu-main
       DESIRED_PYTHON: "3.11"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_11-xpu
       build_environment: linux-binary-manywheel
     secrets:
@@ -2679,7 +2679,7 @@ jobs:
       - name: Login to Amazon ECR
         id: login-ecr
         uses: aws-actions/amazon-ecr-login@v2
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_11-xpu
@@ -2754,7 +2754,7 @@ jobs:
       GPU_ARCH_TYPE: cpu
       DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-cpu
       build_environment: linux-binary-manywheel
     secrets:
@@ -2777,7 +2777,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cpu
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -2819,7 +2819,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinuxcxx11-abi-builder:cpu-cxx11-abi-main
       DESIRED_DEVTOOLSET: cxx11-abi
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-cpu-cxx11-abi
       build_environment: linux-binary-manywheel
     secrets:
@@ -2843,7 +2843,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cpu-cxx11-abi
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -2886,7 +2886,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-cuda11_8
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -2911,7 +2911,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda11_8
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -2955,7 +2955,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       use_split_build: True
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-cuda11_8-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -2981,7 +2981,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda11_8-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -3025,7 +3025,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-cuda12_1
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -3050,7 +3050,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda12_1
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -3094,7 +3094,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       use_split_build: True
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-cuda12_1-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -3120,7 +3120,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda12_1-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -3164,7 +3164,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-cuda12_4
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -3189,7 +3189,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda12_4
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -3233,7 +3233,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       use_split_build: True
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-cuda12_4-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -3259,7 +3259,7 @@ jobs:
       DESIRED_PYTHON: "3.12"
       build_name: manywheel-py3_12-cuda12_4-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -3303,7 +3303,7 @@ jobs:
       GPU_ARCH_TYPE: rocm
       DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.1-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-rocm6_1
       build_environment: linux-binary-manywheel
     secrets:
@@ -3330,7 +3330,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_12-rocm6_1
@@ -3410,7 +3410,7 @@ jobs:
       GPU_ARCH_TYPE: rocm
       DOCKER_IMAGE: pytorch/manylinux-builder:rocm6.2-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-rocm6_2
       build_environment: linux-binary-manywheel
     secrets:
@@ -3437,7 +3437,7 @@ jobs:
     steps:
       - name: Setup ROCm
         uses: ./.github/actions/setup-rocm
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_12-rocm6_2
@@ -3516,7 +3516,7 @@ jobs:
       GPU_ARCH_TYPE: xpu
       DOCKER_IMAGE: pytorch/manylinux2_28-builder:xpu-main
       DESIRED_PYTHON: "3.12"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_12-xpu
       build_environment: linux-binary-manywheel
     secrets:
@@ -3554,7 +3554,7 @@ jobs:
       - name: Login to Amazon ECR
         id: login-ecr
         uses: aws-actions/amazon-ecr-login@v2
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_12-xpu
@@ -3629,7 +3629,7 @@ jobs:
       GPU_ARCH_TYPE: cpu
       DOCKER_IMAGE: pytorch/manylinux-builder:cpu-main
       DESIRED_PYTHON: "3.13"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_13-cpu
       build_environment: linux-binary-manywheel
     secrets:
@@ -3652,7 +3652,7 @@ jobs:
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cpu
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -3694,7 +3694,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinuxcxx11-abi-builder:cpu-cxx11-abi-main
       DESIRED_DEVTOOLSET: cxx11-abi
       DESIRED_PYTHON: "3.13"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_13-cpu-cxx11-abi
       build_environment: linux-binary-manywheel
     secrets:
@@ -3718,7 +3718,7 @@ jobs:
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cpu-cxx11-abi
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -3761,7 +3761,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       DESIRED_PYTHON: "3.13"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_13-cuda11_8
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -3786,7 +3786,7 @@ jobs:
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda11_8
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -3830,7 +3830,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda11.8-main
       use_split_build: True
       DESIRED_PYTHON: "3.13"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_13-cuda11_8-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu11==11.8.89; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu11==11.8.87; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu11==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu11==11.11.3.6; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu11==10.9.0.58; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu11==10.3.0.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu11==11.4.1.48; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu11==11.7.5.86; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu11==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu11==11.8.86; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -3856,7 +3856,7 @@ jobs:
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda11_8-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -3900,7 +3900,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       DESIRED_PYTHON: "3.13"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_13-cuda12_1
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -3925,7 +3925,7 @@ jobs:
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda12_1
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -3969,7 +3969,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.1-main
       use_split_build: True
       DESIRED_PYTHON: "3.13"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_13-cuda12_1-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -3995,7 +3995,7 @@ jobs:
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda12_1-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -4039,7 +4039,7 @@ jobs:
       GPU_ARCH_TYPE: cuda
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       DESIRED_PYTHON: "3.13"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_13-cuda12_4
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -4064,7 +4064,7 @@ jobs:
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda12_4
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -4108,7 +4108,7 @@ jobs:
       DOCKER_IMAGE: pytorch/manylinux-builder:cuda12.4-main
       use_split_build: True
       DESIRED_PYTHON: "3.13"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_13-cuda12_4-split
       build_environment: linux-binary-manywheel
       PYTORCH_EXTRA_INSTALL_REQUIREMENTS: nvidia-cuda-nvrtc-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-runtime-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cuda-cupti-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cublas-cu12==12.4.5.8; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cufft-cu12==11.2.1.3; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-curand-cu12==10.3.5.147; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusolver-cu12==11.6.1.9; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-cusparse-cu12==12.3.1.170; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nccl-cu12==2.21.5; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvtx-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64' | nvidia-nvjitlink-cu12==12.4.127; platform_system == 'Linux' and platform_machine == 'x86_64'
@@ -4134,7 +4134,7 @@ jobs:
       DESIRED_PYTHON: "3.13"
       build_name: manywheel-py3_13-cuda12_4-split
       build_environment: linux-binary-manywheel
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runs_on: linux.4xlarge.nvidia.gpu
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -4177,7 +4177,7 @@ jobs:
       GPU_ARCH_TYPE: xpu
       DOCKER_IMAGE: pytorch/manylinux2_28-builder:xpu-main
       DESIRED_PYTHON: "3.13"
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build_name: manywheel-py3_13-xpu
       build_environment: linux-binary-manywheel
     secrets:
@@ -4215,7 +4215,7 @@ jobs:
       - name: Login to Amazon ECR
         id: login-ecr
         uses: aws-actions/amazon-ecr-login@v2
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: manywheel-py3_13-xpu

.github/workflows/generated-macos-arm64-binary-conda-nightly.yml

@@ -117,7 +117,7 @@ jobs:
           # shellcheck disable=SC1091
           source "${RUNNER_TEMP}/anaconda/bin/activate"
           "${PYTORCH_ROOT}/.circleci/scripts/binary_macos_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_9-cpu
@@ -232,7 +232,7 @@ jobs:
           # shellcheck disable=SC1091
           source "${RUNNER_TEMP}/anaconda/bin/activate"
           "${PYTORCH_ROOT}/.circleci/scripts/binary_macos_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_10-cpu
@@ -347,7 +347,7 @@ jobs:
           # shellcheck disable=SC1091
           source "${RUNNER_TEMP}/anaconda/bin/activate"
           "${PYTORCH_ROOT}/.circleci/scripts/binary_macos_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_11-cpu
@@ -462,7 +462,7 @@ jobs:
           # shellcheck disable=SC1091
           source "${RUNNER_TEMP}/anaconda/bin/activate"
           "${PYTORCH_ROOT}/.circleci/scripts/binary_macos_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_12-cpu

.github/workflows/generated-macos-arm64-binary-libtorch-cxx11-abi-nightly.yml

@@ -49,7 +49,7 @@ jobs:
       DESIRED_DEVTOOLSET: cxx11-abi
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       # NOTE: These environment variables are put here so that they can be applied on every job equally
       #       They are also here because setting them at a workflow level doesn't give us access to the
@@ -121,7 +121,7 @@ jobs:
           # shellcheck disable=SC1091
           source "${RUNNER_TEMP}/anaconda/bin/activate"
           "${PYTORCH_ROOT}/.circleci/scripts/binary_macos_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cpu-shared-with-deps-cxx11-abi

.github/workflows/generated-macos-arm64-binary-wheel-nightly.yml

@@ -118,7 +118,7 @@ jobs:
           # shellcheck disable=SC1091
           source "${RUNNER_TEMP}/anaconda/bin/activate"
           "${PYTORCH_ROOT}/.circleci/scripts/binary_macos_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: wheel-py3_9-cpu
@@ -234,7 +234,7 @@ jobs:
           # shellcheck disable=SC1091
           source "${RUNNER_TEMP}/anaconda/bin/activate"
           "${PYTORCH_ROOT}/.circleci/scripts/binary_macos_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: wheel-py3_10-cpu
@@ -350,7 +350,7 @@ jobs:
           # shellcheck disable=SC1091
           source "${RUNNER_TEMP}/anaconda/bin/activate"
           "${PYTORCH_ROOT}/.circleci/scripts/binary_macos_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: wheel-py3_11-cpu
@@ -466,7 +466,7 @@ jobs:
           # shellcheck disable=SC1091
           source "${RUNNER_TEMP}/anaconda/bin/activate"
           "${PYTORCH_ROOT}/.circleci/scripts/binary_macos_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: wheel-py3_12-cpu

.github/workflows/generated-windows-binary-conda-nightly.yml

@@ -32,9 +32,18 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  get-label-type:
+    name: get-label-type
+    uses: ./.github/workflows/_runner-determinator.yml
+    with:
+      triggering_actor: ${{ github.triggering_actor }}
+      issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
+      curr_branch: ${{ github.head_ref || github.ref_name }}
+      curr_ref_type: ${{ github.ref_type }}
   conda-py3_9-cpu-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -123,7 +132,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_9-cpu
@@ -145,8 +154,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_9-cpu-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_9-cpu-build
-    runs-on: windows.4xlarge.nonephemeral
+    needs:
+      - conda-py3_9-cpu-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -202,7 +213,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_9-cpu
@@ -276,7 +287,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_9-cuda11_8-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -366,7 +378,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_9-cuda11_8
@@ -388,8 +400,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_9-cuda11_8-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_9-cuda11_8-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_9-cuda11_8-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -446,7 +460,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_9-cuda11_8
@@ -521,7 +535,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_9-cuda12_1-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -611,7 +626,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_9-cuda12_1
@@ -633,8 +648,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_9-cuda12_1-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_9-cuda12_1-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_9-cuda12_1-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -691,7 +708,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_9-cuda12_1
@@ -766,7 +783,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_9-cuda12_4-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -856,7 +874,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_9-cuda12_4
@@ -878,8 +896,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_9-cuda12_4-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_9-cuda12_4-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_9-cuda12_4-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -936,7 +956,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_9-cuda12_4
@@ -1011,7 +1031,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_10-cpu-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -1100,7 +1121,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_10-cpu
@@ -1122,8 +1143,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_10-cpu-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_10-cpu-build
-    runs-on: windows.4xlarge.nonephemeral
+    needs:
+      - conda-py3_10-cpu-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -1179,7 +1202,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_10-cpu
@@ -1253,7 +1276,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_10-cuda11_8-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -1343,7 +1367,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_10-cuda11_8
@@ -1365,8 +1389,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_10-cuda11_8-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_10-cuda11_8-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_10-cuda11_8-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -1423,7 +1449,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_10-cuda11_8
@@ -1498,7 +1524,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_10-cuda12_1-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -1588,7 +1615,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_10-cuda12_1
@@ -1610,8 +1637,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_10-cuda12_1-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_10-cuda12_1-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_10-cuda12_1-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -1668,7 +1697,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_10-cuda12_1
@@ -1743,7 +1772,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_10-cuda12_4-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -1833,7 +1863,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_10-cuda12_4
@@ -1855,8 +1885,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_10-cuda12_4-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_10-cuda12_4-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_10-cuda12_4-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -1913,7 +1945,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_10-cuda12_4
@@ -1988,7 +2020,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_11-cpu-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -2077,7 +2110,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_11-cpu
@@ -2099,8 +2132,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_11-cpu-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_11-cpu-build
-    runs-on: windows.4xlarge.nonephemeral
+    needs:
+      - conda-py3_11-cpu-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -2156,7 +2191,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_11-cpu
@@ -2230,7 +2265,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_11-cuda11_8-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -2320,7 +2356,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_11-cuda11_8
@@ -2342,8 +2378,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_11-cuda11_8-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_11-cuda11_8-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_11-cuda11_8-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -2400,7 +2438,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_11-cuda11_8
@@ -2475,7 +2513,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_11-cuda12_1-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -2565,7 +2604,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_11-cuda12_1
@@ -2587,8 +2626,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_11-cuda12_1-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_11-cuda12_1-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_11-cuda12_1-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -2645,7 +2686,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_11-cuda12_1
@@ -2720,7 +2761,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_11-cuda12_4-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -2810,7 +2852,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_11-cuda12_4
@@ -2832,8 +2874,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_11-cuda12_4-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_11-cuda12_4-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_11-cuda12_4-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -2890,7 +2934,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_11-cuda12_4
@@ -2965,7 +3009,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_12-cpu-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -3054,7 +3099,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_12-cpu
@@ -3076,8 +3121,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_12-cpu-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_12-cpu-build
-    runs-on: windows.4xlarge.nonephemeral
+    needs:
+      - conda-py3_12-cpu-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -3133,7 +3180,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_12-cpu
@@ -3207,7 +3254,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_12-cuda11_8-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -3297,7 +3345,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_12-cuda11_8
@@ -3319,8 +3367,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_12-cuda11_8-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_12-cuda11_8-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_12-cuda11_8-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -3377,7 +3427,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_12-cuda11_8
@@ -3452,7 +3502,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_12-cuda12_1-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -3542,7 +3593,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_12-cuda12_1
@@ -3564,8 +3615,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_12-cuda12_1-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_12-cuda12_1-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_12-cuda12_1-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -3622,7 +3675,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_12-cuda12_1
@@ -3697,7 +3750,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   conda-py3_12-cuda12_4-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -3787,7 +3841,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: conda-py3_12-cuda12_4
@@ -3809,8 +3863,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   conda-py3_12-cuda12_4-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: conda-py3_12-cuda12_4-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - conda-py3_12-cuda12_4-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -3867,7 +3923,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: conda-py3_12-cuda12_4

.github/workflows/generated-windows-binary-libtorch-debug-main.yml

@@ -25,9 +25,18 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  get-label-type:
+    name: get-label-type
+    uses: ./.github/workflows/_runner-determinator.yml
+    with:
+      triggering_actor: ${{ github.triggering_actor }}
+      issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
+      curr_branch: ${{ github.head_ref || github.ref_name }}
+      curr_ref_type: ${{ github.ref_type }}
   libtorch-cpu-shared-with-deps-debug-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -42,7 +51,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -120,7 +129,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cpu-shared-with-deps-debug
@@ -142,8 +151,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   libtorch-cpu-shared-with-deps-debug-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: libtorch-cpu-shared-with-deps-debug-build
-    runs-on: windows.4xlarge.nonephemeral
+    needs:
+      - libtorch-cpu-shared-with-deps-debug-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -158,7 +169,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -203,7 +214,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-cpu-shared-with-deps-debug

.github/workflows/generated-windows-binary-libtorch-debug-nightly.yml

@@ -32,9 +32,18 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  get-label-type:
+    name: get-label-type
+    uses: ./.github/workflows/_runner-determinator.yml
+    with:
+      triggering_actor: ${{ github.triggering_actor }}
+      issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
+      curr_branch: ${{ github.head_ref || github.ref_name }}
+      curr_ref_type: ${{ github.ref_type }}
   libtorch-cpu-shared-with-deps-debug-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -49,7 +58,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -127,7 +136,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cpu-shared-with-deps-debug
@@ -149,8 +158,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   libtorch-cpu-shared-with-deps-debug-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: libtorch-cpu-shared-with-deps-debug-build
-    runs-on: windows.4xlarge.nonephemeral
+    needs:
+      - libtorch-cpu-shared-with-deps-debug-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -165,7 +176,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -210,7 +221,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-cpu-shared-with-deps-debug
@@ -279,7 +290,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
       build_name: libtorch-cpu-shared-with-deps-debug
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -288,7 +299,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   libtorch-cuda11_8-shared-with-deps-debug-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -304,7 +316,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -382,7 +394,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cuda11_8-shared-with-deps-debug
@@ -404,8 +416,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   libtorch-cuda11_8-shared-with-deps-debug-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: libtorch-cuda11_8-shared-with-deps-debug-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - libtorch-cuda11_8-shared-with-deps-debug-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -421,7 +435,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -466,7 +480,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-cuda11_8-shared-with-deps-debug
@@ -536,7 +550,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
       build_name: libtorch-cuda11_8-shared-with-deps-debug
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -545,7 +559,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   libtorch-cuda12_1-shared-with-deps-debug-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -561,7 +576,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -639,7 +654,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cuda12_1-shared-with-deps-debug
@@ -661,8 +676,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   libtorch-cuda12_1-shared-with-deps-debug-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: libtorch-cuda12_1-shared-with-deps-debug-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - libtorch-cuda12_1-shared-with-deps-debug-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -678,7 +695,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -723,7 +740,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-cuda12_1-shared-with-deps-debug
@@ -793,7 +810,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
       build_name: libtorch-cuda12_1-shared-with-deps-debug
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -802,7 +819,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   libtorch-cuda12_4-shared-with-deps-debug-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -818,7 +836,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -896,7 +914,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cuda12_4-shared-with-deps-debug
@@ -918,8 +936,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   libtorch-cuda12_4-shared-with-deps-debug-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: libtorch-cuda12_4-shared-with-deps-debug-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - libtorch-cuda12_4-shared-with-deps-debug-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -935,7 +955,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -980,7 +1000,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-cuda12_4-shared-with-deps-debug
@@ -1050,7 +1070,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
       build_name: libtorch-cuda12_4-shared-with-deps-debug
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/generated-windows-binary-libtorch-release-main.yml

@@ -25,9 +25,18 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  get-label-type:
+    name: get-label-type
+    uses: ./.github/workflows/_runner-determinator.yml
+    with:
+      triggering_actor: ${{ github.triggering_actor }}
+      issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
+      curr_branch: ${{ github.head_ref || github.ref_name }}
+      curr_ref_type: ${{ github.ref_type }}
   libtorch-cpu-shared-with-deps-release-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -42,7 +51,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -120,7 +129,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cpu-shared-with-deps-release
@@ -142,8 +151,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   libtorch-cpu-shared-with-deps-release-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: libtorch-cpu-shared-with-deps-release-build
-    runs-on: windows.4xlarge.nonephemeral
+    needs:
+      - libtorch-cpu-shared-with-deps-release-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -158,7 +169,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -203,7 +214,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-cpu-shared-with-deps-release

.github/workflows/generated-windows-binary-libtorch-release-nightly.yml

@@ -32,9 +32,18 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  get-label-type:
+    name: get-label-type
+    uses: ./.github/workflows/_runner-determinator.yml
+    with:
+      triggering_actor: ${{ github.triggering_actor }}
+      issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
+      curr_branch: ${{ github.head_ref || github.ref_name }}
+      curr_ref_type: ${{ github.ref_type }}
   libtorch-cpu-shared-with-deps-release-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -49,7 +58,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -127,7 +136,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cpu-shared-with-deps-release
@@ -149,8 +158,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   libtorch-cpu-shared-with-deps-release-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: libtorch-cpu-shared-with-deps-release-build
-    runs-on: windows.4xlarge.nonephemeral
+    needs:
+      - libtorch-cpu-shared-with-deps-release-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -165,7 +176,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -210,7 +221,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-cpu-shared-with-deps-release
@@ -279,7 +290,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
       build_name: libtorch-cpu-shared-with-deps-release
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -288,7 +299,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   libtorch-cuda11_8-shared-with-deps-release-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -304,7 +316,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -382,7 +394,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cuda11_8-shared-with-deps-release
@@ -404,8 +416,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   libtorch-cuda11_8-shared-with-deps-release-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: libtorch-cuda11_8-shared-with-deps-release-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - libtorch-cuda11_8-shared-with-deps-release-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -421,7 +435,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -466,7 +480,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-cuda11_8-shared-with-deps-release
@@ -536,7 +550,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
       build_name: libtorch-cuda11_8-shared-with-deps-release
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -545,7 +559,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   libtorch-cuda12_1-shared-with-deps-release-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -561,7 +576,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -639,7 +654,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cuda12_1-shared-with-deps-release
@@ -661,8 +676,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   libtorch-cuda12_1-shared-with-deps-release-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: libtorch-cuda12_1-shared-with-deps-release-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - libtorch-cuda12_1-shared-with-deps-release-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -678,7 +695,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -723,7 +740,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-cuda12_1-shared-with-deps-release
@@ -793,7 +810,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
       build_name: libtorch-cuda12_1-shared-with-deps-release
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -802,7 +819,8 @@ jobs:
     uses: ./.github/workflows/_binary-upload.yml
   libtorch-cuda12_4-shared-with-deps-release-build:
     if: ${{ github.repository_owner == 'pytorch' }}
-    runs-on: windows.4xlarge.nonephemeral
+    needs: get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -818,7 +836,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -896,7 +914,7 @@ jobs:
         shell: bash
         run: |
           "${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4.4.0
         if: always()
         with:
           name: libtorch-cuda12_4-shared-with-deps-release
@@ -918,8 +936,10 @@ jobs:
           .github\scripts\kill_active_ssh_sessions.ps1
   libtorch-cuda12_4-shared-with-deps-release-test:  # Testing
     if: ${{ github.repository_owner == 'pytorch' }}
-    needs: libtorch-cuda12_4-shared-with-deps-release-build
-    runs-on: windows.8xlarge.nvidia.gpu
+    needs:
+      - libtorch-cuda12_4-shared-with-deps-release-build
+      - get-label-type
+    runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.g4dn.xlarge"
     timeout-minutes: 240
     env:
       PYTORCH_ROOT: ${{ github.workspace }}/pytorch
@@ -935,7 +955,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
     steps:
       - name: Display EC2 information
         shell: bash
@@ -980,7 +1000,7 @@ jobs:
           echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
           echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
           echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4.1.7
         name: Download Build Artifacts
         with:
           name: libtorch-cuda12_4-shared-with-deps-release
@@ -1050,7 +1070,7 @@ jobs:
       LIBTORCH_VARIANT: shared-with-deps
       # This is a dummy value for libtorch to work correctly with our batch scripts
       # without this value pip does not get installed for some reason
-      DESIRED_PYTHON: "3.8"
+      DESIRED_PYTHON: "3.9"
       build_name: libtorch-cuda12_4-shared-with-deps-release
     secrets:
       github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/inductor-micro-benchmark-x86.yml

@@ -0,0 +1,40 @@
+name: inductor-micro-benchmark-x86
+
+on:
+  schedule:
+    - cron: 0 7 * * *
+  push:
+    tags:
+      - ciflow/inductor-micro-benchmark-cpu-x86/*
+  workflow_dispatch:
+
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref_name }}-${{ github.ref_type == 'branch' && github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }}
+  cancel-in-progress: true
+
+permissions: read-all
+
+jobs:
+  linux-jammy-cpu-py3_9-gcc11-inductor-build:
+    name: linux-jammy-cpu-py3.9-gcc11-inductor
+    uses: ./.github/workflows/_linux-build.yml
+    with:
+      build-environment: linux-jammy-py3.9-gcc11
+      docker-image-name: pytorch-linux-jammy-py3.9-gcc11-inductor-benchmarks
+      # Use metal host for benchmark jobs
+      test-matrix: |
+        { include: [
+          { config: "inductor-micro-benchmark-cpu-x86", shard: 1, num_shards: 1, runner: "linux.24xl.spr-metal" },
+        ]}
+
+  linux-jammy-cpu-py3_9-gcc11-inductor-micro-benchmark-test:
+    name: linux-jammy-cpu-py3.9-gcc11-inductor
+    uses: ./.github/workflows/_linux-test.yml
+    needs: linux-jammy-cpu-py3_9-gcc11-inductor-build
+    with:
+      build-environment: linux-jammy-py3.9-gcc11
+      docker-image: ${{ needs.linux-jammy-cpu-py3_9-gcc11-inductor-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-jammy-cpu-py3_9-gcc11-inductor-build.outputs.test-matrix }}
+      use-gha: anything-non-empty-to-use-gha
+      timeout-minutes: 720

.github/workflows/inductor-perf-test-nightly-x86.yml

@@ -48,12 +48,12 @@ concurrency:
 permissions: read-all
 
 jobs:
-  linux-jammy-cpu-py3_8-gcc11-inductor-build:
-    name: linux-jammy-cpu-py3.8-gcc11-inductor
+  linux-jammy-cpu-py3_9-gcc11-inductor-build:
+    name: linux-jammy-cpu-py3.9-gcc11-inductor
     uses: ./.github/workflows/_linux-build.yml
     with:
-      build-environment: linux-jammy-py3.8-gcc11-build
-      docker-image-name: pytorch-linux-jammy-py3.8-gcc11-inductor-benchmarks
+      build-environment: linux-jammy-py3.9-gcc11-build
+      docker-image-name: pytorch-linux-jammy-py3.9-gcc11-inductor-benchmarks
       test-matrix: |
         { include: [
           { config: "inductor_huggingface_perf_cpu_x86", shard: 1, num_shards: 3, runner: "linux.24xl.spr-metal" },
@@ -74,32 +74,32 @@ jobs:
       HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
 
 
-  linux-jammy-cpu-py3_8-gcc11-inductor-test-nightly:
-    name: linux-jammy-cpu-py3.8-gcc11-inductor
+  linux-jammy-cpu-py3_9-gcc11-inductor-test-nightly:
+    name: linux-jammy-cpu-py3.9-gcc11-inductor
     uses: ./.github/workflows/_linux-test.yml
-    needs: linux-jammy-cpu-py3_8-gcc11-inductor-build
+    needs: linux-jammy-cpu-py3_9-gcc11-inductor-build
     if: github.event.schedule == '0 7 * * *'
     with:
-      build-environment: linux-jammy-py3.8-gcc11-build
+      build-environment: linux-jammy-py3.9-gcc11-build
       dashboard-tag: training-false-inference-true-default-true-dynamic-true-aotinductor-true
-      docker-image: ${{ needs.linux-jammy-cpu-py3_8-gcc11-inductor-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-jammy-cpu-py3_8-gcc11-inductor-build.outputs.test-matrix }}
+      docker-image: ${{ needs.linux-jammy-cpu-py3_9-gcc11-inductor-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-jammy-cpu-py3_9-gcc11-inductor-build.outputs.test-matrix }}
       use-gha: anything-non-empty-to-use-gha
       timeout-minutes: 720
     secrets:
       HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
 
 
-  linux-jammy-cpu-py3_8-gcc11-inductor-test:
-    name: linux-jammy-cpu-py3.8-gcc11-inductor
+  linux-jammy-cpu-py3_9-gcc11-inductor-test:
+    name: linux-jammy-cpu-py3.9-gcc11-inductor
     uses: ./.github/workflows/_linux-test.yml
-    needs: linux-jammy-cpu-py3_8-gcc11-inductor-build
+    needs: linux-jammy-cpu-py3_9-gcc11-inductor-build
     if: github.event_name == 'workflow_dispatch'
     with:
-      build-environment: linux-jammy-py3.8-gcc11-build
+      build-environment: linux-jammy-py3.9-gcc11-build
       dashboard-tag: training-${{ inputs.training }}-inference-${{ inputs.inference }}-default-${{ inputs.default }}-dynamic-${{ inputs.dynamic }}-aotinductor-${{ inputs.aotinductor }}
-      docker-image: ${{ needs.linux-jammy-cpu-py3_8-gcc11-inductor-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-jammy-cpu-py3_8-gcc11-inductor-build.outputs.test-matrix }}
+      docker-image: ${{ needs.linux-jammy-cpu-py3_9-gcc11-inductor-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-jammy-cpu-py3_9-gcc11-inductor-build.outputs.test-matrix }}
       use-gha: anything-non-empty-to-use-gha
       timeout-minutes: 720
     secrets:

.github/workflows/inductor.yml

@@ -35,28 +35,28 @@ jobs:
       build-environment: linux-focal-cuda12.1-py3.10-gcc9-sm86
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9-inductor-benchmarks
       cuda-arch-list: '8.6'
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       test-matrix: |
         { include: [
-          { config: "inductor", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor_distributed", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.12xlarge.nvidia.gpu" },
-          { config: "inductor_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "dynamic_inductor_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "dynamic_inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "dynamic_inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "dynamic_inductor_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "dynamic_inductor_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "aot_inductor_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "aot_inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "aot_inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "aot_inductor_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "aot_inductor_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor_cpp_wrapper_abi_compatible", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor_distributed", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.12xlarge.nvidia.gpu" },
+          { config: "inductor_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "dynamic_inductor_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "dynamic_inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "dynamic_inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "dynamic_inductor_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "dynamic_inductor_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "aot_inductor_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "aot_inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "aot_inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "aot_inductor_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "aot_inductor_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor_cpp_wrapper_abi_compatible", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
         ]}
     secrets:
       HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
@@ -80,11 +80,11 @@ jobs:
       build-environment: linux-focal-cuda12.1-py3.12-gcc9-sm86
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3.12-gcc9-inductor-benchmarks
       cuda-arch-list: '8.6'
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       test-matrix: |
         { include: [
-          { config: "inductor", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
         ]}
 
   linux-focal-cuda12_1-py3_12-gcc9-inductor-test:
@@ -103,10 +103,10 @@ jobs:
     with:
       build-environment: linux-jammy-py3.12-gcc11
       docker-image-name: pytorch-linux-jammy-py3.12-halide
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       test-matrix: |
         { include: [
-          { config: "inductor-halide", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
+          { config: "inductor-halide", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
         ]}
 
   linux-jammy-cpu-py3_12-inductor-halide-test:
@@ -128,11 +128,11 @@ jobs:
       build-environment: linux-focal-cuda12.4-py3.10-gcc9-sm86
       docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9-inductor-benchmarks
       cuda-arch-list: '8.6'
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       test-matrix: |
         { include: [
-          { config: "inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
         ]}
     secrets:
       HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
@@ -149,68 +149,68 @@ jobs:
     secrets:
       HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
 
-  linux-jammy-cpu-py3_8-gcc11-inductor-build:
-    name: linux-jammy-cpu-py3.8-gcc11-inductor
+  linux-jammy-cpu-py3_9-gcc11-inductor-build:
+    name: linux-jammy-cpu-py3.9-gcc11-inductor
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      build-environment: linux-jammy-py3.8-gcc11-build
-      docker-image-name: pytorch-linux-jammy-py3.8-gcc11-inductor-benchmarks
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      build-environment: linux-jammy-py3.9-gcc11-build
+      docker-image-name: pytorch-linux-jammy-py3.9-gcc11-inductor-benchmarks
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       test-matrix: |
         { include: [
-          { config: "inductor_avx512", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "inductor_avx512", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_huggingface_freezing", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_timm_freezing", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_timm_freezing", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_torchbench_freezing", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_torchbench_freezing", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_inductor_huggingface_amp_freezing", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.16xlarge.spr" },
-          { config: "cpu_inductor_timm_amp_freezing", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.16xlarge.spr" },
-          { config: "cpu_inductor_timm_amp_freezing", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.16xlarge.spr" },
-          { config: "cpu_inductor_torchbench_amp_freezing", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.16xlarge.spr" },
-          { config: "cpu_inductor_torchbench_amp_freezing", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.16xlarge.spr" },
-          { config: "dynamic_cpu_inductor_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "dynamic_cpu_inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "dynamic_cpu_inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "dynamic_cpu_inductor_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "dynamic_cpu_inductor_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_aot_inductor_huggingface_freezing", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_aot_inductor_timm_freezing", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_aot_inductor_timm_freezing", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_aot_inductor_torchbench_freezing", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_aot_inductor_torchbench_freezing", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_aot_inductor_torchbench_amp_freezing", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "cpu_aot_inductor_torchbench_amp_freezing", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "dynamic_cpu_aot_inductor_torchbench_freezing", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "dynamic_cpu_aot_inductor_torchbench_freezing", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "dynamic_cpu_aot_inductor_torchbench_amp_freezing", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "dynamic_cpu_aot_inductor_torchbench_amp_freezing", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
-          { config: "inductor_torchbench_cpu_smoketest_perf", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.24xl.spr-metal" },
-          { config: "inductor_avx2", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.10xlarge.avx2" },
-          { config: "inductor_avx2", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.10xlarge.avx2" },
-          { config: "cpu_inductor_huggingface_freezing_avx2", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.10xlarge.avx2" },
-          { config: "cpu_inductor_torchbench_freezing_avx2", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.10xlarge.avx2" },
-          { config: "cpu_inductor_torchbench_freezing_avx2", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.10xlarge.avx2" },
-          { config: "cpu_inductor_timm_freezing_avx2", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.10xlarge.avx2" },
-          { config: "cpu_inductor_timm_freezing_avx2", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.10xlarge.avx2" },
+          { config: "inductor_avx512", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "inductor_avx512", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_freezing_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_freezing_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_freezing_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_freezing_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_freezing_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_inductor_amp_freezing_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.16xlarge.spr" },
+          { config: "cpu_inductor_amp_freezing_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.16xlarge.spr" },
+          { config: "cpu_inductor_amp_freezing_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.16xlarge.spr" },
+          { config: "cpu_inductor_amp_freezing_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.16xlarge.spr" },
+          { config: "cpu_inductor_amp_freezing_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.16xlarge.spr" },
+          { config: "dynamic_cpu_inductor_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "dynamic_cpu_inductor_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "dynamic_cpu_inductor_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "dynamic_cpu_inductor_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "dynamic_cpu_inductor_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_aot_inductor_freezing_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_aot_inductor_freezing_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_aot_inductor_freezing_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_aot_inductor_freezing_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_aot_inductor_freezing_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_aot_inductor_amp_freezing_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "cpu_aot_inductor_amp_freezing_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "dynamic_cpu_aot_inductor_freezing_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "dynamic_cpu_aot_inductor_freezing_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "dynamic_cpu_aot_inductor_amp_freezing_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "dynamic_cpu_aot_inductor_amp_freezing_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
+          { config: "inductor_torchbench_cpu_smoketest_perf", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.24xl.spr-metal" },
+          { config: "inductor_avx2", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.10xlarge.avx2" },
+          { config: "inductor_avx2", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.10xlarge.avx2" },
+          { config: "cpu_inductor_freezing_avx2_huggingface", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.10xlarge.avx2" },
+          { config: "cpu_inductor_freezing_avx2_torchbench", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.10xlarge.avx2" },
+          { config: "cpu_inductor_freezing_avx2_torchbench", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.10xlarge.avx2" },
+          { config: "cpu_inductor_freezing_avx2_timm", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.10xlarge.avx2" },
+          { config: "cpu_inductor_freezing_avx2_timm", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.10xlarge.avx2" },
         ]}
     secrets:
       HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
 
-  linux-jammy-cpu-py3_8-gcc11-inductor-test:
-    name: linux-jammy-cpu-py3.8-gcc11-inductor
+  linux-jammy-cpu-py3_9-gcc11-inductor-test:
+    name: linux-jammy-cpu-py3.9-gcc11-inductor
     uses: ./.github/workflows/_linux-test.yml
-    needs: linux-jammy-cpu-py3_8-gcc11-inductor-build
+    needs: linux-jammy-cpu-py3_9-gcc11-inductor-build
     with:
-      build-environment: linux-jammy-py3.8-gcc11-build
-      docker-image: ${{ needs.linux-jammy-cpu-py3_8-gcc11-inductor-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-jammy-cpu-py3_8-gcc11-inductor-build.outputs.test-matrix }}
+      build-environment: linux-jammy-py3.9-gcc11-build
+      docker-image: ${{ needs.linux-jammy-cpu-py3_9-gcc11-inductor-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-jammy-cpu-py3_9-gcc11-inductor-build.outputs.test-matrix }}
     secrets:
       HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}

.github/workflows/lint.yml

@@ -28,7 +28,7 @@ jobs:
     needs: get-label-type
     with:
       timeout: 120
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge"
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
       docker-image: pytorch-linux-jammy-cuda11.8-cudnn9-py3.9-linter
       # NB: A shallow checkout won't work here because calculate-docker-image requires a full checkout
       # to run git rev-parse HEAD~:.ci/docker when a new image is needed
@@ -45,7 +45,7 @@ jobs:
     needs: get-label-type
     with:
       timeout: 120
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge"
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
       docker-image: pytorch-linux-jammy-cuda11.8-cudnn9-py3.9-linter
       # NB: A shallow checkout won't work here because calculate-docker-image requires a full checkout
       # to run git rev-parse HEAD~:.ci/docker when a new image is needed
@@ -60,7 +60,7 @@ jobs:
     uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     needs: get-label-type
     with:
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge"
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
       docker-image: pytorch-linux-focal-linter
       fetch-depth: 0
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
@@ -95,7 +95,7 @@ jobs:
   pr-sanity-checks:
     name: pr-sanity-checks
     needs: get-label-type
-    runs-on: [self-hosted, "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.large"]
+    runs-on: [self-hosted, "${{ needs.get-label-type.outputs.label-type }}linux.large"]
     # Only run this on pull requests. This check is simple enough to be done without a Docker image
     if: github.event_name == 'pull_request' && !contains(github.event.pull_request.labels.*.name, 'skip-pr-sanity-checks')
     steps:
@@ -116,7 +116,7 @@ jobs:
     uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     needs: get-label-type
     with:
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge"
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
       docker-image: pytorch-linux-focal-linter
       fetch-depth: -1
       submodules: true
@@ -153,7 +153,7 @@ jobs:
     uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     needs: get-label-type
     with:
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge"
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
       docker-image: pytorch-linux-focal-linter
       fetch-depth: 0
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
@@ -192,7 +192,7 @@ jobs:
     uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     needs: get-label-type
     with:
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge"
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
       docker-image: pytorch-linux-focal-linter
       fetch-depth: 0
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
@@ -223,7 +223,7 @@ jobs:
           cache: pip
       - name: Install dependencies
         run: |
-          pip install pytest-rerunfailures==11.1.* pytest-flakefinder==1.1.* pytest-xdist==3.3.* expecttest==0.1.* numpy==1.24.*
+          pip install pytest-rerunfailures==11.1.* pytest-flakefinder==1.1.* pytest-xdist==3.3.* expecttest==0.2.* fbscribelogger==0.1.* numpy==1.24.*
           pip install torch --pre --index-url https://download.pytorch.org/whl/nightly/cpu/
       - name: Run run_test.py (nonretryable)
         run: |

.github/workflows/nightly.yml

@@ -31,9 +31,9 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge"
-      build-environment: linux-jammy-py3.8-gcc11
-      docker-image-name: pytorch-linux-jammy-py3.8-gcc11
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
+      build-environment: linux-jammy-py3.9-gcc11
+      docker-image-name: pytorch-linux-jammy-py3.9-gcc11
 
   docs-push:
     name: docs push
@@ -42,8 +42,8 @@ jobs:
       - docs-build
       - get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
-      build-environment: linux-jammy-py3.8-gcc11
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: linux-jammy-py3.9-gcc11
       docker-image: ${{ needs.docs-build.outputs.docker-image }}
       push: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' || startsWith(github.event.ref, 'refs/tags/v') }}
       run-doxygen: true

.github/workflows/periodic.yml

@@ -52,14 +52,14 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda12.1-py3.10-gcc9
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
       test-matrix: |
         { include: [
-          { config: "nogpu_AVX512", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "nogpu_NO_AVX2", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
+          { config: "nogpu_AVX512", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "nogpu_NO_AVX2", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
         ]}
   linux-focal-cuda12_1-py3_10-gcc9-test:
     name: linux-focal-cuda12.1-py3.10-gcc9
@@ -77,19 +77,19 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda12.4-py3.10-gcc9
       docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "nogpu_AVX512", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "nogpu_NO_AVX2", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "nogpu_AVX512", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "nogpu_NO_AVX2", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
         ]}
 
   linux-focal-cuda12_4-py3_10-gcc9-test:
@@ -104,38 +104,38 @@ jobs:
       docker-image: ${{ needs.linux-focal-cuda12_4-py3_10-gcc9-build.outputs.docker-image }}
       test-matrix: ${{ needs.linux-focal-cuda12_4-py3_10-gcc9-build.outputs.test-matrix }}
 
-  parallelnative-linux-jammy-py3_8-gcc11-build:
-    name: parallelnative-linux-jammy-py3.8-gcc11
+  parallelnative-linux-jammy-py3_9-gcc11-build:
+    name: parallelnative-linux-jammy-py3.9-gcc11
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
-      build-environment: parallelnative-linux-jammy-py3.8-gcc11
-      docker-image-name: pytorch-linux-jammy-py3.8-gcc11
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: parallelnative-linux-jammy-py3.9-gcc11
+      docker-image-name: pytorch-linux-jammy-py3.9-gcc11
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
+          { config: "default", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
         ]}
 
-  parallelnative-linux-jammy-py3_8-gcc11-test:
-    name: parallelnative-linux-jammy-py3.8-gcc11
+  parallelnative-linux-jammy-py3_9-gcc11-test:
+    name: parallelnative-linux-jammy-py3.9-gcc11
     uses: ./.github/workflows/_linux-test.yml
     needs:
-      - parallelnative-linux-jammy-py3_8-gcc11-build
+      - parallelnative-linux-jammy-py3_9-gcc11-build
       - target-determination
     with:
-      build-environment: parallelnative-linux-jammy-py3.8-gcc11
-      docker-image: ${{ needs.parallelnative-linux-jammy-py3_8-gcc11-build.outputs.docker-image }}
-      test-matrix: ${{ needs.parallelnative-linux-jammy-py3_8-gcc11-build.outputs.test-matrix }}
+      build-environment: parallelnative-linux-jammy-py3.9-gcc11
+      docker-image: ${{ needs.parallelnative-linux-jammy-py3_9-gcc11-build.outputs.docker-image }}
+      test-matrix: ${{ needs.parallelnative-linux-jammy-py3_9-gcc11-build.outputs.test-matrix }}
 
   linux-focal-cuda11_8-py3_9-gcc9-build:
     name: linux-focal-cuda11.8-py3.9-gcc9
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda11.8-py3.9-gcc9
       docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9
       cuda-arch-list: 8.6
@@ -159,7 +159,7 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda11.8-py3.10-gcc9-debug
       docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9
       build-with-debug: true
@@ -250,7 +250,6 @@ jobs:
     name: buck-build-test
     uses: ./.github/workflows/_buck-build-test.yml
     with:
-      runner_prefix: "amz2023."
       test-matrix: |
         { include: [
           { config: "default", shard: 1, num_shards: 1, runner: "ubuntu-latest" },
@@ -260,7 +259,6 @@ jobs:
     name: android-emulator-build-test
     uses: ./.github/workflows/_run_android_tests.yml
     with:
-      runner_prefix: "amz2023."
       test-matrix: |
         { include: [
           { config: 'default',
@@ -278,12 +276,12 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-vulkan-focal-py3.11-clang10
       docker-image-name: pytorch-linux-focal-py3.11-clang10
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
+          { config: "default", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
         ]}
 
   linux-vulkan-focal-py3_11-clang10-test:
@@ -300,7 +298,7 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-rocm6.1-py3.8
       docker-image-name: pytorch-linux-focal-rocm-n-py3
       test-matrix: |
@@ -329,15 +327,15 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       use_split_build: true
       build-environment: linux-focal-cuda12.1-py3.10-gcc9
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
       test-matrix: |
         { include: [
-          { config: "nogpu_AVX512", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "nogpu_NO_AVX2", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
+          { config: "nogpu_AVX512", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "nogpu_NO_AVX2", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
         ]}
 
   linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build-test:
@@ -357,7 +355,7 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       use_split_build: true
       build-environment: linux-focal-cuda11.8-py3.9-gcc9
       docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9

.github/workflows/pull.yml

@@ -43,72 +43,71 @@ jobs:
       issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
       curr_branch: ${{ github.head_ref || github.ref_name }}
 
-  linux-jammy-py3_8-gcc11-build:
-    name: linux-jammy-py3.8-gcc11
+  linux-jammy-py3_9-gcc11-build:
+    name: linux-jammy-py3.9-gcc11
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
-      build-environment: linux-jammy-py3.8-gcc11
-      docker-image-name: pytorch-linux-jammy-py3.8-gcc11
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: linux-jammy-py3.9-gcc11
+      docker-image-name: pytorch-linux-jammy-py3.9-gcc11
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 2, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 3, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 4, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "docs_test", shard: 1, num_shards: 1,  runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "backwards_compat", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "distributed", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "distributed", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
+          { config: "default", shard: 1, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 2, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 3, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 4, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "docs_test", shard: 1, num_shards: 1,  runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "backwards_compat", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "distributed", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "distributed", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
         ]}
     secrets: inherit
 
-  linux-jammy-py3_8-gcc11-test:
-    name: linux-jammy-py3.8-gcc11
+  linux-jammy-py3_9-gcc11-test:
+    name: linux-jammy-py3.9-gcc11
     uses: ./.github/workflows/_linux-test.yml
     needs:
-      - linux-jammy-py3_8-gcc11-build
+      - linux-jammy-py3_9-gcc11-build
       - target-determination
     with:
-      build-environment: linux-jammy-py3.8-gcc11
-      docker-image: ${{ needs.linux-jammy-py3_8-gcc11-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-jammy-py3_8-gcc11-build.outputs.test-matrix }}
+      build-environment: linux-jammy-py3.9-gcc11
+      docker-image: ${{ needs.linux-jammy-py3_9-gcc11-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-jammy-py3_9-gcc11-build.outputs.test-matrix }}
     secrets: inherit
 
   linux-docs:
     name: linux-docs
     uses: ./.github/workflows/_docs.yml
-    needs: linux-jammy-py3_8-gcc11-build
+    needs: linux-jammy-py3_9-gcc11-build
     with:
-      runner_prefix: amz2023.
-      build-environment: linux-jammy-py3.8-gcc11
-      docker-image: ${{ needs.linux-jammy-py3_8-gcc11-build.outputs.docker-image }}
+      build-environment: linux-jammy-py3.9-gcc11
+      docker-image: ${{ needs.linux-jammy-py3_9-gcc11-build.outputs.docker-image }}
     secrets: inherit
 
-  linux-jammy-py3_8-gcc11-no-ops:
-    name: linux-jammy-py3.8-gcc11-no-ops
+  linux-jammy-py3_9-gcc11-no-ops:
+    name: linux-jammy-py3.9-gcc11-no-ops
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
-      build-environment: linux-jammy-py3.8-gcc11-no-ops
-      docker-image-name: pytorch-linux-jammy-py3.8-gcc11
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: linux-jammy-py3.9-gcc11-no-ops
+      docker-image-name: pytorch-linux-jammy-py3.9-gcc11
       test-matrix: |
         { include: [
           { config: "default", shard: 1, num_shards: 1 },
         ]}
     secrets: inherit
 
-  linux-jammy-py3_8-gcc11-pch:
-    name: linux-jammy-py3.8-gcc11-pch
+  linux-jammy-py3_9-gcc11-pch:
+    name: linux-jammy-py3.9-gcc11-pch
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
-      build-environment: linux-jammy-py3.8-gcc11-pch
-      docker-image-name: pytorch-linux-jammy-py3.8-gcc11
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: linux-jammy-py3.9-gcc11-pch
+      docker-image-name: pytorch-linux-jammy-py3.9-gcc11
       test-matrix: |
         { include: [
           { config: "default", shard: 1, num_shards: 1 },
@@ -120,17 +119,17 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-jammy-py3.10-clang15-asan
       docker-image-name: pytorch-linux-jammy-py3-clang15-asan
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge" },
-          { config: "default", shard: 2, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge" },
-          { config: "default", shard: 3, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge" },
-          { config: "default", shard: 4, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge" },
-          { config: "default", shard: 5, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge" },
-          { config: "default", shard: 6, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge" },
+          { config: "default", shard: 1, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
+          { config: "default", shard: 2, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
+          { config: "default", shard: 3, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
+          { config: "default", shard: 4, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
+          { config: "default", shard: 5, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
+          { config: "default", shard: 6, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
         ]}
       sync-tag: asan-build
     secrets: inherit
@@ -149,63 +148,63 @@ jobs:
       sync-tag: asan-test
     secrets: inherit
 
-  linux-focal-py3_8-clang10-onnx-build:
-    name: linux-focal-py3.8-clang10-onnx
+  linux-focal-py3_9-clang10-onnx-build:
+    name: linux-focal-py3.9-clang10-onnx
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
-      build-environment: linux-focal-py3.8-clang10-onnx
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: linux-focal-py3.9-clang10-onnx
       docker-image-name: pytorch-linux-focal-py3-clang10-onnx
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
+          { config: "default", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
         ]}
     secrets: inherit
 
-  linux-focal-py3_8-clang10-onnx-test:
-    name: linux-focal-py3.8-clang10-onnx
+  linux-focal-py3_9-clang10-onnx-test:
+    name: linux-focal-py3.9-clang10-onnx
     uses: ./.github/workflows/_linux-test.yml
     needs:
-      - linux-focal-py3_8-clang10-onnx-build
+      - linux-focal-py3_9-clang10-onnx-build
       - target-determination
     with:
-      build-environment: linux-focal-py3.8-clang10-onnx
-      docker-image: ${{ needs.linux-focal-py3_8-clang10-onnx-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-focal-py3_8-clang10-onnx-build.outputs.test-matrix }}
+      build-environment: linux-focal-py3.9-clang10-onnx
+      docker-image: ${{ needs.linux-focal-py3_9-clang10-onnx-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-py3_9-clang10-onnx-build.outputs.test-matrix }}
     secrets: inherit
 
-  linux-focal-py3_8-clang10-build:
-    name: linux-focal-py3.8-clang10
+  linux-focal-py3_9-clang10-build:
+    name: linux-focal-py3.9-clang10
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge"
-      build-environment: linux-focal-py3.8-clang10
-      docker-image-name: pytorch-linux-focal-py3.8-clang10
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge"
+      build-environment: linux-focal-py3.9-clang10
+      docker-image-name: pytorch-linux-focal-py3.9-clang10
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 2, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 3, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 4, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "crossref", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "crossref", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
+          { config: "default", shard: 1, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 2, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 3, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 4, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "crossref", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "crossref", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "dynamo", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "dynamo", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "dynamo", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
         ]}
-  linux-focal-py3_8-clang10-test:
-    name: linux-focal-py3.8-clang10
+  linux-focal-py3_9-clang10-test:
+    name: linux-focal-py3.9-clang10
     uses: ./.github/workflows/_linux-test.yml
     needs:
-      - linux-focal-py3_8-clang10-build
+      - linux-focal-py3_9-clang10-build
       - target-determination
     with:
-      build-environment: linux-focal-py3.8-clang10
-      docker-image: ${{ needs.linux-focal-py3_8-clang10-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-focal-py3_8-clang10-build.outputs.test-matrix }}
+      build-environment: linux-focal-py3.9-clang10
+      docker-image: ${{ needs.linux-focal-py3_9-clang10-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-py3_9-clang10-build.outputs.test-matrix }}
     secrets: inherit
 
   linux-focal-py3_11-clang10-build:
@@ -213,20 +212,20 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-py3.11-clang10
       docker-image-name: pytorch-linux-focal-py3.11-clang10
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 2, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 3, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 4, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "crossref", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "crossref", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
+          { config: "default", shard: 1, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 2, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 3, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 4, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "crossref", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "crossref", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "dynamo", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "dynamo", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "dynamo", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
         ]}
     secrets: inherit
 
@@ -247,18 +246,18 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-py3.12-clang10
       docker-image-name: pytorch-linux-focal-py3.12-clang10
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 2, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 3, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "default", shard: 4, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
+          { config: "default", shard: 1, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 2, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 3, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "default", shard: 4, num_shards: 4, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "dynamo", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "dynamo", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "dynamo", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
         ]}
     secrets: inherit
 
@@ -278,14 +277,14 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda11.8-py3.10-gcc9
       docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9
       test-matrix: |
         { include: [
-          { config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.8xlarge.nvidia.gpu" },
-          { config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.8xlarge.nvidia.gpu" },
-          { config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.8xlarge.nvidia.gpu" },
+          { config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.8xlarge.nvidia.gpu" },
+          { config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.8xlarge.nvidia.gpu" },
+          { config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.8xlarge.nvidia.gpu" },
         ]}
     secrets: inherit
 
@@ -307,16 +306,16 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda12.1-py3.10-gcc9
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
         ]}
     secrets: inherit
 
@@ -338,7 +337,7 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-jammy-py3-clang12-mobile-build
       docker-image-name: pytorch-linux-jammy-py3-clang15-asan
       build-generates-artifacts: false
@@ -348,14 +347,14 @@ jobs:
         ]}
     secrets: inherit
 
-  linux-jammy-cuda-11_8-cudnn9-py3_8-clang12-build:
-    name: linux-jammy-cuda11.8-cudnn9-py3.8-clang12
+  linux-jammy-cuda-11_8-cudnn9-py3_9-clang12-build:
+    name: linux-jammy-cuda11.8-cudnn9-py3.9-clang12
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
-      build-environment: linux-jammy-cuda11.8-cudnn9-py3.8-clang12
-      docker-image-name: pytorch-linux-jammy-cuda11.8-cudnn9-py3.8-clang12
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: linux-jammy-cuda11.8-cudnn9-py3.9-clang12
+      docker-image-name: pytorch-linux-jammy-cuda11.8-cudnn9-py3.9-clang12
       test-matrix: |
         { include: [
           { config: "default", shard: 1, num_shards: 1 },
@@ -367,7 +366,7 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-py3-clang9-mobile-custom-build-static
       docker-image-name: pytorch-linux-focal-py3-clang9-android-ndk-r21e
       build-generates-artifacts: false
@@ -377,28 +376,28 @@ jobs:
         ]}
     secrets: inherit
 
-  linux-focal-py3_8-clang9-xla-build:
-    name: linux-focal-py3_8-clang9-xla
+  linux-focal-py3_9-clang9-xla-build:
+    name: linux-focal-py3_9-clang9-xla
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
-      build-environment: linux-focal-py3.8-clang9-xla
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: linux-focal-py3.9-clang9-xla
       docker-image-name: 308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/xla_base:v1.1-lite
       test-matrix: |
         { include: [
-          { config: "xla", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.12xlarge" },
+          { config: "xla", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.12xlarge" },
         ]}
     secrets: inherit
 
-  linux-focal-py3_8-clang9-xla-test:
-    name: linux-focal-py3_8-clang9-xla
+  linux-focal-py3_9-clang9-xla-test:
+    name: linux-focal-py3_9-clang9-xla
     uses: ./.github/workflows/_linux-test.yml
-    needs: linux-focal-py3_8-clang9-xla-build
+    needs: linux-focal-py3_9-clang9-xla-build
     with:
-      build-environment: linux-focal-py3.8-clang9-xla
-      docker-image: ${{ needs.linux-focal-py3_8-clang9-xla-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-focal-py3_8-clang9-xla-build.outputs.test-matrix }}
+      build-environment: linux-focal-py3.9-clang9-xla
+      docker-image: ${{ needs.linux-focal-py3_9-clang9-xla-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-py3_9-clang9-xla-build.outputs.test-matrix }}
     secrets: inherit
 
   win-vs2019-cpu-py3-build:
@@ -425,13 +424,13 @@ jobs:
     uses: ./.github/workflows/_bazel-build-test.yml
     needs: get-label-type
     with:
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.large"
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.large"
       build-environment: linux-focal-cuda12.1-py3.10-gcc9-bazel-test
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
       cuda-version: cpu
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge" },
+          { config: "default", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
         ]}
     secrets: inherit
 
@@ -440,13 +439,13 @@ jobs:
     uses: ./.github/workflows/_bazel-build-test.yml
     needs: get-label-type
     with:
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.large"
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.large"
       build-environment: linux-focal-cuda12.1-py3.10-gcc9-bazel-test
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
       cuda-version: "12.1"
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
         ]}
     secrets: inherit
 
@@ -455,13 +454,13 @@ jobs:
     uses: ./.github/workflows/_bazel-build-test.yml
     needs: get-label-type
     with:
-      runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.large"
+      runner: "${{ needs.get-label-type.outputs.label-type }}linux.large"
       build-environment: linux-focal-cuda12.4-py3.10-gcc9-bazel-test
       docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9
       cuda-version: "12.4"
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
         ]}
     secrets: inherit
 
@@ -489,14 +488,14 @@ jobs:
         ]}
     secrets: inherit
 
-  linux-jammy-py3_8-gcc11-mobile-lightweight-dispatch-build:
-    name: linux-jammy-py3.8-gcc11-mobile-lightweight-dispatch-build
+  linux-jammy-py3_9-gcc11-mobile-lightweight-dispatch-build:
+    name: linux-jammy-py3.9-gcc11-mobile-lightweight-dispatch-build
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
-      build-environment: linux-jammy-py3.8-gcc111-mobile-lightweight-dispatch-build
-      docker-image-name: pytorch-linux-jammy-py3.8-gcc11
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: linux-jammy-py3.9-gcc111-mobile-lightweight-dispatch-build
+      docker-image-name: pytorch-linux-jammy-py3.9-gcc11
       build-generates-artifacts: false
       test-matrix: |
         { include: [
@@ -511,7 +510,7 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-rocm6.1-py3.8
       docker-image-name: pytorch-linux-focal-rocm-n-py3
       sync-tag: rocm-build
@@ -528,17 +527,17 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda12.1-py3.10-gcc9-sm86
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
       cuda-arch-list: 8.6
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
         ]}
     secrets: inherit
 
@@ -559,12 +558,12 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-jammy-py3-clang12-executorch
       docker-image-name: pytorch-linux-jammy-py3-clang12-executorch
       test-matrix: |
         { include: [
-          { config: "executorch", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
+          { config: "executorch", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
         ]}
     secrets: inherit
 
@@ -583,18 +582,18 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       use_split_build: True
       build-environment: linux-focal-py3.12-clang10
       docker-image-name: pytorch-linux-focal-py3.12-clang10
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 3, runner: "amz2023.linux.2xlarge" },
-          { config: "default", shard: 2, num_shards: 3, runner: "amz2023.linux.2xlarge" },
-          { config: "default", shard: 3, num_shards: 3, runner: "amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 1, num_shards: 3, runner: "amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 2, num_shards: 3, runner: "amz2023.linux.2xlarge" },
-          { config: "dynamo", shard: 3, num_shards: 3, runner: "amz2023.linux.2xlarge" },
+          { config: "default", shard: 1, num_shards: 3, runner: "linux.2xlarge" },
+          { config: "default", shard: 2, num_shards: 3, runner: "linux.2xlarge" },
+          { config: "default", shard: 3, num_shards: 3, runner: "linux.2xlarge" },
+          { config: "dynamo", shard: 1, num_shards: 3, runner: "linux.2xlarge" },
+          { config: "dynamo", shard: 2, num_shards: 3, runner: "linux.2xlarge" },
+          { config: "dynamo", shard: 3, num_shards: 3, runner: "linux.2xlarge" },
         ]}
     secrets: inherit
 
@@ -614,7 +613,7 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda12.1-py3.10-gcc9-sm75
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9-inductor-benchmarks
       cuda-arch-list: '7.5'

.github/workflows/runner-determinator-validator.yml

@@ -0,0 +1,40 @@
+name: Validate Runner Determinator Script is in Sync
+
+on:
+  # Run on PRs when the runner-determinator script is updated to ensure it's copies are kept in sync
+  pull_request:
+    paths:
+      - .github/workflows/_runner-determinator.yml
+      - .github/workflows/runner-determinator-validator.yml
+      - .github/scripts/runner_determinator.py
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }}
+  cancel-in-progress: true
+
+jobs:
+  check-runner-determinator:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    - name: Run Hardcode runner-determinator script
+      id: hardcode-script
+      run: |
+        # Extract the script content from _runner-determinator.yml and skip the first 10 spaces of each line
+        script_content=$(awk '/cat <<EOF > runner_determinator.py/{flag=1;next}/EOF$/{flag=0}flag{print substr($0, 11)}' .github/workflows/_runner-determinator.yml)
+
+        # Write the extracted script content to runner_determinator.py
+        echo "$script_content" > runner_determinator_workflow.py
+
+    - name: Compare runner-determinator script embedded in workflow with checked in script
+      run: |
+        # Compare the extracted runner_determinator script with the existing one
+        # If this check fails, then make sure the contents of .github/scripts/runner_determinator.py is in sync with the
+        # version embedded into .github/workflows/_runner-determinator.yml
+        diff runner_determinator_workflow.py .github/scripts/runner_determinator.py
+      # Fail the job if the scripts are not identical
+      continue-on-error: false

.github/workflows/slow.yml

@@ -50,18 +50,18 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023"
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
       cuda-arch-list: 8.6
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 2, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 3, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 4, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 5, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 6, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 1, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 2, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 3, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 4, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 5, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 6, num_shards: 6, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
         ]}
 
   linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-test:
@@ -81,14 +81,14 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda12.1-py3.10-gcc9-sm86
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
       cuda-arch-list: 8.6
       test-matrix: |
         { include: [
-          { config: "slow", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "slow", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
+          { config: "slow", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "slow", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
         ]}
 
   linux-focal-cuda12_1-py3_10-gcc9-sm86-test:
@@ -102,37 +102,37 @@ jobs:
       docker-image: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-sm86-build.outputs.docker-image }}
       test-matrix: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-sm86-build.outputs.test-matrix }}
 
-  linux-focal-py3_8-clang10-build:
-    name: linux-focal-py3.8-clang10
+  linux-focal-py3_9-clang10-build:
+    name: linux-focal-py3.9-clang10
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
-      build-environment: linux-focal-py3.8-clang10
-      docker-image-name: pytorch-linux-focal-py3.8-clang10
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: linux-focal-py3.9-clang10
+      docker-image-name: pytorch-linux-focal-py3.9-clang10
       test-matrix: |
         { include: [
-          { config: "slow", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "slow", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
+          { config: "slow", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "slow", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
         ]}
 
-  linux-focal-py3_8-clang10-test:
-    name: linux-focal-py3.8-clang10
+  linux-focal-py3_9-clang10-test:
+    name: linux-focal-py3.9-clang10
     uses: ./.github/workflows/_linux-test.yml
     needs:
-      - linux-focal-py3_8-clang10-build
+      - linux-focal-py3_9-clang10-build
       - target-determination
     with:
-      build-environment: linux-focal-py3.8-clang10
-      docker-image: ${{ needs.linux-focal-py3_8-clang10-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-focal-py3_8-clang10-build.outputs.test-matrix }}
+      build-environment: linux-focal-py3.9-clang10
+      docker-image: ${{ needs.linux-focal-py3_9-clang10-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-py3_9-clang10-build.outputs.test-matrix }}
 
   linux-focal-rocm6_1-py3_8-build:
     name: linux-focal-rocm6.1-py3.8
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-rocm6.1-py3.8
       docker-image-name: pytorch-linux-focal-rocm-n-py3
       test-matrix: |
@@ -160,14 +160,14 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-jammy-py3.10-clang15-asan
       docker-image-name: pytorch-linux-jammy-py3-clang15-asan
       test-matrix: |
         { include: [
-          { config: "slow", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge" },
-          { config: "slow", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge" },
-          { config: "slow", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge" },
+          { config: "slow", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
+          { config: "slow", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
+          { config: "slow", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
         ]}
       sync-tag: asan-build
     secrets: inherit

.github/workflows/stale.yml

@@ -21,7 +21,7 @@ on:
 jobs:
   stale:
     if: ${{ github.repository == 'pytorch/pytorch' }}
-    runs-on: linux.large.arc
+    runs-on: linux.large
     permissions:
       contents: read
       pull-requests: write

.github/workflows/trunk.yml

@@ -48,17 +48,17 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda12.4-py3.10-gcc9-sm86
       docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9
       cuda-arch-list: 8.6
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.4xlarge.nvidia.gpu" },
         ]}
 
   linux-focal-cuda12_4-py3_10-gcc9-sm86-test:
@@ -80,7 +80,7 @@ jobs:
       build-environment: libtorch-linux-focal-cuda12.1-py3.7-gcc9
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
       build-generates-artifacts: false
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runner: "linux.4xlarge"
       test-matrix: |
         { include: [
@@ -93,7 +93,7 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda12.1-py3.10-gcc9-no-ops
       docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
       test-matrix: |
@@ -109,7 +109,7 @@ jobs:
       build-environment: libtorch-linux-focal-cuda12.4-py3.7-gcc9
       docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9
       build-generates-artifacts: false
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       runner: "linux.4xlarge"
       test-matrix: |
         { include: [
@@ -122,7 +122,7 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-cuda12.4-py3.10-gcc9-no-ops
       docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9
       test-matrix: |
@@ -138,7 +138,7 @@ jobs:
       docker-image-name: pytorch-linux-focal-py3-clang9-android-ndk-r21e
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 1, runner: "amz2023.linux.2xlarge" },
+          { config: "default", shard: 1, num_shards: 1, runner: "linux.2xlarge" },
         ]}
 
   macos-py3-arm64-build:
@@ -228,7 +228,7 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       build-environment: linux-focal-rocm6.1-py3.8
       docker-image-name: pytorch-linux-focal-rocm-n-py3
       sync-tag: rocm-build
@@ -260,20 +260,20 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       use_split_build: true
       build-environment: linux-focal-cuda12.4-py3.10-gcc9
       docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9
       test-matrix: |
         { include: [
-          { config: "nogpu_AVX512", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "nogpu_NO_AVX2", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.2xlarge" },
-          { config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
-          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.4xlarge.nvidia.gpu" },
+          { config: "nogpu_AVX512", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "nogpu_NO_AVX2", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.2xlarge" },
+          { config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
+          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
         ]}
 
   linux-focal-cuda12_4-py3_10-gcc9-experimental-split-build-test:
@@ -292,15 +292,15 @@ jobs:
     uses: ./.github/workflows/_linux-build.yml
     needs: get-label-type
     with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}amz2023."
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
       use_split_build: true
       build-environment: linux-focal-cuda11.8-py3.10-gcc9
       docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9
       test-matrix: |
         { include: [
-          { config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.8xlarge.nvidia.gpu" },
-          { config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.8xlarge.nvidia.gpu" },
-          { config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}amz2023.linux.8xlarge.nvidia.gpu" },
+          { config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.8xlarge.nvidia.gpu" },
+          { config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.8xlarge.nvidia.gpu" },
+          { config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.8xlarge.nvidia.gpu" },
         ]}
 
   linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build-test:

.github/workflows/upload-test-stats.yml

@@ -2,7 +2,7 @@ name: Upload test stats
 
 on:
   workflow_run:
-    workflows: [pull, trunk, periodic, inductor, unstable, slow, unstable-periodic, inductor-periodic, rocm, inductor-micro-benchmark, inductor-cu124, inductor-rocm]
+    workflows: [pull, trunk, periodic, inductor, unstable, slow, unstable-periodic, inductor-periodic, rocm, inductor-micro-benchmark, inductor-micro-benchmark-x86, inductor-cu124, inductor-rocm]
     types:
       - completed
 

.github/workflows/xpu.yml

@@ -49,3 +49,12 @@ jobs:
       build-environment: linux-jammy-xpu-py3.9
       docker-image: ${{ needs.linux-jammy-xpu-py3_9-build.outputs.docker-image }}
       test-matrix: ${{ needs.linux-jammy-xpu-py3_9-build.outputs.test-matrix }}
+
+  windows-xpu-build:
+    name: win-vs2022-xpu-py3
+    uses: ./.github/workflows/_win-build.yml
+    with:
+      build-environment: win-vs2022-xpu-py3
+      cuda-version: cpu
+      use-xpu: true
+      vc-year: '2022'

.lintrunner.toml

@@ -138,7 +138,7 @@ init_command = [
     '--dry-run={{DRYRUN}}',
     'numpy==1.24.3 ; python_version == "3.8"',
     'numpy==1.26.0 ; python_version >= "3.9"',
-    'expecttest==0.1.6',
+    'expecttest==0.2.1',
     'mypy==1.10.0',
     'sympy==1.12.1 ; python_version == "3.8"',
     'sympy==1.13.0 ; python_version >= "3.9"',
@@ -1482,7 +1482,7 @@ init_command = [
     'black==23.12.1',
     'usort==1.0.8.post1',
     'isort==5.13.2',
-    'ruff==0.6.0',  # sync with RUFF
+    'ruff==0.6.3',  # sync with RUFF
 ]
 is_formatter = true
 
@@ -1567,7 +1567,7 @@ init_command = [
     'python3',
     'tools/linter/adapters/pip_init.py',
     '--dry-run={{DRYRUN}}',
-    'ruff==0.6.0',  # sync with PYFMT
+    'ruff==0.6.3',  # sync with PYFMT
 ]
 is_formatter = true
 

BUILD.bazel

@@ -574,7 +574,7 @@ cu_library(
     name = "torch_cuda",
     srcs = [
         "torch/csrc/distributed/c10d/intra_node_comm.cu",
-        "torch/csrc/distributed/c10d/Utils.cu",
+        "torch/csrc/distributed/c10d/NanCheck.cu",
         "torch/csrc/distributed/c10d/quantization/quantization_gpu.cu",
     ],
     copts = torch_cuda_half_options,
@@ -722,7 +722,7 @@ cc_library(
             "torch/csrc/distributed/c10d/intra_node_comm.cu",
             "torch/csrc/distributed/c10d/CUDASymmetricMemory.cu",
             "torch/csrc/distributed/c10d/CUDASymmetricMemoryOps.cu",
-            "torch/csrc/distributed/c10d/Utils.cu",
+            "torch/csrc/distributed/c10d/NanCheck.cu",
             "torch/csrc/distributed/c10d/quantization/quantization_gpu.cu",
         ],
     )) + torch_sources,

CMakeLists.txt

@@ -490,10 +490,6 @@ if(USE_SYSTEM_LIBS)
   endif()
 endif()
 
-# Used when building Caffe2 through setup.py
-option(BUILDING_WITH_TORCH_LIBS
-       "Tell cmake if Caffe2 is being built alongside torch libs" ON)
-
 # /Z7 override option When generating debug symbols, CMake default to use the
 # flag /Zi. However, it is not compatible with sccache. So we rewrite it off.
 # But some users don't use sccache; this override is for them.
@@ -887,6 +883,16 @@ cmake_dependent_option(
   Will be disabled if not supported by the platform" ON
   "USE_CUDA OR USE_ROCM" OFF)
 
+#
+# Cannot be put into Dependencies.cmake due circular dependency:
+# USE_FLASH_ATTENTION -> USE_ROCM -> Dependencies.cmake -> aotriton.cmake
+#
+if(USE_ROCM)
+  if(USE_FLASH_ATTENTION OR USE_MEM_EFF_ATTENTION)
+    include(cmake/External/aotriton.cmake)
+  endif()
+endif()
+
 if(DEBUG_CUDA)
   string(APPEND CMAKE_CUDA_FLAGS_DEBUG " -lineinfo")
   string(APPEND CMAKE_CUDA_FLAGS_RELWITHDEBINFO " -lineinfo")

CODEOWNERS

@@ -57,7 +57,6 @@ nn/qat/ @jerryzh168
 # Docker
 /.ci/docker/ @jeffdaily
 /.ci/docker/ci_commit_pins/triton.txt @desertfire @Chillee @eellison @shunting314 @bertmaher @jeffdaily @jataylo @jithunnair-amd @pruthvistony
-/.ci/docker/ci_commit_pins/triton-rocm.txt @jeffdaily @jataylo @jithunnair-amd @pruthvistony
 /.ci/docker/ci_commit_pins/triton-xpu.txt @EikanWang @gujinghui
 
 # Github Actions

README.md

@@ -471,7 +471,7 @@ To learn more about making a contribution to Pytorch, please see our [Contributi
 PyTorch is a community-driven project with several skillful engineers and researchers contributing to it.
 
 PyTorch is currently maintained by [Soumith Chintala](http://soumith.ch), [Gregory Chanan](https://github.com/gchanan), [Dmytro Dzhulgakov](https://github.com/dzhulgakov), [Edward Yang](https://github.com/ezyang), and [Nikita Shulga](https://github.com/malfet) with major contributions coming from hundreds of talented individuals in various forms and means.
-A non-exhaustive but growing list needs to mention: Trevor Killeen, Sasank Chilamkurthy, Sergey Zagoruyko, Adam Lerer, Francisco Massa, Alykhan Tejani, Luca Antiga, Alban Desmaison, Andreas Koepf, James Bradbury, Zeming Lin, Yuandong Tian, Guillaume Lample, Marat Dukhan, Natalia Gimelshein, Christian Sarofeen, Martin Raison, Edward Yang, Zachary Devito.
+A non-exhaustive but growing list needs to mention: [Trevor Killeen](https://github.com/killeent), [Sasank Chilamkurthy](https://github.com/chsasank), [Sergey Zagoruyko](https://github.com/szagoruyko), [Adam Lerer](https://github.com/adamlerer), [Francisco Massa](https://github.com/fmassa), [Alykhan Tejani](https://github.com/alykhantejani), [Luca Antiga](https://github.com/lantiga), [Alban Desmaison](https://github.com/albanD), [Andreas Koepf](https://github.com/andreaskoepf), [James Bradbury](https://github.com/jamesb93), [Zeming Lin](https://github.com/ebetica), [Yuandong Tian](https://github.com/yuandong-tian), [Guillaume Lample](https://github.com/glample), [Marat Dukhan](https://github.com/Maratyszcza), [Natalia Gimelshein](https://github.com/ngimel), [Christian Sarofeen](https://github.com/csarofeen), [Martin Raison](https://github.com/martinraison), [Edward Yang](https://github.com/ezyang), [Zachary Devito](https://github.com/zdevito).
 
 Note: This project is unrelated to [hughperkins/pytorch](https://github.com/hughperkins/pytorch) with the same name. Hugh is a valuable contributor to the Torch community and has helped with many things Torch and PyTorch.
 

aten/src/ATen/AccumulateType.cpp

@@ -9,6 +9,8 @@ c10::ScalarType toAccumulateType(c10::ScalarType type, c10::DeviceType device) {
       switch (device) {                                                                            \
         case DeviceType::CUDA:                                                                     \
           return CppTypeToScalarType<at::acc_type_device<scalar_t, c10::DeviceType::CUDA>>::value; \
+        case DeviceType::XPU:                                                                      \
+          return CppTypeToScalarType<at::acc_type_device<scalar_t, c10::DeviceType::XPU>>::value;  \
         case DeviceType::MPS:                                                                      \
           return CppTypeToScalarType<at::acc_type_device<scalar_t, c10::DeviceType::MPS>>::value;  \
         default:                                                                                   \

aten/src/ATen/Context.h

@@ -52,7 +52,7 @@ class TORCH_API Context {
     } else if (device_type == at::kIPU) {
       return at::detail::getIPUHooks().getDefaultIPUGenerator(device.index());
     } else if (device_type == at::kPrivateUse1) {
-      return at::GetPrivateUse1HooksInterface()->getDefaultGenerator(
+      return at::detail::getPrivateUse1Hooks().getDefaultGenerator(
           device.index());
     } else {
       AT_ERROR(c10::DeviceTypeName(device_type), " device type not enabled.");
@@ -91,7 +91,7 @@ class TORCH_API Context {
     } else if (device_type == at::kXPU) {
       return at::detail::getXPUHooks().getDeviceFromPtr(data);
     } else if (device_type == at::kPrivateUse1) {
-      return at::GetPrivateUse1HooksInterface()->getDeviceFromPtr(data);
+      return at::detail::getPrivateUse1Hooks().getDeviceFromPtr(data);
     } else {
       AT_ERROR(c10::DeviceTypeName(device_type), " device type not enabled.");
     }
@@ -182,7 +182,7 @@ class TORCH_API Context {
   void lazyInitPrivateUse1() {
     c10::call_once(thp_init, [&] {
       if (isPrivateUse1HooksRegistered()) {
-        at::GetPrivateUse1HooksInterface()->initPrivateUse1();
+        at::detail::getPrivateUse1Hooks().initPrivateUse1();
       }
     });
   }

aten/src/ATen/EmptyTensor.cpp

@@ -21,7 +21,7 @@ c10::Allocator* GetCPUAllocatorMaybePinned(bool pin_memory) {
     } else if (at::globalContext().hasXPU()) {
       return at::detail::getXPUHooks().getPinnedMemoryAllocator();
     } else if(at::isPrivateUse1HooksRegistered()) {
-      return at::GetPrivateUse1HooksInterface()->getPinnedMemoryAllocator();
+      return at::detail::getPrivateUse1Hooks().getPinnedMemoryAllocator();
     } else {
       TORCH_CHECK(false, "Need to provide pin_memory allocator to use pin memory.")
     }

aten/src/ATen/FunctionalTensorWrapper.cpp

@@ -707,7 +707,12 @@ bool are_all_mutations_under_no_grad_or_inference_mode(const Tensor& functional_
 }
 
 bool isFunctionalTensor(const at::Tensor& tensor) {
-  return tensor.unsafeGetTensorImpl()->key_set().has(c10::DispatchKey::Functionalize);
+   return tensor.unsafeGetTensorImpl()->key_set().has(c10::DispatchKey::Functionalize);
+}
+
+bool isBaseTensor(const at::Tensor& tensor) {
+  TORCH_INTERNAL_ASSERT_DEBUG_ONLY(isFunctionalTensor(tensor));
+  return unsafeGetFunctionalWrapper(tensor)->isBaseTensor();
 }
 
 bool isFunctionalTensor(const std::optional<Tensor>& t) {

aten/src/ATen/FunctionalTensorWrapper.h

@@ -165,6 +165,12 @@ struct TORCH_API FunctionalTensorWrapper : public c10::TensorImpl {
     was_storage_changed_ = true;
   }
 
+  // A FunctionalTensor is considered a base if its not a view of another
+  // tensor.
+  bool isBaseTensor() const {
+    return view_metas_.empty();
+  }
+
   c10::SymInt get_storage_size(bool before) {
     return functional_storage_impl()->get_storage_size(before);
   }
@@ -290,6 +296,8 @@ TORCH_API inline FunctionalTensorWrapper* unsafeGetFunctionalWrapper(
   return functional_impl;
 }
 
+TORCH_API bool isBaseTensor(const at::Tensor& tensor);
+
 TORCH_API bool isFunctionalTensor(const at::Tensor& tensor);
 TORCH_API bool isFunctionalTensor(const std::optional<Tensor>& t);
 TORCH_API bool isFunctionalTensor(