[Experiment only] Collect cpp_wrapper perf numbers

.ci/aarch64_linux/aarch64_ci_build.sh

@@ -6,6 +6,19 @@ GPU_ARCH_VERSION=${GPU_ARCH_VERSION:-}
 SCRIPTPATH="$( cd -- "$(dirname "$0")" >/dev/null 2>&1 ; pwd -P )"
 source $SCRIPTPATH/aarch64_ci_setup.sh
 
+tagged_version() {
+  GIT_DESCRIBE="git --git-dir /pytorch/.git describe --tags --match v[0-9]*.[0-9]*.[0-9]*"
+  if ${GIT_DESCRIBE} --exact >/dev/null; then
+    ${GIT_DESCRIBE}
+  else
+    return 1
+  fi
+}
+
+if tagged_version >/dev/null; then
+  export OVERRIDE_PACKAGE_VERSION="$(tagged_version | sed -e 's/^v//' -e 's/-.*$//')"
+fi
+
 ###############################################################################
 # Run aarch64 builder python
 ###############################################################################

.ci/aarch64_linux/aarch64_wheel_ci_build.py

@@ -80,7 +80,7 @@ def update_wheel(wheel_path) -> None:
         "/usr/local/cuda/lib64/libnvToolsExt.so.1",
         "/usr/local/cuda/lib64/libnvJitLink.so.12",
         "/usr/local/cuda/lib64/libnvrtc.so.12",
-        "/usr/local/cuda/lib64/libnvrtc-builtins.so.12.6",
+        "/usr/local/cuda/lib64/libnvrtc-builtins.so.12.4",
         "/usr/local/cuda/lib64/libcudnn_adv.so.9",
         "/usr/local/cuda/lib64/libcudnn_cnn.so.9",
         "/usr/local/cuda/lib64/libcudnn_graph.so.9",

.ci/docker/aotriton_version.txt

@@ -1,5 +1,5 @@
-0.8b
-manylinux_2_28
+0.7b
+manylinux_2_17
 rocm6.2
-6f8cbcac8a92775291bb1ba8f514d4beb350baf4
-e938def5d32869fe2e00aec0300f354c9f157867bebdf2e104d732b94cb238d8
+9be04068c3c0857a4cfd17d7e39e71d0423ebac2
+3e9e1959d23b93d78a08fcc5f868125dc3854dece32fd9458be9ef4467982291

.ci/docker/build.sh

@@ -179,21 +179,6 @@ case "$image" in
     TRITON=yes
     INDUCTOR_BENCHMARKS=yes
     ;;
-  pytorch-linux-focal-cuda12.4-cudnn9-py3.13-gcc9-inductor-benchmarks)
-    CUDA_VERSION=12.4.1
-    CUDNN_VERSION=9
-    ANACONDA_PYTHON_VERSION=3.13
-    GCC_VERSION=9
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    KATEX=yes
-    UCX_COMMIT=${_UCX_COMMIT}
-    UCC_COMMIT=${_UCC_COMMIT}
-    CONDA_CMAKE=yes
-    TRITON=yes
-    INDUCTOR_BENCHMARKS=yes
-    ;;
   pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9)
     CUDA_VERSION=11.8.0
     CUDNN_VERSION=9

.ci/docker/common/install_base.sh

@@ -76,8 +76,7 @@ install_ubuntu() {
     vim \
     unzip \
     gpg-agent \
-    gdb \
-    bc
+    gdb
 
   # Should resolve issues related to various apt package repository cert issues
   # see: https://github.com/pytorch/pytorch/issues/65931

.ci/docker/common/install_cache.sh

@@ -9,7 +9,12 @@ install_ubuntu() {
   # Instead use lib and headers from OpenSSL1.1 installed in `install_openssl.sh``
   apt-get install -y cargo
   echo "Checking out sccache repo"
-  git clone https://github.com/mozilla/sccache -b v0.8.2
+  if [ -n "$CUDA_VERSION" ]; then
+      # TODO: Remove this
+      git clone https://github.com/pytorch/sccache
+  else
+      git clone https://github.com/mozilla/sccache -b v0.8.2
+  fi
   cd sccache
   echo "Building sccache"
   cargo build --release
@@ -39,7 +44,16 @@ export PATH="/opt/cache/bin:$PATH"
 if [ -n "$ROCM_VERSION" ]; then
   curl --retry 3 http://repo.radeon.com/misc/.sccache_amd/sccache -o /opt/cache/bin/sccache
 else
-  install_ubuntu
+  ID=$(grep -oP '(?<=^ID=).+' /etc/os-release | tr -d '"')
+  if [ -n "$CUDA_VERSION" ]; then
+    # TODO: Install the pre-built binary from S3 as building from source
+    # https://github.com/pytorch/sccache has started failing mysteriously
+    # in which sccache server couldn't start with the following error:
+    #   sccache: error: Invalid argument (os error 22)
+    install_binary
+  else
+    install_ubuntu
+  fi
 fi
 chmod a+x /opt/cache/bin/sccache
 
@@ -47,26 +61,21 @@ function write_sccache_stub() {
   # Unset LD_PRELOAD for ps because of asan + ps issues
   # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90589
   if [ $1 == "gcc" ]; then
-    # Do not call sccache recursively when dumping preprocessor argument
-    # For some reason it's very important for the first cached nvcc invocation
-    cat >"/opt/cache/bin/$1" <<EOF
+  # Do not call sccache recursively when dumping preprocessor argument
+  # For some reason it's very important for the first cached nvcc invocation
+    cat > "/opt/cache/bin/$1" <<EOF
 #!/bin/sh
 
-# sccache does not support -E flag, so we need to call the original compiler directly in order to avoid calling this wrapper recursively
-for arg in "\$@"; do
-  if [ "\$arg" = "-E" ]; then
-    exec $(which $1) "\$@"
-  fi
-done
-
-if [ \$(env -u LD_PRELOAD ps -p \$PPID -o comm=) != sccache ]; then
+if [ "\$1" = "-E" ] || [ "\$2" = "-E" ]; then
+  exec $(which $1) "\$@"
+elif [ \$(env -u LD_PRELOAD ps -p \$PPID -o comm=) != sccache ]; then
   exec sccache $(which $1) "\$@"
 else
   exec $(which $1) "\$@"
 fi
 EOF
   else
-    cat >"/opt/cache/bin/$1" <<EOF
+    cat > "/opt/cache/bin/$1" <<EOF
 #!/bin/sh
 
 if [ \$(env -u LD_PRELOAD ps -p \$PPID -o comm=) != sccache ]; then
@@ -116,7 +125,7 @@ if [ -n "$ROCM_VERSION" ]; then
     TOPDIR=$(dirname $OLDCOMP)
     WRAPPED="$TOPDIR/original/$COMPNAME"
     mv "$OLDCOMP" "$WRAPPED"
-    printf "#!/bin/sh\nexec sccache $WRAPPED \"\$@\"" >"$OLDCOMP"
+    printf "#!/bin/sh\nexec sccache $WRAPPED \"\$@\"" > "$OLDCOMP"
     chmod a+x "$OLDCOMP"
   }
 

.ci/docker/common/install_conda.sh

@@ -25,8 +25,7 @@ if [ -n "$ANACONDA_PYTHON_VERSION" ]; then
   mkdir -p /opt/conda
   chown jenkins:jenkins /opt/conda
 
-  SCRIPT_FOLDER="$( cd "$(dirname "$0")" ; pwd -P )"
-  source "${SCRIPT_FOLDER}/common_utils.sh"
+  source "$(dirname "${BASH_SOURCE[0]}")/common_utils.sh"
 
   pushd /tmp
   wget -q "${BASE_URL}/${CONDA_FILE}"
@@ -66,7 +65,7 @@ if [ -n "$ANACONDA_PYTHON_VERSION" ]; then
 
   # Install PyTorch conda deps, as per https://github.com/pytorch/pytorch README
   if [[ $(uname -m) == "aarch64" ]]; then
-    conda_install "openblas==0.3.28=*openmp*"
+    conda_install "openblas==0.3.25=*openmp*"
   else
     conda_install "mkl=2021.4.0 mkl-include=2021.4.0"
   fi
@@ -85,9 +84,8 @@ if [ -n "$ANACONDA_PYTHON_VERSION" ]; then
 
   # Magma package names are concatenation of CUDA major and minor ignoring revision
   # I.e. magma-cuda102 package corresponds to CUDA_VERSION=10.2 and CUDA_VERSION=10.2.89
-  # Magma is installed from a tarball in the ossci-linux bucket into the conda env
   if [ -n "$CUDA_VERSION" ]; then
-    ${SCRIPT_FOLDER}/install_magma_conda.sh $(cut -f1-2 -d'.' <<< ${CUDA_VERSION}) ${ANACONDA_PYTHON_VERSION}
+    conda_install magma-cuda$(TMP=${CUDA_VERSION/./};echo ${TMP%.*[0-9]}) -c pytorch
   fi
 
   # Install some other packages, including those needed for Python test reporting

.ci/docker/common/install_cuda_aarch64.sh

@@ -20,10 +20,10 @@ function install_cusparselt_062 {
 function install_cusparselt_063 {
     # cuSparseLt license: https://docs.nvidia.com/cuda/cusparselt/license.html
     mkdir tmp_cusparselt && pushd tmp_cusparselt
-    wget -q https://developer.download.nvidia.com/compute/cusparselt/redist/libcusparse_lt/linux-sbsa/libcusparse_lt-linux-sbsa-0.6.3.2-archive.tar.xz
-    tar xf libcusparse_lt-linux-sbsa-0.6.3.2-archive.tar.xz
-    cp -a libcusparse_lt-linux-sbsa-0.6.3.2-archive/include/* /usr/local/cuda/include/
-    cp -a libcusparse_lt-linux-sbsa-0.6.3.2-archive/lib/* /usr/local/cuda/lib64/
+    wget -q https://developer.download.nvidia.com/compute/cusparselt/redist/libcusparse_lt/linux-x86_64/libcusparse_lt-linux-x86_64-0.6.3.2-archive.tar.xz
+    tar xf libcusparse_lt-linux-x86_64-0.6.3.2-archive.tar.xz
+    cp -a libcusparse_lt-linux-x86_64-0.6.3.2-archive/include/* /usr/local/cuda/include/
+    cp -a libcusparse_lt-linux-x86_64-0.6.3.2-archive/lib/* /usr/local/cuda/lib64/
     popd
     rm -rf tmp_cusparselt
 }

.ci/docker/common/install_executorch.sh

@@ -43,6 +43,8 @@ install_pip_dependencies() {
 
 setup_executorch() {
   pushd executorch
+  # Setup swiftshader and Vulkan SDK which are required to build the Vulkan delegate
+  as_jenkins bash .ci/scripts/setup-vulkan-linux-deps.sh
 
   export PYTHON_EXECUTABLE=python
   export EXECUTORCH_BUILD_PYBIND=ON

.ci/docker/common/install_inductor_benchmark_deps.sh

@@ -7,20 +7,14 @@ source "$(dirname "${BASH_SOURCE[0]}")/common_utils.sh"
 function install_huggingface() {
   local version
   commit=$(get_pinned_commit huggingface)
+  pip_install pandas==2.0.3
   pip_install "git+https://github.com/huggingface/transformers@${commit}"
 }
 
 function install_timm() {
   local commit
   commit=$(get_pinned_commit timm)
-
-  # TODO (huydhn): There is no torchvision release on 3.13 when I write this, so
-  # I'm using nightly here instead. We just need to package to be able to install
-  # TIMM. Removing this once vision has a release on 3.13
-  if [[ "${ANACONDA_PYTHON_VERSION}" == "3.13" ]]; then
-    pip_install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu124
-  fi
-
+  pip_install pandas==2.0.3
   pip_install "git+https://github.com/huggingface/pytorch-image-models@${commit}"
   # Clean up
   conda_run pip uninstall -y cmake torch torchvision triton

.ci/docker/common/install_magma.sh

@@ -3,6 +3,8 @@
 
 set -eou pipefail
 
+MAGMA_VERSION="2.5.2"
+
 function do_install() {
     cuda_version=$1
     cuda_version_nodot=${1/./}
@@ -15,7 +17,7 @@ function do_install() {
         set -x
         tmp_dir=$(mktemp -d)
         pushd ${tmp_dir}
-        curl -OLs https://ossci-linux.s3.us-east-1.amazonaws.com/${magma_archive}
+        curl -OLs https://anaconda.org/pytorch/magma-cuda${cuda_version_nodot}/${MAGMA_VERSION}/download/linux-64/${magma_archive}
         tar -xvf "${magma_archive}"
         mkdir -p "${cuda_dir}/magma"
         mv include "${cuda_dir}/magma/include"

.ci/docker/common/install_magma_conda.sh

@@ -1,26 +0,0 @@
-#!/usr/bin/env bash
-# Script that replaces the magma install from a conda package
-
-set -eou pipefail
-
-function do_install() {
-    cuda_version_nodot=${1/./}
-    anaconda_python_version=$2
-
-    MAGMA_VERSION="2.6.1"
-    magma_archive="magma-cuda${cuda_version_nodot}-${MAGMA_VERSION}-1.tar.bz2"
-
-    anaconda_dir="/opt/conda/envs/py_${anaconda_python_version}"
-    (
-        set -x
-        tmp_dir=$(mktemp -d)
-        pushd ${tmp_dir}
-        curl -OLs https://ossci-linux.s3.us-east-1.amazonaws.com/${magma_archive}
-        tar -xvf "${magma_archive}"
-        mv include/* "${anaconda_dir}/include/"
-        mv lib/* "${anaconda_dir}/lib"
-        popd
-    )
-}
-
-do_install $1 $2

.ci/docker/common/install_openblas.sh

@@ -4,7 +4,7 @@
 set -ex
 
 cd /
-git clone https://github.com/OpenMathLib/OpenBLAS.git -b v0.3.28 --depth 1 --shallow-submodules
+git clone https://github.com/OpenMathLib/OpenBLAS.git -b v0.3.25 --depth 1 --shallow-submodules
 
 
 OPENBLAS_BUILD_FLAGS="

.ci/docker/libtorch/build.sh

@@ -39,7 +39,17 @@ case ${GPU_ARCH_TYPE} in
         BASE_TARGET=rocm
         DOCKER_TAG=rocm${GPU_ARCH_VERSION}
         GPU_IMAGE=rocm/dev-ubuntu-20.04:${GPU_ARCH_VERSION}-complete
-        PYTORCH_ROCM_ARCH="gfx900;gfx906;gfx908;gfx90a;gfx1030;gfx1100;gfx1101;gfx942"
+        PYTORCH_ROCM_ARCH="gfx900;gfx906;gfx908;gfx90a;gfx1030;gfx1100"
+        ROCM_REGEX="([0-9]+)\.([0-9]+)[\.]?([0-9]*)"
+        if [[ $GPU_ARCH_VERSION =~ $ROCM_REGEX ]]; then
+            ROCM_VERSION_INT=$((${BASH_REMATCH[1]}*10000 + ${BASH_REMATCH[2]}*100 + ${BASH_REMATCH[3]:-0}))
+        else
+            echo "ERROR: rocm regex failed"
+            exit 1
+        fi
+        if [[ $ROCM_VERSION_INT -ge 60000 ]]; then
+            PYTORCH_ROCM_ARCH+=";gfx942"
+        fi
         DOCKER_GPU_BUILD_ARG="--build-arg PYTORCH_ROCM_ARCH=${PYTORCH_ROCM_ARCH}"
         ;;
     *)

.ci/docker/linter-cuda/Dockerfile

@@ -25,8 +25,7 @@ ENV PATH /opt/conda/envs/py_$ANACONDA_PYTHON_VERSION/bin:/opt/conda/bin:$PATH
 COPY requirements-ci.txt /opt/conda/requirements-ci.txt
 COPY ./common/install_conda.sh install_conda.sh
 COPY ./common/common_utils.sh common_utils.sh
-COPY ./common/install_magma_conda.sh install_magma_conda.sh
-RUN bash ./install_conda.sh && rm install_conda.sh install_magma_conda.sh common_utils.sh /opt/conda/requirements-ci.txt
+RUN bash ./install_conda.sh && rm install_conda.sh common_utils.sh /opt/conda/requirements-ci.txt
 
 # Install cuda and cudnn
 ARG CUDA_VERSION

.ci/docker/manywheel/build.sh

@@ -97,7 +97,14 @@ case ${GPU_ARCH_TYPE} in
             DEVTOOLSET_VERSION="11"
             GPU_IMAGE=rocm/dev-almalinux-8:${GPU_ARCH_VERSION}-complete
         fi
-        PYTORCH_ROCM_ARCH="gfx900;gfx906;gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101"
+        PYTORCH_ROCM_ARCH="gfx900;gfx906;gfx908;gfx90a;gfx942;gfx1030;gfx1100"
+        ROCM_REGEX="([0-9]+)\.([0-9]+)[\.]?([0-9]*)"
+        if [[ $GPU_ARCH_VERSION =~ $ROCM_REGEX ]]; then
+            ROCM_VERSION_INT=$((${BASH_REMATCH[1]}*10000 + ${BASH_REMATCH[2]}*100 + ${BASH_REMATCH[3]:-0}))
+        else
+            echo "ERROR: rocm regex failed"
+            exit 1
+        fi
         DOCKER_GPU_BUILD_ARG="--build-arg ROCM_VERSION=${GPU_ARCH_VERSION} --build-arg PYTORCH_ROCM_ARCH=${PYTORCH_ROCM_ARCH} --build-arg DEVTOOLSET_VERSION=${DEVTOOLSET_VERSION}"
         ;;
     xpu)

.ci/docker/requirements-ci.txt

@@ -90,7 +90,7 @@ librosa>=0.6.2 ; python_version < "3.11"
 #Pinned versions:
 #test that import:
 
-mypy==1.13.0
+mypy==1.11.2
 # Pin MyPy version because new errors are likely to appear with each release
 #Description: linter
 #Pinned versions: 1.10.0
@@ -132,9 +132,6 @@ numpy==1.22.4; python_version == "3.9" or python_version == "3.10"
 numpy==1.26.2; python_version == "3.11" or python_version == "3.12"
 numpy==2.1.2; python_version >= "3.13"
 
-pandas==2.0.3; python_version < "3.13"
-pandas==2.2.3; python_version >= "3.13"
-
 #onnxruntime
 #Description: scoring engine for Open Neural Network Exchange (ONNX) models
 #Pinned versions: 1.9.0
@@ -158,7 +155,7 @@ optree==0.13.0
 #test_pointwise_ops.py, test_dtensor_ops.py, test_torchinductor.py, test_fx.py,
 #test_fake_tensor.py, test_mps.py
 
-pillow==11.0.0
+pillow==10.3.0
 #Description:  Python Imaging Library fork
 #Pinned versions: 10.3.0
 #test that import:
@@ -193,11 +190,6 @@ pytest-rerunfailures>=10.3
 #Pinned versions:
 #test that import:
 
-pytest-subtests==0.13.1
-#Description: plugin for subtest support
-#Pinned versions:
-#test that import:
-
 #pytest-benchmark
 #Description: fixture for benchmarking code
 #Pinned versions: 3.2.3
@@ -245,7 +237,7 @@ scikit-image==0.22.0 ; python_version >= "3.10"
 #test that import:
 
 scipy==1.10.1 ; python_version <= "3.11"
-scipy==1.14.1 ; python_version >= "3.12"
+scipy==1.12.0 ; python_version == "3.12"
 # Pin SciPy because of failing distribution tests (see #60347)
 #Description: scientific python
 #Pinned versions: 1.10.1
@@ -309,20 +301,19 @@ z3-solver==4.12.2.0
 #Pinned versions:
 #test that import:
 
-tensorboard==2.13.0 ; python_version < "3.13"
-tensorboard==2.18.0 ; python_version >= "3.13"
+tensorboard==2.13.0
 #Description: Also included in .ci/docker/requirements-docs.txt
 #Pinned versions:
 #test that import: test_tensorboard
 
 pywavelets==1.4.1 ; python_version < "3.12"
-pywavelets==1.7.0 ; python_version >= "3.12"
+pywavelets==1.5.0 ; python_version >= "3.12"
 #Description: This is a requirement of scikit-image, we need to pin
 # it here because 1.5.0 conflicts with numpy 1.21.2 used in CI
 #Pinned versions: 1.4.1
 #test that import:
 
-lxml==5.3.0
+lxml==5.0.0
 #Description: This is a requirement of unittest-xml-reporting
 
 # Python-3.9 binaries

.ci/docker/requirements-docs.txt

@@ -14,8 +14,7 @@ matplotlib==3.5.3
 #Description: This is used to generate PyTorch docs
 #Pinned versions: 3.5.3
 
-tensorboard==2.13.0 ; python_version < "3.13"
-tensorboard==2.18.0 ; python_version >= "3.13"
+tensorboard==2.13.0
 #Description: This is used to generate PyTorch docs
 #Pinned versions: 2.13.0
 

.ci/docker/ubuntu-cuda/Dockerfile

@@ -30,8 +30,7 @@ ARG CONDA_CMAKE
 COPY requirements-ci.txt /opt/conda/requirements-ci.txt
 COPY ./common/install_conda.sh install_conda.sh
 COPY ./common/common_utils.sh common_utils.sh
-COPY ./common/install_magma_conda.sh install_magma_conda.sh
-RUN bash ./install_conda.sh && rm install_conda.sh install_magma_conda.sh common_utils.sh /opt/conda/requirements-ci.txt
+RUN bash ./install_conda.sh && rm install_conda.sh common_utils.sh /opt/conda/requirements-ci.txt
 
 # Install gcc
 ARG GCC_VERSION
@@ -81,8 +80,6 @@ RUN bash ./install_openssl.sh
 ENV OPENSSL_DIR /opt/openssl
 
 ARG INDUCTOR_BENCHMARKS
-ARG ANACONDA_PYTHON_VERSION
-ENV ANACONDA_PYTHON_VERSION=$ANACONDA_PYTHON_VERSION
 COPY ./common/install_inductor_benchmark_deps.sh install_inductor_benchmark_deps.sh
 COPY ./common/common_utils.sh common_utils.sh
 COPY ci_commit_pins/huggingface.txt huggingface.txt

.ci/docker/ubuntu/Dockerfile

@@ -36,8 +36,7 @@ ENV DOCS=$DOCS
 COPY requirements-ci.txt requirements-docs.txt /opt/conda/
 COPY ./common/install_conda.sh install_conda.sh
 COPY ./common/common_utils.sh common_utils.sh
-COPY ./common/install_magma_conda.sh install_magma_conda.sh
-RUN bash ./install_conda.sh && rm install_conda.sh install_magma_conda.sh common_utils.sh /opt/conda/requirements-ci.txt /opt/conda/requirements-docs.txt
+RUN bash ./install_conda.sh && rm install_conda.sh common_utils.sh /opt/conda/requirements-ci.txt /opt/conda/requirements-docs.txt
 RUN if [ -n "${UNINSTALL_DILL}" ]; then pip uninstall -y dill; fi
 
 # Install gcc

.ci/manywheel/build_common.sh

@@ -18,14 +18,12 @@ retry () {
     $*  || (sleep 1 && $*) || (sleep 2 && $*) || (sleep 4 && $*) || (sleep 8 && $*)
 }
 
-PLATFORM="manylinux2014_x86_64"
 # TODO move this into the Docker images
 OS_NAME=$(awk -F= '/^NAME/{print $2}' /etc/os-release)
 if [[ "$OS_NAME" == *"CentOS Linux"* ]]; then
     retry yum install -q -y zip openssl
 elif [[ "$OS_NAME" == *"AlmaLinux"* ]]; then
     retry yum install -q -y zip openssl
-    PLATFORM="manylinux_2_28_x86_64"
 elif [[ "$OS_NAME" == *"Red Hat Enterprise Linux"* ]]; then
     retry dnf install -q -y zip openssl
 elif [[ "$OS_NAME" == *"Ubuntu"* ]]; then
@@ -255,11 +253,11 @@ make_wheel_record() {
     FPATH=$1
     if echo $FPATH | grep RECORD >/dev/null 2>&1; then
         # if the RECORD file, then
-        echo "\"$FPATH\",,"
+        echo "$FPATH,,"
     else
         HASH=$(openssl dgst -sha256 -binary $FPATH | openssl base64 | sed -e 's/+/-/g' | sed -e 's/\//_/g' | sed -e 's/=//g')
         FSIZE=$(ls -nl $FPATH | awk '{print $5}')
-        echo "\"$FPATH\",sha256=$HASH,$FSIZE"
+        echo "$FPATH,sha256=$HASH,$FSIZE"
     fi
 }
 
@@ -379,12 +377,6 @@ for pkg in /$WHEELHOUSE_DIR/torch_no_python*.whl /$WHEELHOUSE_DIR/torch*linux*.w
         $PATCHELF_BIN --print-rpath $sofile
     done
 
-    # create Manylinux 2_28 tag this needs to happen before regenerate the RECORD
-    if [[ $PLATFORM == "manylinux_2_28_x86_64" && $GPU_ARCH_TYPE != "cpu-s390x" && $GPU_ARCH_TYPE != "xpu" ]]; then
-        wheel_file=$(echo $(basename $pkg) | sed -e 's/-cp.*$/.dist-info\/WHEEL/g')
-        sed -i -e s#linux_x86_64#"${PLATFORM}"# $wheel_file;
-    fi
-
     # regenerate the RECORD file with new hashes
     record_file=$(echo $(basename $pkg) | sed -e 's/-cp.*$/.dist-info\/RECORD/g')
     if [[ -e $record_file ]]; then
@@ -424,20 +416,12 @@ for pkg in /$WHEELHOUSE_DIR/torch_no_python*.whl /$WHEELHOUSE_DIR/torch*linux*.w
         popd
     fi
 
-    # Rename wheel for Manylinux 2_28
-    if [[ $PLATFORM == "manylinux_2_28_x86_64" && $GPU_ARCH_TYPE != "cpu-s390x" && $GPU_ARCH_TYPE != "xpu" ]]; then
-        pkg_name=$(echo $(basename $pkg) | sed -e s#linux_x86_64#"${PLATFORM}"#)
-        zip -rq $pkg_name $PREIX*
-        rm -f $pkg
-        mv $pkg_name $(dirname $pkg)/$pkg_name
-    else
-        # zip up the wheel back
-        zip -rq $(basename $pkg) $PREIX*
-        # remove original wheel
-        rm -f $pkg
-        mv $(basename $pkg) $pkg
-    fi
+    # zip up the wheel back
+    zip -rq $(basename $pkg) $PREIX*
 
+    # replace original wheel
+    rm -f $pkg
+    mv $(basename $pkg) $pkg
     cd ..
     rm -rf tmp
 done
@@ -490,9 +474,9 @@ if [[ -z "$BUILD_PYTHONLESS" ]]; then
   echo "$(date) :: Running tests"
   pushd "$PYTORCH_ROOT"
 
-
+  #TODO: run_tests.sh and check_binary.sh should be moved to pytorch/pytorch project
   LD_LIBRARY_PATH=/usr/local/nvidia/lib64 \
-          "${PYTORCH_ROOT}/.ci/pytorch/run_tests.sh" manywheel "${py_majmin}" "$DESIRED_CUDA"
+          "/builder/run_tests.sh" manywheel "${py_majmin}" "$DESIRED_CUDA"
   popd
   echo "$(date) :: Finished tests"
 fi

.ci/manywheel/build_libtorch.sh

@@ -225,11 +225,11 @@ make_wheel_record() {
     FPATH=$1
     if echo $FPATH | grep RECORD >/dev/null 2>&1; then
         # if the RECORD file, then
-        echo "\"$FPATH\",,"
+        echo "$FPATH,,"
     else
         HASH=$(openssl dgst -sha256 -binary $FPATH | openssl base64 | sed -e 's/+/-/g' | sed -e 's/\//_/g' | sed -e 's/=//g')
         FSIZE=$(ls -nl $FPATH | awk '{print $5}')
-        echo "\"$FPATH\",sha256=$HASH,$FSIZE"
+        echo "$FPATH,sha256=$HASH,$FSIZE"
     fi
 }
 

.ci/manywheel/build_rocm.sh

@@ -107,29 +107,17 @@ if [[ $ROCM_INT -ge 60200 ]]; then
 fi
 
 OS_NAME=`awk -F= '/^NAME/{print $2}' /etc/os-release`
-if [[ "$OS_NAME" == *"CentOS Linux"* || "$OS_NAME" == *"AlmaLinux"* ]]; then
+if [[ "$OS_NAME" == *"CentOS Linux"* ]]; then
     LIBGOMP_PATH="/usr/lib64/libgomp.so.1"
     LIBNUMA_PATH="/usr/lib64/libnuma.so.1"
     LIBELF_PATH="/usr/lib64/libelf.so.1"
-    if [[ "$OS_NAME" == *"CentOS Linux"* ]]; then
-        LIBTINFO_PATH="/usr/lib64/libtinfo.so.5"
-    else
-        LIBTINFO_PATH="/usr/lib64/libtinfo.so.6"
-    fi
+    LIBTINFO_PATH="/usr/lib64/libtinfo.so.5"
     LIBDRM_PATH="/opt/amdgpu/lib64/libdrm.so.2"
     LIBDRM_AMDGPU_PATH="/opt/amdgpu/lib64/libdrm_amdgpu.so.1"
     if [[ $ROCM_INT -ge 60100 ]]; then
         # Below libs are direct dependencies of libhipsolver
         LIBSUITESPARSE_CONFIG_PATH="/lib64/libsuitesparseconfig.so.4"
-        if [[ "$OS_NAME" == *"CentOS Linux"* ]]; then
-            LIBCHOLMOD_PATH="/lib64/libcholmod.so.2"
-            # Below libs are direct dependencies of libsatlas
-            LIBGFORTRAN_PATH="/lib64/libgfortran.so.3"
-        else
-            LIBCHOLMOD_PATH="/lib64/libcholmod.so.3"
-            # Below libs are direct dependencies of libsatlas
-            LIBGFORTRAN_PATH="/lib64/libgfortran.so.5"
-        fi
+        LIBCHOLMOD_PATH="/lib64/libcholmod.so.2"
         # Below libs are direct dependencies of libcholmod
         LIBAMD_PATH="/lib64/libamd.so.2"
         LIBCAMD_PATH="/lib64/libcamd.so.2"
@@ -137,6 +125,7 @@ if [[ "$OS_NAME" == *"CentOS Linux"* || "$OS_NAME" == *"AlmaLinux"* ]]; then
         LIBCOLAMD_PATH="/lib64/libcolamd.so.2"
         LIBSATLAS_PATH="/lib64/atlas/libsatlas.so.3"
         # Below libs are direct dependencies of libsatlas
+        LIBGFORTRAN_PATH="/lib64/libgfortran.so.3"
         LIBQUADMATH_PATH="/lib64/libquadmath.so.0"
     fi
     MAYBE_LIB64=lib64
@@ -186,12 +175,9 @@ do
     OS_SO_FILES[${#OS_SO_FILES[@]}]=$file_name # Append lib to array
 done
 
-# FIXME: Temporary until https://github.com/pytorch/pytorch/pull/137443 lands
-# Install AOTriton
-if [ -e ${PYTORCH_ROOT}/.ci/docker/aotriton_version.txt ]; then
-    cp -a ${PYTORCH_ROOT}/.ci/docker/aotriton_version.txt aotriton_version.txt
-    bash ${PYTORCH_ROOT}/.ci/docker/common/install_aotriton.sh ${ROCM_HOME} && rm aotriton_version.txt
-    export AOTRITON_INSTALLED_PREFIX=${ROCM_HOME}/aotriton
+# PyTorch-version specific
+# AOTriton dependency only for PyTorch >= 2.4
+if (( $(echo "${PYTORCH_VERSION} 2.4" | awk '{print ($1 >= $2)}') )); then
     ROCM_SO_FILES+=("libaotriton_v2.so")
 fi
 
@@ -266,20 +252,6 @@ RCCL_SHARE_FILES=($(ls $RCCL_SHARE_SRC))
 DEPS_AUX_SRCLIST+=(${RCCL_SHARE_FILES[@]/#/$RCCL_SHARE_SRC/})
 DEPS_AUX_DSTLIST+=(${RCCL_SHARE_FILES[@]/#/$RCCL_SHARE_DST/})
 
-# PyTorch 2.6+ (AOTriton 0.8b+)
-# AKS = "AOTriton Kernel Storage", a file format to store GPU kernels compactly
-if (( $(echo "${PYTORCH_VERSION} 2.6" | awk '{print ($1 >= $2)}') )); then
-    LIBAOTRITON_DIR=$(find "$ROCM_HOME/lib/" -name "libaotriton_v2.so" -printf '%h\n')
-    if [[ -z ${LIBAOTRITON_DIR} ]]; then
-        LIBAOTRITON_DIR=$(find "$ROCM_HOME/" -name "libaotriton_v2.so" -printf '%h\n')
-    fi
-    AKS_FILES=($(find "${LIBAOTRITON_DIR}/aotriton.images" -type f -name '*.aks?' -printf '%P\n'))
-    AKS_SRC="${LIBAOTRITON_DIR}/aotriton.images"
-    AKS_DST="lib/aotriton.images"
-    DEPS_AUX_SRCLIST+=(${AKS_FILES[@]/#/${AKS_SRC}/})
-    DEPS_AUX_DSTLIST+=(${AKS_FILES[@]/#/${AKS_DST}/})
-fi
-
 echo "PYTORCH_ROCM_ARCH: ${PYTORCH_ROCM_ARCH}"
 
 SCRIPTPATH="$( cd "$(dirname "$0")" ; pwd -P )"

.ci/pytorch/build.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-set -ex -o pipefail
+set -ex
 
 # Required environment variable: $BUILD_ENVIRONMENT
 # (This is set by default in the Docker images we build, so you don't
@@ -87,7 +87,7 @@ else
 
   # Workaround required for MKL library linkage
   # https://github.com/pytorch/pytorch/issues/119557
-  if [[ "$ANACONDA_PYTHON_VERSION" = "3.12" || "$ANACONDA_PYTHON_VERSION" = "3.13" ]]; then
+  if [ "$ANACONDA_PYTHON_VERSION" = "3.12" ]; then
     export CMAKE_LIBRARY_PATH="/opt/conda/envs/py_$ANACONDA_PYTHON_VERSION/lib/"
     export CMAKE_INCLUDE_PATH="/opt/conda/envs/py_$ANACONDA_PYTHON_VERSION/include/"
   fi
@@ -191,7 +191,7 @@ fi
 
 # We only build FlashAttention files for CUDA 8.0+, and they require large amounts of
 # memory to build and will OOM
-if [[ "$BUILD_ENVIRONMENT" == *cuda* ]] && [[ 1 -eq $(echo "${TORCH_CUDA_ARCH_LIST} >= 8.0" | bc) ]]; then
+if [[ "$BUILD_ENVIRONMENT" == *cuda* ]] && [[ "$TORCH_CUDA_ARCH_LIST" == *"8.6"* || "$TORCH_CUDA_ARCH_LIST" == *"8.0"* ]]; then
   echo "WARNING: FlashAttention files require large amounts of memory to build and will OOM"
   echo "Setting MAX_JOBS=(nproc-2)/3 to reduce memory usage"
   export MAX_JOBS="$(( $(nproc --ignore=2) / 3 ))"
@@ -230,7 +230,7 @@ fi
 
 # Do not change workspace permissions for ROCm CI jobs
 # as it can leave workspace with bad permissions for cancelled jobs
-if [[ "$BUILD_ENVIRONMENT" != *rocm* && "$BUILD_ENVIRONMENT" != *s390x* && -d /var/lib/jenkins/workspace ]]; then
+if [[ "$BUILD_ENVIRONMENT" != *rocm* && "$BUILD_ENVIRONMENT" != *s390x* ]]; then
   # Workaround for dind-rootless userid mapping (https://github.com/pytorch/ci-infra/issues/96)
   WORKSPACE_ORIGINAL_OWNER_ID=$(stat -c '%u' "/var/lib/jenkins/workspace")
   cleanup_workspace() {
@@ -250,6 +250,7 @@ if [[ "$BUILD_ENVIRONMENT" == *-bazel-* ]]; then
   set -e
 
   get_bazel
+  install_sccache_nvcc_for_bazel
 
   # Leave 1 CPU free and use only up to 80% of memory to reduce the change of crashing
   # the runner
@@ -395,7 +396,7 @@ if [[ "$BUILD_ENVIRONMENT" != *libtorch* && "$BUILD_ENVIRONMENT" != *bazel* ]];
   # don't do this for libtorch as libtorch is C++ only and thus won't have python tests run on its build
   python tools/stats/export_test_times.py
 fi
-# don't do this for bazel or s390x as they don't use sccache
-if [[ "$BUILD_ENVIRONMENT" != *s390x* && "$BUILD_ENVIRONMENT" != *-bazel-* ]]; then
+
+if [[ "$BUILD_ENVIRONMENT" != *s390x* ]]; then
   print_sccache_stats
 fi

.ci/pytorch/check_binary.sh

@@ -1,394 +0,0 @@
-#!/bin/bash
-
-# shellcheck disable=SC2086,SC2006,SC2207,SC2076,SC2155,SC2046,SC1091,SC2143
-# TODO: Re-enable shellchecks above
-
-set -eux -o pipefail
-
-# This script checks the following things on binaries
-# 1. The gcc abi matches DESIRED_DEVTOOLSET
-# 2. MacOS binaries do not link against OpenBLAS
-# 3. There are no protobuf symbols of any sort anywhere (turned off, because
-#    this is currently not true)
-# 4. Standard Python imports work
-# 5. MKL is available everywhere except for MacOS wheels
-# 6. XNNPACK is available everywhere except for MacOS wheels
-# 7. CUDA is setup correctly and does not hang
-# 8. Magma is available for CUDA builds
-# 9. CuDNN is available for CUDA builds
-#
-# This script needs the env variables DESIRED_PYTHON, DESIRED_CUDA,
-# DESIRED_DEVTOOLSET and PACKAGE_TYPE
-#
-# This script expects PyTorch to be installed into the active Python (the
-# Python returned by `which python`). Or, if this is testing a libtorch
-# Pythonless binary, then it expects to be in the root folder of the unzipped
-# libtorch package.
-
-
-if [[ -z ${DESIRED_PYTHON:-} ]]; then
-  export DESIRED_PYTHON=${MATRIX_PYTHON_VERSION:-}
-fi
-if [[ -z ${DESIRED_CUDA:-} ]]; then
-  export DESIRED_CUDA=${MATRIX_DESIRED_CUDA:-}
-fi
-if [[ -z ${DESIRED_DEVTOOLSET:-} ]]; then
-  export DESIRED_DEVTOOLSET=${MATRIX_DESIRED_DEVTOOLSET:-}
-fi
-if [[ -z ${PACKAGE_TYPE:-} ]]; then
-  export PACKAGE_TYPE=${MATRIX_PACKAGE_TYPE:-}
-fi
-
-# The install root depends on both the package type and the os
-# All MacOS packages use conda, even for the wheel packages.
-if [[ "$PACKAGE_TYPE" == libtorch ]]; then
-  # NOTE: Only $PWD works on both CentOS and Ubuntu
-  export install_root="$PWD"
-else
-
-  if [[ $DESIRED_PYTHON =~ ([0-9].[0-9]+)t ]]; then
-    # For python that is maj.mint keep original version
-    py_dot="$DESIRED_PYTHON"
-  elif [[ $DESIRED_PYTHON =~ ([0-9].[0-9]+) ]];  then
-    # Strip everything but major.minor from DESIRED_PYTHON version
-    py_dot="${BASH_REMATCH[0]}"
-  else
-    echo "Unexpected ${DESIRED_PYTHON} format"
-    exit 1
-  fi
-  export install_root="$(dirname $(which python))/../lib/python${py_dot}/site-packages/torch/"
-fi
-
-###############################################################################
-# Setup XPU ENV
-###############################################################################
-if [[ "$DESIRED_CUDA" == 'xpu' ]]; then
-  set +u
-  # Refer https://www.intel.com/content/www/us/en/developer/articles/tool/pytorch-prerequisites-for-intel-gpus.html
-  source /opt/intel/oneapi/compiler/latest/env/vars.sh
-  source /opt/intel/oneapi/pti/latest/env/vars.sh
-fi
-
-###############################################################################
-# Check GCC ABI
-###############################################################################
-
-# NOTE [ Building libtorch with old vs. new gcc ABI ]
-#
-# Packages built with one version of ABI could not be linked against by client
-# C++ libraries that were compiled using the other version of ABI. Since both
-# gcc ABIs are still common in the wild, we need to support both ABIs. Currently:
-#
-# - All the nightlies built on CentOS 7 + devtoolset7 use the old gcc ABI.
-# - All the nightlies built on Ubuntu 16.04 + gcc 5.4 use the new gcc ABI.
-
-echo "Checking that the gcc ABI is what we expect"
-if [[ "$(uname)" != 'Darwin' ]]; then
-  function is_expected() {
-    if [[ "$DESIRED_DEVTOOLSET" == *"cxx11-abi"* || "$DESIRED_CUDA" == *"rocm"* ]]; then
-      if [[ "$1" -gt 0 || "$1" == "ON " ]]; then
-        echo 1
-      fi
-    else
-      if [[ -z "$1" || "$1" == 0 || "$1" == "OFF" ]]; then
-        echo 1
-      fi
-    fi
-  }
-
-  # First we check that the env var in TorchConfig.cmake is correct
-
-  # We search for D_GLIBCXX_USE_CXX11_ABI=1 in torch/TorchConfig.cmake
-  torch_config="${install_root}/share/cmake/Torch/TorchConfig.cmake"
-  if [[ ! -f "$torch_config" ]]; then
-    echo "No TorchConfig.cmake found!"
-    ls -lah "$install_root/share/cmake/Torch"
-    exit 1
-  fi
-  echo "Checking the TorchConfig.cmake"
-  cat "$torch_config"
-
-  # The sed call below is
-  #   don't print lines by default (only print the line we want)
-  # -n
-  #   execute the following expression
-  # e
-  #   replace lines that match with the first capture group and print
-  # s/.*D_GLIBCXX_USE_CXX11_ABI=\(.\)".*/\1/p
-  #   any characters, D_GLIBCXX_USE_CXX11_ABI=, exactly one any character, a
-  #   quote, any characters
-  #   Note the exactly one single character after the '='. In the case that the
-  #     variable is not set the '=' will be followed by a '"' immediately and the
-  #     line will fail the match and nothing will be printed; this is what we
-  #     want.  Otherwise it will capture the 0 or 1 after the '='.
-  # /.*D_GLIBCXX_USE_CXX11_ABI=\(.\)".*/
-  #   replace the matched line with the capture group and print
-  # /\1/p
-  actual_gcc_abi="$(sed -ne 's/.*D_GLIBCXX_USE_CXX11_ABI=\(.\)".*/\1/p' < "$torch_config")"
-  if [[ "$(is_expected "$actual_gcc_abi")" != 1 ]]; then
-    echo "gcc ABI $actual_gcc_abi not as expected."
-    exit 1
-  fi
-
-  # We also check that there are [not] cxx11 symbols in libtorch
-  #
-  echo "Checking that symbols in libtorch.so have the right gcc abi"
-  python3 "$(dirname ${BASH_SOURCE[0]})/smoke_test/check_binary_symbols.py"
-
-  echo "cxx11 symbols seem to be in order"
-fi # if on Darwin
-
-###############################################################################
-# Check for no OpenBLAS
-# TODO Check for no Protobuf symbols (not finished)
-# Print *all* runtime dependencies
-###############################################################################
-# We have to loop through all shared libraries for this
-if [[ "$(uname)" == 'Darwin' ]]; then
-  all_dylibs=($(find "$install_root" -name '*.dylib'))
-  for dylib in "${all_dylibs[@]}"; do
-    echo "All dependencies of $dylib are $(otool -L $dylib) with rpath $(otool -l $dylib | grep LC_RPATH -A2)"
-
-    # Check that OpenBlas is not linked to on Macs
-    echo "Checking the OpenBLAS is not linked to"
-    if [[ -n "$(otool -L $dylib | grep -i openblas)" ]]; then
-      echo "ERROR: Found openblas as a dependency of $dylib"
-      echo "Full dependencies is: $(otool -L $dylib)"
-      exit 1
-    fi
-
-    # Check for protobuf symbols
-    #proto_symbols="$(nm $dylib | grep protobuf)" || true
-    #if [[ -n "$proto_symbols" ]]; then
-    #  echo "ERROR: Detected protobuf symbols in $dylib"
-    #  echo "Symbols are $proto_symbols"
-    #  exit 1
-    #fi
-  done
-else
-  all_libs=($(find "$install_root" -name '*.so'))
-  for lib in "${all_libs[@]}"; do
-    echo "All dependencies of $lib are $(ldd $lib) with runpath $(objdump -p $lib | grep RUNPATH)"
-
-    # Check for protobuf symbols
-    #proto_symbols=$(nm $lib | grep protobuf) || true
-    #if [[ -n "$proto_symbols" ]]; then
-    #  echo "ERROR: Detected protobuf symbols in $lib"
-    #  echo "Symbols are $proto_symbols"
-    #  exit 1
-    #fi
-  done
-fi
-
-setup_link_flags () {
-  REF_LIB="-Wl,-R${install_root}/lib"
-  if [[ "$(uname)" == 'Darwin' ]]; then
-    REF_LIB="-Wl,-rpath ${install_root}/lib"
-  fi
-  ADDITIONAL_LINKER_FLAGS=""
-  if [[ "$(uname)" == 'Linux' ]]; then
-    ADDITIONAL_LINKER_FLAGS="-Wl,--no-as-needed"
-  fi
-  C10_LINK_FLAGS=""
-  if [ -f "${install_root}/lib/libc10.so" ] || [ -f "${install_root}/lib/libc10.dylib" ]; then
-    C10_LINK_FLAGS="-lc10"
-  fi
-  TORCH_CPU_LINK_FLAGS=""
-  if [ -f "${install_root}/lib/libtorch_cpu.so" ] || [ -f "${install_root}/lib/libtorch_cpu.dylib" ]; then
-    TORCH_CPU_LINK_FLAGS="-ltorch_cpu"
-  fi
-  TORCH_CUDA_LINK_FLAGS=""
-  if [ -f "${install_root}/lib/libtorch_cuda.so" ] || [ -f "${install_root}/lib/libtorch_cuda.dylib" ]; then
-    TORCH_CUDA_LINK_FLAGS="-ltorch_cuda"
-  elif [ -f "${install_root}/lib/libtorch_cuda_cpp.so" ] && [ -f "${install_root}/lib/libtorch_cuda_cpp.so" ] || \
-    [ -f "${install_root}/lib/libtorch_cuda_cu.dylib" ] && [ -f "${install_root}/lib/libtorch_cuda_cu.dylib" ]; then
-    TORCH_CUDA_LINK_FLAGS="-ltorch_cuda_cpp -ltorch_cuda_cu"
-  fi
-}
-
-TEST_CODE_DIR="$(dirname $(realpath ${BASH_SOURCE[0]}))/test_example_code"
-build_and_run_example_cpp () {
-  if [[ "$DESIRED_DEVTOOLSET" == *"cxx11-abi"* ]]; then
-    GLIBCXX_USE_CXX11_ABI=1
-  else
-    GLIBCXX_USE_CXX11_ABI=0
-  fi
-  setup_link_flags
-  g++ ${TEST_CODE_DIR}/$1.cpp -I${install_root}/include -I${install_root}/include/torch/csrc/api/include -D_GLIBCXX_USE_CXX11_ABI=$GLIBCXX_USE_CXX11_ABI -std=gnu++17 -L${install_root}/lib ${REF_LIB} ${ADDITIONAL_LINKER_FLAGS} -ltorch $TORCH_CPU_LINK_FLAGS $TORCH_CUDA_LINK_FLAGS $C10_LINK_FLAGS -o $1
-  ./$1
-}
-
-build_example_cpp_with_incorrect_abi () {
-  if [[ "$DESIRED_DEVTOOLSET" == *"cxx11-abi"* ]]; then
-    GLIBCXX_USE_CXX11_ABI=0
-  else
-    GLIBCXX_USE_CXX11_ABI=1
-  fi
-  set +e
-  setup_link_flags
-  g++ ${TEST_CODE_DIR}/$1.cpp -I${install_root}/include -I${install_root}/include/torch/csrc/api/include -D_GLIBCXX_USE_CXX11_ABI=$GLIBCXX_USE_CXX11_ABI -std=gnu++17 -L${install_root}/lib ${REF_LIB} ${ADDITIONAL_LINKER_FLAGS} -ltorch $TORCH_CPU_LINK_FLAGS $TORCH_CUDA_LINK_FLAGS $C10_LINK_FLAGS -o $1
-  ERRCODE=$?
-  set -e
-  if [ "$ERRCODE" -eq "0" ]; then
-    echo "Building example with incorrect ABI didn't throw error. Aborting."
-    exit 1
-  else
-    echo "Building example with incorrect ABI throws expected error. Proceeding."
-  fi
-}
-
-###############################################################################
-# Check simple Python/C++ calls
-###############################################################################
-if [[ "$PACKAGE_TYPE" == 'libtorch' ]]; then
-  # NS: Set LD_LIBRARY_PATH for CUDA builds, but perhaps it should be removed
-  if [[ "$DESIRED_CUDA" == "cu"* ]]; then
-    export LD_LIBRARY_PATH=/usr/local/cuda/lib64
-  fi
-  build_and_run_example_cpp simple-torch-test
-  # `_GLIBCXX_USE_CXX11_ABI` is always ignored by gcc in devtoolset7, so we test
-  # the expected failure case for Ubuntu 16.04 + gcc 5.4 only.
-  if [[ "$DESIRED_DEVTOOLSET" == *"cxx11-abi"* ]]; then
-    build_example_cpp_with_incorrect_abi simple-torch-test
-  fi
-else
-  pushd /tmp
-  python -c 'import torch'
-  popd
-fi
-
-###############################################################################
-# Check torch.git_version
-###############################################################################
-if [[ "$PACKAGE_TYPE" != 'libtorch' ]]; then
-  pushd /tmp
-  python -c 'import torch; assert torch.version.git_version != "Unknown"'
-  python -c 'import torch; assert torch.version.git_version != None'
-  popd
-fi
-
-
-###############################################################################
-# Check for MKL
-###############################################################################
-
-if [[ "$PACKAGE_TYPE" == 'libtorch' ]]; then
-  echo "Checking that MKL is available"
-  build_and_run_example_cpp check-torch-mkl
-elif [[ "$(uname -m)" != "arm64" && "$(uname -m)" != "s390x" ]]; then
-  if [[ "$(uname)" != 'Darwin' || "$PACKAGE_TYPE" != *wheel ]]; then
-    if [[ "$(uname -m)" == "aarch64" ]]; then
-      echo "Checking that MKLDNN is available on aarch64"
-      pushd /tmp
-      python -c 'import torch; exit(0 if torch.backends.mkldnn.is_available() else 1)'
-      popd
-    else
-      echo "Checking that MKL is available"
-      pushd /tmp
-      python -c 'import torch; exit(0 if torch.backends.mkl.is_available() else 1)'
-      popd
-    fi
-  fi
-fi
-
-###############################################################################
-# Check for XNNPACK
-###############################################################################
-
-if [[ "$PACKAGE_TYPE" == 'libtorch' ]]; then
-  echo "Checking that XNNPACK is available"
-  build_and_run_example_cpp check-torch-xnnpack
-else
-  if [[ "$(uname)" != 'Darwin' || "$PACKAGE_TYPE" != *wheel ]] && [[ "$(uname -m)" != "s390x"  ]]; then
-    echo "Checking that XNNPACK is available"
-    pushd /tmp
-    python -c 'import torch.backends.xnnpack; exit(0 if torch.backends.xnnpack.enabled else 1)'
-    popd
-  fi
-fi
-
-###############################################################################
-# Check CUDA configured correctly
-###############################################################################
-# Skip these for Windows machines without GPUs
-if [[ "$OSTYPE" == "msys" ]]; then
-    GPUS=$(wmic path win32_VideoController get name)
-    if [[ ! "$GPUS" == *NVIDIA* ]]; then
-        echo "Skip CUDA tests for machines without a Nvidia GPU card"
-        exit 0
-    fi
-fi
-
-# Test that CUDA builds are setup correctly
-if [[ "$DESIRED_CUDA" != 'cpu' && "$DESIRED_CUDA" != 'xpu' && "$DESIRED_CUDA" != 'cpu-cxx11-abi' && "$DESIRED_CUDA" != *"rocm"* && "$(uname -m)" != "s390x" ]]; then
-  if [[ "$PACKAGE_TYPE" == 'libtorch' ]]; then
-    build_and_run_example_cpp check-torch-cuda
-  else
-    pushd /tmp
-    echo "Checking that CUDA archs are setup correctly"
-    timeout 20 python -c 'import torch; torch.randn([3,5]).cuda()'
-
-    # These have to run after CUDA is initialized
-
-    echo "Checking that magma is available"
-    python -c 'import torch; torch.rand(1).cuda(); exit(0 if torch.cuda.has_magma else 1)'
-
-    echo "Checking that CuDNN is available"
-    python -c 'import torch; exit(0 if torch.backends.cudnn.is_available() else 1)'
-
-    # Validates builds is free of linker regressions reported in https://github.com/pytorch/pytorch/issues/57744
-    echo "Checking that exception handling works"
-    python -c "import torch; from unittest import TestCase;TestCase().assertRaises(RuntimeError, lambda:torch.eye(7, 7, device='cuda:7'))"
-
-    echo "Checking that basic RNN works"
-    python ${TEST_CODE_DIR}/rnn_smoke.py
-
-    echo "Checking that basic CNN works"
-    python "${TEST_CODE_DIR}/cnn_smoke.py"
-
-    echo "Test that linalg works"
-    python -c "import torch;x=torch.rand(3,3,device='cuda');print(torch.linalg.svd(torch.mm(x.t(), x)))"
-
-    popd
-  fi # if libtorch
-fi # if cuda
-
-##########################
-# Run parts of smoke tests
-##########################
-if [[ "$PACKAGE_TYPE" != 'libtorch' ]]; then
-  pushd "$(dirname ${BASH_SOURCE[0]})/smoke_test"
-  python -c "from smoke_test import test_linalg; test_linalg()"
-  if [[ "$DESIRED_CUDA" == *cuda* ]]; then
-    python -c "from smoke_test import test_linalg; test_linalg('cuda')"
-  fi
-  popd
-fi
-
-###############################################################################
-# Check PyTorch supports TCP_TLS gloo transport
-###############################################################################
-
-if [[ "$(uname)" == 'Linux' && "$PACKAGE_TYPE" != 'libtorch' ]]; then
-  GLOO_CHECK="import torch.distributed as dist
-try:
-    dist.init_process_group('gloo', rank=0, world_size=1)
-except RuntimeError as e:
-    print(e)
-"
-  RESULT=`GLOO_DEVICE_TRANSPORT=TCP_TLS MASTER_ADDR=localhost MASTER_PORT=63945 python -c "$GLOO_CHECK"`
-  GLOO_TRANSPORT_IS_NOT_SUPPORTED='gloo transport is not supported'
-  if [[ "$RESULT" =~ "$GLOO_TRANSPORT_IS_NOT_SUPPORTED" ]]; then
-    echo "PyTorch doesn't support TLS_TCP transport, please build with USE_GLOO_WITH_OPENSSL=1"
-    exit 1
-  fi
-fi
-
-###############################################################################
-# Check for C++ ABI compatibility between gcc7 and gcc9 compiled binaries
-###############################################################################
-if [[ "$(uname)" == 'Linux' && ("$PACKAGE_TYPE" == 'conda' || "$PACKAGE_TYPE" == 'manywheel')]]; then
-  pushd /tmp
-  python -c "import torch; exit(0 if torch.compiled_with_cxx11_abi() else (0 if torch._C._PYBIND11_BUILD_ABI == '_cxxabi1011' else 1))"
-  popd
-fi

.ci/pytorch/common_utils.sh

@@ -111,6 +111,26 @@ function get_bazel() {
   chmod u+x tools/bazel
 }
 
+# This function is bazel specific because of the bug
+# in the bazel that requires some special paths massaging
+# as a workaround. See
+# https://github.com/bazelbuild/bazel/issues/10167
+function install_sccache_nvcc_for_bazel() {
+  sudo mv /usr/local/cuda/bin/nvcc /usr/local/cuda/bin/nvcc-real
+
+  # Write the `/usr/local/cuda/bin/nvcc`
+  cat << EOF | sudo tee /usr/local/cuda/bin/nvcc
+#!/bin/sh
+if [ \$(env -u LD_PRELOAD ps -p \$PPID -o comm=) != sccache ]; then
+  exec sccache /usr/local/cuda/bin/nvcc "\$@"
+else
+  exec external/local_cuda/cuda/bin/nvcc-real "\$@"
+fi
+EOF
+
+  sudo chmod +x /usr/local/cuda/bin/nvcc
+}
+
 function install_monkeytype {
   # Install MonkeyType
   pip_install MonkeyType
@@ -192,7 +212,7 @@ function install_torchrec_and_fbgemm() {
 
 function clone_pytorch_xla() {
   if [[ ! -d ./xla ]]; then
-    git clone --recursive -b r2.6 https://github.com/pytorch/xla.git
+    git clone --recursive --quiet https://github.com/pytorch/xla.git
     pushd xla
     # pin the xla hash so that we don't get broken by changes to xla
     git checkout "$(cat ../.github/ci_commit_pins/xla.txt)"

.ci/pytorch/macos-test.sh

@@ -190,19 +190,11 @@ test_torchbench_perf() {
   TEST_REPORTS_DIR=$(pwd)/test/test-reports
   mkdir -p "$TEST_REPORTS_DIR"
 
-  local backend=eager
-  local dtype=notset
-  local device=mps
-
   echo "Setup complete, launching torchbench training performance run"
-  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py \
-    --performance --backend "$backend" --training --devices "$device" \
-    --output "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_training_${device}_performance.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --backend eager --training --devices mps --output "$TEST_REPORTS_DIR/torchbench_training.csv"
 
   echo "Launching torchbench inference performance run"
-  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py \
-    --performance --backend "$backend" --inference --devices "$device" \
-    --output "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_inference_${device}_performance.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --backend eager --inference --devices mps --output "$TEST_REPORTS_DIR/torchbench_training.csv"
 
   echo "Pytorch benchmark on mps device completed"
 }
@@ -217,27 +209,26 @@ test_torchbench_smoketest() {
 
   TEST_REPORTS_DIR=$(pwd)/test/test-reports
   mkdir -p "$TEST_REPORTS_DIR"
-
-  local backend=eager
-  local dtype=notset
-  local device=mps
-
-  touch "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_training_${device}_performance.csv"
-  touch "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_inference_${device}_performance.csv"
+  touch "$TEST_REPORTS_DIR"/torchbench_training.csv
+  touch "$TEST_REPORTS_DIR"/torchbench_inference.csv
 
   echo "Setup complete, launching torchbench training performance run"
-  for model in hf_T5 llama BERT_pytorch dcgan hf_GPT2 yolov3 resnet152; do
-    PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py \
-      --performance --only "$model" --backend "$backend" --training --devices "$device" \
-      --output "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_training_${device}_performance.csv"
-  done
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only hf_T5 --backend eager --training --devices mps --output "$TEST_REPORTS_DIR/torchbench_training.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only llama --backend eager --training --devices mps --output "$TEST_REPORTS_DIR/torchbench_training.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only BERT_pytorch --backend eager --training --devices mps --output "$TEST_REPORTS_DIR/torchbench_training.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only dcgan --backend eager --training --devices mps --output "$TEST_REPORTS_DIR/torchbench_training.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only hf_GPT2 --backend eager --training --devices mps --output "$TEST_REPORTS_DIR/torchbench_training.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only yolov3 --backend eager --training --devices mps --output "$TEST_REPORTS_DIR/torchbench_training.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only resnet152 --backend eager --training --devices mps --output "$TEST_REPORTS_DIR/torchbench_training.csv"
 
   echo "Launching torchbench inference performance run"
-  for model in hf_T5 llama BERT_pytorch dcgan hf_GPT2 yolov3 resnet152; do
-    PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py \
-      --performance --only "$model" --backend "$backend" --inference --devices "$device" \
-      --output "$TEST_REPORTS_DIR/inductor_${backend}_torchbench_${dtype}_inference_${device}_performance.csv"
-  done
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only hf_T5 --backend eager --inference --devices mps --output "$TEST_REPORTS_DIR/torchbench_inference.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only llama --backend eager --inference --devices mps --output "$TEST_REPORTS_DIR/torchbench_inference.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only BERT_pytorch --backend eager --inference --devices mps --output "$TEST_REPORTS_DIR/torchbench_inference.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only dcgan --backend eager --inference --devices mps --output "$TEST_REPORTS_DIR/torchbench_inference.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only hf_GPT2 --backend eager --inference --devices mps --output "$TEST_REPORTS_DIR/torchbench_inference.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only yolov3 --backend eager --inference --devices mps --output "$TEST_REPORTS_DIR/torchbench_inference.csv"
+  PYTHONPATH="$(pwd)"/torchbench python benchmarks/dynamo/torchbench.py --performance --only resnet152 --backend eager --inference --devices mps --output "$TEST_REPORTS_DIR/torchbench_inference.csv"
 
   echo "Pytorch benchmark on mps device completed"
 }
@@ -276,6 +267,25 @@ test_timm_perf() {
 
 install_tlparse
 
+if [[ $TEST_CONFIG == *"test_mps"* ]]; then
+  if [[ $NUM_TEST_SHARDS -gt 1 ]]; then
+    test_python_shard "${SHARD_NUMBER}"
+    if [[ "${SHARD_NUMBER}" == 1 ]]; then
+      test_libtorch
+      test_custom_script_ops
+    elif [[ "${SHARD_NUMBER}" == 2 ]]; then
+      test_jit_hooks
+      test_custom_backend
+    fi
+  else
+    test_python_all
+    test_libtorch
+    test_custom_script_ops
+    test_jit_hooks
+    test_custom_backend
+  fi
+fi
+
 if [[ $TEST_CONFIG == *"perf_all"* ]]; then
   test_torchbench_perf
   test_hf_perf
@@ -288,19 +298,4 @@ elif [[ $TEST_CONFIG == *"perf_timm"* ]]; then
   test_timm_perf
 elif [[ $TEST_CONFIG == *"perf_smoketest"* ]]; then
   test_torchbench_smoketest
-elif [[ $NUM_TEST_SHARDS -gt 1 ]]; then
-  test_python_shard "${SHARD_NUMBER}"
-  if [[ "${SHARD_NUMBER}" == 1 ]]; then
-    test_libtorch
-    test_custom_script_ops
-  elif [[ "${SHARD_NUMBER}" == 2 ]]; then
-    test_jit_hooks
-    test_custom_backend
-  fi
-else
-  test_python_all
-  test_libtorch
-  test_custom_script_ops
-  test_jit_hooks
-  test_custom_backend
 fi

.ci/pytorch/run_tests.sh

@@ -1,436 +0,0 @@
-#!/bin/bash
-# shellcheck disable=SC2086,SC2048,SC2068,SC2145,SC2034,SC2207,SC2143
-# TODO: Re-enable shellchecks above
-
-set -eux -o pipefail
-
-# Essentially runs pytorch/test/run_test.py, but keeps track of which tests to
-# skip in a centralized place.
-#
-# TODO Except for a few tests, this entire file is a giant TODO. Why are these
-# tests # failing?
-# TODO deal with Windows
-
-# This script expects to be in the pytorch root folder
-if [[ ! -d 'test' || ! -f 'test/run_test.py' ]]; then
-    echo "builder/test.sh expects to be run from the Pytorch root directory " \
-         "but I'm actually in $(pwd)"
-    exit 2
-fi
-
-# Allow master skip of all tests
-if [[ -n "${SKIP_ALL_TESTS:-}" ]]; then
-    exit 0
-fi
-
-# If given specific test params then just run those
-if [[ -n "${RUN_TEST_PARAMS:-}" ]]; then
-    echo "$(date) :: Calling user-command $(pwd)/test/run_test.py ${RUN_TEST_PARAMS[@]}"
-    python test/run_test.py ${RUN_TEST_PARAMS[@]}
-    exit 0
-fi
-
-# Function to retry functions that sometimes timeout or have flaky failures
-retry () {
-    $*  || (sleep 1 && $*) || (sleep 2 && $*) || (sleep 4 && $*) || (sleep 8 && $*)
-}
-
-# Parameters
-##############################################################################
-if [[ "$#" != 3 ]]; then
-  if [[ -z "${DESIRED_PYTHON:-}" || -z "${DESIRED_CUDA:-}" || -z "${PACKAGE_TYPE:-}" ]]; then
-    echo "USAGE: run_tests.sh  PACKAGE_TYPE  DESIRED_PYTHON  DESIRED_CUDA"
-    echo "The env variable PACKAGE_TYPE must be set to 'conda' or 'manywheel' or 'libtorch'"
-    echo "The env variable DESIRED_PYTHON must be set like '2.7mu' or '3.6m' etc"
-    echo "The env variable DESIRED_CUDA must be set like 'cpu' or 'cu80' etc"
-    exit 1
-  fi
-  package_type="$PACKAGE_TYPE"
-  py_ver="$DESIRED_PYTHON"
-  cuda_ver="$DESIRED_CUDA"
-else
-  package_type="$1"
-  py_ver="$2"
-  cuda_ver="$3"
-fi
-
-if [[ "$cuda_ver" == 'cpu-cxx11-abi' ]]; then
-    cuda_ver="cpu"
-fi
-
-# cu80, cu90, cu100, cpu
-if [[ ${#cuda_ver} -eq 4 ]]; then
-    cuda_ver_majmin="${cuda_ver:2:1}.${cuda_ver:3:1}"
-elif [[ ${#cuda_ver} -eq 5 ]]; then
-    cuda_ver_majmin="${cuda_ver:2:2}.${cuda_ver:4:1}"
-fi
-
-NUMPY_PACKAGE=""
-if [[ ${py_ver} == "3.10" ]]; then
-    PROTOBUF_PACKAGE="protobuf>=3.17.2"
-    NUMPY_PACKAGE="numpy>=1.21.2"
-else
-    PROTOBUF_PACKAGE="protobuf=3.14.0"
-fi
-
-# Environment initialization
-if [[ "$(uname)" == Darwin ]]; then
-    # Install the testing dependencies
-    retry conda install -yq future hypothesis ${NUMPY_PACKAGE} ${PROTOBUF_PACKAGE} pytest setuptools six typing_extensions pyyaml
-else
-    retry pip install -qr requirements.txt || true
-    retry pip install -q hypothesis protobuf pytest setuptools || true
-    numpy_ver=1.15
-    case "$(python --version 2>&1)" in
-      *2* | *3.5* | *3.6*)
-        numpy_ver=1.11
-        ;;
-    esac
-    retry pip install -q "numpy==${numpy_ver}" || true
-fi
-
-echo "Testing with:"
-pip freeze
-conda list || true
-
-##############################################################################
-# Smoke tests
-##############################################################################
-# TODO use check_binary.sh, which requires making sure it runs on Windows
-pushd /
-echo "Smoke testing imports"
-python -c 'import torch'
-
-# Test that MKL is there
-if [[ "$(uname)" == 'Darwin' && "$package_type" == *wheel ]]; then
-    echo 'Not checking for MKL on Darwin wheel packages'
-else
-    echo "Checking that MKL is available"
-    python -c 'import torch; exit(0 if torch.backends.mkl.is_available() else 1)'
-fi
-
-if [[ "$OSTYPE" == "msys" ]]; then
-    GPUS=$(wmic path win32_VideoController get name)
-    if [[ ! "$GPUS" == *NVIDIA* ]]; then
-        echo "Skip CUDA tests for machines without a Nvidia GPU card"
-        exit 0
-    fi
-fi
-
-# Test that the version number is consistent during building and testing
-if [[ "$PYTORCH_BUILD_NUMBER" -gt 1 ]]; then
-    expected_version="${PYTORCH_BUILD_VERSION}.post${PYTORCH_BUILD_NUMBER}"
-else
-    expected_version="${PYTORCH_BUILD_VERSION}"
-fi
-echo "Checking that we are testing the package that is just built"
-python -c "import torch; exit(0 if torch.__version__ == '$expected_version' else 1)"
-
-# Test that CUDA builds are setup correctly
-if [[ "$cuda_ver" != 'cpu' ]]; then
-    cuda_installed=1
-    nvidia-smi || cuda_installed=0
-    if [[ "$cuda_installed" == 0 ]]; then
-      echo "Skip CUDA tests for machines without a Nvidia GPU card"
-    else
-      # Test CUDA archs
-      echo "Checking that CUDA archs are setup correctly"
-      timeout 20 python -c 'import torch; torch.randn([3,5]).cuda()'
-
-      # These have to run after CUDA is initialized
-      echo "Checking that magma is available"
-      python -c 'import torch; torch.rand(1).cuda(); exit(0 if torch.cuda.has_magma else 1)'
-      echo "Checking that CuDNN is available"
-      python -c 'import torch; exit(0 if torch.backends.cudnn.is_available() else 1)'
-    fi
-fi
-
-# Check that OpenBlas is not linked to on MacOS
-if [[ "$(uname)" == 'Darwin' ]]; then
-    echo "Checking the OpenBLAS is not linked to"
-    all_dylibs=($(find "$(python -c "import site; print(site.getsitepackages()[0])")"/torch -name '*.dylib'))
-    for dylib in "${all_dylibs[@]}"; do
-        if [[ -n "$(otool -L $dylib | grep -i openblas)" ]]; then
-            echo "Found openblas as a dependency of $dylib"
-            echo "Full dependencies is: $(otool -L $dylib)"
-            exit 1
-        fi
-    done
-
-    echo "Checking that OpenMP is available"
-    python -c "import torch; exit(0 if torch.backends.openmp.is_available() else 1)"
-fi
-
-popd
-
-# TODO re-enable the other tests after the nightlies are moved to CI. This is
-# because the binaries keep breaking, often from additional tests, that aren't
-# real problems. Once these are on circleci and a smoke-binary-build is added
-# to PRs then this should stop happening and these can be re-enabled.
-echo "Not running unit tests. Hopefully these problems are caught by CI"
-exit 0
-
-
-##############################################################################
-# Running unit tests (except not right now)
-##############################################################################
-echo "$(date) :: Starting tests for $package_type package for python$py_ver and $cuda_ver"
-
-# We keep track of exact tests to skip, as otherwise we would be hardly running
-# any tests. But b/c of issues working with pytest/normal-python-test/ and b/c
-# of special snowflake tests in test/run_test.py we also take special care of
-# those
-tests_to_skip=()
-
-#
-# Entire file exclusions
-##############################################################################
-entire_file_exclusions=("-x")
-
-# cpp_extensions doesn't work with pytest, so we exclude it from the pytest run
-# here and then manually run it later. Note that this is only because this
-# entire_fil_exclusions flag is only passed to the pytest run
-entire_file_exclusions+=("cpp_extensions")
-
-# TODO temporary line to fix next days nightlies, but should be removed when
-# issue is fixed
-entire_file_exclusions+=('type_info')
-
-if [[ "$cuda_ver" == 'cpu' ]]; then
-    # test/test_cuda.py exits early if the installed torch is not built with
-    # CUDA, but the exit doesn't work when running with pytest, so pytest will
-    # still try to run all the CUDA tests and then fail
-    entire_file_exclusions+=("cuda")
-    entire_file_exclusions+=("nccl")
-fi
-
-if [[ "$(uname)" == 'Darwin' || "$OSTYPE" == "msys" ]]; then
-    # pytest on Mac doesn't like the exits in these files
-    entire_file_exclusions+=('c10d')
-    entire_file_exclusions+=('distributed')
-
-    # pytest doesn't mind the exit but fails the tests. On Mac we run this
-    # later without pytest
-    entire_file_exclusions+=('thd_distributed')
-fi
-
-
-#
-# Universal flaky tests
-##############################################################################
-
-# RendezvousEnvTest sometimes hangs forever
-# Otherwise it will fail on CUDA with
-#   Traceback (most recent call last):
-#     File "test_c10d.py", line 179, in test_common_errors
-#       next(gen)
-#   AssertionError: ValueError not raised
-tests_to_skip+=('RendezvousEnvTest and test_common_errors')
-
-# This hung forever once on conda_3.5_cu92
-tests_to_skip+=('TestTorch and test_sum_dim')
-
-# test_trace_warn isn't actually flaky, but it doesn't work with pytest so we
-# just skip it
-tests_to_skip+=('TestJit and test_trace_warn')
-#
-# Python specific flaky tests
-##############################################################################
-
-# test_dataloader.py:721: AssertionError
-# looks like a timeout, but interestingly only appears on python 3
-if [[ "$py_ver" == 3* ]]; then
-    tests_to_skip+=('TestDataLoader and test_proper_exit')
-fi
-
-#
-# CUDA flaky tests, all package types
-##############################################################################
-if [[ "$cuda_ver" != 'cpu' ]]; then
-
-    #
-    # DistributedDataParallelTest
-    # All of these seem to fail
-    tests_to_skip+=('DistributedDataParallelTest')
-
-    #
-    # RendezvousEnvTest
-    # Traceback (most recent call last):
-    #   File "test_c10d.py", line 201, in test_nominal
-    #     store0, rank0, size0 = next(gen0)
-    #   File "/opt/python/cp36-cp36m/lib/python3.6/site-packages/torch/distributed/rendezvous.py", line 131, in _env_rendezvous_handler
-    #     store = TCPStore(master_addr, master_port, start_daemon)
-    # RuntimeError: Address already in use
-    tests_to_skip+=('RendezvousEnvTest and test_nominal')
-
-    #
-    # TestCppExtension
-    #
-    # Traceback (most recent call last):
-    #   File "test_cpp_extensions.py", line 134, in test_jit_cudnn_extension
-    #     with_cuda=True)
-    #   File "/opt/python/cp35-cp35m/lib/python3.5/site-packages/torch/utils/cpp_extension.py", line 552, in load
-    #     with_cuda)
-    #   File "/opt/python/cp35-cp35m/lib/python3.5/site-packages/torch/utils/cpp_extension.py", line 729, in _jit_compile
-    #     return _import_module_from_library(name, build_directory)
-    #   File "/opt/python/cp35-cp35m/lib/python3.5/site-packages/torch/utils/cpp_extension.py", line 867, in _import_module_from_library
-    #     return imp.load_module(module_name, file, path, description)
-    #   File "/opt/python/cp35-cp35m/lib/python3.5/imp.py", line 243, in load_module
-    #     return load_dynamic(name, filename, file)
-    #   File "/opt/python/cp35-cp35m/lib/python3.5/imp.py", line 343, in load_dynamic
-    #     return _load(spec)
-    #   File "<frozen importlib._bootstrap>", line 693, in _load
-    #   File "<frozen importlib._bootstrap>", line 666, in _load_unlocked
-    #   File "<frozen importlib._bootstrap>", line 577, in module_from_spec
-    #   File "<frozen importlib._bootstrap_external>", line 938, in create_module
-    #   File "<frozen importlib._bootstrap>", line 222, in _call_with_frames_removed
-    # ImportError: libcudnn.so.7: cannot open shared object file: No such file or directory
-    tests_to_skip+=('TestCppExtension and test_jit_cudnn_extension')
-
-    #
-    # TestCuda
-    #
-
-    # 3.7_cu80
-    #  RuntimeError: CUDA error: out of memory
-    tests_to_skip+=('TestCuda and test_arithmetic_large_tensor')
-
-    # 3.7_cu80
-    # RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch-nightly_1538097262541/work/aten/src/THC/THCTensorCopy.cu:205
-    tests_to_skip+=('TestCuda and test_autogpu')
-
-    #
-    # TestDistBackend
-    #
-
-    # Traceback (most recent call last):
-    #   File "test_thd_distributed.py", line 1046, in wrapper
-    #     self._join_and_reduce(fn)
-    #   File "test_thd_distributed.py", line 1108, in _join_and_reduce
-    #     self.assertEqual(p.exitcode, first_process.exitcode)
-    #   File "/pytorch/test/common.py", line 399, in assertEqual
-    #     super(TestCase, self).assertEqual(x, y, message)
-    # AssertionError: None != 77 :
-    tests_to_skip+=('TestDistBackend and test_all_gather_group')
-    tests_to_skip+=('TestDistBackend and test_all_reduce_group_max')
-    tests_to_skip+=('TestDistBackend and test_all_reduce_group_min')
-    tests_to_skip+=('TestDistBackend and test_all_reduce_group_sum')
-    tests_to_skip+=('TestDistBackend and test_all_reduce_group_product')
-    tests_to_skip+=('TestDistBackend and test_barrier_group')
-    tests_to_skip+=('TestDistBackend and test_broadcast_group')
-
-    # Traceback (most recent call last):
-    #   File "test_thd_distributed.py", line 1046, in wrapper
-    #     self._join_and_reduce(fn)
-    #   File "test_thd_distributed.py", line 1108, in _join_and_reduce
-    #     self.assertEqual(p.exitcode, first_process.exitcode)
-    #   File "/pytorch/test/common.py", line 397, in assertEqual
-    #     super(TestCase, self).assertLessEqual(abs(x - y), prec, message)
-    # AssertionError: 12 not less than or equal to 1e-05
-    tests_to_skip+=('TestDistBackend and test_barrier')
-
-    # Traceback (most recent call last):
-    #   File "test_distributed.py", line 1267, in wrapper
-    #     self._join_and_reduce(fn)
-    #   File "test_distributed.py", line 1350, in _join_and_reduce
-    #     self.assertEqual(p.exitcode, first_process.exitcode)
-    #   File "/pytorch/test/common.py", line 399, in assertEqual
-    #     super(TestCase, self).assertEqual(x, y, message)
-    # AssertionError: None != 1
-    tests_to_skip+=('TestDistBackend and test_broadcast')
-
-    # Memory leak very similar to all the conda ones below, but appears on manywheel
-    # 3.6m_cu80
-    # AssertionError: 1605632 not less than or equal to 1e-05 : __main__.TestEndToEndHybridFrontendModels.test_vae_cuda leaked 1605632 bytes CUDA memory on device 0
-    tests_to_skip+=('TestEndToEndHybridFrontendModels and test_vae_cuda')
-
-    # ________________________ TestNN.test_embedding_bag_cuda ________________________
-    #
-    # self = <test_nn.TestNN testMethod=test_embedding_bag_cuda>
-    # dtype = torch.float32
-    #
-    #     @unittest.skipIf(not TEST_CUDA, "CUDA unavailable")
-    #     @repeat_test_for_types(ALL_TENSORTYPES)
-    #     @skipIfRocm
-    #     def test_embedding_bag_cuda(self, dtype=torch.float):
-    #         self._test_EmbeddingBag(True, 'sum', False, dtype)
-    #         self._test_EmbeddingBag(True, 'mean', False, dtype)
-    #         self._test_EmbeddingBag(True, 'max', False, dtype)
-    #         if dtype != torch.half:
-    #             # torch.cuda.sparse.HalfTensor is not enabled.
-    #             self._test_EmbeddingBag(True, 'sum', True, dtype)
-    # >           self._test_EmbeddingBag(True, 'mean', True, dtype)
-    #
-    # test_nn.py:2144:
-    # _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
-    # test_nn.py:2062: in _test_EmbeddingBag
-    #     _test_vs_Embedding(N, D, B, L)
-    # test_nn.py:2059: in _test_vs_Embedding
-    #     self.assertEqual(es_weight_grad, e.weight.grad, needed_prec)
-    # common.py:373: in assertEqual
-    #     assertTensorsEqual(x, y)
-    # common.py:365: in assertTensorsEqual
-    #     self.assertLessEqual(max_err, prec, message)
-    # E   AssertionError: tensor(0.0000, device='cuda:0', dtype=torch.float32) not less than or equal to 2e-05 :
-    #  1 failed, 1202 passed, 19 skipped, 2 xfailed, 796 warnings in 1166.73 seconds =
-    # Traceback (most recent call last):
-    #   File "test/run_test.py", line 391, in <module>
-    #     main()
-    #   File "test/run_test.py", line 383, in main
-    #     raise RuntimeError(message)
-    tests_to_skip+=('TestNN and test_embedding_bag_cuda')
-fi
-
-##############################################################################
-# MacOS specific flaky tests
-##############################################################################
-
-if [[ "$(uname)" == 'Darwin' ]]; then
-    # TestCppExtensions by default uses a temp folder in /tmp. This doesn't
-    # work for this Mac machine cause there is only one machine and /tmp is
-    # shared. (All the linux builds are on docker so have their own /tmp).
-    tests_to_skip+=('TestCppExtension')
-fi
-
-# Turn the set of tests to skip into an invocation that pytest understands
-excluded_tests_logic=''
-for exclusion in "${tests_to_skip[@]}"; do
-    if [[ -z "$excluded_tests_logic" ]]; then
-        # Only true for i==0
-        excluded_tests_logic="not ($exclusion)"
-    else
-        excluded_tests_logic="$excluded_tests_logic and not ($exclusion)"
-    fi
-done
-
-
-##############################################################################
-# Run the tests
-##############################################################################
-echo
-echo "$(date) :: Calling 'python test/run_test.py -v -p pytest ${entire_file_exclusions[@]} -- --disable-pytest-warnings -k '$excluded_tests_logic'"
-
-python test/run_test.py -v -p pytest ${entire_file_exclusions[@]} -- --disable-pytest-warnings -k "'" "$excluded_tests_logic" "'"
-
-echo
-echo "$(date) :: Finished 'python test/run_test.py -v -p pytest ${entire_file_exclusions[@]} -- --disable-pytest-warnings -k '$excluded_tests_logic'"
-
-# cpp_extensions don't work with pytest, so we run them without pytest here,
-# except there's a failure on CUDA builds (documented above), and
-# cpp_extensions doesn't work on a shared mac machine (also documented above)
-if [[ "$cuda_ver" == 'cpu' && "$(uname)" != 'Darwin' ]]; then
-    echo
-    echo "$(date) :: Calling 'python test/run_test.py -v -i cpp_extensions'"
-    python test/run_test.py -v -i cpp_extensions
-    echo
-    echo "$(date) :: Finished 'python test/run_test.py -v -i cpp_extensions'"
-fi
-
-# thd_distributed can run on Mac but not in pytest
-if [[ "$(uname)" == 'Darwin' ]]; then
-    echo
-    echo "$(date) :: Calling 'python test/run_test.py -v -i thd_distributed'"
-    python test/run_test.py -v -i thd_distributed
-    echo
-    echo "$(date) :: Finished 'python test/run_test.py -v -i thd_distributed'"
-fi

.ci/pytorch/smoke_test/check_binary_symbols.py

@@ -1,130 +0,0 @@
-#!/usr/bin/env python3
-import concurrent.futures
-import distutils.sysconfig
-import functools
-import itertools
-import os
-import re
-from pathlib import Path
-from typing import Any, List, Tuple
-
-
-# We also check that there are [not] cxx11 symbols in libtorch
-#
-# To check whether it is using cxx11 ABI, check non-existence of symbol:
-PRE_CXX11_SYMBOLS = (
-    "std::basic_string<",
-    "std::list",
-)
-# To check whether it is using pre-cxx11 ABI, check non-existence of symbol:
-CXX11_SYMBOLS = (
-    "std::__cxx11::basic_string",
-    "std::__cxx11::list",
-)
-# NOTE: Checking the above symbols in all namespaces doesn't work, because
-# devtoolset7 always produces some cxx11 symbols even if we build with old ABI,
-# and CuDNN always has pre-cxx11 symbols even if we build with new ABI using gcc 5.4.
-# Instead, we *only* check the above symbols in the following namespaces:
-LIBTORCH_NAMESPACE_LIST = (
-    "c10::",
-    "at::",
-    "caffe2::",
-    "torch::",
-)
-
-
-def _apply_libtorch_symbols(symbols):
-    return [
-        re.compile(f"{x}.*{y}")
-        for (x, y) in itertools.product(LIBTORCH_NAMESPACE_LIST, symbols)
-    ]
-
-
-LIBTORCH_CXX11_PATTERNS = _apply_libtorch_symbols(CXX11_SYMBOLS)
-
-LIBTORCH_PRE_CXX11_PATTERNS = _apply_libtorch_symbols(PRE_CXX11_SYMBOLS)
-
-
-@functools.lru_cache(100)
-def get_symbols(lib: str) -> List[Tuple[str, str, str]]:
-    from subprocess import check_output
-
-    lines = check_output(f'nm "{lib}"|c++filt', shell=True)
-    return [x.split(" ", 2) for x in lines.decode("latin1").split("\n")[:-1]]
-
-
-def grep_symbols(lib: str, patterns: List[Any]) -> List[str]:
-    def _grep_symbols(
-        symbols: List[Tuple[str, str, str]], patterns: List[Any]
-    ) -> List[str]:
-        rc = []
-        for _s_addr, _s_type, s_name in symbols:
-            for pattern in patterns:
-                if pattern.match(s_name):
-                    rc.append(s_name)
-                    continue
-        return rc
-
-    all_symbols = get_symbols(lib)
-    num_workers = 32
-    chunk_size = (len(all_symbols) + num_workers - 1) // num_workers
-
-    def _get_symbols_chunk(i):
-        return all_symbols[i * chunk_size : (i + 1) * chunk_size]
-
-    with concurrent.futures.ThreadPoolExecutor(max_workers=32) as executor:
-        tasks = [
-            executor.submit(_grep_symbols, _get_symbols_chunk(i), patterns)
-            for i in range(num_workers)
-        ]
-        return functools.reduce(list.__add__, (x.result() for x in tasks), [])
-
-
-def check_lib_symbols_for_abi_correctness(lib: str, pre_cxx11_abi: bool = True) -> None:
-    print(f"lib: {lib}")
-    cxx11_symbols = grep_symbols(lib, LIBTORCH_CXX11_PATTERNS)
-    pre_cxx11_symbols = grep_symbols(lib, LIBTORCH_PRE_CXX11_PATTERNS)
-    num_cxx11_symbols = len(cxx11_symbols)
-    num_pre_cxx11_symbols = len(pre_cxx11_symbols)
-    print(f"num_cxx11_symbols: {num_cxx11_symbols}")
-    print(f"num_pre_cxx11_symbols: {num_pre_cxx11_symbols}")
-    if pre_cxx11_abi:
-        if num_cxx11_symbols > 0:
-            raise RuntimeError(
-                f"Found cxx11 symbols, but there shouldn't be any, see: {cxx11_symbols[:100]}"
-            )
-        if num_pre_cxx11_symbols < 1000:
-            raise RuntimeError("Didn't find enough pre-cxx11 symbols.")
-        # Check for no recursive iterators, regression test for https://github.com/pytorch/pytorch/issues/133437
-        rec_iter_symbols = grep_symbols(
-            lib, [re.compile("std::filesystem::recursive_directory_iterator.*")]
-        )
-        if len(rec_iter_symbols) > 0:
-            raise RuntimeError(
-                f"recursive_directory_iterator in used pre-CXX11 binaries, see; {rec_iter_symbols}"
-            )
-    else:
-        if num_pre_cxx11_symbols > 0:
-            raise RuntimeError(
-                f"Found pre-cxx11 symbols, but there shouldn't be any, see: {pre_cxx11_symbols[:100]}"
-            )
-        if num_cxx11_symbols < 100:
-            raise RuntimeError("Didn't find enought cxx11 symbols")
-
-
-def main() -> None:
-    if "install_root" in os.environ:
-        install_root = Path(os.getenv("install_root"))  # noqa: SIM112
-    else:
-        if os.getenv("PACKAGE_TYPE") == "libtorch":
-            install_root = Path(os.getcwd())
-        else:
-            install_root = Path(distutils.sysconfig.get_python_lib()) / "torch"
-
-    libtorch_cpu_path = install_root / "lib" / "libtorch_cpu.so"
-    pre_cxx11_abi = "cxx11-abi" not in os.getenv("DESIRED_DEVTOOLSET", "")
-    check_lib_symbols_for_abi_correctness(libtorch_cpu_path, pre_cxx11_abi)
-
-
-if __name__ == "__main__":
-    main()

.ci/pytorch/smoke_test/max_autotune.py

@@ -1,205 +0,0 @@
-import argparse
-
-from torchvision import datasets, transforms
-
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-import torch.optim as optim
-from torch.optim.lr_scheduler import StepLR
-
-
-class Net(nn.Module):
-    def __init__(self):
-        super(Net, self).__init__()  # noqa: UP008
-        self.conv1 = nn.Conv2d(1, 32, 3, 1)
-        self.conv2 = nn.Conv2d(32, 64, 3, 1)
-        self.dropout1 = nn.Dropout(0.25)
-        self.dropout2 = nn.Dropout(0.5)
-        self.fc1 = nn.Linear(9216, 128)
-        self.fc2 = nn.Linear(128, 10)
-
-    def forward(self, x):
-        x = self.conv1(x)
-        x = F.relu(x)
-        x = self.conv2(x)
-        x = F.relu(x)
-        x = F.max_pool2d(x, 2)
-        x = self.dropout1(x)
-        x = torch.flatten(x, 1)
-        x = self.fc1(x)
-        x = F.relu(x)
-        x = self.dropout2(x)
-        x = self.fc2(x)
-        output = F.log_softmax(x, dim=1)
-        return output
-
-
-def train(args, model, device, train_loader, optimizer, epoch):
-    model.train()
-    for batch_idx, (data, target) in enumerate(train_loader):
-        data, target = data.to(device), target.to(device)
-        optimizer.zero_grad()
-        output = model(data)
-        loss = F.nll_loss(output, target)
-        loss.backward()
-        optimizer.step()
-        if batch_idx % args.log_interval == 0:
-            print(
-                f"Train Epoch: {epoch} [{batch_idx * len(data)}/{len(train_loader.dataset)} ({100. * batch_idx / len(train_loader):.0f}%)]\tLoss: {loss.item():.6f}"  # noqa: B950
-            )
-            if args.dry_run:
-                break
-
-
-def test(model, device, test_loader):
-    model.eval()
-    test_loss = 0
-    correct = 0
-    with torch.no_grad():
-        for data, target in test_loader:
-            data, target = data.to(device), target.to(device)
-            output = model(data)
-            test_loss += F.nll_loss(
-                output, target, reduction="sum"
-            ).item()  # sum up batch loss
-            pred = output.argmax(
-                dim=1, keepdim=True
-            )  # get the index of the max log-probability
-            correct += pred.eq(target.view_as(pred)).sum().item()
-
-    test_loss /= len(test_loader.dataset)
-
-    print(
-        f"\nTest set: Average loss: {test_loss:.4f}, Accuracy: {correct}/{len(test_loader.dataset)} ({100. * correct / len(test_loader.dataset):.0f}%)\n"  # noqa: B950
-    )
-
-
-def timed(fn):
-    start = torch.cuda.Event(enable_timing=True)
-    end = torch.cuda.Event(enable_timing=True)
-    start.record()
-    result = fn()
-    end.record()
-    torch.cuda.synchronize()
-    return result, start.elapsed_time(end) / 1000
-
-
-def main():
-    # Training settings
-    parser = argparse.ArgumentParser(description="PyTorch MNIST Example")
-    parser.add_argument(
-        "--batch-size",
-        type=int,
-        default=64,
-        metavar="N",
-        help="input batch size for training (default: 64)",
-    )
-    parser.add_argument(
-        "--test-batch-size",
-        type=int,
-        default=1000,
-        metavar="N",
-        help="input batch size for testing (default: 1000)",
-    )
-    parser.add_argument(
-        "--epochs",
-        type=int,
-        default=4,
-        metavar="N",
-        help="number of epochs to train (default: 14)",
-    )
-    parser.add_argument(
-        "--lr",
-        type=float,
-        default=1.0,
-        metavar="LR",
-        help="learning rate (default: 1.0)",
-    )
-    parser.add_argument(
-        "--gamma",
-        type=float,
-        default=0.7,
-        metavar="M",
-        help="Learning rate step gamma (default: 0.7)",
-    )
-    parser.add_argument(
-        "--no-cuda", action="store_true", default=False, help="disables CUDA training"
-    )
-    parser.add_argument(
-        "--no-mps",
-        action="store_true",
-        default=False,
-        help="disables macOS GPU training",
-    )
-    parser.add_argument(
-        "--dry-run",
-        action="store_true",
-        default=False,
-        help="quickly check a single pass",
-    )
-    parser.add_argument(
-        "--seed", type=int, default=1, metavar="S", help="random seed (default: 1)"
-    )
-    parser.add_argument(
-        "--log-interval",
-        type=int,
-        default=100,
-        metavar="N",
-        help="how many batches to wait before logging training status",
-    )
-    parser.add_argument(
-        "--save-model",
-        action="store_true",
-        default=False,
-        help="For Saving the current Model",
-    )
-    args = parser.parse_args()
-    use_cuda = not args.no_cuda and torch.cuda.is_available()
-    use_mps = not args.no_mps and torch.backends.mps.is_available()
-
-    torch.manual_seed(args.seed)
-    torch.backends.cuda.matmul.allow_tf32 = True
-
-    if use_cuda:
-        device = torch.device("cuda")
-    elif use_mps:
-        device = torch.device("mps")
-    else:
-        device = torch.device("cpu")
-
-    train_kwargs = {"batch_size": args.batch_size}
-    test_kwargs = {"batch_size": args.test_batch_size}
-    if use_cuda:
-        cuda_kwargs = {"num_workers": 1, "pin_memory": True, "shuffle": True}
-        train_kwargs.update(cuda_kwargs)
-        test_kwargs.update(cuda_kwargs)
-
-    transform = transforms.Compose(
-        [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]
-    )
-    dataset1 = datasets.MNIST("../data", train=True, download=True, transform=transform)
-    dataset2 = datasets.MNIST("../data", train=False, transform=transform)
-    train_loader = torch.utils.data.DataLoader(dataset1, **train_kwargs)
-    test_loader = torch.utils.data.DataLoader(dataset2, **test_kwargs)
-
-    model = Net().to(device)
-    opt_model = torch.compile(model, mode="max-autotune")
-    optimizer = optim.Adadelta(opt_model.parameters(), lr=args.lr)
-
-    scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma)
-    for epoch in range(1, args.epochs + 1):
-        print(
-            f"Training Time: {timed(lambda: train(args, opt_model, device, train_loader, optimizer, epoch))[1]}"
-        )
-        print(
-            f"Evaluation Time: {timed(lambda: test(opt_model, device, test_loader))[1]}"
-        )
-        scheduler.step()
-
-    if args.save_model:
-        torch.save(opt_model.state_dict(), "mnist_cnn.pt")
-
-
-if __name__ == "__main__":
-    main()

.ci/pytorch/smoke_test/smoke_test.py

@@ -1,385 +0,0 @@
-import argparse
-import importlib
-import json
-import os
-import re
-import subprocess
-import sys
-from pathlib import Path
-
-import torch
-import torch._dynamo
-import torch.nn as nn
-import torch.nn.functional as F
-
-
-if "MATRIX_GPU_ARCH_VERSION" in os.environ:
-    gpu_arch_ver = os.getenv("MATRIX_GPU_ARCH_VERSION")
-else:
-    gpu_arch_ver = os.getenv("GPU_ARCH_VERSION")  # Use fallback if available
-gpu_arch_type = os.getenv("MATRIX_GPU_ARCH_TYPE")
-channel = os.getenv("MATRIX_CHANNEL")
-package_type = os.getenv("MATRIX_PACKAGE_TYPE")
-target_os = os.getenv("TARGET_OS", sys.platform)
-BASE_DIR = Path(__file__).parent.parent.parent
-
-is_cuda_system = gpu_arch_type == "cuda"
-NIGHTLY_ALLOWED_DELTA = 3
-
-MODULES = [
-    {
-        "name": "torchvision",
-        "repo": "https://github.com/pytorch/vision.git",
-        "smoke_test": "./vision/test/smoke_test.py",
-        "extension": "extension",
-        "repo_name": "vision",
-    },
-    {
-        "name": "torchaudio",
-        "repo": "https://github.com/pytorch/audio.git",
-        "smoke_test": "./audio/test/smoke_test/smoke_test.py --no-ffmpeg",
-        "extension": "_extension",
-        "repo_name": "audio",
-    },
-]
-
-
-class Net(nn.Module):
-    def __init__(self):
-        super().__init__()
-        self.conv1 = nn.Conv2d(1, 32, 3, 1)
-        self.conv2 = nn.Conv2d(32, 64, 3, 1)
-        self.fc1 = nn.Linear(9216, 1)
-
-    def forward(self, x):
-        x = self.conv1(x)
-        x = self.conv2(x)
-        x = F.max_pool2d(x, 2)
-        x = torch.flatten(x, 1)
-        output = self.fc1(x)
-        return output
-
-
-def load_json_from_basedir(filename: str):
-    try:
-        with open(BASE_DIR / filename) as fptr:
-            return json.load(fptr)
-    except FileNotFoundError as exc:
-        raise ImportError(f"File {filename} not found error: {exc.strerror}") from exc
-    except json.JSONDecodeError as exc:
-        raise ImportError(f"Invalid JSON {filename}") from exc
-
-
-def read_release_matrix():
-    return load_json_from_basedir("release_matrix.json")
-
-
-def test_numpy():
-    import numpy as np
-
-    x = np.arange(5)
-    torch.tensor(x)
-
-
-def check_version(package: str) -> None:
-    release_version = os.getenv("RELEASE_VERSION")
-    # if release_version is specified, use it to validate the packages
-    if release_version:
-        release_matrix = read_release_matrix()
-        stable_version = release_matrix["torch"]
-    else:
-        stable_version = os.getenv("MATRIX_STABLE_VERSION")
-
-    # only makes sense to check nightly package where dates are known
-    if channel == "nightly":
-        check_nightly_binaries_date(package)
-    elif stable_version is not None:
-        if not torch.__version__.startswith(stable_version):
-            raise RuntimeError(
-                f"Torch version mismatch, expected {stable_version} for channel {channel}. But its {torch.__version__}"
-            )
-
-        if release_version and package == "all":
-            for module in MODULES:
-                imported_module = importlib.import_module(module["name"])
-                module_version = imported_module.__version__
-                if not module_version.startswith(release_matrix[module["name"]]):
-                    raise RuntimeError(
-                        f"{module['name']} version mismatch, expected: \
-                            {release_matrix[module['name']]} for channel {channel}. But its {module_version}"
-                    )
-                else:
-                    print(f"{module['name']} version actual: {module_version} expected: \
-                        {release_matrix[module['name']]} for channel {channel}.")
-
-    else:
-        print(f"Skip version check for channel {channel} as stable version is None")
-
-
-def check_nightly_binaries_date(package: str) -> None:
-    from datetime import datetime
-
-    format_dt = "%Y%m%d"
-
-    date_t_str = re.findall("dev\\d+", torch.__version__)
-    date_t_delta = datetime.now() - datetime.strptime(date_t_str[0][3:], format_dt)
-    if date_t_delta.days >= NIGHTLY_ALLOWED_DELTA:
-        raise RuntimeError(
-            f"the binaries are from {date_t_str} and are more than {NIGHTLY_ALLOWED_DELTA} days old!"
-        )
-
-    if package == "all":
-        for module in MODULES:
-            imported_module = importlib.import_module(module["name"])
-            module_version = imported_module.__version__
-            date_m_str = re.findall("dev\\d+", module_version)
-            date_m_delta = datetime.now() - datetime.strptime(
-                date_m_str[0][3:], format_dt
-            )
-            print(f"Nightly date check for {module['name']} version {module_version}")
-            if date_m_delta.days > NIGHTLY_ALLOWED_DELTA:
-                raise RuntimeError(
-                    f"Expected {module['name']} to be less then {NIGHTLY_ALLOWED_DELTA} days. But its {date_m_delta}"
-                )
-
-
-def test_cuda_runtime_errors_captured() -> None:
-    cuda_exception_missed = True
-    try:
-        print("Testing test_cuda_runtime_errors_captured")
-        torch._assert_async(torch.tensor(0, device="cuda"))
-        torch._assert_async(torch.tensor(0 + 0j, device="cuda"))
-    except RuntimeError as e:
-        if re.search("CUDA", f"{e}"):
-            print(f"Caught CUDA exception with success: {e}")
-            cuda_exception_missed = False
-        else:
-            raise e
-    if cuda_exception_missed:
-        raise RuntimeError("Expected CUDA RuntimeError but have not received!")
-
-
-def smoke_test_cuda(
-    package: str, runtime_error_check: str, torch_compile_check: str
-) -> None:
-    if not torch.cuda.is_available() and is_cuda_system:
-        raise RuntimeError(f"Expected CUDA {gpu_arch_ver}. However CUDA is not loaded.")
-
-    if package == "all" and is_cuda_system:
-        for module in MODULES:
-            imported_module = importlib.import_module(module["name"])
-            # TBD for vision move extension module to private so it will
-            # be _extention.
-            version = "N/A"
-            if module["extension"] == "extension":
-                version = imported_module.extension._check_cuda_version()
-            else:
-                version = imported_module._extension._check_cuda_version()
-            print(f"{module['name']} CUDA: {version}")
-
-    # torch.compile is available on macos-arm64 and Linux for python 3.8-3.13
-    if (
-        torch_compile_check == "enabled"
-        and sys.version_info < (3, 14, 0)
-        and target_os in ["linux", "linux-aarch64", "macos-arm64", "darwin"]
-    ):
-        smoke_test_compile("cuda" if torch.cuda.is_available() else "cpu")
-
-    if torch.cuda.is_available():
-        if torch.version.cuda != gpu_arch_ver:
-            raise RuntimeError(
-                f"Wrong CUDA version. Loaded: {torch.version.cuda} Expected: {gpu_arch_ver}"
-            )
-        print(f"torch cuda: {torch.version.cuda}")
-        # todo add cudnn version validation
-        print(f"torch cudnn: {torch.backends.cudnn.version()}")
-        print(f"cuDNN enabled? {torch.backends.cudnn.enabled}")
-
-        torch.cuda.init()
-        print("CUDA initialized successfully")
-        print(f"Number of CUDA devices: {torch.cuda.device_count()}")
-        for i in range(torch.cuda.device_count()):
-            print(f"Device {i}: {torch.cuda.get_device_name(i)}")
-
-        # nccl is availbale only on Linux
-        if sys.platform in ["linux", "linux2"]:
-            print(f"torch nccl version: {torch.cuda.nccl.version()}")
-
-        if runtime_error_check == "enabled":
-            test_cuda_runtime_errors_captured()
-
-
-def smoke_test_conv2d() -> None:
-    import torch.nn as nn
-
-    print("Testing smoke_test_conv2d")
-    # With square kernels and equal stride
-    m = nn.Conv2d(16, 33, 3, stride=2)
-    # non-square kernels and unequal stride and with padding
-    m = nn.Conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2))
-    assert m is not None
-    # non-square kernels and unequal stride and with padding and dilation
-    basic_conv = nn.Conv2d(
-        16, 33, (3, 5), stride=(2, 1), padding=(4, 2), dilation=(3, 1)
-    )
-    input = torch.randn(20, 16, 50, 100)
-    output = basic_conv(input)
-
-    if is_cuda_system:
-        print("Testing smoke_test_conv2d with cuda")
-        conv = nn.Conv2d(3, 3, 3).cuda()
-        x = torch.randn(1, 3, 24, 24, device="cuda")
-        with torch.cuda.amp.autocast():
-            out = conv(x)
-        assert out is not None
-
-        supported_dtypes = [torch.float16, torch.float32, torch.float64]
-        for dtype in supported_dtypes:
-            print(f"Testing smoke_test_conv2d with cuda for {dtype}")
-            conv = basic_conv.to(dtype).cuda()
-            input = torch.randn(20, 16, 50, 100, device="cuda").type(dtype)
-            output = conv(input)
-            assert output is not None
-
-
-def test_linalg(device="cpu") -> None:
-    print(f"Testing smoke_test_linalg on {device}")
-    A = torch.randn(5, 3, device=device)
-    U, S, Vh = torch.linalg.svd(A, full_matrices=False)
-    assert (
-        U.shape == A.shape
-        and S.shape == torch.Size([3])
-        and Vh.shape == torch.Size([3, 3])
-    )
-    torch.dist(A, U @ torch.diag(S) @ Vh)
-
-    U, S, Vh = torch.linalg.svd(A)
-    assert (
-        U.shape == torch.Size([5, 5])
-        and S.shape == torch.Size([3])
-        and Vh.shape == torch.Size([3, 3])
-    )
-    torch.dist(A, U[:, :3] @ torch.diag(S) @ Vh)
-
-    A = torch.randn(7, 5, 3, device=device)
-    U, S, Vh = torch.linalg.svd(A, full_matrices=False)
-    torch.dist(A, U @ torch.diag_embed(S) @ Vh)
-
-    if device == "cuda":
-        supported_dtypes = [torch.float32, torch.float64]
-        for dtype in supported_dtypes:
-            print(f"Testing smoke_test_linalg with cuda for {dtype}")
-            A = torch.randn(20, 16, 50, 100, device=device, dtype=dtype)
-            torch.linalg.svd(A)
-
-
-def smoke_test_compile(device: str = "cpu") -> None:
-    supported_dtypes = [torch.float16, torch.float32, torch.float64]
-
-    def foo(x: torch.Tensor) -> torch.Tensor:
-        return torch.sin(x) + torch.cos(x)
-
-    for dtype in supported_dtypes:
-        print(f"Testing smoke_test_compile for {device} and {dtype}")
-        x = torch.rand(3, 3, device=device).type(dtype)
-        x_eager = foo(x)
-        x_pt2 = torch.compile(foo)(x)
-        torch.testing.assert_close(x_eager, x_pt2)
-
-    # Check that SIMD were detected for the architecture
-    if device == "cpu":
-        from torch._inductor.codecache import pick_vec_isa
-
-        isa = pick_vec_isa()
-        if not isa:
-            raise RuntimeError("Can't detect vectorized ISA for CPU")
-        print(f"Picked CPU ISA {type(isa).__name__} bit width {isa.bit_width()}")
-
-    # Reset torch dynamo since we are changing mode
-    torch._dynamo.reset()
-    dtype = torch.float32
-    torch.set_float32_matmul_precision("high")
-    print(f"Testing smoke_test_compile with mode 'max-autotune' for {dtype}")
-    x = torch.rand(64, 1, 28, 28, device=device).type(torch.float32)
-    model = Net().to(device=device)
-    x_pt2 = torch.compile(model, mode="max-autotune")(x)
-
-
-def smoke_test_modules():
-    cwd = os.getcwd()
-    for module in MODULES:
-        if module["repo"]:
-            if not os.path.exists(f"{cwd}/{module['repo_name']}"):
-                print(f"Path does not exist: {cwd}/{module['repo_name']}")
-                try:
-                    subprocess.check_output(
-                        f"git clone --depth 1 {module['repo']}",
-                        stderr=subprocess.STDOUT,
-                        shell=True,
-                    )
-                except subprocess.CalledProcessError as exc:
-                    raise RuntimeError(
-                        f"Cloning {module['repo']} FAIL: {exc.returncode} Output: {exc.output}"
-                    ) from exc
-            try:
-                smoke_test_command = f"python3 {module['smoke_test']}"
-                if target_os == "windows":
-                    smoke_test_command = f"python {module['smoke_test']}"
-                output = subprocess.check_output(
-                    smoke_test_command,
-                    stderr=subprocess.STDOUT,
-                    shell=True,
-                    universal_newlines=True,
-                )
-            except subprocess.CalledProcessError as exc:
-                raise RuntimeError(
-                    f"Module {module['name']} FAIL: {exc.returncode} Output: {exc.output}"
-                ) from exc
-            else:
-                print(f"Output: \n{output}\n")
-
-
-def main() -> None:
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        "--package",
-        help="Package to include in smoke testing",
-        type=str,
-        choices=["all", "torchonly"],
-        default="all",
-    )
-    parser.add_argument(
-        "--runtime-error-check",
-        help="No Runtime Error check",
-        type=str,
-        choices=["enabled", "disabled"],
-        default="enabled",
-    )
-    parser.add_argument(
-        "--torch-compile-check",
-        help="Check torch compile",
-        type=str,
-        choices=["enabled", "disabled"],
-        default="enabled",
-    )
-    options = parser.parse_args()
-    print(f"torch: {torch.__version__}")
-    print(torch.__config__.parallel_info())
-
-    check_version(options.package)
-    smoke_test_conv2d()
-    test_linalg()
-    test_numpy()
-    if is_cuda_system:
-        test_linalg("cuda")
-
-    if options.package == "all":
-        smoke_test_modules()
-
-    smoke_test_cuda(
-        options.package, options.runtime_error_check, options.torch_compile_check
-    )
-
-
-if __name__ == "__main__":
-    main()

.ci/pytorch/test.sh

@@ -14,7 +14,7 @@ source "$(dirname "${BASH_SOURCE[0]}")/common.sh"
 
 # Do not change workspace permissions for ROCm CI jobs
 # as it can leave workspace with bad permissions for cancelled jobs
-if [[ "$BUILD_ENVIRONMENT" != *rocm* && -d /var/lib/jenkins/workspace ]]; then
+if [[ "$BUILD_ENVIRONMENT" != *rocm* ]]; then
   # Workaround for dind-rootless userid mapping (https://github.com/pytorch/ci-infra/issues/96)
   WORKSPACE_ORIGINAL_OWNER_ID=$(stat -c '%u' "/var/lib/jenkins/workspace")
   cleanup_workspace() {
@@ -487,6 +487,8 @@ test_perf_for_dashboard() {
     device=cuda_a10g
   fi
 
+  export TORCHINDUCTOR_CPP_WRAPPER=1
+
   for mode in "${modes[@]}"; do
     if [[ "$mode" == "inference" ]]; then
       dtype=bfloat16
@@ -1412,7 +1414,7 @@ test_linux_aarch64() {
        inductor/test_pattern_matcher inductor/test_perf inductor/test_profiler inductor/test_select_algorithm inductor/test_smoke \
        inductor/test_split_cat_fx_passes inductor/test_standalone_compile inductor/test_torchinductor \
        inductor/test_torchinductor_codegen_dynamic_shapes inductor/test_torchinductor_dynamic_shapes inductor/test_memory \
-       inductor/test_triton_cpu_backend inductor/test_triton_extension_backend inductor/test_mkldnn_pattern_matcher inductor/test_cpu_cpp_wrapper \
+       inductor/test_triton_cpu_backend inductor/test_triton_extension_backend \
        --shard "$SHARD_NUMBER" "$NUM_TEST_SHARDS" --verbose
 }
 
@@ -1421,9 +1423,9 @@ if ! [[ "${BUILD_ENVIRONMENT}" == *libtorch* || "${BUILD_ENVIRONMENT}" == *-baze
   (cd test && python -c "import torch; print(torch.__config__.parallel_info())")
 fi
 if [[ "${TEST_CONFIG}" == *numpy_2* ]]; then
-  # Install numpy-2.0.2 and compatible scipy & numba versions
-  python -mpip install --pre numpy==2.0.2 scipy==1.13.1 numba==0.60.0
-  python test/run_test.py --include dynamo/test_functions.py dynamo/test_unspec.py test_binary_ufuncs.py test_fake_tensor.py test_linalg.py test_numpy_interop.py test_tensor_creation_ops.py test_torch.py torch_np/test_basic.py
+  # Install numpy-2.0.2 and test inductor tracing
+  python -mpip install --pre numpy==2.0.2
+  python test/run_test.py --include dynamo/test_unspec.py
 elif [[ "${BUILD_ENVIRONMENT}" == *aarch64* && "${TEST_CONFIG}" != *perf_cpu_aarch64* ]]; then
   test_linux_aarch64
 elif [[ "${TEST_CONFIG}" == *backward* ]]; then

.ci/pytorch/test_example_code/CMakeLists.txt

@@ -1,26 +0,0 @@
-cmake_minimum_required(VERSION 3.0 FATAL_ERROR)
-project(simple-torch-test)
-
-find_package(Torch REQUIRED)
-set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TORCH_CXX_FLAGS}")
-
-
-add_executable(simple-torch-test simple-torch-test.cpp)
-target_include_directories(simple-torch-test PRIVATE  ${TORCH_INCLUDE_DIRS})
-target_link_libraries(simple-torch-test "${TORCH_LIBRARIES}")
-set_property(TARGET simple-torch-test PROPERTY CXX_STANDARD 17)
-
-find_package(CUDAToolkit 11.8)
-
-target_link_libraries(simple-torch-test CUDA::cudart CUDA::cufft CUDA::cusparse CUDA::cublas CUDA::cusolver)
-find_library(CUDNN_LIBRARY NAMES cudnn)
-target_link_libraries(simple-torch-test  ${CUDNN_LIBRARY} )
-if(MSVC)
-  file(GLOB TORCH_DLLS  "$ENV{CUDA_PATH}/bin/cudnn64_8.dll" "$ENV{NVTOOLSEXT_PATH}/bin/x64/*.dll")
-  message("dlls to copy "  ${TORCH_DLLS})
-  add_custom_command(TARGET simple-torch-test
-                     POST_BUILD
-                     COMMAND ${CMAKE_COMMAND} -E copy_if_different
-                     ${TORCH_DLLS}
-                     $<TARGET_FILE_DIR:simple-torch-test>)
-endif(MSVC)

.ci/pytorch/test_example_code/check-torch-cuda.cpp

@@ -1,15 +0,0 @@
-#include <torch/torch.h>
-
-int main(int argc, const char* argv[]) {
-    std::cout << "Checking that CUDA archs are setup correctly" << std::endl;
-    TORCH_CHECK(torch::rand({ 3, 5 }, torch::Device(torch::kCUDA)).defined(), "CUDA archs are not setup correctly");
-
-    // These have to run after CUDA is initialized
-
-    std::cout << "Checking that magma is available" << std::endl;
-    TORCH_CHECK(torch::hasMAGMA(), "MAGMA is not available");
-
-    std::cout << "Checking that CuDNN is available" << std::endl;
-    TORCH_CHECK(torch::cuda::cudnn_is_available(), "CuDNN is not available");
-    return 0;
-}

.ci/pytorch/test_example_code/check-torch-mkl.cpp

@@ -1,6 +0,0 @@
-#include <torch/torch.h>
-
-int main(int argc, const char* argv[]) {
-    TORCH_CHECK(torch::hasMKL(), "MKL is not available");
-    return 0;
-}

.ci/pytorch/test_example_code/check-torch-xnnpack.cpp

@@ -1,7 +0,0 @@
-#include <ATen/ATen.h>
-#include <torch/torch.h>
-
-int main(int argc, const char* argv[]) {
-    TORCH_CHECK(at::globalContext().isXNNPACKAvailable(), "XNNPACK is not available");
-    return 0;
-}

.ci/pytorch/test_example_code/cnn_smoke.py

@@ -1,38 +0,0 @@
-r"""
-It's used to check basic rnn features with cuda.
-For example, it would throw exception if some components are missing
-"""
-
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-import torch.optim as optim
-
-
-class SimpleCNN(nn.Module):
-    def __init__(self):
-        super().__init__()
-        self.conv = nn.Conv2d(1, 1, 3)
-        self.pool = nn.MaxPool2d(2, 2)
-
-    def forward(self, inputs):
-        output = self.pool(F.relu(self.conv(inputs)))
-        output = output.view(1)
-        return output
-
-
-# Mock one infer
-device = torch.device("cuda:0")
-net = SimpleCNN().to(device)
-net_inputs = torch.rand((1, 1, 5, 5), device=device)
-outputs = net(net_inputs)
-print(outputs)
-
-criterion = nn.MSELoss()
-optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.1)
-
-# Mock one step training
-label = torch.full((1,), 1.0, dtype=torch.float, device=device)
-loss = criterion(outputs, label)
-loss.backward()
-optimizer.step()

.ci/pytorch/test_example_code/rnn_smoke.py

@@ -1,14 +0,0 @@
-r"""
-It's used to check basic rnn features with cuda.
-For example, it would throw exception if missing some components are missing
-"""
-
-import torch
-import torch.nn as nn
-
-
-device = torch.device("cuda:0")
-rnn = nn.RNN(10, 20, 2).to(device)
-inputs = torch.randn(5, 3, 10).to(device)
-h0 = torch.randn(2, 3, 20).to(device)
-output, hn = rnn(inputs, h0)

.ci/pytorch/test_example_code/simple-torch-test.cpp

@@ -1,6 +0,0 @@
-#include <torch/torch.h>
-
-int main(int argc, const char* argv[]) {
-    TORCH_WARN("Simple test passed!");
-    return 0;
-}

.ci/pytorch/win-test.sh

@@ -35,7 +35,7 @@ if [[ "$BUILD_ENVIRONMENT" == *cuda* ]]; then
 fi
 
 # TODO: Move both of them to Windows AMI
-python -m pip install pytest-rerunfailures==10.3 pytest-cpp==2.3.0 tensorboard==2.13.0 pytest-subtests==0.13.1
+python -m pip install pytest-rerunfailures==10.3 pytest-cpp==2.3.0 tensorboard==2.13.0
 
 # Install Z3 optional dependency for Windows builds.
 python -m pip install z3-solver==4.12.2.0

.ci/pytorch/windows/build_pytorch.bat

@@ -1,133 +0,0 @@
-@echo off
-
-:: This script parses args, installs required libraries (miniconda, MKL,
-:: Magma), and then delegates to cpu.bat, cuda80.bat, etc.
-
-if not "%CUDA_VERSION%" == "" if not "%PYTORCH_BUILD_VERSION%" == "" if not "%PYTORCH_BUILD_NUMBER%" == "" goto env_end
-if "%~1"=="" goto arg_error
-if "%~2"=="" goto arg_error
-if "%~3"=="" goto arg_error
-if not "%~4"=="" goto arg_error
-goto arg_end
-
-:arg_error
-
-echo Illegal number of parameters. Pass cuda version, pytorch version, build number
-echo CUDA version should be Mm with no dot, e.g. '80'
-echo DESIRED_PYTHON should be M.m, e.g. '2.7'
-exit /b 1
-
-:arg_end
-
-set CUDA_VERSION=%~1
-set PYTORCH_BUILD_VERSION=%~2
-set PYTORCH_BUILD_NUMBER=%~3
-
-:env_end
-
-set CUDA_PREFIX=cuda%CUDA_VERSION%
-if "%CUDA_VERSION%" == "cpu" set CUDA_PREFIX=cpu
-if "%CUDA_VERSION%" == "xpu" set CUDA_PREFIX=xpu
-
-if "%DESIRED_PYTHON%" == "" set DESIRED_PYTHON=3.5;3.6;3.7
-set DESIRED_PYTHON_PREFIX=%DESIRED_PYTHON:.=%
-set DESIRED_PYTHON_PREFIX=py%DESIRED_PYTHON_PREFIX:;=;py%
-
-set SRC_DIR=%~dp0
-pushd %SRC_DIR%
-
-:: Install Miniconda3
-set "CONDA_HOME=%CD%\conda"
-set "tmp_conda=%CONDA_HOME%"
-set "miniconda_exe=%CD%\miniconda.exe"
-rmdir /s /q conda
-del miniconda.exe
-curl --retry 3 -k https://repo.anaconda.com/miniconda/Miniconda3-py311_23.9.0-0-Windows-x86_64.exe -o "%miniconda_exe%"
-start /wait "" "%miniconda_exe%" /S /InstallationType=JustMe /RegisterPython=0 /AddToPath=0 /D=%tmp_conda%
-if ERRORLEVEL 1 exit /b 1
-set "ORIG_PATH=%PATH%"
-set "PATH=%CONDA_HOME%;%CONDA_HOME%\scripts;%CONDA_HOME%\Library\bin;%PATH%"
-
-:: create a new conda environment and install packages
-:try
-SET /A tries=3
-:loop
-IF %tries% LEQ 0 GOTO :exception
-call condaenv.bat
-IF %ERRORLEVEL% EQU 0 GOTO :done
-SET /A "tries=%tries%-1"
-:exception
-echo "Failed to create conda env"
-exit /B 1
-:done
-
-:: Download MAGMA Files on CUDA builds
-set MAGMA_VERSION=2.5.4
-
-if "%DEBUG%" == "1" (
-    set BUILD_TYPE=debug
-) else (
-    set BUILD_TYPE=release
-)
-
-if not "%CUDA_VERSION%" == "cpu" if not "%CUDA_VERSION%" == "xpu" (
-    rmdir /s /q magma_%CUDA_PREFIX%_%BUILD_TYPE%
-    del magma_%CUDA_PREFIX%_%BUILD_TYPE%.7z
-    curl -k https://s3.amazonaws.com/ossci-windows/magma_%MAGMA_VERSION%_%CUDA_PREFIX%_%BUILD_TYPE%.7z -o magma_%CUDA_PREFIX%_%BUILD_TYPE%.7z
-    7z x -aoa magma_%CUDA_PREFIX%_%BUILD_TYPE%.7z -omagma_%CUDA_PREFIX%_%BUILD_TYPE%
-)
-
-:: Install sccache
-if "%USE_SCCACHE%" == "1" (
-    mkdir %CD%\tmp_bin
-    curl -k https://s3.amazonaws.com/ossci-windows/sccache.exe --output %CD%\tmp_bin\sccache.exe
-    curl -k https://s3.amazonaws.com/ossci-windows/sccache-cl.exe --output %CD%\tmp_bin\sccache-cl.exe
-    if not "%CUDA_VERSION%" == "" (
-        set ADDITIONAL_PATH=%CD%\tmp_bin
-        set SCCACHE_IDLE_TIMEOUT=1500
-
-        :: randomtemp is used to resolve the intermittent build error related to CUDA.
-        :: code: https://github.com/peterjc123/randomtemp-rust
-        :: issue: https://github.com/pytorch/pytorch/issues/25393
-        ::
-        :: CMake requires a single command as CUDA_NVCC_EXECUTABLE, so we push the wrappers
-        :: randomtemp.exe and sccache.exe into a batch file which CMake invokes.
-        curl -kL https://github.com/peterjc123/randomtemp-rust/releases/download/v0.4/randomtemp.exe --output %SRC_DIR%\tmp_bin\randomtemp.exe
-        echo @"%SRC_DIR%\tmp_bin\randomtemp.exe" "%SRC_DIR%\tmp_bin\sccache.exe" "%CUDA_PATH%\bin\nvcc.exe" %%* > "%SRC_DIR%/tmp_bin/nvcc.bat"
-        cat %SRC_DIR%/tmp_bin/nvcc.bat
-        set CUDA_NVCC_EXECUTABLE=%SRC_DIR%/tmp_bin/nvcc.bat
-        :: CMake doesn't accept back-slashes in the path
-        for /F "usebackq delims=" %%n in (`cygpath -m "%CUDA_PATH%\bin\nvcc.exe"`) do set CMAKE_CUDA_COMPILER=%%n
-        set CMAKE_CUDA_COMPILER_LAUNCHER=%SRC_DIR%\tmp_bin\randomtemp.exe;%SRC_DIR%\tmp_bin\sccache.exe
-    )
-)
-
-set PYTORCH_BINARY_BUILD=1
-set TH_BINARY_BUILD=1
-set INSTALL_TEST=0
-
-for %%v in (%DESIRED_PYTHON_PREFIX%) do (
-    :: Activate Python Environment
-    set PYTHON_PREFIX=%%v
-    set "CONDA_LIB_PATH=%CONDA_HOME%\envs\%%v\Library\bin"
-    if not "%ADDITIONAL_PATH%" == "" (
-        set "PATH=%ADDITIONAL_PATH%;%CONDA_HOME%\envs\%%v;%CONDA_HOME%\envs\%%v\scripts;%CONDA_HOME%\envs\%%v\Library\bin;%ORIG_PATH%"
-    ) else (
-        set "PATH=%CONDA_HOME%\envs\%%v;%CONDA_HOME%\envs\%%v\scripts;%CONDA_HOME%\envs\%%v\Library\bin;%ORIG_PATH%"
-    )
-    pip install ninja
-    @setlocal
-    :: Set Flags
-    if not "%CUDA_VERSION%"=="cpu" if not "%CUDA_VERSION%" == "xpu" (
-        set MAGMA_HOME=%cd%\magma_%CUDA_PREFIX%_%BUILD_TYPE%
-    )
-    echo "Calling arch build script"
-    call %CUDA_PREFIX%.bat
-    if ERRORLEVEL 1 exit /b 1
-    @endlocal
-)
-
-set "PATH=%ORIG_PATH%"
-popd
-
-if ERRORLEVEL 1 exit /b 1

.ci/pytorch/windows/condaenv.bat

@@ -1,26 +0,0 @@
-IF "%DESIRED_PYTHON%"=="" (
-    echo DESIRED_PYTHON is NOT defined.
-    exit /b 1
-)
-
-:: Create a new conda environment
-setlocal EnableDelayedExpansion
-FOR %%v IN (%DESIRED_PYTHON%) DO (
-    set PYTHON_VERSION_STR=%%v
-    set PYTHON_VERSION_STR=!PYTHON_VERSION_STR:.=!
-    conda remove -n py!PYTHON_VERSION_STR! --all -y || rmdir %CONDA_HOME%\envs\py!PYTHON_VERSION_STR! /s
-    if "%%v" == "3.8" call conda create -n py!PYTHON_VERSION_STR! -y -q numpy=1.11 pyyaml boto3 cmake ninja typing_extensions setuptools=72.1.0 python=%%v
-    if "%%v" == "3.9" call conda create -n py!PYTHON_VERSION_STR! -y -q numpy=2.0.1 pyyaml boto3 cmake ninja typing_extensions setuptools=72.1.0 python=%%v
-    if "%%v" == "3.10" call conda create -n py!PYTHON_VERSION_STR! -y -q -c=conda-forge numpy=2.0.1 pyyaml boto3 cmake ninja typing_extensions setuptools=72.1.0 python=%%v
-    if "%%v" == "3.11" call conda create -n py!PYTHON_VERSION_STR! -y -q -c=conda-forge numpy=2.0.1 pyyaml boto3 cmake ninja typing_extensions setuptools=72.1.0 python=%%v
-    if "%%v" == "3.12" call conda create -n py!PYTHON_VERSION_STR! -y -q -c=conda-forge numpy=2.0.1 pyyaml boto3 cmake ninja typing_extensions setuptools=72.1.0 python=%%v
-    if "%%v" == "3.13" call conda create -n py!PYTHON_VERSION_STR! -y -q -c=conda-forge numpy=2.1.2 pyyaml boto3 cmake ninja typing_extensions setuptools=72.1.0 python=%%v
-    call conda run -n py!PYTHON_VERSION_STR! pip install mkl-include
-    call conda run -n py!PYTHON_VERSION_STR! pip install mkl-static
-)
-endlocal
-
-:: Install libuv
-conda install -y -q -c conda-forge libuv=1.39
-set libuv_ROOT=%CONDA_HOME%\Library
-echo libuv_ROOT=%libuv_ROOT%

.ci/pytorch/windows/cpu.bat

@@ -1,30 +0,0 @@
-@echo off
-
-set MODULE_NAME=pytorch
-
-IF NOT EXIST "setup.py" IF NOT EXIST "%MODULE_NAME%" (
-    call internal\clone.bat
-    cd %~dp0
-) ELSE (
-    call internal\clean.bat
-)
-
-IF ERRORLEVEL 1 goto :eof
-
-call internal\check_deps.bat
-IF ERRORLEVEL 1 goto :eof
-
-REM Check for optional components
-
-echo Disabling CUDA
-set USE_CUDA=0
-
-call internal\check_opts.bat
-IF ERRORLEVEL 1 goto :eof
-
-if exist "%NIGHTLIES_PYTORCH_ROOT%" cd %NIGHTLIES_PYTORCH_ROOT%\..
-call %~dp0\internal\copy_cpu.bat
-IF ERRORLEVEL 1 goto :eof
-
-call %~dp0\internal\setup.bat
-IF ERRORLEVEL 1 goto :eof

.ci/pytorch/windows/cuda118.bat

@@ -1,59 +0,0 @@
-@echo off
-
-set MODULE_NAME=pytorch
-
-IF NOT EXIST "setup.py" IF NOT EXIST "%MODULE_NAME%" (
-    call internal\clone.bat
-    cd %~dp0
-) ELSE (
-    call internal\clean.bat
-)
-IF ERRORLEVEL 1 goto :eof
-
-call internal\check_deps.bat
-IF ERRORLEVEL 1 goto :eof
-
-REM Check for optional components
-
-set USE_CUDA=
-set CMAKE_GENERATOR=Visual Studio 15 2017 Win64
-
-IF "%NVTOOLSEXT_PATH%"=="" (
-    IF EXIST "C:\Program Files\NVIDIA Corporation\NvToolsExt\lib\x64\nvToolsExt64_1.lib"  (
-        set NVTOOLSEXT_PATH=C:\Program Files\NVIDIA Corporation\NvToolsExt
-    ) ELSE (
-        echo NVTX ^(Visual Studio Extension ^for CUDA^) ^not installed, failing
-        exit /b 1
-    )
-)
-
-IF "%CUDA_PATH_V118%"=="" (
-    IF EXIST "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin\nvcc.exe" (
-        set "CUDA_PATH_V118=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8"
-    ) ELSE (
-        echo CUDA 11.8 not found, failing
-        exit /b 1
-    )
-)
-
-IF "%BUILD_VISION%" == "" (
-    set TORCH_CUDA_ARCH_LIST=3.7+PTX;5.0;6.0;6.1;7.0;7.5;8.0;8.6;9.0
-    set TORCH_NVCC_FLAGS=-Xfatbin -compress-all
-) ELSE (
-    set NVCC_FLAGS=-D__CUDA_NO_HALF_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_35,code=sm_35 -gencode=arch=compute_50,code=sm_50 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=compute_80 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_90,code=compute_90
-)
-
-set "CUDA_PATH=%CUDA_PATH_V118%"
-set "PATH=%CUDA_PATH_V118%\bin;%PATH%"
-
-:optcheck
-
-call internal\check_opts.bat
-IF ERRORLEVEL 1 goto :eof
-
-if exist "%NIGHTLIES_PYTORCH_ROOT%" cd %NIGHTLIES_PYTORCH_ROOT%\..
-call  %~dp0\internal\copy.bat
-IF ERRORLEVEL 1 goto :eof
-
-call  %~dp0\internal\setup.bat
-IF ERRORLEVEL 1 goto :eof

.ci/pytorch/windows/cuda124.bat

@@ -1,59 +0,0 @@
-@echo off
-
-set MODULE_NAME=pytorch
-
-IF NOT EXIST "setup.py" IF NOT EXIST "%MODULE_NAME%" (
-    call internal\clone.bat
-    cd %~dp0
-) ELSE (
-    call internal\clean.bat
-)
-IF ERRORLEVEL 1 goto :eof
-
-call internal\check_deps.bat
-IF ERRORLEVEL 1 goto :eof
-
-REM Check for optional components
-
-set USE_CUDA=
-set CMAKE_GENERATOR=Visual Studio 15 2017 Win64
-
-IF "%NVTOOLSEXT_PATH%"=="" (
-    IF EXIST "C:\Program Files\NVIDIA Corporation\NvToolsExt\lib\x64\nvToolsExt64_1.lib"  (
-        set NVTOOLSEXT_PATH=C:\Program Files\NVIDIA Corporation\NvToolsExt
-    ) ELSE (
-        echo NVTX ^(Visual Studio Extension ^for CUDA^) ^not installed, failing
-        exit /b 1
-    )
-)
-
-IF "%CUDA_PATH_V124%"=="" (
-    IF EXIST "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin\nvcc.exe" (
-        set "CUDA_PATH_V124=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
-    ) ELSE (
-        echo CUDA 12.4 not found, failing
-        exit /b 1
-    )
-)
-
-IF "%BUILD_VISION%" == "" (
-    set TORCH_CUDA_ARCH_LIST=5.0;6.0;6.1;7.0;7.5;8.0;8.6;9.0
-    set TORCH_NVCC_FLAGS=-Xfatbin -compress-all
-) ELSE (
-    set NVCC_FLAGS=-D__CUDA_NO_HALF_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_50,code=sm_50 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=compute_80 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_90,code=compute_90
-)
-
-set "CUDA_PATH=%CUDA_PATH_V124%"
-set "PATH=%CUDA_PATH_V124%\bin;%PATH%"
-
-:optcheck
-
-call internal\check_opts.bat
-IF ERRORLEVEL 1 goto :eof
-
-if exist "%NIGHTLIES_PYTORCH_ROOT%" cd %NIGHTLIES_PYTORCH_ROOT%\..
-call  %~dp0\internal\copy.bat
-IF ERRORLEVEL 1 goto :eof
-
-call  %~dp0\internal\setup.bat
-IF ERRORLEVEL 1 goto :eof

.ci/pytorch/windows/cuda126.bat

@@ -1,59 +0,0 @@
-@echo off
-
-set MODULE_NAME=pytorch
-
-IF NOT EXIST "setup.py" IF NOT EXIST "%MODULE_NAME%" (
-    call internal\clone.bat
-    cd %~dp0
-) ELSE (
-    call internal\clean.bat
-)
-IF ERRORLEVEL 1 goto :eof
-
-call internal\check_deps.bat
-IF ERRORLEVEL 1 goto :eof
-
-REM Check for optional components
-
-set USE_CUDA=
-set CMAKE_GENERATOR=Visual Studio 15 2017 Win64
-
-IF "%NVTOOLSEXT_PATH%"=="" (
-    IF EXIST "C:\Program Files\NVIDIA Corporation\NvToolsExt\lib\x64\nvToolsExt64_1.lib"  (
-        set NVTOOLSEXT_PATH=C:\Program Files\NVIDIA Corporation\NvToolsExt
-    ) ELSE (
-        echo NVTX ^(Visual Studio Extension ^for CUDA^) ^not installed, failing
-        exit /b 1
-    )
-)
-
-IF "%CUDA_PATH_V126%"=="" (
-    IF EXIST "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin\nvcc.exe" (
-        set "CUDA_PATH_V126=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6"
-    ) ELSE (
-        echo CUDA 12.6 not found, failing
-        exit /b 1
-    )
-)
-
-IF "%BUILD_VISION%" == "" (
-    set TORCH_CUDA_ARCH_LIST=5.0;6.0;6.1;7.0;7.5;8.0;8.6;9.0
-    set TORCH_NVCC_FLAGS=-Xfatbin -compress-all
-) ELSE (
-    set NVCC_FLAGS=-D__CUDA_NO_HALF_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_50,code=sm_50 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=compute_80 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_90,code=compute_90
-)
-
-set "CUDA_PATH=%CUDA_PATH_V126%"
-set "PATH=%CUDA_PATH_V126%\bin;%PATH%"
-
-:optcheck
-
-call internal\check_opts.bat
-IF ERRORLEVEL 1 goto :eof
-
-if exist "%NIGHTLIES_PYTORCH_ROOT%" cd %NIGHTLIES_PYTORCH_ROOT%\..
-call  %~dp0\internal\copy.bat
-IF ERRORLEVEL 1 goto :eof
-
-call  %~dp0\internal\setup.bat
-IF ERRORLEVEL 1 goto :eof

.ci/pytorch/windows/internal/7z_install.bat

@@ -1,9 +0,0 @@
-@echo off
-
-curl -k https://www.7-zip.org/a/7z1805-x64.exe -O
-if errorlevel 1 exit /b 1
-
-start /wait 7z1805-x64.exe /S
-if errorlevel 1 exit /b 1
-
-set "PATH=%ProgramFiles%\7-Zip;%PATH%"

.ci/pytorch/windows/internal/build_wheels.bat

@@ -1,11 +0,0 @@
-call windows/internal/vc_install_helper.bat
-if errorlevel 1 exit /b 1
-
-call windows/internal/cuda_install.bat
-if errorlevel 1 exit /b 1
-
-call windows/internal/xpu_install.bat
-if errorlevel 1 exit /b 1
-
-call windows/build_pytorch.bat %CUDA_VERSION% %PYTORCH_BUILD_VERSION% %PYTORCH_BUILD_NUMBER%
-if errorlevel 1 exit /b 1

.ci/pytorch/windows/internal/check_deps.bat

@@ -1,80 +0,0 @@
-@echo off
-
-REM Check for necessary components
-echo "Checking dependencies"
-IF NOT "%PROCESSOR_ARCHITECTURE%"=="AMD64" (
-    echo You should use 64 bits Windows to build and run PyTorch
-    exit /b 1
-)
-
-echo "Cmake check"
-IF "%BUILD_VISION%" == "" (
-    where /q cmake.exe
-
-    IF ERRORLEVEL 1 (
-        echo CMake is required to compile PyTorch on Windows
-        exit /b 1
-    )
-)
-
-if not exist "%ProgramFiles(x86)%\Microsoft Visual Studio\Installer\vswhere.exe" (
-    echo Visual Studio %VC_YEAR% C++ BuildTools is required to compile PyTorch on Windows
-    exit /b 1
-)
-
-set VC_VERSION_LOWER=17
-set VC_VERSION_UPPER=18
-if "%VC_YEAR%" == "2019" (
-    set VC_VERSION_LOWER=16
-    set VC_VERSION_UPPER=17
-)
-
-if NOT "%VS15INSTALLDIR%" == "" if exist "%VS15INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" (
-    set "VS15VCVARSALL=%VS15INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat"
-    goto vswhere
-)
-
-for /f "usebackq tokens=*" %%i in (`"%ProgramFiles(x86)%\Microsoft Visual Studio\Installer\vswhere.exe" -legacy -products * -version [%VC_VERSION_LOWER%^,%VC_VERSION_UPPER%^) -property installationPath`) do (
-    if exist "%%i" if exist "%%i\VC\Auxiliary\Build\vcvarsall.bat" (
-        set "VS15INSTALLDIR=%%i"
-        set "VS15VCVARSALL=%%i\VC\Auxiliary\Build\vcvarsall.bat"
-        goto vswhere
-    )
-)
-
-:vswhere
-IF "%VS15VCVARSALL%"=="" (
-    echo Visual Studio %VC_YEAR% C++ BuildTools is required to compile PyTorch on Windows
-    exit /b 1
-)
-
-set MSSdk=1
-set DISTUTILS_USE_SDK=1
-
-where /q python.exe
-
-IF ERRORLEVEL 1 (
-    echo Python x64 3.5 or up is required to compile PyTorch on Windows
-    exit /b 1
-)
-
-for /F "usebackq delims=" %%i in (`python -c "import sys; print('{0[0]}{0[1]}'.format(sys.version_info))"`) do (
-    set /a PYVER=%%i
-)
-
-if  %PYVER% LSS 35 (
-    echo Warning: PyTorch for Python 2 under Windows is experimental.
-    echo Python x64 3.5 or up is recommended to compile PyTorch on Windows
-    echo Maybe you can create a virual environment if you have conda installed:
-    echo ^> conda create -n test python=3.6 pyyaml numpy
-    echo ^> activate test
-)
-
-for /F "usebackq delims=" %%i in (`python -c "import struct;print( 8 * struct.calcsize('P'))"`) do (
-    set /a PYSIZE=%%i
-)
-
-if %PYSIZE% NEQ 64 (
-    echo Python x64 3.5 or up is required to compile PyTorch on Windows
-    exit /b 1
-)

.ci/pytorch/windows/internal/check_opts.bat

@@ -1,47 +0,0 @@
-@echo off
-
-REM Check for optional components
-
-where /q ninja.exe
-
-IF NOT ERRORLEVEL 1 (
-    echo Ninja found, using it to speed up builds
-    set CMAKE_GENERATOR=Ninja
-)
-
-IF "%USE_SCCACHE%" == "0" goto sccache_end
-
-where /q clcache.exe
-
-IF NOT ERRORLEVEL 1 (
-    echo clcache found, using it to speed up builds
-    set CC=clcache
-    set CXX=clcache
-)
-
-where /q sccache-cl.exe
-
-IF NOT ERRORLEVEL 1 (
-    echo sccache-cl found, using it to speed up builds
-    set CC=sccache-cl
-    set CXX=sccache-cl
-)
-
-IF "%CC%" == "sccache-cl" IF "%CXX%" == "sccache-cl" goto sccache_end
-
-where /q sccache.exe
-
-IF NOT ERRORLEVEL 1 (
-    echo sccache found, using it to speed up builds
-    set CC=sccache cl
-    set CXX=sccache cl
-)
-
-:sccache_end
-
-IF exist "%MKLProductDir%\mkl\lib\intel64_win" (
-    echo MKL found, adding it to build
-    set "LIB=%MKLProductDir%\mkl\lib\intel64_win;%MKLProductDir%\compiler\lib\intel64_win;%LIB%";
-)
-
-exit /b 0

.ci/pytorch/windows/internal/clean.bat

@@ -1,5 +0,0 @@
-@echo off
-
-cd %MODULE_NAME%
-python setup.py clean
-cd ..

.ci/pytorch/windows/internal/clone.bat

@@ -1,51 +0,0 @@
-@echo off
-
-:: The conda and wheels jobs are separated on Windows, so we don't need to clone again.
-if not exist "%NIGHTLIES_PYTORCH_ROOT%" goto clone_pytorch
-echo "Changing to NIGHTLIES_PYTORCH_ROOT"
-cd "%NIGHTLIES_PYTORCH_ROOT%"
-goto submodule
-
-:clone_pytorch
-
-git clone https://github.com/%PYTORCH_REPO%/%MODULE_NAME%
-
-cd %MODULE_NAME%
-
-IF NOT "%PYTORCH_BRANCH%" == "latest" goto latest_end
-
-:latest_start
-
-if NOT "%NIGHTLIES_DATE%" == "" goto date_end
-
-:date_start
-
-set "DATE_CMD=Get-Date ([System.TimeZoneInfo]::ConvertTimeFromUtc((Get-Date).ToUniversalTime(), [System.TimeZoneInfo]::FindSystemTimeZoneById('Pacific Standard Time'))) -f 'yyyy_MM_dd'"
-set "DATE_COMPACT_CMD=Get-Date ([System.TimeZoneInfo]::ConvertTimeFromUtc((Get-Date).ToUniversalTime(), [System.TimeZoneInfo]::FindSystemTimeZoneById('Pacific Standard Time'))) -f 'yyyyMMdd'"
-
-FOR /F "delims=" %%i IN ('powershell -c "%DATE_CMD%"') DO set NIGHTLIES_DATE=%%i
-FOR /F "delims=" %%i IN ('powershell -c "%DATE_COMPACT_CMD%"') DO set NIGHTLIES_DATE_COMPACT=%%i
-
-:date_end
-
-if "%NIGHTLIES_DATE_COMPACT%" == "" set NIGHTLIES_DATE_COMPACT=%NIGHTLIES_DATE:~0,4%%NIGHTLIES_DATE:~5,2%%NIGHTLIES_DATE:~8,2%
-
-:: Switch to the latest commit by 11:59 yesterday
-echo PYTORCH_BRANCH is set to latest so I will find the last commit
-echo before 0:00 midnight on %NIGHTLIES_DATE%
-set git_date=%NIGHTLIES_DATE:_=-%
-FOR /F "delims=" %%i IN ('git log --before %git_date% -n 1 "--pretty=%%H"') DO set last_commit=%%i
-echo Setting PYTORCH_BRANCH to %last_commit% since that was the last
-echo commit before %NIGHTLIES_DATE%
-set PYTORCH_BRANCH=%last_commit%
-
-:latest_end
-
-IF "%PYTORCH_BRANCH%" == "" set PYTORCH_BRANCH=v%PYTORCH_BUILD_VERSION%
-git checkout %PYTORCH_BRANCH%
-IF ERRORLEVEL 1 git checkout tags/%PYTORCH_BRANCH%
-
-:submodule
-
-git submodule update --init --recursive
-IF ERRORLEVEL 1 exit /b 1

.ci/pytorch/windows/internal/copy.bat

@@ -1,26 +0,0 @@
-copy "%CUDA_PATH%\bin\cusparse*64_*.dll*" pytorch\torch\lib
-copy "%CUDA_PATH%\bin\cublas*64_*.dll*" pytorch\torch\lib
-copy "%CUDA_PATH%\bin\cudart*64_*.dll*" pytorch\torch\lib
-copy "%CUDA_PATH%\bin\curand*64_*.dll*" pytorch\torch\lib
-copy "%CUDA_PATH%\bin\cufft*64_*.dll*" pytorch\torch\lib
-copy "%CUDA_PATH%\bin\cusolver*64_*.dll*" pytorch\torch\lib
-
-copy "%CUDA_PATH%\bin\cudnn*64_*.dll*" pytorch\torch\lib
-copy "%CUDA_PATH%\bin\nvrtc*64_*.dll*" pytorch\torch\lib
-copy "%CUDA_PATH%\extras\CUPTI\lib64\cupti64_*.dll*" pytorch\torch\lib
-
-copy "C:\Program Files\NVIDIA Corporation\NvToolsExt\bin\x64\nvToolsExt64_1.dll*" pytorch\torch\lib
-copy "%CONDA_LIB_PATH%\libiomp*5md.dll" pytorch\torch\lib
-
-:: Should be set in build_pytorch.bat
-copy "%libuv_ROOT%\bin\uv.dll" pytorch\torch\lib
-
-::copy zlib if it exist in windows/system32
-if exist "C:\Windows\System32\zlibwapi.dll" (
-    copy "C:\Windows\System32\zlibwapi.dll"  pytorch\torch\lib
-)
-
-::copy nvJitLink dll is requires for cuda 12+
-if exist "%CUDA_PATH%\bin\nvJitLink_*.dll*" (
-    copy "%CUDA_PATH%\bin\nvJitLink_*.dll*"  pytorch\torch\lib
-)

.ci/pytorch/windows/internal/copy_cpu.bat

@@ -1,3 +0,0 @@
-copy "%CONDA_LIB_PATH%\libiomp*5md.dll" pytorch\torch\lib
-:: Should be set in build_pytorch.bat
-copy "%libuv_ROOT%\bin\uv.dll" pytorch\torch\lib

.ci/pytorch/windows/internal/cuda_install.bat

@@ -1,190 +0,0 @@
-@echo on
-
-if "%CUDA_VERSION%" == "cpu" (
-    echo Skipping for CPU builds
-    exit /b 0
-)
-if "%CUDA_VERSION%" == "xpu" (
-    echo Skipping for XPU builds
-    exit /b 0
-)
-
-set SRC_DIR=%NIGHTLIES_PYTORCH_ROOT%
-if not exist "%SRC_DIR%\temp_build" mkdir "%SRC_DIR%\temp_build"
-
-set /a CUDA_VER=%CUDA_VERSION%
-set CUDA_VER_MAJOR=%CUDA_VERSION:~0,-1%
-set CUDA_VER_MINOR=%CUDA_VERSION:~-1,1%
-set CUDA_VERSION_STR=%CUDA_VER_MAJOR%.%CUDA_VER_MINOR%
-set CUDNN_FOLDER="cuda"
-set CUDNN_LIB_FOLDER="lib\x64"
-
-:: Skip all of this if we already have cuda installed
-if exist "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%\bin\nvcc.exe" goto set_cuda_env_vars
-
-if %CUDA_VER% EQU 118 goto cuda118
-if %CUDA_VER% EQU 121 goto cuda121
-if %CUDA_VER% EQU 124 goto cuda124
-if %CUDA_VER% EQU 126 goto cuda126
-
-echo CUDA %CUDA_VERSION_STR% is not supported
-exit /b 1
-
-:cuda118
-
-set CUDA_INSTALL_EXE=cuda_11.8.0_522.06_windows.exe
-if not exist "%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%" (
-    curl -k -L "https://ossci-windows.s3.amazonaws.com/%CUDA_INSTALL_EXE%" --output "%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%"
-    if errorlevel 1 exit /b 1
-    set "CUDA_SETUP_FILE=%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%"
-    set "ARGS=cuda_profiler_api_11.8 thrust_11.8 nvcc_11.8 cuobjdump_11.8 nvprune_11.8 nvprof_11.8 cupti_11.8 cublas_11.8 cublas_dev_11.8 cudart_11.8 cufft_11.8 cufft_dev_11.8 curand_11.8 curand_dev_11.8 cusolver_11.8 cusolver_dev_11.8 cusparse_11.8 cusparse_dev_11.8 npp_11.8 npp_dev_11.8 nvrtc_11.8 nvrtc_dev_11.8 nvml_dev_11.8 nvtx_11.8"
-)
-
-set CUDNN_FOLDER=cudnn-windows-x86_64-9.5.0.50_cuda11-archive
-set CUDNN_LIB_FOLDER="lib"
-set "CUDNN_INSTALL_ZIP=%CUDNN_FOLDER%.zip"
-if not exist "%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%" (
-    curl -k -L "http://s3.amazonaws.com/ossci-windows/%CUDNN_INSTALL_ZIP%" --output "%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%"
-    if errorlevel 1 exit /b 1
-    set "CUDNN_SETUP_FILE=%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%"
-)
-
-@REM cuDNN 8.3+ required zlib to be installed on the path
-echo Installing ZLIB dlls
-curl -k -L "http://s3.amazonaws.com/ossci-windows/zlib123dllx64.zip" --output "%SRC_DIR%\temp_build\zlib123dllx64.zip"
-7z x "%SRC_DIR%\temp_build\zlib123dllx64.zip" -o"%SRC_DIR%\temp_build\zlib"
-xcopy /Y "%SRC_DIR%\temp_build\zlib\dll_x64\*.dll" "C:\Windows\System32"
-
-goto cuda_common
-
-:cuda124
-
-set CUDA_INSTALL_EXE=cuda_12.4.0_551.61_windows.exe
-if not exist "%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%" (
-    curl -k -L "https://ossci-windows.s3.amazonaws.com/%CUDA_INSTALL_EXE%" --output "%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%"
-    if errorlevel 1 exit /b 1
-    set "CUDA_SETUP_FILE=%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%"
-    set "ARGS=cuda_profiler_api_12.4 thrust_12.4 nvcc_12.4 cuobjdump_12.4 nvprune_12.4 nvprof_12.4 cupti_12.4 cublas_12.4 cublas_dev_12.4 cudart_12.4 cufft_12.4 cufft_dev_12.4 curand_12.4 curand_dev_12.4 cusolver_12.4 cusolver_dev_12.4 cusparse_12.4 cusparse_dev_12.4 npp_12.4 npp_dev_12.4 nvrtc_12.4 nvrtc_dev_12.4 nvml_dev_12.4 nvjitlink_12.4 nvtx_12.4"
-)
-
-set CUDNN_FOLDER=cudnn-windows-x86_64-9.5.0.50_cuda12-archive
-set CUDNN_LIB_FOLDER="lib"
-set "CUDNN_INSTALL_ZIP=%CUDNN_FOLDER%.zip"
-if not exist "%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%" (
-    curl -k -L "http://s3.amazonaws.com/ossci-windows/%CUDNN_INSTALL_ZIP%" --output "%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%"
-    if errorlevel 1 exit /b 1
-    set "CUDNN_SETUP_FILE=%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%"
-)
-
-@REM cuDNN 8.3+ required zlib to be installed on the path
-echo Installing ZLIB dlls
-curl -k -L "http://s3.amazonaws.com/ossci-windows/zlib123dllx64.zip" --output "%SRC_DIR%\temp_build\zlib123dllx64.zip"
-7z x "%SRC_DIR%\temp_build\zlib123dllx64.zip" -o"%SRC_DIR%\temp_build\zlib"
-xcopy /Y "%SRC_DIR%\temp_build\zlib\dll_x64\*.dll" "C:\Windows\System32"
-
-goto cuda_common
-
-:cuda126
-
-set CUDA_INSTALL_EXE=cuda_12.6.2_560.94_windows.exe
-if not exist "%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%" (
-    curl -k -L "https://ossci-windows.s3.amazonaws.com/%CUDA_INSTALL_EXE%" --output "%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%"
-    if errorlevel 1 exit /b 1
-    set "CUDA_SETUP_FILE=%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%"
-    set "ARGS=cuda_profiler_api_12.6 thrust_12.6 nvcc_12.6 cuobjdump_12.6 nvprune_12.6 nvprof_12.6 cupti_12.6 cublas_12.6 cublas_dev_12.6 cudart_12.6 cufft_12.6 cufft_dev_12.6 curand_12.6 curand_dev_12.6 cusolver_12.6 cusolver_dev_12.6 cusparse_12.6 cusparse_dev_12.6 npp_12.6 npp_dev_12.6 nvrtc_12.6 nvrtc_dev_12.6 nvml_dev_12.6 nvjitlink_12.6 nvtx_12.6"
-)
-
-set CUDNN_FOLDER=cudnn-windows-x86_64-9.5.0.50_cuda12-archive
-set CUDNN_LIB_FOLDER="lib"
-set "CUDNN_INSTALL_ZIP=%CUDNN_FOLDER%.zip"
-if not exist "%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%" (
-    curl -k -L "http://s3.amazonaws.com/ossci-windows/%CUDNN_INSTALL_ZIP%" --output "%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%"
-    if errorlevel 1 exit /b 1
-    set "CUDNN_SETUP_FILE=%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%"
-)
-
-@REM cuDNN 8.3+ required zlib to be installed on the path
-echo Installing ZLIB dlls
-curl -k -L "http://s3.amazonaws.com/ossci-windows/zlib123dllx64.zip" --output "%SRC_DIR%\temp_build\zlib123dllx64.zip"
-7z x "%SRC_DIR%\temp_build\zlib123dllx64.zip" -o"%SRC_DIR%\temp_build\zlib"
-xcopy /Y "%SRC_DIR%\temp_build\zlib\dll_x64\*.dll" "C:\Windows\System32"
-
-goto cuda_common
-
-:cuda_common
-:: NOTE: We only install CUDA if we don't have it installed already.
-:: With GHA runners these should be pre-installed as part of our AMI process
-:: If you cannot find the CUDA version you want to build for here then please
-:: add it @ https://github.com/pytorch/test-infra/tree/main/aws/ami/windows
-if not exist "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%\bin\nvcc.exe" (
-    if not exist "%SRC_DIR%\temp_build\NvToolsExt.7z" (
-        curl -k -L https://ossci-windows.s3.us-east-1.amazonaws.com/builder/NvToolsExt.7z --output "%SRC_DIR%\temp_build\NvToolsExt.7z"
-        if errorlevel 1 exit /b 1
-    )
-
-    if not exist "%SRC_DIR%\temp_build\gpu_driver_dlls.zip" (
-        curl -k -L "https://ossci-windows.s3.us-east-1.amazonaws.com/builder/additional_dlls.zip" --output "%SRC_DIR%\temp_build\gpu_driver_dlls.zip"
-        if errorlevel 1 exit /b 1
-    )
-
-    echo Installing CUDA toolkit...
-    7z x %CUDA_SETUP_FILE% -o"%SRC_DIR%\temp_build\cuda"
-    pushd "%SRC_DIR%\temp_build\cuda"
-
-    sc config wuauserv start= disabled
-    sc stop wuauserv
-    sc query wuauserv
-
-    start /wait setup.exe -s %ARGS% -loglevel:6 -log:"%cd%/cuda_install_logs"
-    echo %errorlevel%
-
-    popd
-
-    echo Installing VS integration...
-    if "%VC_YEAR%" == "2019" (
-        xcopy /Y "%SRC_DIR%\temp_build\cuda\CUDAVisualStudioIntegration\extras\visual_studio_integration\MSBuildExtensions\*.*" "C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\MSBuild\Microsoft\VC\v160\BuildCustomizations"
-    )
-    if "%VC_YEAR%" == "2022" (
-        xcopy /Y "%SRC_DIR%\temp_build\cuda\CUDAVisualStudioIntegration\extras\visual_studio_integration\MSBuildExtensions\*.*" "C:\Program Files (x86)\Microsoft Visual Studio\2022\BuildTools\MSBuild\Microsoft\VC\v170\BuildCustomizations"
-    )
-
-    echo Installing NvToolsExt...
-    7z x %SRC_DIR%\temp_build\NvToolsExt.7z -o"%SRC_DIR%\temp_build\NvToolsExt"
-    mkdir "%ProgramFiles%\NVIDIA Corporation\NvToolsExt\bin\x64"
-    mkdir "%ProgramFiles%\NVIDIA Corporation\NvToolsExt\include"
-    mkdir "%ProgramFiles%\NVIDIA Corporation\NvToolsExt\lib\x64"
-    xcopy /Y "%SRC_DIR%\temp_build\NvToolsExt\bin\x64\*.*" "%ProgramFiles%\NVIDIA Corporation\NvToolsExt\bin\x64"
-    xcopy /Y "%SRC_DIR%\temp_build\NvToolsExt\include\*.*" "%ProgramFiles%\NVIDIA Corporation\NvToolsExt\include"
-    xcopy /Y "%SRC_DIR%\temp_build\NvToolsExt\lib\x64\*.*" "%ProgramFiles%\NVIDIA Corporation\NvToolsExt\lib\x64"
-
-    echo Installing cuDNN...
-    7z x %CUDNN_SETUP_FILE% -o"%SRC_DIR%\temp_build\cudnn"
-    xcopy /Y "%SRC_DIR%\temp_build\cudnn\%CUDNN_FOLDER%\bin\*.*" "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%\bin"
-    xcopy /Y "%SRC_DIR%\temp_build\cudnn\%CUDNN_FOLDER%\%CUDNN_LIB_FOLDER%\*.*" "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%\lib\x64"
-    xcopy /Y "%SRC_DIR%\temp_build\cudnn\%CUDNN_FOLDER%\include\*.*" "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%\include"
-
-    echo Installing GPU driver DLLs
-    7z x %SRC_DIR%\temp_build\gpu_driver_dlls.zip -o"C:\Windows\System32"
-
-    echo Cleaning temp files
-    rd /s /q "%SRC_DIR%\temp_build" || ver > nul
-
-    if not exist "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%\bin\nvcc.exe" (
-        echo CUDA %CUDA_VERSION_STR% installed failed.
-        echo --------- setup.exe.log -------
-        type "%SRC_DIR%\temp_build\cuda\cuda_install_logs\LOG.setup.exe.log"
-        echo --------- RunDll32.exe.log
-        type "%SRC_DIR%\temp_build\cuda\cuda_install_logs\LOG.RunDll32.exe.log"
-        exit /b 1
-    )
-)
-
-goto set_cuda_env_vars
-
-:set_cuda_env_vars
-
-echo Setting up environment...
-set "PATH=%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%\bin;%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%\libnvvp;%PATH%"
-set "CUDA_PATH=%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%"
-set "CUDA_PATH_V%CUDA_VER_MAJOR%_%CUDA_VER_MINOR%=%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%"
-set "NVTOOLSEXT_PATH=%ProgramFiles%\NVIDIA Corporation\NvToolsExt"

.ci/pytorch/windows/internal/driver_update.bat

@@ -1,9 +0,0 @@
-set WIN_DRIVER_VN=528.89
-set "DRIVER_DOWNLOAD_LINK=https://ossci-windows.s3.amazonaws.com/%WIN_DRIVER_VN%-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe"
-curl --retry 3 -kL %DRIVER_DOWNLOAD_LINK% --output %WIN_DRIVER_VN%-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe
-if errorlevel 1 exit /b 1
-
-start /wait %WIN_DRIVER_VN%-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe -s -noreboot
-if errorlevel 1 exit /b 1
-
-del %WIN_DRIVER_VN%-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe || ver > NUL

.ci/pytorch/windows/internal/env_fix.bat

@@ -1,38 +0,0 @@
-@echo off
-
-:: Caution: Please don't use this script locally
-:: It may destroy your build environment.
-
-setlocal
-
-if not exist "%ProgramFiles(x86)%\Microsoft Visual Studio\Installer\vswhere.exe" (
-    echo Visual Studio %VC_YEAR% C++ BuildTools is required to compile PyTorch on Windows
-    exit /b 1
-)
-
-set VC_VERSION_LOWER=17
-set VC_VERSION_UPPER=18
-if "%VC_YEAR%" == "2019" (
-    set VC_VERSION_LOWER=16
-    set VC_VERSION_UPPER=17
-)
-
-for /f "usebackq tokens=*" %%i in (`"%ProgramFiles(x86)%\Microsoft Visual Studio\Installer\vswhere.exe" -legacy -products * -version [%VC_VERSION_LOWER%^,%VC_VERSION_UPPER%^) -property installationPath`) do (
-    if exist "%%i" if exist "%%i\VC\Auxiliary\Build\vcvarsall.bat" (
-        set "VS15INSTALLDIR=%%i"
-        set "VS15VCVARSALL=%%i\VC\Auxiliary\Build\vcvarsall.bat"
-        goto vswhere
-    )
-)
-
-:vswhere
-
-if "%VS15VCVARSALL%"=="" (
-    echo Visual Studio %VC_YEAR% C++ BuildTools is required to compile PyTorch on Windows
-    exit /b 1
-)
-
-call "%VS15VCVARSALL%" x86_amd64
-for /f "usebackq tokens=*" %%i in (`where link.exe`) do move "%%i" "%%i.bak"
-
-endlocal

.ci/pytorch/windows/internal/setup.bat

@@ -1,106 +0,0 @@
-@echo off
-
-echo The flags after configuring:
-echo USE_CUDA=%USE_CUDA%
-echo CMAKE_GENERATOR=%CMAKE_GENERATOR%
-if "%USE_CUDA%"==""  echo CUDA_PATH=%CUDA_PATH%
-if NOT "%CC%"==""   echo CC=%CC%
-if NOT "%CXX%"==""  echo CXX=%CXX%
-if NOT "%DISTUTILS_USE_SDK%"==""  echo DISTUTILS_USE_SDK=%DISTUTILS_USE_SDK%
-
-set SRC_DIR=%NIGHTLIES_PYTORCH_ROOT%
-
-IF "%VSDEVCMD_ARGS%" == "" (
-    call "%VS15VCVARSALL%" x64
-) ELSE (
-    call "%VS15VCVARSALL%" x64 %VSDEVCMD_ARGS%
-)
-
-pushd %SRC_DIR%
-
-IF NOT exist "setup.py" (
-    cd %MODULE_NAME%
-)
-
-if "%CXX%"=="sccache cl" goto sccache_start
-if "%CXX%"=="sccache-cl" goto sccache_start
-goto sccache_end
-
-:sccache_start
-set SCCACHE_IDLE_TIMEOUT=0
-
-sccache --stop-server
-sccache --start-server
-sccache --zero-stats
-
-:sccache_end
-
-
-if "%BUILD_PYTHONLESS%" == "" goto pytorch else goto libtorch
-
-:libtorch
-set VARIANT=shared-with-deps
-
-mkdir libtorch
-mkdir libtorch\bin
-mkdir libtorch\cmake
-mkdir libtorch\include
-mkdir libtorch\lib
-mkdir libtorch\share
-mkdir libtorch\test
-
-mkdir build
-pushd build
-python ../tools/build_libtorch.py
-popd
-
-IF ERRORLEVEL 1 exit /b 1
-IF NOT ERRORLEVEL 0 exit /b 1
-
-move /Y torch\bin\*.* libtorch\bin\
-move /Y torch\cmake\*.* libtorch\cmake\
-robocopy /move /e torch\include\ libtorch\include\
-move /Y torch\lib\*.* libtorch\lib\
-robocopy /move /e torch\share\ libtorch\share\
-move /Y torch\test\*.* libtorch\test\
-
-move /Y libtorch\bin\*.dll libtorch\lib\
-
-echo %PYTORCH_BUILD_VERSION% > libtorch\build-version
-git rev-parse HEAD > libtorch\build-hash
-
-IF "%DEBUG%" == "" (
-    set LIBTORCH_PREFIX=libtorch-win-%VARIANT%
-) ELSE (
-    set LIBTORCH_PREFIX=libtorch-win-%VARIANT%-debug
-)
-
-7z a -tzip "%LIBTORCH_PREFIX%-%PYTORCH_BUILD_VERSION%.zip" libtorch\*
-:: Cleanup raw data to save space
-rmdir /s /q libtorch
-
-if not exist ..\output mkdir ..\output
-copy /Y "%LIBTORCH_PREFIX%-%PYTORCH_BUILD_VERSION%.zip" "%PYTORCH_FINAL_PACKAGE_DIR%\"
-copy /Y "%LIBTORCH_PREFIX%-%PYTORCH_BUILD_VERSION%.zip" "%PYTORCH_FINAL_PACKAGE_DIR%\%LIBTORCH_PREFIX%-latest.zip"
-
-goto build_end
-
-:pytorch
-python setup.py bdist_wheel -d "%PYTORCH_FINAL_PACKAGE_DIR%"
-
-:build_end
-IF ERRORLEVEL 1 exit /b 1
-IF NOT ERRORLEVEL 0 exit /b 1
-
-if "%CXX%"=="sccache cl" goto sccache_cleanup
-if "%CXX%"=="sccache-cl" goto sccache_cleanup
-goto sccache_cleanup_end
-
-:sccache_cleanup
-sccache --show-stats
-taskkill /im sccache.exe /f /t || ver > nul
-taskkill /im nvcc.exe /f /t || ver > nul
-
-:sccache_cleanup_end
-
-cd ..

.ci/pytorch/windows/internal/smoke_test.bat

@@ -1,242 +0,0 @@
-set SRC_DIR=%~dp0
-
-pushd %SRC_DIR%\..
-
-if not "%CUDA_VERSION%" == "cpu" if not "%CUDA_VERSION%" == "xpu" call internal\driver_update.bat
-if errorlevel 1 exit /b 1
-
-if "%CUDA_VERSION%" == "xpu" (
-    call internal\xpu_install.bat
-    if errorlevel 1 exit /b 1
-    call "%ProgramFiles(x86)%\Intel\oneAPI\setvars.bat"
-    if errorlevel 1 exit /b 1
-)
-
-set "ORIG_PATH=%PATH%"
-
-setlocal EnableDelayedExpansion
-set NVIDIA_GPU_EXISTS=0
-for /F "delims=" %%i in ('wmic path win32_VideoController get name') do (
-    set GPUS=%%i
-    if not "x!GPUS:NVIDIA=!" == "x!GPUS!" (
-        SET NVIDIA_GPU_EXISTS=1
-        goto gpu_check_end
-    )
-)
-:gpu_check_end
-endlocal & set NVIDIA_GPU_EXISTS=%NVIDIA_GPU_EXISTS%
-
-if "%PACKAGE_TYPE%" == "wheel" goto wheel
-if "%PACKAGE_TYPE%" == "conda" goto conda
-if "%PACKAGE_TYPE%" == "libtorch" goto libtorch
-
-echo "unknown package type"
-exit /b 1
-
-:wheel
-echo "install wheel package"
-
-set PYTHON_INSTALLER_URL=
-if "%DESIRED_PYTHON%" == "3.13" set "PYTHON_INSTALLER_URL=https://www.python.org/ftp/python/3.13.0/python-3.13.0-amd64.exe"
-if "%DESIRED_PYTHON%" == "3.12" set "PYTHON_INSTALLER_URL=https://www.python.org/ftp/python/3.12.0/python-3.12.0-amd64.exe"
-if "%DESIRED_PYTHON%" == "3.11" set "PYTHON_INSTALLER_URL=https://www.python.org/ftp/python/3.11.0/python-3.11.0-amd64.exe"
-if "%DESIRED_PYTHON%" == "3.10" set "PYTHON_INSTALLER_URL=https://www.python.org/ftp/python/3.10.0/python-3.10.0-amd64.exe"
-if "%DESIRED_PYTHON%" == "3.9" set "PYTHON_INSTALLER_URL=https://www.python.org/ftp/python/3.9.0/python-3.9.0-amd64.exe"
-if "%DESIRED_PYTHON%" == "3.8" set "PYTHON_INSTALLER_URL=https://www.python.org/ftp/python/3.8.2/python-3.8.2-amd64.exe"
-if "%PYTHON_INSTALLER_URL%" == "" (
-    echo Python %DESIRED_PYTHON% not supported yet
-)
-
-del python-amd64.exe
-curl --retry 3 -kL "%PYTHON_INSTALLER_URL%" --output python-amd64.exe
-if errorlevel 1 exit /b 1
-
-:: According to https://docs.python.org/3/using/windows.html, setting PrependPath to 1 will prepend
-:: the installed Python to PATH system-wide. Even calling set PATH=%ORIG_PATH% later on won't make
-:: a change. As the builder directory will be removed after the smoke test, all subsequent non-binary
-:: jobs will fail to find any Python executable there
-start /wait "" python-amd64.exe /quiet InstallAllUsers=1 PrependPath=0 Include_test=0 TargetDir=%CD%\Python
-if errorlevel 1 exit /b 1
-
-set "PATH=%CD%\Python%PYTHON_VERSION%\Scripts;%CD%\Python;%PATH%"
-
-if "%DESIRED_PYTHON%" == "3.13" pip install -q --pre numpy==2.1.0 protobuf
-if "%DESIRED_PYTHON%" == "3.12" pip install -q --pre numpy==2.0.2 protobuf
-if "%DESIRED_PYTHON%" == "3.11" pip install -q --pre numpy==2.0.2 protobuf
-if "%DESIRED_PYTHON%" == "3.10" pip install -q --pre numpy==2.0.2 protobuf
-if "%DESIRED_PYTHON%" == "3.9" pip install -q --pre numpy==2.0.2 protobuf
-if "%DESIRED_PYTHON%" == "3.8" pip install -q numpy protobuf
-
-if errorlevel 1 exit /b 1
-
-for /F "delims=" %%i in ('where /R "%PYTORCH_FINAL_PACKAGE_DIR:/=\%" *.whl') do pip install "%%i"
-if errorlevel 1 exit /b 1
-
-goto smoke_test
-
-:conda
-echo "install conda package"
-
-:: Install Miniconda3
-set "CONDA_HOME=%CD%\conda"
-set "tmp_conda=%CONDA_HOME%"
-set "miniconda_exe=%CD%\miniconda.exe"
-set "CONDA_EXTRA_ARGS=cpuonly -c pytorch-nightly"
-if "%CUDA_VERSION%" == "118" (
-    set "CONDA_EXTRA_ARGS=pytorch-cuda=11.8 -c nvidia -c pytorch-nightly"
-)
-if "%CUDA_VERSION%" == "121" (
-    set "CONDA_EXTRA_ARGS=pytorch-cuda=12.1 -c nvidia -c pytorch-nightly"
-)
-if "%CUDA_VERSION%" == "124" (
-    set "CONDA_EXTRA_ARGS=pytorch-cuda=12.4 -c nvidia -c pytorch-nightly"
-)
-if "%CUDA_VERSION%" == "126" (
-    set "CONDA_EXTRA_ARGS=pytorch-cuda=12.6 -c nvidia -c pytorch-nightly"
-)
-
-rmdir /s /q conda
-del miniconda.exe
-curl -k https://repo.anaconda.com/miniconda/Miniconda3-latest-Windows-x86_64.exe -o "%miniconda_exe%"
-start /wait "" "%miniconda_exe%" /S /InstallationType=JustMe /RegisterPython=0 /AddToPath=0 /D=%tmp_conda%
-if ERRORLEVEL 1 exit /b 1
-
-set "PATH=%CONDA_HOME%;%CONDA_HOME%\scripts;%CONDA_HOME%\Library\bin;%PATH%"
-
-conda create -qyn testenv python=%DESIRED_PYTHON%
-if errorlevel 1 exit /b 1
-call conda install -yq conda-build
-if errorlevel 1 exit /b 1
-call %CONDA_HOME%\condabin\activate.bat testenv
-if errorlevel 1 exit /b 1
-set "NO_ARCH_PATH=%PYTORCH_FINAL_PACKAGE_DIR:/=\%\noarch"
-mkdir %NO_ARCH_PATH%
-for /F "delims=" %%i in ('where /R "%PYTORCH_FINAL_PACKAGE_DIR:/=\%" *') do xcopy "%%i" %NO_ARCH_PATH% /Y
-if ERRORLEVEL 1 exit /b 1
-call conda index %PYTORCH_FINAL_PACKAGE_DIR%
-if errorlevel 1 exit /b 1
-call conda install -yq -c "file:///%PYTORCH_FINAL_PACKAGE_DIR%" pytorch==%PYTORCH_BUILD_VERSION% -c pytorch -c numba/label/dev -c nvidia
-if ERRORLEVEL 1 exit /b 1
-call conda install -yq numpy
-if ERRORLEVEL 1 exit /b 1
-
-set /a CUDA_VER=%CUDA_VERSION%
-set CUDA_VER_MAJOR=%CUDA_VERSION:~0,-1%
-set CUDA_VER_MINOR=%CUDA_VERSION:~-1,1%
-set CUDA_VERSION_STR=%CUDA_VER_MAJOR%.%CUDA_VER_MINOR%
-
-:: Install package we just build
-
-
-:smoke_test
-python -c "import torch"
-if ERRORLEVEL 1 exit /b 1
-
-echo Checking that MKL is available
-python -c "import torch; exit(0 if torch.backends.mkl.is_available() else 1)"
-if ERRORLEVEL 1 exit /b 1
-
-if "%NVIDIA_GPU_EXISTS%" == "0" (
-    echo "Skip CUDA tests for machines without a Nvidia GPU card"
-    goto end
-)
-
-echo Checking that CUDA archs are setup correctly
-python -c "import torch; torch.randn([3,5]).cuda()"
-if ERRORLEVEL 1 exit /b 1
-
-echo Checking that magma is available
-python -c "import torch; torch.rand(1).cuda(); exit(0 if torch.cuda.has_magma else 1)"
-if ERRORLEVEL 1 exit /b 1
-
-echo Checking that CuDNN is available
-python -c "import torch; exit(0 if torch.backends.cudnn.is_available() else 1)"
-if ERRORLEVEL 1 exit /b 1
-
-echo Checking that basic RNN works
-python %PYTORCH_ROOT%\.ci\pytorch\test_example_code\rnn_smoke.py
-
-if ERRORLEVEL 1 exit /b 1
-
-echo Checking that basic CNN works
-python %PYTORCH_ROOT%\.ci\pytorch\test_example_code\cnn_smoke.py
-if ERRORLEVEL 1 exit /b 1
-
-goto end
-
-:libtorch
-echo "install and test libtorch"
-
-if "%VC_YEAR%" == "2019" powershell internal\vs2019_install.ps1
-if "%VC_YEAR%" == "2022" powershell internal\vs2022_install.ps1
-
-if ERRORLEVEL 1 exit /b 1
-
-for /F "delims=" %%i in ('where /R "%PYTORCH_FINAL_PACKAGE_DIR:/=\%" *-latest.zip') do 7z x "%%i" -otmp
-if ERRORLEVEL 1 exit /b 1
-
-pushd tmp\libtorch
-
-set VC_VERSION_LOWER=17
-set VC_VERSION_UPPER=18
-IF "%VC_YEAR%" == "2019" (
-    set VC_VERSION_LOWER=16
-    set VC_VERSION_UPPER=17
-)
-
-for /f "usebackq tokens=*" %%i in (`"%ProgramFiles(x86)%\Microsoft Visual Studio\Installer\vswhere.exe" -legacy -products * -version [%VC_VERSION_LOWER%^,%VC_VERSION_UPPER%^) -property installationPath`) do (
-    if exist "%%i" if exist "%%i\VC\Auxiliary\Build\vcvarsall.bat" (
-        set "VS15INSTALLDIR=%%i"
-        set "VS15VCVARSALL=%%i\VC\Auxiliary\Build\vcvarsall.bat"
-        goto vswhere
-    )
-)
-
-:vswhere
-IF "%VS15VCVARSALL%"=="" (
-    echo Visual Studio %VC_YEAR% C++ BuildTools is required to compile PyTorch test on Windows
-    exit /b 1
-)
-call "%VS15VCVARSALL%" x64
-
-set install_root=%CD%
-set INCLUDE=%INCLUDE%;%install_root%\include;%install_root%\include\torch\csrc\api\include
-set LIB=%LIB%;%install_root%\lib
-set PATH=%PATH%;%install_root%\lib
-
-cl %PYTORCH_ROOT%\.ci\pytorch\test_example_code\simple-torch-test.cpp c10.lib torch_cpu.lib /EHsc /std:c++17
-if ERRORLEVEL 1 exit /b 1
-
-.\simple-torch-test.exe
-if ERRORLEVEL 1 exit /b 1
-
-cl %PYTORCH_ROOT%\.ci\pytorch\test_example_code\check-torch-mkl.cpp c10.lib torch_cpu.lib /EHsc /std:c++17
-if ERRORLEVEL 1 exit /b 1
-
-.\check-torch-mkl.exe
-if ERRORLEVEL 1 exit /b 1
-
-if "%NVIDIA_GPU_EXISTS%" == "0" (
-    echo "Skip CUDA tests for machines without a Nvidia GPU card"
-    goto end
-)
-
-set BUILD_SPLIT_CUDA=
-if exist "%install_root%\lib\torch_cuda_cu.lib" if exist "%install_root%\lib\torch_cuda_cpp.lib" set BUILD_SPLIT_CUDA=ON
-
-if "%BUILD_SPLIT_CUDA%" == "ON" (
-    cl %PYTORCH_ROOT%\.ci\pytorch\test_example_code\check-torch-cuda.cpp torch_cpu.lib c10.lib torch_cuda_cu.lib torch_cuda_cpp.lib /EHsc /std:c++17 /link /INCLUDE:?warp_size@cuda@at@@YAHXZ /INCLUDE:?_torch_cuda_cu_linker_symbol_op_cuda@native@at@@YA?AVTensor@2@AEBV32@@Z
-) else (
-    cl %PYTORCH_ROOT%\.ci\pytorch\test_example_code\check-torch-cuda.cpp torch_cpu.lib c10.lib torch_cuda.lib /EHsc /std:c++17 /link /INCLUDE:?warp_size@cuda@at@@YAHXZ
-)
-.\check-torch-cuda.exe
-if ERRORLEVEL 1 exit /b 1
-
-popd
-
-echo Cleaning temp files
-rd /s /q "tmp" || ver > nul
-
-:end
-set "PATH=%ORIG_PATH%"
-popd

.ci/pytorch/windows/internal/static_lib_test.bat

@@ -1,132 +0,0 @@
-set SRC_DIR=%~dp0
-
-pushd %SRC_DIR%\..
-
-if "%CUDA_VERSION%" == "cpu" call internal\driver_update.bat
-if errorlevel 1 exit /b 1
-
-call internal\cuda_install.bat
-set LIB=%CUDA_PATH%\lib\x64;%LIB%
-if errorlevel 1 exit /b 1
-set "ORIG_PATH=%PATH%"
-
-setlocal EnableDelayedExpansion
-set NVIDIA_GPU_EXISTS=0
-for /F "delims=" %%i in ('wmic path win32_VideoController get name') do (
-    set GPUS=%%i
-    if not "x!GPUS:NVIDIA=!" == "x!GPUS!" (
-        SET NVIDIA_GPU_EXISTS=1
-        goto gpu_check_end
-    )
-)
-:gpu_check_end
-endlocal & set NVIDIA_GPU_EXISTS=%NVIDIA_GPU_EXISTS%
-
-:: Download MAGMA Files on CUDA builds
-set MAGMA_VERSION=2.5.4
-set CUDA_PREFIX=cuda%CUDA_VERSION%
-if "%CUDA_VERSION%" == "92" set MAGMA_VERSION=2.5.2
-if "%CUDA_VERSION%" == "100" set MAGMA_VERSION=2.5.2
-
-if "%DEBUG%" == "1" (
-    set BUILD_TYPE=debug
-) else (
-    set BUILD_TYPE=release
-)
-
-if not "%CUDA_VERSION%" == "cpu" (
-    rmdir /s /q magma_%CUDA_PREFIX%_%BUILD_TYPE%
-    del magma_%CUDA_PREFIX%_%BUILD_TYPE%.7z
-    curl -k https://s3.amazonaws.com/ossci-windows/magma_%MAGMA_VERSION%_%CUDA_PREFIX%_%BUILD_TYPE%.7z -o magma_%CUDA_PREFIX%_%BUILD_TYPE%.7z
-    7z x -aoa magma_%CUDA_PREFIX%_%BUILD_TYPE%.7z -omagma_%CUDA_PREFIX%_%BUILD_TYPE%
-    set LIB=%CD%\magma_%CUDA_PREFIX%_%BUILD_TYPE%\lib;%LIB%
-)
-
-echo "install conda package"
-
-:: Install Miniconda3
-set "CONDA_HOME=%CD%\conda"
-set "tmp_conda=%CONDA_HOME%"
-set "miniconda_exe=%CD%\miniconda.exe"
-
-rmdir /s /q conda
-del miniconda.exe
-curl -k https://repo.anaconda.com/miniconda/Miniconda3-latest-Windows-x86_64.exe -o "%miniconda_exe%"
-start /wait "" "%miniconda_exe%" /S /InstallationType=JustMe /RegisterPython=0 /AddToPath=0 /D=%tmp_conda%
-if ERRORLEVEL 1 exit /b 1
-
-set "PATH=%CONDA_HOME%;%CONDA_HOME%\scripts;%CONDA_HOME%\Library\bin;%PATH%"
-
-conda create -qyn testenv python=%DESIRED_PYTHON%
-if errorlevel 1 exit /b 1
-
-call %CONDA_HOME%\condabin\activate.bat testenv
-if errorlevel 1 exit /b 1
-
-call conda install  -y -q -c conda-forge libuv=1.39
-call conda install -y -q intel-openmp
-
-echo "install and test libtorch"
-pip install cmake
-echo "installing cmake"
-
-if "%VC_YEAR%" == "2019" powershell internal\vs2019_install.ps1
-if "%VC_YEAR%" == "2022" powershell internal\vs2022_install.ps1
-
-if ERRORLEVEL 1 exit /b 1
-
-for /F "delims=" %%i in ('where /R "%PYTORCH_FINAL_PACKAGE_DIR:/=\%" *-latest.zip') do 7z x "%%i" -otmp
-if ERRORLEVEL 1 exit /b 1
-
-
-pushd tmp\libtorch
-
-set VC_VERSION_LOWER=17
-set VC_VERSION_UPPER=18
-IF "%VC_YEAR%" == "2019" (
-    set VC_VERSION_LOWER=16
-    set VC_VERSION_UPPER=17
-)
-
-for /f "usebackq tokens=*" %%i in (`"%ProgramFiles(x86)%\Microsoft Visual Studio\Installer\vswhere.exe" -legacy -products * -version [%VC_VERSION_LOWER%^,%VC_VERSION_UPPER%^) -property installationPath`) do (
-    if exist "%%i" if exist "%%i\VC\Auxiliary\Build\vcvarsall.bat" (
-        set "VS15INSTALLDIR=%%i"
-        set "VS15VCVARSALL=%%i\VC\Auxiliary\Build\vcvarsall.bat"
-        goto vswhere
-    )
-)
-
-:vswhere
-IF "%VS15VCVARSALL%"=="" (
-    echo Visual Studio %VC_YEAR% C++ BuildTools is required to compile PyTorch test on Windows
-    exit /b 1
-)
-call "%VS15VCVARSALL%" x64
-
-set install_root=%CD%
-set INCLUDE=%INCLUDE%;%install_root%\include;%install_root%\include\torch\csrc\api\include
-set LIB=%LIB%;%install_root%\lib\x64
-set PATH=%PATH%;%install_root%\lib
-
-
-cd %PYTORCH_ROOT%\.ci\pytorch\test_example_code\
-mkdir build
-cd build
-
-cmake -DCMAKE_PREFIX_PATH=%install_root% ..
-
-if ERRORLEVEL 1 exit /b 1
-
-cmake --build . --config Release
-
-.\Release\simple-torch-test.exe
-if ERRORLEVEL 1 exit /b 1
-
-popd
-
-echo Cleaning temp files
-rd /s /q "tmp" || ver > nul
-
-:end
-set "PATH=%ORIG_PATH%"
-popd

.ci/pytorch/windows/internal/vc_install_helper.bat

@@ -1,21 +0,0 @@
-if "%VC_YEAR%" == "2019" powershell windows/internal/vs2019_install.ps1
-if "%VC_YEAR%" == "2022" powershell windows/internal/vs2022_install.ps1
-
-set VC_VERSION_LOWER=17
-set VC_VERSION_UPPER=18
-if "%VC_YEAR%" == "2019" (
-    set VC_VERSION_LOWER=16
-    set VC_VERSION_UPPER=17
-)
-
-for /f "usebackq tokens=*" %%i in (`"%ProgramFiles(x86)%\Microsoft Visual Studio\Installer\vswhere.exe"  -products Microsoft.VisualStudio.Product.BuildTools -version [%VC_VERSION_LOWER%^,%VC_VERSION_UPPER%^) -property installationPath`) do (
-    if exist "%%i" if exist "%%i\VC\Auxiliary\Build\vcvarsall.bat" (
-        set "VS15INSTALLDIR=%%i"
-        goto vswhere
-    )
-)
-
-:vswhere
-echo "Setting VSINSTALLDIR to %VS15INSTALLDIR%"
-
-if errorlevel 1 exit /b 1

.ci/pytorch/windows/internal/vs2019_install.ps1

@@ -1,48 +0,0 @@
-# https://developercommunity.visualstudio.com/t/install-specific-version-of-vs-component/1142479
-# https://docs.microsoft.com/en-us/visualstudio/releases/2019/history#release-dates-and-build-numbers
-
-# 16.8.6 BuildTools
-$VS_DOWNLOAD_LINK = "https://ossci-windows.s3.us-east-1.amazonaws.com/vs16.8.6_BuildTools.exe"
-$COLLECT_DOWNLOAD_LINK = "https://aka.ms/vscollect.exe"
-$VS_INSTALL_ARGS = @("--nocache","--quiet","--wait", "--add Microsoft.VisualStudio.Workload.VCTools",
-                                                     "--add Microsoft.Component.MSBuild",
-                                                     "--add Microsoft.VisualStudio.Component.Roslyn.Compiler",
-                                                     "--add Microsoft.VisualStudio.Component.TextTemplating",
-                                                     "--add Microsoft.VisualStudio.Component.VC.CoreIde",
-                                                     "--add Microsoft.VisualStudio.Component.VC.Redist.14.Latest",
-                                                     "--add Microsoft.VisualStudio.ComponentGroup.NativeDesktop.Core",
-                                                     "--add Microsoft.VisualStudio.Component.VC.Tools.x86.x64",
-                                                     "--add Microsoft.VisualStudio.ComponentGroup.NativeDesktop.Win81")
-
-curl.exe --retry 3 -kL $VS_DOWNLOAD_LINK --output vs_installer.exe
-if ($LASTEXITCODE -ne 0) {
-    echo "Download of the VS 2019 Version 16.8.5 installer failed"
-    exit 1
-}
-
-if (Test-Path "${env:ProgramFiles(x86)}\Microsoft Visual Studio\Installer\vswhere.exe") {
-    $existingPath = & "${env:ProgramFiles(x86)}\Microsoft Visual Studio\Installer\vswhere.exe" -products "Microsoft.VisualStudio.Product.BuildTools" -version "[16, 17)" -property installationPath
-    if ($existingPath -ne $null) {
-        if (!${env:CIRCLECI}) {
-            echo "Found correctly versioned existing BuildTools installation in $existingPath"
-            exit 0
-        }
-        echo "Found existing BuildTools installation in $existingPath, keeping it"
-    }
-}
-
-$process = Start-Process "${PWD}\vs_installer.exe" -ArgumentList $VS_INSTALL_ARGS -NoNewWindow -Wait -PassThru
-Remove-Item -Path vs_installer.exe -Force
-$exitCode = $process.ExitCode
-if (($exitCode -ne 0) -and ($exitCode -ne 3010)) {
-    echo "VS 2019 installer exited with code $exitCode, which should be one of [0, 3010]."
-    curl.exe --retry 3 -kL $COLLECT_DOWNLOAD_LINK --output Collect.exe
-    if ($LASTEXITCODE -ne 0) {
-        echo "Download of the VS Collect tool failed."
-        exit 1
-    }
-    Start-Process "${PWD}\Collect.exe" -NoNewWindow -Wait -PassThru
-    New-Item -Path "C:\w\build-results" -ItemType "directory" -Force
-    Copy-Item -Path "C:\Users\${env:USERNAME}\AppData\Local\Temp\vslogs.zip" -Destination "C:\w\build-results\"
-    exit 1
-}

.ci/pytorch/windows/internal/vs2022_install.ps1

@@ -1,48 +0,0 @@
-# https://developercommunity.visualstudio.com/t/install-specific-version-of-vs-component/1142479
-# https://learn.microsoft.com/en-us/visualstudio/releases/2022/release-history#evergreen-bootstrappers
-
-# 17.4.3 BuildTools
-$VS_DOWNLOAD_LINK = "https://download.visualstudio.microsoft.com/download/pr/8f480125-28b8-4a2c-847c-c2b02a8cdd1b/64be21d4ada005d7d07896ed0b004c322409bd04d6e8eba4c03c9fa39c928e7a/vs_BuildTools.exe"
-$COLLECT_DOWNLOAD_LINK = "https://aka.ms/vscollect.exe"
-$VS_INSTALL_ARGS = @("--nocache","--quiet","--wait", "--add Microsoft.VisualStudio.Workload.VCTools",
-                                                     "--add Microsoft.Component.MSBuild",
-                                                     "--add Microsoft.VisualStudio.Component.Roslyn.Compiler",
-                                                     "--add Microsoft.VisualStudio.Component.TextTemplating",
-                                                     "--add Microsoft.VisualStudio.Component.VC.CoreIde",
-                                                     "--add Microsoft.VisualStudio.Component.VC.Redist.14.Latest",
-                                                     "--add Microsoft.VisualStudio.ComponentGroup.NativeDesktop.Core",
-                                                     "--add Microsoft.VisualStudio.Component.VC.Tools.x86.x64",
-                                                     "--add Microsoft.VisualStudio.ComponentGroup.NativeDesktop.Win81")
-
-curl.exe --retry 3 -kL $VS_DOWNLOAD_LINK --output vs_installer.exe
-if ($LASTEXITCODE -ne 0) {
-    echo "Download of the VS $VC_YEAR Version $VS_VERSION installer failed"
-    exit 1
-}
-
-if (Test-Path "${env:ProgramFiles(x86)}\Microsoft Visual Studio\Installer\vswhere.exe") {
-    $existingPath = & "${env:ProgramFiles(x86)}\Microsoft Visual Studio\Installer\vswhere.exe" -products "Microsoft.VisualStudio.Product.BuildTools" -version "[17, 18)" -property installationPath
-    if ($existingPath -ne $null) {
-        if (!${env:CIRCLECI}) {
-            echo "Found correctly versioned existing BuildTools installation in $existingPath"
-            exit 0
-        }
-        echo "Found existing BuildTools installation in $existingPath, keeping it"
-    }
-}
-
-$process = Start-Process "${PWD}\vs_installer.exe" -ArgumentList $VS_INSTALL_ARGS -NoNewWindow -Wait -PassThru
-Remove-Item -Path vs_installer.exe -Force
-$exitCode = $process.ExitCode
-if (($exitCode -ne 0) -and ($exitCode -ne 3010)) {
-    echo "VS $VC_YEAR installer exited with code $exitCode, which should be one of [0, 3010]."
-    curl.exe --retry 3 -kL $COLLECT_DOWNLOAD_LINK --output Collect.exe
-    if ($LASTEXITCODE -ne 0) {
-        echo "Download of the VS Collect tool failed."
-        exit 1
-    }
-    Start-Process "${PWD}\Collect.exe" -NoNewWindow -Wait -PassThru
-    New-Item -Path "C:\w\build-results" -ItemType "directory" -Force
-    Copy-Item -Path "C:\Users\${env:USERNAME}\AppData\Local\Temp\vslogs.zip" -Destination "C:\w\build-results\"
-    exit 1
-}

.ci/pytorch/windows/internal/vs_install.bat

@@ -1,28 +0,0 @@
-@echo off
-
-set VS_DOWNLOAD_LINK=https://download.visualstudio.microsoft.com/download/pr/8f480125-28b8-4a2c-847c-c2b02a8cdd1b/64be21d4ada005d7d07896ed0b004c322409bd04d6e8eba4c03c9fa39c928e7a/vs_BuildTools.exe
-IF "%VS_LATEST%" == "1" (
-   set VS_INSTALL_ARGS= --nocache --norestart --quiet --wait --add Microsoft.VisualStudio.Workload.VCTools
-   set VSDEVCMD_ARGS=
-) ELSE (
-   set VS_INSTALL_ARGS=--nocache --quiet --wait --add Microsoft.VisualStudio.Workload.VCTools ^
-                                                --add Microsoft.VisualStudio.Component.VC.Tools.14.34 ^
-                                                --add Microsoft.Component.MSBuild ^
-                                                --add Microsoft.VisualStudio.Component.Roslyn.Compiler ^
-                                                --add Microsoft.VisualStudio.Component.TextTemplating ^
-                                                --add Microsoft.VisualStudio.Component.VC.CoreIde ^
-                                                --add Microsoft.VisualStudio.Component.VC.Redist.14.Latest ^
-                                                --add Microsoft.VisualStudio.ComponentGroup.NativeDesktop.Core ^
-                                                --add Microsoft.VisualStudio.Component.VC.Tools.x86.x64 ^
-                                                --add Microsoft.VisualStudio.Component.VC.Tools.14.34 ^
-                                                --add Microsoft.VisualStudio.ComponentGroup.NativeDesktop.Win81
-   set VSDEVCMD_ARGS=-vcvars_ver=14.34
-)
-
-curl -k -L %VS_DOWNLOAD_LINK% --output vs_installer.exe
-if errorlevel 1 exit /b 1
-
-start /wait .\vs_installer.exe %VS_INSTALL_ARGS%
-if not errorlevel 0 exit /b 1
-if errorlevel 1 if not errorlevel 3010 exit /b 1
-if errorlevel 3011 exit /b 1

.ci/pytorch/windows/internal/xpu_install.bat

@@ -1,119 +0,0 @@
-@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-gpus.html
-
-if not "%CUDA_VERSION%" == "xpu" (
-    echo Skipping for non XPU builds
-    exit /b 0
-)
-
-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_BUNDLE_PRODUCT_NAME=intel.oneapi.win.intel-for-pytorch-gpu-dev.product
-set XPU_BUNDLE_VERSION=0.5.3+31
-set XPU_BUNDLE_INSTALLED=0
-set XPU_BUNDLE_UNINSTALL=0
-set XPU_EXTRA_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_EXTRA_PRODUCT_NAME=intel.oneapi.win.intel-pti-dev.product
-set XPU_EXTRA_VERSION=0.9.0+36
-set XPU_EXTRA_INSTALLED=0
-set XPU_EXTRA_UNINSTALL=0
-
-if not [%XPU_VERSION%]==[] if [%XPU_VERSION%]==[2025.0] (
-    set XPU_BUNDLE_URL=https://registrationcenter-download.intel.com/akdlm/IRC_NAS/efc86abd-cb77-452e-a03f-a741895b8ece/intel-deep-learning-essentials-2025.0.0.336_offline.exe
-    set XPU_BUNDLE_PRODUCT_NAME=intel.oneapi.win.deep-learning-essentials.product
-    set XPU_BUNDLE_VERSION=2025.0.0+335
-    set XPU_BUNDLE_INSTALLED=0
-    set XPU_BUNDLE_UNINSTALL=0
-    set XPU_EXTRA_URL=NULL
-    set XPU_EXTRA_PRODUCT_NAME=intel.oneapi.win.compiler.product
-    set XPU_EXTRA_VERSION=2025.0.1+1226
-    set XPU_EXTRA_INSTALLED=0
-    set XPU_EXTRA_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 %%a --product-ver %%b --log-dir uninstall_bundle
-            set XPU_BUNDLE_UNINSTALL=1
-        )
-    )
-    if "%%a"=="%XPU_EXTRA_PRODUCT_NAME%" (
-        echo %%a Installed Version: %%b
-        set XPU_EXTRA_INSTALLED=1
-        if not "%XPU_EXTRA_VERSION%"=="%%b" (
-            start /wait "Installer Title" "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" --action=remove --eula=accept --silent --product-id %%a --product-ver %%b --log-dir uninstall_bundle
-            set XPU_EXTRA_UNINSTALL=1
-        )
-    )
-    if not "%%b" == "Version" if not [%%b]==[] if not "%%a"=="%XPU_BUNDLE_PRODUCT_NAME%" if not "%%a"=="%XPU_EXTRA_PRODUCT_NAME%" (
-        echo "Uninstalling...."
-        start /wait "Installer Title" "%XPU_BUNDLE_PARENT_DIR%\Installer\installer.exe" --action=remove --eula=accept --silent --product-id %%a --product-ver %%b --log-dir uninstall_bundle
-    )
-)
-if errorlevel 1 exit /b 1
-if exist xpu_bundle_installed_ver.log del xpu_bundle_installed_ver.log
-if exist uninstall_bundle rmdir /s /q uninstall_bundle
-if "%XPU_BUNDLE_INSTALLED%"=="0" goto xpu_bundle_install
-if "%XPU_BUNDLE_UNINSTALL%"=="1" goto xpu_bundle_install
-
-:xpu_extra_check
-
-if "%XPU_EXTRA_URL%"=="NULL" goto xpu_install_end
-if "%XPU_EXTRA_INSTALLED%"=="0" goto xpu_extra_install
-if "%XPU_EXTRA_UNINSTALL%"=="1" goto xpu_extra_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
-goto xpu_extra_check
-
-:xpu_extra_install
-
-curl -o xpu_extra.exe --retry 3 --retry-all-errors -k %XPU_EXTRA_URL%
-echo "Intel XPU EXTRA installing..."
-start /wait "Intel XPU EXTRA Installer" "xpu_extra.exe" --action=install --eula=accept --silent --log-dir install_bundle
-if errorlevel 1 exit /b 1
-del xpu_extra.exe
-
-:xpu_install_end

.ci/pytorch/windows/xpu.bat

@@ -1,41 +0,0 @@
-@echo on
-
-set MODULE_NAME=pytorch
-
-IF NOT EXIST "setup.py" IF NOT EXIST "%MODULE_NAME%" (
-    call internal\clone.bat
-    cd %~dp0
-) ELSE (
-    call internal\clean.bat
-)
-IF ERRORLEVEL 1 goto :eof
-
-call internal\check_deps.bat
-IF ERRORLEVEL 1 goto :eof
-
-REM Check for optional components
-
-echo Disabling CUDA
-set USE_CUDA=0
-
-call internal\check_opts.bat
-IF ERRORLEVEL 1 goto :eof
-
-echo Activate XPU Bundle env
-set VS2022INSTALLDIR=%VS15INSTALLDIR%
-set XPU_BUNDLE_ROOT=%ProgramFiles(x86)%\Intel\oneAPI
-call "%XPU_BUNDLE_ROOT%\compiler\latest\env\vars.bat"
-call "%XPU_BUNDLE_ROOT%\ocloc\latest\env\vars.bat"
-IF ERRORLEVEL 1 goto :eof
-
-:: Workaround for https://github.com/pytorch/pytorch/issues/134989
-set CMAKE_SHARED_LINKER_FLAGS=/FORCE:MULTIPLE
-set CMAKE_MODULE_LINKER_FLAGS=/FORCE:MULTIPLE
-set CMAKE_EXE_LINKER_FLAGS=/FORCE:MULTIPLE
-
-if exist "%NIGHTLIES_PYTORCH_ROOT%" cd %NIGHTLIES_PYTORCH_ROOT%\..
-call %~dp0\internal\copy_cpu.bat
-IF ERRORLEVEL 1 goto :eof
-
-call %~dp0\internal\setup.bat
-IF ERRORLEVEL 1 goto :eof

.ci/wheel/build_wheel.sh

@@ -1,281 +0,0 @@
-#!/usr/bin/env bash
-set -ex
-SOURCE_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null && pwd )"
-
-# Env variables that should be set:
-#   DESIRED_PYTHON
-#     Which Python version to build for in format 'Maj.min' e.g. '2.7' or '3.6'
-#
-#   PYTORCH_FINAL_PACKAGE_DIR
-#     **absolute** path to folder where final whl packages will be stored. The
-#     default should not be used when calling this from a script. The default
-#     is 'whl', and corresponds to the default in the wheel/upload.sh script.
-#
-#   MAC_PACKAGE_WORK_DIR
-#     absolute path to a workdir in which to clone an isolated conda
-#     installation and pytorch checkout. If the pytorch checkout already exists
-#     then it will not be overwritten.
-
-# Function to retry functions that sometimes timeout or have flaky failures
-retry () {
-    $*  || (sleep 1 && $*) || (sleep 2 && $*) || (sleep 4 && $*) || (sleep 8 && $*)
-}
-
-# Parameters
-if [[ -n "$DESIRED_PYTHON" && -n "$PYTORCH_BUILD_VERSION" && -n "$PYTORCH_BUILD_NUMBER" ]]; then
-    desired_python="$DESIRED_PYTHON"
-    build_version="$PYTORCH_BUILD_VERSION"
-    build_number="$PYTORCH_BUILD_NUMBER"
-else
-    if [ "$#" -ne 3 ]; then
-        echo "illegal number of parameters. Need PY_VERSION BUILD_VERSION BUILD_NUMBER"
-        echo "for example: build_wheel.sh 2.7 0.1.6 20"
-        echo "Python version should be in format 'M.m'"
-        exit 1
-    fi
-    desired_python=$1
-    build_version=$2
-    build_number=$3
-fi
-
-echo "Building for Python: $desired_python Version: $build_version Build: $build_number"
-python_nodot="$(echo $desired_python | tr -d m.u)"
-
-# Version: setup.py uses $PYTORCH_BUILD_VERSION.post$PYTORCH_BUILD_NUMBER if
-# PYTORCH_BUILD_NUMBER > 1
-if [[ -n "$OVERRIDE_PACKAGE_VERSION" ]]; then
-    # This will be the *exact* version, since build_number<1
-    build_version="$OVERRIDE_PACKAGE_VERSION"
-    build_number=0
-    build_number_prefix=''
-else
-    if [[ $build_number -eq 1 ]]; then
-        build_number_prefix=""
-    else
-        build_number_prefix=".post$build_number"
-    fi
-fi
-export PYTORCH_BUILD_VERSION=$build_version
-export PYTORCH_BUILD_NUMBER=$build_number
-
-package_type="${PACKAGE_TYPE:-wheel}"
-# Fill in empty parameters with defaults
-if [[ -z "$TORCH_PACKAGE_NAME" ]]; then
-    TORCH_PACKAGE_NAME='torch'
-fi
-TORCH_PACKAGE_NAME="$(echo $TORCH_PACKAGE_NAME | tr '-' '_')"
-if [[ -z "$PYTORCH_REPO" ]]; then
-    PYTORCH_REPO='pytorch'
-fi
-if [[ -z "$PYTORCH_BRANCH" ]]; then
-    PYTORCH_BRANCH="v${build_version}"
-fi
-if [[ -z "$RUN_TEST_PARAMS" ]]; then
-    RUN_TEST_PARAMS=()
-fi
-if [[ -z "$PYTORCH_FINAL_PACKAGE_DIR" ]]; then
-    if [[ -n "$BUILD_PYTHONLESS" ]]; then
-        PYTORCH_FINAL_PACKAGE_DIR='libtorch'
-    else
-        PYTORCH_FINAL_PACKAGE_DIR='whl'
-    fi
-fi
-mkdir -p "$PYTORCH_FINAL_PACKAGE_DIR" || true
-
-# Create an isolated directory to store this builds pytorch checkout and conda
-# installation
-if [[ -z "$MAC_PACKAGE_WORK_DIR" ]]; then
-    MAC_PACKAGE_WORK_DIR="$(pwd)/tmp_wheel_conda_${DESIRED_PYTHON}_$(date +%H%M%S)"
-fi
-mkdir -p "$MAC_PACKAGE_WORK_DIR" || true
-if [[ -n ${GITHUB_ACTIONS} ]]; then
-    pytorch_rootdir="${PYTORCH_ROOT:-${MAC_PACKAGE_WORK_DIR}/pytorch}"
-else
-    pytorch_rootdir="${MAC_PACKAGE_WORK_DIR}/pytorch"
-fi
-whl_tmp_dir="${MAC_PACKAGE_WORK_DIR}/dist"
-mkdir -p "$whl_tmp_dir"
-
-mac_version='macosx_11_0_arm64'
-libtorch_arch='arm64'
-
-# Create a consistent wheel package name to rename the wheel to
-wheel_filename_new="${TORCH_PACKAGE_NAME}-${build_version}${build_number_prefix}-cp${python_nodot}-none-${mac_version}.whl"
-
-###########################################################
-
-# Have a separate Pytorch repo clone
-if [[ ! -d "$pytorch_rootdir" ]]; then
-    git clone "https://github.com/${PYTORCH_REPO}/pytorch" "$pytorch_rootdir"
-    pushd "$pytorch_rootdir"
-    if ! git checkout "$PYTORCH_BRANCH" ; then
-        echo "Could not checkout $PYTORCH_BRANCH, so trying tags/v${build_version}"
-        git checkout tags/v${build_version}
-    fi
-    popd
-fi
-pushd "$pytorch_rootdir"
-git submodule update --init --recursive
-popd
-
-##########################
-# now build the binary
-
-
-export TH_BINARY_BUILD=1
-export INSTALL_TEST=0 # dont install test binaries into site-packages
-export MACOSX_DEPLOYMENT_TARGET=10.15
-export CMAKE_PREFIX_PATH=${CONDA_PREFIX:-"$(dirname $(which conda))/../"}
-
-SETUPTOOLS_PINNED_VERSION="=46.0.0"
-PYYAML_PINNED_VERSION="=5.3"
-EXTRA_CONDA_INSTALL_FLAGS=""
-case $desired_python in
-    3.13)
-        echo "Using 3.13 deps"
-        SETUPTOOLS_PINNED_VERSION=">=68.0.0"
-        PYYAML_PINNED_VERSION=">=6.0.1"
-        NUMPY_PINNED_VERSION="=2.1.0"
-        ;;
-    3.12)
-        echo "Using 3.12 deps"
-        SETUPTOOLS_PINNED_VERSION=">=68.0.0"
-        PYYAML_PINNED_VERSION=">=6.0.1"
-        NUMPY_PINNED_VERSION="=2.0.2"
-        ;;
-    3.11)
-        echo "Using 3.11 deps"
-        SETUPTOOLS_PINNED_VERSION=">=46.0.0"
-        PYYAML_PINNED_VERSION=">=5.3"
-        NUMPY_PINNED_VERSION="=2.0.2"
-        ;;
-    3.10)
-        echo "Using 3.10 deps"
-        SETUPTOOLS_PINNED_VERSION=">=46.0.0"
-        PYYAML_PINNED_VERSION=">=5.3"
-        NUMPY_PINNED_VERSION="=2.0.2"
-        ;;
-    3.9)
-        echo "Using 3.9 deps"
-        SETUPTOOLS_PINNED_VERSION=">=46.0.0"
-        PYYAML_PINNED_VERSION=">=5.3"
-        NUMPY_PINNED_VERSION="=2.0.2"
-        ;;
-    *)
-        echo "Using default deps"
-        NUMPY_PINNED_VERSION="=1.11.3"
-        ;;
-esac
-
-# Install into a fresh env
-tmp_env_name="wheel_py$python_nodot"
-conda create ${EXTRA_CONDA_INSTALL_FLAGS} -yn "$tmp_env_name" python="$desired_python"
-source activate "$tmp_env_name"
-
-pip install -q "numpy=${NUMPY_PINNED_VERSION}"  "pyyaml${PYYAML_PINNED_VERSION}" requests
-retry pip install -qr "${pytorch_rootdir}/requirements.txt" || true
-# TODO : Remove me later (but in the interim, use Anaconda cmake, to find Anaconda installed OpenMP)
-retry pip uninstall -y cmake
-retry conda install ${EXTRA_CONDA_INSTALL_FLAGS} -yq  llvm-openmp=14.0.6 cmake ninja "setuptools${SETUPTOOLS_PINNED_VERSION}" typing_extensions
-
-# For USE_DISTRIBUTED=1 on macOS, need libuv and pkg-config to find libuv.
-export USE_DISTRIBUTED=1
-retry conda install ${EXTRA_CONDA_INSTALL_FLAGS} -yq libuv pkg-config
-
-if [[ -n "$CROSS_COMPILE_ARM64" ]]; then
-    export CMAKE_OSX_ARCHITECTURES=arm64
-fi
-export USE_MKLDNN=OFF
-export USE_QNNPACK=OFF
-export BUILD_TEST=OFF
-
-pushd "$pytorch_rootdir"
-echo "Calling setup.py bdist_wheel at $(date)"
-
-if [[ "$USE_SPLIT_BUILD" == "true" ]]; then
-    echo "Calling setup.py bdist_wheel for split build (BUILD_LIBTORCH_WHL)"
-    BUILD_LIBTORCH_WHL=1 BUILD_PYTHON_ONLY=0 python setup.py bdist_wheel -d "$whl_tmp_dir"
-    echo "Finished setup.py bdist_wheel for split build (BUILD_LIBTORCH_WHL)"
-    echo "Calling setup.py bdist_wheel for split build (BUILD_PYTHON_ONLY)"
-    BUILD_PYTHON_ONLY=1 BUILD_LIBTORCH_WHL=0 python setup.py bdist_wheel -d "$whl_tmp_dir" --cmake
-    echo "Finished setup.py bdist_wheel for split build (BUILD_PYTHON_ONLY)"
-else
-    python setup.py bdist_wheel -d "$whl_tmp_dir"
-fi
-
-echo "Finished setup.py bdist_wheel at $(date)"
-
-if [[ $package_type != 'libtorch' ]]; then
-    echo "delocating wheel dependencies"
-    retry pip install https://github.com/matthew-brett/delocate/archive/refs/tags/0.10.4.zip
-    echo "found the following wheels:"
-    find $whl_tmp_dir -name "*.whl"
-    echo "running delocate"
-    find $whl_tmp_dir -name "*.whl" | xargs -I {} delocate-wheel -v {}
-    find $whl_tmp_dir -name "*.whl"
-    find $whl_tmp_dir -name "*.whl" | xargs -I {} delocate-listdeps {}
-    echo "Finished delocating wheels at $(date)"
-fi
-
-echo "The wheel is in $(find $whl_tmp_dir -name '*.whl')"
-
-wheel_filename_gen=$(find $whl_tmp_dir -name '*.whl' | head -n1 | xargs -I {} basename {})
-popd
-
-if [[ -z "$BUILD_PYTHONLESS" ]]; then
-    # Copy the whl to a final destination before tests are run
-    echo "Renaming Wheel file: $wheel_filename_gen to $wheel_filename_new"
-    cp "$whl_tmp_dir/$wheel_filename_gen" "$PYTORCH_FINAL_PACKAGE_DIR/$wheel_filename_new"
-
-    ##########################
-    # now test the binary, unless it's cross compiled arm64
-    if [[ -z "$CROSS_COMPILE_ARM64" ]]; then
-        pip uninstall -y "$TORCH_PACKAGE_NAME" || true
-        pip uninstall -y "$TORCH_PACKAGE_NAME" || true
-
-        # Create new "clean" conda environment for testing
-        conda create ${EXTRA_CONDA_INSTALL_FLAGS} -yn "test_conda_env" python="$desired_python"
-        conda activate test_conda_env
-
-        pip install "$PYTORCH_FINAL_PACKAGE_DIR/$wheel_filename_new" -v
-
-        echo "$(date) :: Running tests"
-        # TODO: Add real tests, as run_test.sh from builder is a glorified no-op
-        # pushd "$pytorch_rootdir"
-        # "${SOURCE_DIR}/../run_tests.sh" 'wheel' "$desired_python" 'cpu'
-        # popd
-        echo "$(date) :: Finished tests"
-    fi
-else
-    pushd "$pytorch_rootdir"
-
-    mkdir -p libtorch/{lib,bin,include,share}
-    cp -r "$(pwd)/build/lib" "$(pwd)/libtorch/"
-
-    # for now, the headers for the libtorch package will just be
-    # copied in from the wheel
-    unzip -d any_wheel "$whl_tmp_dir/$wheel_filename_gen"
-    if [[ -d $(pwd)/any_wheel/torch/include ]]; then
-        cp -r "$(pwd)/any_wheel/torch/include" "$(pwd)/libtorch/"
-    else
-        cp -r "$(pwd)/any_wheel/torch/lib/include" "$(pwd)/libtorch/"
-    fi
-    cp -r "$(pwd)/any_wheel/torch/share/cmake" "$(pwd)/libtorch/share/"
-    if [[ "${libtorch_arch}" == "x86_64" ]]; then
-      if [[ -x "$(pwd)/any_wheel/torch/.dylibs/libiomp5.dylib" ]]; then
-          cp -r "$(pwd)/any_wheel/torch/.dylibs/libiomp5.dylib" "$(pwd)/libtorch/lib/"
-      else
-          cp -r "$(pwd)/any_wheel/torch/lib/libiomp5.dylib" "$(pwd)/libtorch/lib/"
-      fi
-    else
-      cp -r "$(pwd)/any_wheel/torch/lib/libomp.dylib" "$(pwd)/libtorch/lib/"
-    fi
-    rm -rf "$(pwd)/any_wheel"
-
-    echo $PYTORCH_BUILD_VERSION > libtorch/build-version
-    echo "$(pushd $pytorch_rootdir && git rev-parse HEAD)" > libtorch/build-hash
-
-    zip -rq "$PYTORCH_FINAL_PACKAGE_DIR/libtorch-macos-${libtorch_arch}-$PYTORCH_BUILD_VERSION.zip" libtorch
-    cp "$PYTORCH_FINAL_PACKAGE_DIR/libtorch-macos-${libtorch_arch}-$PYTORCH_BUILD_VERSION.zip"  \
-       "$PYTORCH_FINAL_PACKAGE_DIR/libtorch-macos-${libtorch_arch}-latest.zip"
-fi

.circleci/scripts/binary_linux_build.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+
+echo "RUNNING ON $(uname -a) WITH $(nproc) CPUS AND $(free -m)"
+set -eux -o pipefail
+source /env
+
+# Because most Circle executors only have 20 CPUs, using more causes OOMs w/ Ninja and nvcc parallelization
+MEMORY_LIMIT_MAX_JOBS=18
+NUM_CPUS=$(( $(nproc) - 2 ))
+
+# Defaults here for **binary** linux builds so they can be changed in one place
+export MAX_JOBS=${MAX_JOBS:-$(( ${NUM_CPUS} > ${MEMORY_LIMIT_MAX_JOBS} ? ${MEMORY_LIMIT_MAX_JOBS} : ${NUM_CPUS} ))}
+
+if [[ "${DESIRED_CUDA}" =~ cu1[1-2][0-9] ]]; then
+  export BUILD_SPLIT_CUDA="ON"
+fi
+
+# Parse the parameters
+if [[ "$PACKAGE_TYPE" == 'conda' ]]; then
+  build_script='conda/build_pytorch.sh'
+elif [[ "$DESIRED_CUDA" == cpu ]]; then
+  build_script='manywheel/build_cpu.sh'
+elif [[ "$DESIRED_CUDA" == *"rocm"* ]]; then
+  build_script='manywheel/build_rocm.sh'
+else
+  build_script='manywheel/build.sh'
+fi
+
+if [[ "$CIRCLE_BRANCH" == "main" ]] || [[ "$CIRCLE_BRANCH" == "master" ]] || [[ "$CIRCLE_BRANCH" == release/* ]]; then
+  export BUILD_DEBUG_INFO=1
+fi
+
+# Build the package
+SKIP_ALL_TESTS=1 "/builder/$build_script"

.circleci/scripts/binary_linux_test.sh

@@ -22,7 +22,10 @@ fi
 python_nodot="\$(echo $DESIRED_PYTHON | tr -d m.u)"
 
 # Set up Python
-if [[ "$PACKAGE_TYPE" != libtorch ]]; then
+if [[ "$PACKAGE_TYPE" == conda ]]; then
+  retry conda create -qyn testenv python="$DESIRED_PYTHON"
+  source activate testenv >/dev/null
+elif [[ "$PACKAGE_TYPE" != libtorch ]]; then
   python_path="/opt/python/cp\$python_nodot-cp\${python_nodot}"
   if [[ "\$python_nodot" = *t ]]; then
     python_digits="\$(echo $DESIRED_PYTHON | tr -cd [:digit:])"
@@ -55,6 +58,9 @@ mv /final_pkgs/debug-*.zip /tmp/debug_final_pkgs || echo "no debug packages to m
 # Install the package
 # These network calls should not have 'retry's because they are installing
 # locally and aren't actually network calls
+# TODO there is duplicated and inconsistent test-python-env setup across this
+#   file, builder/smoke_test.sh, and builder/run_tests.sh, and also in the
+#   conda build scripts themselves. These should really be consolidated
 # Pick only one package of multiple available (which happens as result of workflow re-runs)
 pkg="/final_pkgs/\$(ls -1 /final_pkgs|sort|tail -1)"
 if [[ "\$PYTORCH_BUILD_VERSION" == *dev* ]]; then
@@ -63,7 +69,30 @@ else
     CHANNEL="test"
 fi
 
-if [[ "$PACKAGE_TYPE" != libtorch ]]; then
+if [[ "$PACKAGE_TYPE" == conda ]]; then
+  (
+    # For some reason conda likes to re-activate the conda environment when attempting this install
+    # which means that a deactivate is run and some variables might not exist when that happens,
+    # namely CONDA_MKL_INTERFACE_LAYER_BACKUP from libblas so let's just ignore unbound variables when
+    # it comes to the conda installation commands
+    set +u
+    retry conda install \${EXTRA_CONDA_FLAGS} -yq \
+      "numpy\${NUMPY_PIN}" \
+      mkl>=2018 \
+      ninja \
+      sympy>=1.12 \
+      typing-extensions \
+      ${PROTOBUF_PACKAGE}
+    if [[ "$DESIRED_CUDA" == 'cpu' ]]; then
+      retry conda install -c pytorch -y cpuonly
+    else
+      cu_ver="${DESIRED_CUDA:2:2}.${DESIRED_CUDA:4}"
+      CUDA_PACKAGE="pytorch-cuda"
+      retry conda install \${EXTRA_CONDA_FLAGS} -yq -c nvidia -c "pytorch-\${CHANNEL}" "pytorch-cuda=\${cu_ver}"
+    fi
+    conda install \${EXTRA_CONDA_FLAGS} -y "\$pkg" --offline
+  )
+elif [[ "$PACKAGE_TYPE" != libtorch ]]; then
   if [[ "\$BUILD_ENVIRONMENT" != *s390x* ]]; then
     if [[ "$USE_SPLIT_BUILD" == "true" ]]; then
       pkg_no_python="$(ls -1 /final_pkgs/torch_no_python* | sort |tail -1)"
@@ -87,15 +116,15 @@ if [[ "$PACKAGE_TYPE" == libtorch ]]; then
 fi
 
 # Test the package
-/pytorch/.ci/pytorch/check_binary.sh
+/builder/check_binary.sh
 
 if [[ "\$GPU_ARCH_TYPE" != *s390x* && "\$GPU_ARCH_TYPE" != *xpu* && "\$GPU_ARCH_TYPE" != *rocm*  && "$PACKAGE_TYPE" != libtorch ]]; then
   # Exclude s390, xpu, rocm and libtorch builds from smoke testing
-  python /pytorch/.ci/pytorch/smoke_test/smoke_test.py --package=torchonly --torch-compile-check disabled
+  python /builder/test/smoke_test/smoke_test.py --package=torchonly --torch-compile-check disabled
 fi
 
 # Clean temp files
-cd /pytorch/.ci/pytorch/ && git clean -ffdx
+cd /builder && git clean -ffdx
 
 # =================== The above code will be executed inside Docker container ===================
 EOL

.circleci/scripts/binary_macos_build.sh

@@ -7,5 +7,9 @@ mkdir -p "$PYTORCH_FINAL_PACKAGE_DIR"
 # Build
 export USE_PYTORCH_METAL_EXPORT=1
 export USE_COREML_DELEGATE=1
-export TORCH_PACKAGE_NAME="$(echo $TORCH_PACKAGE_NAME | tr '-' '_')"
-"${PYTORCH_ROOT}/.ci/wheel/build_wheel.sh"
+if [[ "$PACKAGE_TYPE" == conda ]]; then
+  "${BUILDER_ROOT}/conda/build_pytorch.sh"
+else
+  export TORCH_PACKAGE_NAME="$(echo $TORCH_PACKAGE_NAME | tr '-' '_')"
+  "${BUILDER_ROOT}/wheel/build_wheel.sh"
+fi

.circleci/scripts/binary_macos_test.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+set -eux -o pipefail
+
+source "/Users/distiller/project/env"
+export "PATH=$workdir/miniconda/bin:$PATH"
+pkg="$workdir/final_pkgs/$(ls $workdir/final_pkgs)"
+
+# Create a new test env
+# TODO cut all this out into a separate test job and have an entirely different
+# miniconda
+if [[ "$PACKAGE_TYPE" != libtorch ]]; then
+  source deactivate || true
+  conda create -qyn test python="$DESIRED_PYTHON"
+  source activate test >/dev/null
+fi
+
+# Install the package
+if [[ "$PACKAGE_TYPE" == libtorch ]]; then
+  pkg="$(ls $workdir/final_pkgs/*-latest.zip)"
+  unzip "$pkg" -d /tmp
+  cd /tmp/libtorch
+elif [[ "$PACKAGE_TYPE" == conda ]]; then
+  conda install -y "$pkg"
+else
+  pip install "$pkg" -v
+fi
+
+# Test
+if [[ "$PACKAGE_TYPE" == libtorch ]]; then
+  $workdir/builder/check_binary.sh
+else
+  pushd "$workdir/pytorch"
+  $workdir/builder/run_tests.sh "$PACKAGE_TYPE" "$DESIRED_PYTHON" "$DESIRED_CUDA"
+fi

.circleci/scripts/binary_populate_env.sh

@@ -75,8 +75,9 @@ export PYTORCH_BUILD_NUMBER=1
 TRITON_VERSION=$(cat $PYTORCH_ROOT/.ci/docker/triton_version.txt)
 
 # Here PYTORCH_EXTRA_INSTALL_REQUIREMENTS is already set for the all the wheel builds hence append TRITON_CONSTRAINT
-TRITON_CONSTRAINT="platform_system == 'Linux' and platform_machine == 'x86_64'"
-if [[ "$PACKAGE_TYPE" =~ .*wheel.* &&  -n "${PYTORCH_EXTRA_INSTALL_REQUIREMENTS:-}" && ! "$PYTORCH_BUILD_VERSION" =~ .*xpu.* ]]; then
+TRITON_CONSTRAINT="platform_system == 'Linux' and platform_machine == 'x86_64' and python_version < '3.13'"
+if [[ "$PACKAGE_TYPE" =~ .*wheel.* &&  -n "${PYTORCH_EXTRA_INSTALL_REQUIREMENTS:-}" ]]; then
+  # Only linux Python < 3.13 are supported wheels for triton
   TRITON_REQUIREMENT="triton==${TRITON_VERSION}; ${TRITON_CONSTRAINT}"
   if [[ -n "$PYTORCH_BUILD_VERSION" && "$PYTORCH_BUILD_VERSION" =~ .*dev.* ]]; then
       TRITON_SHORTHASH=$(cut -c1-8 $PYTORCH_ROOT/.ci/docker/ci_commit_pins/triton.txt)

.circleci/scripts/binary_windows_build.sh

@@ -19,9 +19,13 @@ fi
 echo "Free space on filesystem before build:"
 df -h
 
-pushd "$PYTORCH_ROOT/.ci/pytorch/"
-export NIGHTLIES_PYTORCH_ROOT="$PYTORCH_ROOT"
-./windows/internal/build_wheels.bat
+pushd "$BUILDER_ROOT"
+if [[ "$PACKAGE_TYPE" == 'conda' ]]; then
+    ./windows/internal/build_conda.bat
+elif [[ "$PACKAGE_TYPE" == 'wheel' || "$PACKAGE_TYPE" == 'libtorch' ]]; then
+    export NIGHTLIES_PYTORCH_ROOT="$PYTORCH_ROOT"
+    ./windows/internal/build_wheels.bat
+fi
 
 echo "Free space on filesystem after build:"
 df -h

.circleci/scripts/binary_windows_test.sh

@@ -11,7 +11,8 @@ if [[ "$DESIRED_CUDA" == 'xpu' ]]; then
     export XPU_VERSION=2025.0
 fi
 
-pushd "$PYTORCH_ROOT/.ci/pytorch/"
+pushd "$BUILDER_ROOT"
+
 ./windows/internal/smoke_test.bat
 
 popd

.github/actions/download-td-artifacts/action.yml

@@ -26,4 +26,4 @@ runs:
       shell: bash
       run: |
         mkdir -p .additional_ci_files
-        mv td_results.json .additional_ci_files/td_results.json || true
+        mv td_results.json .additional_ci_files/td_results.json

.github/actions/test-pytorch-binary/action.yml

@@ -30,6 +30,7 @@ runs:
           --tty \
           --detach \
           -v "${GITHUB_WORKSPACE}/pytorch:/pytorch" \
+          -v "${GITHUB_WORKSPACE}/builder:/builder" \
           -v "${RUNNER_TEMP}/artifacts:/final_pkgs" \
           -w / \
           "${DOCKER_IMAGE}"

.github/ci_commit_pins/xla.txt

@@ -1 +1 @@
-r2.6
+2ec22641e390cda25ec7c61fcbce07507727d584

.github/pytorch-probot.yml

@@ -10,6 +10,7 @@ ciflow_push_tags:
 - ciflow/inductor-perf-compare
 - ciflow/inductor-micro-benchmark
 - ciflow/inductor-micro-benchmark-cpu-x86
+- ciflow/inductor-cu124
 - ciflow/inductor-cu126
 - ciflow/linux-aarch64
 - ciflow/mps
@@ -28,7 +29,6 @@ retryable_workflows:
 - trunk
 - linux-binary
 - windows-binary
-- inductor-A100-perf-nightly
 labeler_config: labeler.yml
 label_to_label_config: label_to_label.yml
 mergebot: True

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

@@ -17,7 +17,6 @@ pytest==7.3.2
 pytest-xdist==3.3.1
 pytest-rerunfailures==10.3
 pytest-flakefinder==1.1.0
-pytest-subtests==0.13.1
 scipy==1.10.1
 sympy==1.12.1 ; python_version == "3.8"
 sympy==1.13.1 ; python_version >= "3.9"

.github/scripts/amd/package_triton_wheel.sh

@@ -30,14 +30,9 @@ fi
 # Remove packaged libs and headers
 rm -rf $TRITON_ROCM_DIR/include/*
 
+LIBTINFO_PATH="/usr/lib64/libtinfo.so.5"
 LIBNUMA_PATH="/usr/lib64/libnuma.so.1"
 LIBELF_PATH="/usr/lib64/libelf.so.1"
-OS_NAME=`awk -F= '/^NAME/{print $2}' /etc/os-release`
-if [[ "$OS_NAME" == *"CentOS Linux"* ]]; then
-    LIBTINFO_PATH="/usr/lib64/libtinfo.so.5"
-else
-    LIBTINFO_PATH="/usr/lib64/libtinfo.so.6"
-fi
 
 OS_SO_PATHS=(
     $LIBELF_PATH

.github/scripts/filter_test_configs.py

@@ -39,9 +39,9 @@ SUPPORTED_PERIODICAL_MODES: Dict[str, Callable[[Optional[str]], bool]] = {
 }
 
 # The link to the published list of disabled jobs
-DISABLED_JOBS_URL = "https://ossci-metrics.s3.amazonaws.com/disabled-jobs.json?versionId=pQg1WJZKNqoisT5kAGG9Wmbuns5zBdBc"
+DISABLED_JOBS_URL = "https://ossci-metrics.s3.amazonaws.com/disabled-jobs.json"
 # and unstable jobs
-UNSTABLE_JOBS_URL = "https://ossci-metrics.s3.amazonaws.com/unstable-jobs.json?versionId=ddADM6lf9NqVTA0APn69zl3M7nMda4DH"
+UNSTABLE_JOBS_URL = "https://ossci-metrics.s3.amazonaws.com/unstable-jobs.json"
 
 # Some constants used to handle disabled and unstable jobs
 JOB_NAME_SEP = "/"
@@ -332,7 +332,7 @@ def process_jobs(
         # The job name from github is in the PLATFORM / JOB (CONFIG) format, so breaking
         # it into its two components first
         current_platform, _ = (n.strip() for n in job_name.split(JOB_NAME_SEP, 1) if n)
-    except ValueError:
+    except ValueError as error:
         warnings.warn(f"Invalid job name {job_name}, returning")
         return test_matrix
 

.github/scripts/generate_binary_build_matrix.py

@@ -17,10 +17,10 @@ from typing import Dict, List, Optional, Tuple
 
 # NOTE: Also update the CUDA sources in tools/nightly.py when changing this list
 CUDA_ARCHES = ["11.8", "12.4", "12.6"]
-CUDA_ARCHES_FULL_VERSION = {"11.8": "11.8.0", "12.4": "12.4.1", "12.6": "12.6.3"}
+CUDA_ARCHES_FULL_VERSION = {"11.8": "11.8.0", "12.4": "12.4.1", "12.6": "12.6.2"}
 CUDA_ARCHES_CUDNN_VERSION = {"11.8": "9", "12.4": "9", "12.6": "9"}
 
-ROCM_ARCHES = ["6.1", "6.2.4"]
+ROCM_ARCHES = ["6.1", "6.2"]
 
 XPU_ARCHES = ["xpu"]
 
@@ -162,7 +162,7 @@ WHEEL_CONTAINER_IMAGES = {
     "12.4": f"pytorch/manylinux-builder:cuda12.4-{DEFAULT_TAG}",
     "12.6": f"pytorch/manylinux2_28-builder:cuda12.6-{DEFAULT_TAG}",
     **{
-        gpu_arch: f"pytorch/manylinux2_28-builder:rocm{gpu_arch}-{DEFAULT_TAG}"
+        gpu_arch: f"pytorch/manylinux-builder:rocm{gpu_arch}-{DEFAULT_TAG}"
         for gpu_arch in ROCM_ARCHES
     },
     "xpu": f"pytorch/manylinux2_28-builder:xpu-{DEFAULT_TAG}",
@@ -170,7 +170,7 @@ WHEEL_CONTAINER_IMAGES = {
     "cpu-cxx11-abi": f"pytorch/manylinuxcxx11-abi-builder:cpu-cxx11-abi-{DEFAULT_TAG}",
     "cpu-aarch64": f"pytorch/manylinux2_28_aarch64-builder:cpu-aarch64-{DEFAULT_TAG}",
     "cpu-s390x": f"pytorch/manylinuxs390x-builder:cpu-s390x-{DEFAULT_TAG}",
-    "cuda-aarch64": f"pytorch/manylinuxaarch64-builder:cuda12.6-{DEFAULT_TAG}",
+    "cuda-aarch64": f"pytorch/manylinuxaarch64-builder:cuda12.4-{DEFAULT_TAG}",
 }
 
 
@@ -194,6 +194,13 @@ LIBTORCH_CONTAINER_IMAGES: Dict[Tuple[str, str], str] = {
         ): f"pytorch/libtorch-cxx11-builder:cuda{gpu_arch}-{DEFAULT_TAG}"
         for gpu_arch in CUDA_ARCHES
     },
+    **{
+        (
+            gpu_arch,
+            PRE_CXX11_ABI,
+        ): f"pytorch/manylinux-builder:rocm{gpu_arch}-{DEFAULT_TAG}"
+        for gpu_arch in ROCM_ARCHES
+    },
     **{
         (
             gpu_arch,
@@ -215,7 +222,7 @@ def translate_desired_cuda(gpu_arch_type: str, gpu_arch_version: str) -> str:
         "cpu-cxx11-abi": "cpu-cxx11-abi",
         "cpu-s390x": "cpu",
         "cuda": f"cu{gpu_arch_version.replace('.', '')}",
-        "cuda-aarch64": "cu126",
+        "cuda-aarch64": "cu124",
         "rocm": f"rocm{gpu_arch_version}",
         "xpu": "xpu",
     }.get(gpu_arch_type, gpu_arch_version)
@@ -255,9 +262,7 @@ def generate_libtorch_matrix(
             gpu_arch_type = arch_type(arch_version)
             gpu_arch_version = "" if arch_version == "cpu" else arch_version
             # ROCm builds without-deps failed even in ROCm runners; skip for now
-            if gpu_arch_type == "rocm" and (
-                "without-deps" in libtorch_variant or "pre-cxx11" in abi_version
-            ):
+            if gpu_arch_type == "rocm" and "without-deps" in libtorch_variant:
                 continue
             ret.append(
                 {
@@ -328,9 +333,10 @@ def generate_wheels_matrix(
                 else arch_version
             )
 
-            # TODO: Enable python 3.13 on aarch64, windows
+            # TODO: Enable python 3.13 on rocm, aarch64, windows
             if (
-                os
+                gpu_arch_type == "rocm"
+                or os
                 not in [
                     "linux",
                     "linux-s390x",
@@ -376,11 +382,7 @@ def generate_wheels_matrix(
                         ),
                         "use_split_build": "True" if use_split_build else "False",
                         "devtoolset": (
-                            "cxx11-abi"
-                            if (
-                                arch_version == "cuda-aarch64" or arch_version == "12.6"
-                            )
-                            else ""
+                            "cxx11-abi" if arch_version == "cuda-aarch64" else ""
                         ),
                         "container_image": WHEEL_CONTAINER_IMAGES[arch_version],
                         "package_type": package_type,
@@ -426,8 +428,7 @@ def generate_wheels_matrix(
                         "use_split_build": "True" if use_split_build else "False",
                         "devtoolset": (
                             "cxx11-abi"
-                            if (arch_version in ["cpu-cxx11-abi", "cpu-aarch64", "xpu"])
-                            or gpu_arch_type == "rocm"
+                            if arch_version in ["cpu-cxx11-abi", "cpu-aarch64"]
                             else ""
                         ),
                         "container_image": WHEEL_CONTAINER_IMAGES[arch_version],

.github/scripts/report_git_status.sh

@@ -1,9 +1,5 @@
 #!/usr/bin/env bash
-
-set -eux
-
 CHANGES=$(git status --porcelain "$1")
 echo "$CHANGES"
-# NB: Use --no-pager here to avoid git diff asking for a prompt to continue
-git --no-pager diff "$1"
+git diff "$1"
 [ -z "$CHANGES" ]

.github/scripts/runner_determinator.py

@@ -258,7 +258,7 @@ def load_yaml(yaml_text: str) -> Any:
     try:
         data = yaml.safe_load(yaml_text)
         return data
-    except yaml.YAMLError:
+    except yaml.YAMLError as exc:
         log.exception("Error loading YAML")
         raise
 

.github/scripts/test_trymerge.py

@@ -898,7 +898,7 @@ class TestBypassFailures(TestCase):
         repo = DummyGitRepo()
         # Check that failure is classified as flaky but still raises exception
         with warnings.catch_warnings(record=True) as w, self.assertRaises(RuntimeError):
-            find_matching_merge_rule(pr, repo)
+            rule = find_matching_merge_rule(pr, repo)
         self.assertEqual(len(w), 1)
         self.assertIn(
             "1 checks failed but were likely due flakiness or broken trunk",

.github/scripts/trymerge.py

@@ -1747,7 +1747,7 @@ def get_classifications(
         try:
             print(f"From Dr.CI checkrun summary: {drci_summary}")
             drci_classifications = json.loads(str(drci_summary))
-        except json.JSONDecodeError:
+        except json.JSONDecodeError as error:
             warn("Invalid Dr.CI checkrun summary")
             drci_classifications = {}
 
@@ -1918,6 +1918,7 @@ def do_revert_prs(
     dry_run: bool = False,
 ) -> None:
     # Prepare and push revert commits
+    commit_shas: List[str] = []
     for commit_sha, pr in shas_and_prs:
         revert_msg = f"\nReverted {pr.get_pr_url()} on behalf of {prefix_with_github_url(author_login)}"
         revert_msg += extra_msg

.github/templates/common.yml.j2

@@ -8,7 +8,7 @@
 # NOTE: If testing pytorch/builder changes you can change this variable to change what pytorch/builder reference
 #       the binary builds will check out
 {%- set builder_repo = "pytorch/builder" -%}
-{%- set builder_branch = "release/2.6" -%}
+{%- set builder_branch = "main" -%}
 
 {%- macro concurrency(build_environment) -%}
 concurrency:
@@ -36,7 +36,7 @@ concurrency:
 {%- macro setup_ec2_windows() -%}
       !{{ display_ec2_information() }}
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
-        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-ssh@main
         continue-on-error: true
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}

.github/templates/linux_binary_build_workflow.yml.j2

@@ -55,7 +55,7 @@ jobs:
   get-label-type:
     if: github.repository_owner == 'pytorch'
     name: get-label-type
-    uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@release/2.6
+    uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@main
     with:
       triggering_actor: ${{ github.triggering_actor }}
       issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
@@ -145,9 +145,10 @@ jobs:
         with:
           name: !{{ config["build_name"] }}
           path: "${{ runner.temp }}/artifacts/"
-      !{{ common.checkout(deep_clone=False, directory="pytorch", checkout_pr_head=False) }}
+      !{{ common.checkout(deep_clone=False, directory="pytorch") }}
+      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch) }}
       - name: Pull Docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
         with:
           docker-image: !{{ config["container_image"] }}
       - name: Test Pytorch binary
@@ -166,12 +167,13 @@ jobs:
         with:
           name: !{{ config["build_name"] }}
           path: "${{ runner.temp }}/artifacts/"
-      !{{ common.checkout(deep_clone=False, directory="pytorch", checkout_pr_head=False) }}
+      !{{ common.checkout(deep_clone=False, directory="pytorch") }}
+      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch) }}
       - name: ROCm set GPU_FLAG
         run: |
           echo "GPU_FLAG=--device=/dev/mem --device=/dev/kfd --device=/dev/dri --group-add video --group-add daemon" >> "${GITHUB_ENV}"
       - name: Pull Docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
         with:
           docker-image: !{{ config["container_image"] }}
       - name: Test Pytorch binary

.github/templates/macos_binary_build_workflow.yml.j2

@@ -78,7 +78,8 @@ jobs:
           elif [ -d "/Applications/Xcode_13.3.1.app" ]; then
             echo "DEVELOPER_DIR=/Applications/Xcode_13.3.1.app/Contents/Developer" >> "${GITHUB_ENV}"
           fi
-      !{{ common.checkout(deep_clone=False, directory="pytorch", checkout_pr_head=False) }}
+      !{{ common.checkout(deep_clone=False, directory="pytorch") }}
+      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch) }}
       - name: Install sccache (only for non-forked PRs, and pushes to trunk)
         uses: nick-fields/retry@v3.0.0
         if: ${{ github.event_name == 'push' || github.event.pull_request.head.repo.full_name == github.repository }}

.github/templates/windows_binary_build_workflow.yml.j2

@@ -56,7 +56,7 @@ jobs:
   get-label-type:
     if: github.repository_owner == 'pytorch'
     name: get-label-type
-    uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@release/2.6
+    uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@main
     with:
       triggering_actor: ${{ github.triggering_actor }}
       issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
@@ -80,7 +80,8 @@ jobs:
     steps:
       !{{ common.setup_ec2_windows() }}
       !{{ set_runner_specific_vars() }}
-      !{{ common.checkout(deep_clone=False, directory="pytorch", checkout_pr_head=False) }}
+      !{{ common.checkout(deep_clone=False, directory="pytorch") }}
+      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch) }}
       - name: Populate binary env
         shell: bash
         run: |
@@ -121,7 +122,8 @@ jobs:
         with:
           name: !{{ config["build_name"] }}
           path: "${{ env.PYTORCH_FINAL_PACKAGE_DIR }}"
-      !{{ common.checkout(deep_clone=False, directory="pytorch", checkout_pr_head=False) }}
+      !{{ common.checkout(deep_clone=False, directory="pytorch") }}
+      !{{ common.checkout(deep_clone=False, directory="builder", repository=common.builder_repo, branch=common.builder_branch) }}
       - name: Populate binary env
         shell: bash
         run: |

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

@@ -47,7 +47,7 @@ jobs:
       reenabled-issues: ${{ steps.filter.outputs.reenabled-issues }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
         with:
           fetch-depth: 1
           submodules: false
@@ -69,25 +69,25 @@ jobs:
     runs-on: ${{ matrix.runner }}
     steps:
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-ssh@main
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
 
       - name: Setup Linux
         uses: ./.github/actions/setup-linux
 
       - name: Calculate docker image
         id: calculate-docker-image
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
         with:
           docker-image-name: ${{ inputs.docker-image-name }}
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 
@@ -97,7 +97,7 @@ jobs:
         run: echo "IN_CONTAINER_RUNNER=$(if [ -f /.inarc ] || [ -f /.incontainer ]; then echo true ; else echo false; fi)" >> "$GITHUB_OUTPUT"
 
       - name: Install nvidia driver, nvidia-docker runtime, set GPU_FLAG
-        uses: pytorch/test-infra/.github/actions/setup-nvidia@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-nvidia@main
         if: ${{ inputs.cuda-version != 'cpu' && steps.check_container_runner.outputs.IN_CONTAINER_RUNNER == 'false' }}
 
       - name: Output disk space left
@@ -209,5 +209,5 @@ jobs:
           file-suffix: bazel-${{ github.job }}_${{ steps.get-job-id.outputs.job-id }}
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.6
+        uses: pytorch/test-infra/.github/actions/teardown-linux@main
         if: always()

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

@@ -159,13 +159,13 @@ jobs:
 
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
         if: inputs.build_environment != 'linux-s390x-binary-manywheel'
-        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-ssh@main
         continue-on-error: true
         with:
           github-secret: ${{ secrets.github-token }}
 
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
         with:
           no-sudo: ${{ inputs.build_environment == 'linux-aarch64-binary-manywheel' || inputs.build_environment == 'linux-s390x-binary-manywheel' }}
 
@@ -195,6 +195,7 @@ jobs:
       - name: Checkout PyTorch to pytorch dir
         uses: malfet/checkout@silent-checkout
         with:
+          ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
           submodules: recursive
           path: pytorch
           quiet-checkout: true
@@ -205,6 +206,21 @@ jobs:
           git clean -fxd
         working-directory: pytorch
 
+      - name: Checkout pytorch/builder to builder dir
+        uses: malfet/checkout@silent-checkout
+        with:
+          ref: main
+          submodules: recursive
+          repository: pytorch/builder
+          path: builder
+          quiet-checkout: true
+
+      - name: Clean pytorch/builder checkout
+        run: |
+          # Remove any artifacts from the previous checkouts
+          git clean -fxd
+        working-directory: builder
+
       - name: Check if the job is disabled
         id: filter
         uses: ./pytorch/.github/actions/filter-test-configs
@@ -219,7 +235,7 @@ jobs:
 
       - name: Pull Docker image
         if: ${{ steps.filter.outputs.is-test-matrix-empty == 'False' && inputs.build_environment != 'linux-s390x-binary-manywheel' }}
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
         with:
           docker-image: ${{ inputs.DOCKER_IMAGE }}
 
@@ -230,6 +246,7 @@ jobs:
           mkdir -p artifacts/
           container_name=$(docker run \
             -e BINARY_ENV_FILE \
+            -e BUILDER_ROOT \
             -e BUILD_ENVIRONMENT \
             -e DESIRED_CUDA \
             -e DESIRED_DEVTOOLSET \
@@ -247,6 +264,7 @@ jobs:
             --tty \
             --detach \
             -v "${GITHUB_WORKSPACE}/pytorch:/pytorch" \
+            -v "${GITHUB_WORKSPACE}/builder:/builder" \
             -v "${RUNNER_TEMP}/artifacts:/artifacts" \
             -w / \
             "${DOCKER_IMAGE}"
@@ -254,8 +272,10 @@ jobs:
           docker exec -t -w "${PYTORCH_ROOT}" "${container_name}" bash -c "bash .circleci/scripts/binary_populate_env.sh"
           if [[ ${BUILD_ENVIRONMENT} == *"aarch64"* ]]; then
             docker exec -t "${container_name}" bash -c "source ${BINARY_ENV_FILE} && bash /pytorch/.ci/aarch64_linux/aarch64_ci_build.sh"
-          else
+          elif [[ ${{ inputs.PACKAGE_TYPE }} == "manywheel" || ${{ inputs.PACKAGE_TYPE }} == "libtorch" ]]; then
             docker exec -t "${container_name}" bash -c "source ${BINARY_ENV_FILE} && bash /pytorch/.ci/${{ inputs.PACKAGE_TYPE }}/build.sh"
+          else
+            docker exec -t "${container_name}" bash -c "source ${BINARY_ENV_FILE} && bash /builder/${{ inputs.PACKAGE_TYPE }}/build.sh"
           fi
 
       - name: Chown artifacts
@@ -275,7 +295,7 @@ jobs:
 
       - name: Teardown Linux
         if: always() && inputs.build_environment != 'linux-s390x-binary-manywheel'
-        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.6
+        uses: pytorch/test-infra/.github/actions/teardown-linux@main
 
       - name: Chown workspace
         if: always() && inputs.build_environment != 'linux-s390x-binary-manywheel'

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

@@ -142,14 +142,14 @@ jobs:
 
       - name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
         if: inputs.build_environment != 'linux-s390x-binary-manywheel'
-        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-ssh@main
         continue-on-error: true
         with:
           github-secret: ${{ secrets.github-token }}
 
         # Setup the environment
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
         with:
           no-sudo: ${{ inputs.build_environment == 'linux-aarch64-binary-manywheel' || inputs.build_environment == 'linux-s390x-binary-manywheel' }}
 
@@ -172,6 +172,7 @@ jobs:
       - name: Checkout PyTorch to pytorch dir
         uses: malfet/checkout@silent-checkout
         with:
+          ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
           submodules: recursive
           path: pytorch
 
@@ -181,6 +182,20 @@ jobs:
           git clean -fxd
         working-directory: pytorch
 
+      - name: Checkout pytorch/builder to builder dir
+        uses: malfet/checkout@silent-checkout
+        with:
+          ref: main
+          submodules: recursive
+          repository: pytorch/builder
+          path: builder
+
+      - name: Clean pytorch/builder checkout
+        run: |
+          # Remove any artifacts from the previous checkouts
+          git clean -fxd
+        working-directory: builder
+
       - name: Check if the job is disabled
         id: filter
         uses: ./pytorch/.github/actions/filter-test-configs
@@ -201,12 +216,12 @@ jobs:
           path: "${{ runner.temp }}/artifacts/"
 
       - name: Install nvidia driver, nvidia-docker runtime, set GPU_FLAG
-        uses: pytorch/test-infra/.github/actions/setup-nvidia@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-nvidia@main
         if: ${{ inputs.GPU_ARCH_TYPE == 'cuda' && steps.filter.outputs.is-test-matrix-empty == 'False' }}
 
       - name: Pull Docker image
         if: ${{ steps.filter.outputs.is-test-matrix-empty == 'False' && inputs.build_environment != 'linux-s390x-binary-manywheel' }}
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
         with:
           docker-image: ${{ inputs.DOCKER_IMAGE }}
 
@@ -216,7 +231,7 @@ jobs:
 
       - name: Teardown Linux
         if: always() && inputs.build_environment != 'linux-s390x-binary-manywheel'
-        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.6
+        uses: pytorch/test-infra/.github/actions/teardown-linux@main
 
       - name: Chown workspace
         if: always() && inputs.build_environment != 'linux-s390x-binary-manywheel'

.github/workflows/_binary-upload.yml

@@ -103,7 +103,7 @@ jobs:
       USE_SPLIT_BUILD: ${{ inputs.use_split_build }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
         with:
           no-sudo: true
 

.github/workflows/_docs.yml

@@ -84,7 +84,7 @@ jobs:
     name: build-docs-${{ matrix.docs_type }}-${{ inputs.push }}
     steps:
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-ssh@main
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
           instructions: |
@@ -95,7 +95,7 @@ jobs:
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
 
       - name: Setup Linux
         uses: ./.github/actions/setup-linux
@@ -110,12 +110,12 @@ jobs:
 
       - name: Calculate docker image
         id: calculate-docker-image
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
         with:
           docker-image-name: ${{ inputs.docker-image }}
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 
@@ -222,5 +222,5 @@ jobs:
           s3-prefix: pytorch/pytorch/${{ github.event.pull_request.number }}/functorchdocs
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.6
+        uses: pytorch/test-infra/.github/actions/teardown-linux@main
         if: always()

.github/workflows/_linux-build.yml

@@ -108,7 +108,7 @@ jobs:
       test-matrix: ${{ steps.filter.outputs.test-matrix }}
     steps:
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-ssh@main
         if: inputs.build-environment != 'linux-s390x-binary-manywheel'
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -118,7 +118,7 @@ jobs:
       # checkout because when we run this action we don't *have* a local
       # checkout. In other cases you should prefer a local checkout.
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
         with:
           no-sudo: true
 
@@ -136,7 +136,7 @@ jobs:
 
       - name: Calculate docker image
         id: calculate-docker-image
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
         if: inputs.build-environment != 'linux-s390x-binary-manywheel'
         with:
           docker-image-name: ${{ inputs.docker-image-name }}
@@ -152,7 +152,7 @@ jobs:
           echo "docker pull ghcr.io/pytorch/ci-image:${tag/:/-}"
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
         if: inputs.build-environment != 'linux-s390x-binary-manywheel'
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
@@ -224,12 +224,6 @@ jobs:
             JENKINS_USER="--user jenkins"
             USED_IMAGE="${DOCKER_IMAGE}"
           fi
-
-          # Leaving 1GB for the runner and other things
-          TOTAL_AVAILABLE_MEMORY_IN_GB=$(awk '/MemTotal/ { printf "%.3f \n", $2/1024/1024 - 1 }' /proc/meminfo)
-          # https://docs.docker.com/engine/containers/resource_constraints/#--memory-swap-details
-          TOTAL_MEMORY_WITH_SWAP=$(("${TOTAL_AVAILABLE_MEMORY_IN_GB%.*}" * 2))
-
           # detached container should get cleaned up by teardown_ec2_linux
           # Used for JENKINS_USER, which can be empty
           # shellcheck disable=SC2086
@@ -250,10 +244,7 @@ jobs:
             -e PR_LABELS \
             -e OUR_GITHUB_JOB_ID \
             -e HUGGING_FACE_HUB_TOKEN \
-            -e SCRIBE_GRAPHQL_ACCESS_TOKEN \
             -e USE_SPLIT_BUILD \
-            --memory="${TOTAL_AVAILABLE_MEMORY_IN_GB%.*}g" \
-            --memory-swap="${TOTAL_MEMORY_WITH_SWAP}g" \
             --env-file="/tmp/github_env_${GITHUB_RUN_ID}" \
             --security-opt seccomp=unconfined \
             --cap-add=SYS_PTRACE \
@@ -320,7 +311,7 @@ jobs:
           build-time: ${{ steps.build.outputs.build_time }}
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.6
+        uses: pytorch/test-infra/.github/actions/teardown-linux@main
         if: always() && inputs.build-environment != 'linux-s390x-binary-manywheel'
 
       - name: Cleanup docker

.github/workflows/_linux-test.yml

@@ -54,7 +54,7 @@ on:
           since we are investigating the behaviour of the monitor script with different tests.
         required: false
         type: boolean
-        default: false
+        default: true
     secrets:
       HUGGING_FACE_HUB_TOKEN:
         required: false
@@ -80,7 +80,7 @@ jobs:
     timeout-minutes: ${{ matrix.mem_leak_check == 'mem_leak_check' && 600 || inputs.timeout-minutes }}
     steps:
       - name: Setup SSH (Click me for login details)
-        uses: pytorch/test-infra/.github/actions/setup-ssh@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-ssh@main
         if: ${{ !contains(matrix.runner, 'gcp.a100') }}
         with:
           github-secret: ${{ secrets.GITHUB_TOKEN }}
@@ -89,7 +89,7 @@ jobs:
               docker exec -it $(docker container ps --format '{{.ID}}') bash
 
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
         with:
           no-sudo: true
 
@@ -106,7 +106,7 @@ jobs:
 
       - name: Calculate docker image
         id: calculate-docker-image
-        uses: pytorch/test-infra/.github/actions/calculate-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
         with:
           docker-image-name: ${{ inputs.docker-image }}
 
@@ -120,7 +120,7 @@ jobs:
           echo "docker pull ghcr.io/pytorch/ci-image:${tag/:/-}"
 
       - name: Pull docker image
-        uses: pytorch/test-infra/.github/actions/pull-docker-image@release/2.6
+        uses: pytorch/test-infra/.github/actions/pull-docker-image@main
         with:
           docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
 
@@ -131,7 +131,7 @@ jobs:
 
       - name: Install nvidia driver, nvidia-docker runtime, set GPU_FLAG
         id: install-nvidia-driver
-        uses: pytorch/test-infra/.github/actions/setup-nvidia@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-nvidia@main
         if: ${{ contains(inputs.build-environment, 'cuda') && !contains(matrix.config, 'nogpu') && steps.check_container_runner.outputs.IN_CONTAINER_RUNNER == 'false' }}
 
       - name: Setup GPU_FLAG for docker run
@@ -331,7 +331,7 @@ jobs:
           job_identifier: ${{ github.workflow }}_${{ inputs.build-environment }}
 
       - name: Upload the benchmark results
-        uses: pytorch/test-infra/.github/actions/upload-benchmark-results@release/2.6
+        uses: pytorch/test-infra/.github/actions/upload-benchmark-results@main
         with:
           benchmark-results-dir: test/test-reports
           dry-run: false
@@ -377,7 +377,7 @@ jobs:
           path: ./**/core.[1-9]*
 
       - name: Teardown Linux
-        uses: pytorch/test-infra/.github/actions/teardown-linux@release/2.6
+        uses: pytorch/test-infra/.github/actions/teardown-linux@main
         if: always() && steps.check_container_runner.outputs.IN_CONTAINER_RUNNER == 'false'
 
       # NB: We are currently having an intermittent GPU-related issue on G5 runners with

.github/workflows/_mac-build.yml

@@ -71,11 +71,11 @@ jobs:
       test-matrix: ${{ steps.filter.outputs.test-matrix }}
     steps:
       - name: Clean up disk space before running MacOS workflow
-        uses: pytorch/test-infra/.github/actions/check-disk-space@release/2.6
+        uses: pytorch/test-infra/.github/actions/check-disk-space@main
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
 
       - name: Set xcode version
         env:
@@ -87,7 +87,7 @@ jobs:
 
       - name: Setup miniconda
         if: inputs.environment-file == ''
-        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@main
         with:
           python-version: ${{ inputs.python-version }}
           environment-file: .github/requirements/conda-env-${{ runner.os }}-${{ runner.arch }}
@@ -97,7 +97,7 @@ jobs:
       # environment even though the arch is x86-64
       - name: Setup miniconda using the provided environment file
         if: inputs.environment-file != ''
-        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@main
         with:
           python-version: ${{ inputs.python-version }}
           environment-file: ${{ inputs.environment-file }}
@@ -207,4 +207,4 @@ jobs:
       - name: Clean up disk space
         if: always()
         continue-on-error: true
-        uses: pytorch/test-infra/.github/actions/check-disk-space@release/2.6
+        uses: pytorch/test-infra/.github/actions/check-disk-space@main

.github/workflows/_mac-test-mps.yml

@@ -41,7 +41,7 @@ jobs:
       reenabled-issues: ${{ steps.filter.outputs.reenabled-issues }}
     steps:
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
         with:
           submodules: false
 
@@ -82,7 +82,7 @@ jobs:
           use-gha: true
 
       - name: Setup miniconda
-        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@main
         with:
           python-version: ${{ inputs.python-version }}
           environment-file: .github/requirements/conda-env-${{ runner.os }}-${{ runner.arch }}
@@ -169,4 +169,4 @@ jobs:
       - name: Clean up disk space
         if: always()
         continue-on-error: true
-        uses: pytorch/test-infra/.github/actions/check-disk-space@release/2.6
+        uses: pytorch/test-infra/.github/actions/check-disk-space@main

.github/workflows/_mac-test.yml

@@ -82,19 +82,11 @@ jobs:
           done
 
       - name: Clean up disk space before running MacOS workflow
-        uses: pytorch/test-infra/.github/actions/check-disk-space@release/2.6
+        uses: pytorch/test-infra/.github/actions/check-disk-space@main
 
       # [see note: pytorch repo ref]
       - name: Checkout PyTorch
-        uses: pytorch/pytorch/.github/actions/checkout-pytorch@release/2.6
-
-      - name: Start monitoring script
-        id: monitor-script
-        if: ${{ !inputs.disable-monitor }}
-        continue-on-error: true
-        run: |
-          ${CONDA_RUN} python3 -m tools.stats.monitor > usage_log.txt 2>&1 &
-          echo "monitor-script-pid=${!}" >> "${GITHUB_OUTPUT}"
+        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
 
       - name: Download build artifacts
         uses: ./.github/actions/download-build-artifacts
@@ -109,12 +101,20 @@ jobs:
           use-gha: true
 
       - name: Setup miniconda
-        uses: pytorch/test-infra/.github/actions/setup-miniconda@release/2.6
+        uses: pytorch/test-infra/.github/actions/setup-miniconda@main
         with:
           python-version: ${{ inputs.python-version }}
           environment-file: .github/requirements/conda-env-${{ runner.os }}-${{ runner.arch }}
           pip-requirements-file: .github/requirements/pip-requirements-${{ runner.os }}.txt
 
+      - name: Start monitoring script
+        id: monitor-script
+        if: ${{ !inputs.disable-monitor }}
+        continue-on-error: true
+        run: |
+          ${CONDA_RUN} python3 -m tools.stats.monitor > usage_log.txt 2>&1 &
+          echo "monitor-script-pid=${!}" >> "${GITHUB_OUTPUT}"
+
       - name: Parse ref
         id: parse-ref
         run: .github/scripts/parse_ref.py
@@ -224,7 +224,7 @@ jobs:
           file-suffix: ${{ github.job }}-${{ matrix.config }}-${{ matrix.shard }}-${{ matrix.num_shards }}-${{ matrix.runner }}_${{ steps.get-job-id.outputs.job-id }}
 
       - name: Upload the benchmark results
-        uses: pytorch/test-infra/.github/actions/upload-benchmark-results@release/2.6
+        uses: pytorch/test-infra/.github/actions/upload-benchmark-results@main
         with:
           benchmark-results-dir: test/test-reports
           dry-run: false
@@ -234,4 +234,4 @@ jobs:
       - name: Clean up disk space
         if: always()
         continue-on-error: true
-        uses: pytorch/test-infra/.github/actions/check-disk-space@release/2.6
+        uses: pytorch/test-infra/.github/actions/check-disk-space@main